System

Abstract

A system is provided.SOLUTION: A system, comprising: means for a user selecting a training title on a terminal; means for sending the selected training title to a server; means for the server obtaining historical data of the user, capability assessment data, and current work data; means for the server analyzing the data using an AI engine to assess a skill set and a learning style of the user; means for generating a personalized training program based on the assessment; means for sending the generated training program to the terminal; and means for the terminal presenting to the user and starting the training.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Traditional training and education programs tend to have uniform content and do not adequately address the individual needs and circumstances of each employee. This often results in poor learning effectiveness and a decline in employee motivation. Furthermore, there is also the issue that employee skills are not improved efficiently, which does not lead to corporate growth or improved competitiveness. To solve this, a system is needed that provides personalized training programs that are optimal for each employee. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means: A means for a user to select a training title on a terminal and a means for transmitting the selected training title to a server are provided. The server acquires the user's past history data, ability assessment data, and current work data, and analyzes this data using an AI engine. A means is provided for evaluating the user's skill set and learning style based on the analysis results and generating a personalized training program. The generated training program is transmitted to the terminal, which presents it to the user and starts the training. This system makes it possible to provide an optimized training program for each employee, which is expected to improve learning effectiveness and motivation. In addition, the server has a means for recording the progress of the training program and delivering the next training content in a timely manner, enabling long-term skill improvement and maintenance.

[0006] "User" refers to an individual who uses the system and participates in the training program.

[0007] "Terminal" refers to a device operated by a user and used to select a training title and take a training program.

[0008] "Training title" refers to the name of various training programs that the user can select.

[0009] "Server" refers to a computer system that processes data, analyzes data, and generates training programs.

[0010] "History data" refers to the user's past training history and learning records.

[0011] "Ability evaluation data" refers to data resulting from an evaluation of a user's abilities and skills.

[0012] "Business data" refers to data related to the user's current job duties and work.

[0013] An "AI engine" refers to a system that uses artificial intelligence technology to analyze data and evaluate users' skills.

[0014] A "skill set" refers to the collection of skills and abilities that a user currently possesses.

[0015] "Learning style" refers to the method or approach in which a user learns most effectively.

[0016] A "personalized training program" refers to training content that is customized to suit the individual needs and circumstances of each user.

[0017] "Program progress" refers to data that indicates how far a user has progressed through each step of the training program.

[0018] "Training Resources" refers to the learning materials and materials provided in the training program, such as videos, textbooks, and quizzes. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention aims to provide a personalized training program based on the needs of each user. In the system of the present invention, the user selects a training title on the terminal, and the server generates and provides the optimal training program based on the selection. Specifically, the process is as follows:

[0041] First, the user launches the application on their device and selects the desired program from among multiple training titles. This selection is sent to the server via the device. The server then acquires and analyzes the received training title information, as well as the user's past history data, ability evaluation data, and current work data stored in the database.

[0042] The server uses an AI engine to analyze this data and assess the user's current skill set, gaps, and optimal learning style. Based on this assessment, it generates a list of training modules that are best suited to the user and combines them to create a personalized training program.

[0043] The server sends the generated training program to the terminal, which then presents it to the user. The user checks the content of the training program and begins the training if they are satisfied. During the training, the terminal sends the user's progress information to the server, which records this progress. This allows the next training module to be provided in a timely manner.

[0044] It is designed to help users efficiently acquire the skills they need to maximize their learning, and by regularly monitoring their progress, it also helps them maintain and improve their skills over the long term.

[0045] Specific examples

[0046] A specific example is shown below.

[0047] Example 1: Presentation skills training

[0048] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[0049] 2. The terminal sends the selected training title to the server.

[0050] 3. The server retrieves the user's past history data, ability evaluation data, and current work data from the database based on the user ID and the selected training title information.

[0051] 4. The server calls the AI ​​engine and provides these data as input.

[0052] 5. The AI ​​engine analyzes the user's skill set and assesses their skillset and weaknesses. For example, they may be able to create basic slides, but lack effective slide design and audience interaction.

[0053] 6. The server selects training modules based on the results of these evaluations, such as "Advanced Slide Design" and "Effective Public Speaking."

[0054] 7. The server combines the selected modules to create a personalized training program and sends it to the terminal.

[0055] 8. The device presents the training program to the user. The user begins the training and sends progress information to the server as they complete each step.

[0056] 9. The server will record your progress and provide you with the next training content in a timely manner.

[0057] Through this process, users can receive training that is optimized for them, maximizing their learning effect and helping to increase their motivation and continuously improve their skills.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The user starts the application on the terminal and selects the desired training title "improving presentation skills" from among a number of training titles.

[0061] Step 2:

[0062] The device sends request data including the selected training title to the server. For example, the data is sent in JSON format along with the user ID.

[0063] Step 3:

[0064] The server receives the request and accesses a database to obtain the user's history data, performance assessment data, and current job data.

[0065] Step 4:

[0066] The server inputs this acquired data into an AI engine and provides it as parameters for analyzing the user's skill set, skill gaps, and optimal learning style.

[0067] Step 5:

[0068] The AI ​​engine analyzes the data and evaluates the user's skills, such as their current ability to create slides, their ability to interact with the audience, and any gaps in their skills that may be required.

[0069] Step 6:

[0070] The server receives the analysis results from the AI ​​engine and generates a personalized training program based on them, combining modules such as "Advanced Slide Design" and "Effective Public Speaking."

[0071] Step 7:

[0072] The server sends the generated training program to the terminal, which includes details of each module and the order in which they are executed.

[0073] Step 8:

[0074] The terminal presents the received training program to the user, and displays the program content and module configuration.

[0075] Step 9:

[0076] The user checks the presented program and, if satisfied, begins the training by, for example, pressing the "Start" button.

[0077] Step 10:

[0078] The terminal notifies the server of the user's training start action.

[0079] Step 11:

[0080] The server approves the start of the training and provides the necessary training resources (videos, texts, quizzes, etc.).

[0081] Step 12:

[0082] The terminal sequentially displays these resources to the user, and the training program progresses.

[0083] Step 13:

[0084] As the user completes each step, the terminal sends progress information to the server, for example, sending progress data upon completion of each module.

[0085] Step 14:

[0086] The server records the progress and delivers the next training module in a timely manner, and can also flexibly adjust the next step according to the progress.

[0087] Step 15:

[0088] The terminal then presents the user with the next training module, and so on until the entire training program is completed.

[0089] Through these steps, users can receive training programs optimized for them and improve their skills.

[0090] Example 1

[0091] 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."

[0092] Conventional training systems have struggled to provide personalized training programs based on individual user needs. This is due to a lack of technology to comprehensively analyze each user's history data, ability assessment data, and current work data, and automatically generate training programs based on that data. Furthermore, there was no mechanism in place to monitor training progress in real time and provide the next appropriate training module in a timely manner.

[0093] 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.

[0094] In this invention, the server includes means for a user to select a training title on a terminal, means for transmitting the selected training title to the server, means for acquiring the user's past history data, ability assessment data, and current work data, means for analyzing the data using a generative AI model and evaluating the user's skill set and learning style, means for generating a personalized training program based on the evaluation, means for transmitting the generated training program to the terminal, means for the terminal to present the program to the user and start the training, means for transmitting progress information to the server, and means for recording the progress information and providing the next training content in a timely manner. This allows users to receive training programs suited to their individual needs and enables effective skill improvement.

[0095] "User" refers to any individual or legal entity participating in the training program.

[0096] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[0097] "Server" refers to a computer system that performs database access, data analysis, and training program generation and delivery.

[0098] "Training title" refers to the name or theme of the training program selected by the user.

[0099] "Database" refers to an information system that stores users' past history data, performance evaluation data, and current business data.

[0100] "Generative AI model" refers to the artificial intelligence engine that analyzes data and generates personalized training programs.

[0101] A "skill set" refers to the collection of skills and knowledge possessed by a user.

[0102] "Learning style" refers to the method or format in which a user learns optimally.

[0103] "Personalized training program" refers to a learning plan that is customized to meet the user's individual needs.

[0104] "Progress Information" refers to progress data collected as a user progresses through a training program.

[0105] "Training Module" means a separate learning unit or session that forms part of a training program.

[0106] "Real-time" refers to data and information being processed and updated instantly.

[0107] The present invention is a system that provides personalized training programs based on the needs of each user. In this system, the user selects a training title on the terminal, and the server generates and provides the optimal training program based on that selection. The details are explained below.

[0108] First, the user launches the application installed on the terminal and selects the desired program from the multiple training titles provided. For example, if the user selects the training title "Improve Presentation Skills," this information is sent to the server via the terminal. The server retrieves the received training title information, as well as the user's past history data, ability evaluation data, and current work data stored in the database.

[0109] The server collects this data and analyzes it using a generative AI model. Specifically, it evaluates the user's current skill set, gaps, and optimal learning style. Based on this evaluation, the server generates a list of training modules that are optimal for the user and combines them to create a personalized training program.

[0110] The generated training program is again sent from the server to the terminal. The terminal presents this training program to the user, and the user begins the training. As the training progresses, the terminal sends progress information to the server, which records this progress. This allows the next training module to be provided in a timely manner.

[0111] Through this system, users can receive training that is optimized for them, allowing them to efficiently acquire the necessary skills. Furthermore, by regularly monitoring their progress, it is possible to maintain and improve their skills over the long term.

[0112] Specific examples

[0113] A specific example is shown below.

[0114] Example 1: Presentation skills training

[0115] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[0116] 2. The terminal sends the selected training title to the server.

[0117] 3. The server retrieves the user's past history data, ability evaluation data, and current work data from the database based on the user ID and the selected training title information.

[0118] 4. The server invokes the generative AI model, providing these data as input.

[0119] 5. The generative AI model analyzes and evaluates the user's skill set and skills gaps. For example, it may say, "You have basic slide creation skills, but lack effective slide design and audience interaction."

[0120] 6. The server selects training modules based on these evaluation results, such as "Advanced Slide Design" and "Effective Public Speaking."

[0121] 7. The server combines the selected modules to create a personalized training program and sends it to the terminal.

[0122] 8. The device presents the training program to the user. The user begins the training and sends progress information to the server as they complete each step.

[0123] 9. The server will record your progress and provide you with the next training content in a timely manner.

[0124] Through this process, users can receive training that is optimized for them, maximizing their learning effect and helping to increase their motivation and continuously improve their skills.

[0125] Prompt Sentence Examples

[0126] "I am currently seeking training in 'improving presentation skills.' Please select the most appropriate training module for me based on my past and current work data."

[0127] In this way, by using this system, users can receive training programs tailored to their individual needs, enabling them to acquire skills effectively.

[0128] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0129] Step 1:

[0130] The user launches the app on their device and selects a training title. First, the user clicks on the desired training title from the multiple training titles provided. This selection information (training title, user ID, etc.) is entered into the device. The device stores this information in its internal memory.

[0131] Input: User ID, training title

[0132] Output: Selection information

[0133] Step 2:

[0134] The device sends the selected training title to the server. The device creates an API request and sends the selection information to the server using the HTTP POST method. For example, the device constructs the data in JSON format and sends it to the specified endpoint.

[0135] Input: Selection information

[0136] Output: API request

[0137] Step 3:

[0138] The server references the database based on the user ID and training title information to retrieve the required data. Based on the received user ID and training title, the server executes an SQL query to retrieve the following data: The user's past history data, ability evaluation data, and current job data.

[0139] Input: User ID, training title

[0140] Output: Acquired data (history data, performance evaluation data, business data)

[0141] Step 4:

[0142] The server calls the generative AI model to analyze the data. The server provides the acquired data as input to the AI ​​engine. The AI ​​engine analyzes this data and evaluates the user's current skill set, missing skills, and optimal learning style. This evaluation result is generated.

[0143] Input: Acquired data (history data, performance evaluation data, business data)

[0144] Output: Analysis results (skill set, skills gaps, learning style)

[0145] Step 5:

[0146] The server selects the most suitable training module based on the analysis results. The server lists the most suitable training modules based on the analysis results of the AI ​​engine. For example, "Advanced Slide Design" and "Effective Public Speaking" are selected.

[0147] Input: Analysis results

[0148] Output: Selection module

[0149] Step 6:

[0150] The server sends the generated training program to the device. The server combines the selection modules to generate a personalized training program and sends it to the device. It issues an HTTP POST request using the API endpoint.

[0151] Input: Selection module

[0152] Output: Personalized training program

[0153] Step 7:

[0154] The terminal presents the training program to the user. The terminal analyzes the received training program and displays it on the user interface. The user confirms the contents of the training program and starts it.

[0155] Input: Personalized Training Program

[0156] Output: Display training program

[0157] Step 8:

[0158] The user starts the training and sends progress information from the device to the server. As the user progresses through the training, the device periodically sends progress information to the server. For example, progress information is collected each time each step is completed.

[0159] Input: Training progress

[0160] Output: Progress information

[0161] Step 9:

[0162] The server records the progress information and provides the next training content in a timely manner. The server records the received progress information in a database and prepares to provide the next training module based on that information. The next module is sent to the terminal in a timely manner according to the progress.

[0163] Input: Progress information

[0164] Output: Next training module

[0165] Through these steps, users can efficiently receive training that is optimized for them, maximizing the effectiveness of their learning.

[0166] (Application example 1)

[0167] 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."

[0168] In recent years, with the widespread use of robots in factories, improving the skills of operators and maintenance personnel has become increasingly important. However, standardized, one-size-fits-all training programs are difficult to address, making it difficult to efficiently acquire skills. Conventional training programs do not adequately consider users' past work history or on-site requirements, making it difficult to maximize users' learning efficiency. Given this background, there is a need to provide personalized training programs based on each user's skill level and past work history in order to efficiently improve skills.

[0169] 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.

[0170] In this invention, the server includes: means for a user to select a training title on a terminal; means for transmitting the selected training title to the server; means for the server to acquire the user's past history data, ability evaluation data, and current work data; means for analyzing the data using an AI engine and evaluating the user's skill set and learning style; means for generating a personalized training program; means for transmitting the generated training program to the terminal; means for the terminal to present the program to the user and start the training; means for the terminal to provide training titles related to the operation and maintenance of factory robots; means for the server to recommend the next training module required based on the user's current skill level and past work history; and means for recording progress information of the training modules and providing the next module at an appropriate time. This makes it possible to provide an optimal training program based on each user's skill level and work history, thereby efficiently improving skills.

[0171] "Users" refer to factory operators and maintenance personnel who use this system to take training programs.

[0172] A "terminal" is a device that a user operates, and includes tablets and displays built into factory robots.

[0173] "Training Title" refers to the name of a particular training program selected by the user.

[0174] "Server" refers to the central system that manages the information and data selected by the user and analyzes the data using an AI engine.

[0175] "History data" refers to data related to the user's past behavioral history, such as records of tasks and operations performed by the user in the past, and error reports.

[0176] "Ability Assessment Data" refers to assessment data related to a user's skill level and abilities, including past test results and assessment reports.

[0177] "Current work data" refers to data related to the work the user is currently responsible for, including current job duties and project information.

[0178] An "AI engine" refers to a system that uses artificial intelligence technology to analyze data and evaluate a user's skill set and shortcomings.

[0179] A "skill set" refers to the collection of skills and abilities that a user possesses.

[0180] "Learning style" refers to characteristics that indicate how a user learns most effectively.

[0181] "Personalized training program" refers to a training program that is customized based on the user's individual needs and skill level.

[0182] A "factory robot" is an automated machine used in a factory to carry out manufacturing and maintenance processes.

[0183] "Training Module" means a separate learning unit within a training program that provides independent learning content.

[0184] This invention realizes a system that provides personalized training programs for factory robot operators and maintenance personnel. In this system, a user selects a training title on a terminal, and a server generates and provides an optimal training program based on the user's selection.

[0185] In a specific embodiment, the following process is performed. First, the user starts up the terminal and selects a desired program from multiple training titles. This selection is sent to the server via the terminal. The server acquires and analyzes the received training title information, as well as the user's past history data, ability assessment data, and current work data stored in a database. The server analyzes the data using an AI engine (e.g., TENSORFLOW (registered trademark)) and evaluates the user's current skill set, skill gaps, and optimal learning style. Based on the evaluation results, the server generates a list of training modules optimal for the user and combines them to create a personalized training program. The generated training program is sent to the terminal, which presents it to the user. The user reviews the content of the presented training program and, if satisfied, begins the training. During the training, the terminal transmits the user's progress information to the server, which records this progress. This allows the next training module to be provided in a timely manner.

[0186] Hardware and software used

[0187] The following hardware and software are used to realize this system.

[0188] Hardware: ANDROID(R) / iOS compatible tablet, display built into factory robot

[0189] software:

[0190] Server side: Python

[0191] Database management: MySQL (registered trademark)

[0192] AI analysis engine: TensorFlow

[0193] Application frontend: React Native

[0194] Program processing explanation

[0195] The server uses TensorFlow to analyze the user's selected training title, past history data, ability assessment data, and current work data. The analysis evaluates the user's skill set and learning style, and generates optimal training modules based on that. The generated training modules are organized into a personalized training program and sent to the user's device at the appropriate time.

[0196] Specific examples

[0197] For example, if a user selects a training title such as "Precise Operation of a Robot Arm," the server will generate a customized training program that allows the user to learn in stages from "Basic Grip Operation" to "High-Precision Positioning Techniques" based on the frequency of past operational errors and evaluation data.

[0198] Prompt Sentence Examples

[0199] An example of a prompt sentence to input to the generative AI model is as follows:

[0200] "For the training title 'Precision Operation of Robot Arms' selected by user ID 5678, please recommend the next necessary training module based on past operation errors and current evaluation data."

[0201] These prompts allow users to receive training that is optimized for their skill level and needs, enabling them to improve their skills efficiently.

[0202] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0203] Step 1:

[0204] The user starts up the terminal and selects the desired program from among multiple training titles.

[0205] Input: List of training titles

[0206] Output: Selected training title

[0207] Specific operation: The user selects the desired training title from the list of training titles displayed on the device screen by tapping it. The selected training title is then saved in the device.

[0208] Step 2:

[0209] The terminal transmits the selected training title to the server.

[0210] Input: Selected training title

[0211] Output: Training title sent to the server

[0212] Specific operation: The device uses its internal communication function to send the selected training title to the server via the network, along with the user ID and time information.

[0213] Step 3:

[0214] The server acquires the user's past history data, performance evaluation data, and current business data.

[0215] Input: User ID and selected training title

[0216] Output: User's past history data, performance evaluation data, current work data

[0217] Specific operation: The server accesses the database and retrieves past history data (e.g., operation error history), ability evaluation data (e.g., skill evaluation results), and current business data (e.g., information about the project currently in charge) corresponding to the user ID.

[0218] Step 4:

[0219] The server uses an AI engine to analyze the data and assess the user's skill set and learning style.

[0220] Input: User's past history data, performance evaluation data, current work data

[0221] Output: Assessment of user skill sets and learning styles

[0222] How it works: The server launches an AI engine such as TensorFlow to analyze the input data. Specifically, it preprocesses the dataset and inputs it into a model to evaluate the strengths and weaknesses of the user's skills and the optimal learning method.

[0223] Step 5:

[0224] The server generates a personalized training program based on the assessment.

[0225] Input: User skill set and learning style assessment results

[0226] Output: Personalized training program

[0227] Specific operation: Based on the evaluation results, the server selects appropriate training modules (e.g., "basic grip operation" and "high-precision positioning techniques") and combines them to generate a personalized training program.

[0228] Step 6:

[0229] The server transmits the generated training program to the terminal.

[0230] Enter: personalized training programs.

[0231] Output: Training program sent to the device

[0232] Specific operation: The server transmits the generated training program to the terminal via the network, including the program sequence and detailed information.

[0233] Step 7:

[0234] The terminal presents the training program to the user, and the user starts the training.

[0235] Input: Training program sent from the server

[0236] Output: User who started the training

[0237] Specific operation: The device displays the training program on the screen, and the training begins when the user presses the "Start" button. The user proceeds with the learning according to the presented content.

[0238] Step 8:

[0239] The terminal transmits the user's progress information to the server.

[0240] Input: User training progress information

[0241] Output: Progress information sent to the server

[0242] Specific operation: The terminal records the user's training progress (e.g., completed modules, test results) in real time and transmits it to the server in a timely manner.

[0243] Step 9:

[0244] The server records progress information and provides the next training module at the appropriate time.

[0245] Input: User training progress information

[0246] Output: Next training module

[0247] Specific operation: The server stores the received progress information in a database, automatically selects the next required training module, and sends it to the terminal at the appropriate time.

[0248] 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.

[0249] The present invention relates to a system that recognizes a user's emotions and provides a personalized training program based on the results. In this system, the user selects a training title on a terminal, and the server generates and provides an optimal training program based on that selection. The system also analyzes the user's emotional state using an emotion engine. This makes it possible to customize the training program according to the user's emotional state.

[0250] First, the user launches the application on their device and selects the desired program from among multiple training titles. This selection is sent to the server via the device. The server then acquires and analyzes the received training title information, as well as the user's past history data, ability evaluation data, and current work data stored in the database.

[0251] The server uses an AI engine to analyze this data and assess the user's current skill set, gaps, and optimal learning style. It also uses an emotion engine to analyze the user's emotional state. The emotion engine uses facial and voice data to recognize emotions and assess their state.

[0252] Based on the evaluation results from both the AI ​​engine and the emotion engine, the server generates a list of training modules that are optimal for the user and combines them to create a personalized training program. For example, if the user is feeling stressed, a training module for relaxation can be added.

[0253] The server sends the generated training program to the terminal, which then presents it to the user. The user reviews the content of the training program and begins the training if they are satisfied. During the training, the terminal sends the user's progress information and emotional data to the server, which records the progress and emotional state. This allows the next training module to be provided in a timely manner based on the user's emotional state.

[0254] It is designed to help users efficiently acquire the skills necessary to maximize their learning outcomes, and by taking into account the user's emotional state, it can improve learning motivation and manage stress.

[0255] Specific examples

[0256] A specific example is shown below.

[0257] Example 1: Presentation skills training

[0258] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[0259] 2. The terminal sends the selected training title to the server.

[0260] 3. The server retrieves the user's past history data, ability evaluation data, and current work data from the database based on the user ID and the selected training title information.

[0261] 4. The server calls the AI ​​engine, provides this data as input, and evaluates the user's skill set and skills gaps, such as their current ability to create slides, their ability to interact with the audience, and the skills gaps they need.

[0262] 5. The emotion engine analyzes the user's facial expression and voice data to assess whether the user is feeling stressed or highly motivated.

[0263] 6. Based on the evaluation results from the AI ​​engine and emotion engine, the server generates a personalized training program that includes modules on "Advanced Slide Design," "Effective Public Speaking," and stress management.

[0264] 7. The server transmits the generated training program to the terminal.

[0265] 8. The device presents the training program to the user. The user begins the training, and each time the device completes a step, it sends progress information and emotion data to the server.

[0266] 9. The server records the progress and emotional state and provides the next training content in a timely manner.

[0267] This system allows users to receive training tailored to their needs, maximizing learning effectiveness, and by taking into account their emotional state, it can improve their motivation and manage stress.

[0268] The processing flow will be explained below.

[0269] Step 1:

[0270] The user starts the application on the terminal and selects the desired training title "Improve Presentation Skills" from the list of available training titles.

[0271] Step 2:

[0272] The device sends request data including the selected training title to the server. For example, the data is sent in JSON format along with the user ID.

[0273] Step 3:

[0274] The server receives the request and accesses a database to obtain the user's history data, performance assessment data, and current job data.

[0275] Step 4:

[0276] The server inputs this data into the AI ​​engine and emotion engine, providing it as parameters for analyzing the user's skill set, skill gaps, optimal learning style, and emotional state.

[0277] Step 5:

[0278] The emotion engine analyzes the user's facial expression and voice data to assess their emotional state, for example, determining whether they are stressed, relaxed, or motivated.

[0279] Step 6:

[0280] Based on these inputs, the AI ​​engine assesses the user's current skill set, any gaps in skills, and their optimal learning style.

[0281] Step 7:

[0282] The server receives the evaluation results of the AI ​​engine and emotion engine and generates a list of training modules that are optimal for the user's condition. For example, in addition to the modules "Advanced Slide Design" and "Effective Public Speaking," a module for stress management can be added.

[0283] Step 8:

[0284] The server transmits the generated personalized training program to the terminal.

[0285] Step 9:

[0286] The terminal presents the received training program to the user, and displays the program content and module configuration.

[0287] Step 10:

[0288] The user checks the presented program and, if satisfied, begins the training by, for example, pressing the "Start" button.

[0289] Step 11:

[0290] The terminal notifies the server of the user's training start action.

[0291] Step 12:

[0292] The server approves the start of the training and provides the necessary training resources (videos, texts, quizzes, etc.).

[0293] Step 13:

[0294] The terminal sequentially displays these resources to the user, and the training program progresses.

[0295] Step 14:

[0296] Each time the user completes a step, the terminal transmits its progress information and emotional data to the server, for example, sending progress data and emotional state upon completion of each module.

[0297] Step 15:

[0298] The server records the progress and emotional state of the user, and delivers the next training module in a timely manner according to the user's emotional state.

[0299] Step 16:

[0300] The terminal then presents the user with the next training module and repeats this until the entire training program is complete, for example, if the user is feeling stressed, a module on relaxation may be included.

[0301] Through these steps, users can receive personalized training programs and improve their skills. Furthermore, by taking into account the user's emotional state, it is possible to improve motivation and manage stress.

[0302] Example 2

[0303] 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."

[0304] Conventional training systems provided training programs based only on the user's past history and ability evaluation data, making it difficult to provide effective training programs that took into account the emotional state of each individual user.Furthermore, they did not have the functionality to analyze progress information and emotional data in real time and provide the next training content in a timely manner, making it difficult to maximize the learning effect of users.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0306] In this invention, the server includes means for acquiring the user's past history data, ability evaluation data, and current work data, means for analyzing the data using an artificial intelligence engine to evaluate the user's skill set and learning style, and means for analyzing the user's emotional state using an emotion analysis engine, thereby enabling the provision of a personalized training program that takes the user's emotional state into consideration.

[0307] A "user" is a person who uses the system to take a training program.

[0308] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0309] The "Training title" is the name of the training program selected by the user, and indicates the specific training content.

[0310] "Server" is the central computer responsible for data processing, generation and distribution of training programs.

[0311] "Past history data" refers to data that records the training programs that the user has previously attended and the user's learning history.

[0312] "Ability evaluation data" is data that includes evaluation results regarding the skills and abilities of a user.

[0313] "Current business data" refers to data that includes information about the user's current job duties and business.

[0314] "Artificial Intelligence Engine" refers to software and algorithms used to analyze acquired data and assess a user's skill set and learning style.

[0315] "Emotion Analysis Engine" refers to software and algorithms for analyzing a user's emotional state.

[0316] A "personalized training program" is a training program that is individually created taking into account the user's skill set and emotional state.

[0317] "Progress information" is data that indicates the progress of a user as they progress through a training program.

[0318] "Emotion data" is data relating to emotions acquired by analyzing the user's facial expressions and voice.

[0319] The present invention relates to a system that recognizes a user's emotions and provides a personalized training program based on the results.

[0320] First, the user launches the application on their device and selects the desired program from among multiple training titles. This selection is sent to the server via the device. The training title information selected by the user is sent to the server as JSON format data.

[0321] The server retrieves the received training title information, as well as the user's past history data, ability evaluation data, and current job data stored in the database. Specifically, it extracts the necessary information using an SQL SELECT query.

[0322] The server then launches an artificial intelligence engine (e.g., TensorFlow) and provides the acquired user data as input. The AI ​​engine uses this data to analyze the user's current skill set and gaps, as well as assess their appropriate learning style.

[0323] Furthermore, the server uses an emotion analysis engine (e.g., a general emotion recognition API) to analyze the user's facial expression and voice data sent from the device. The emotion analysis engine evaluates the user's stress level and motivation state.

[0324] Based on the evaluation results of the AI ​​engine and the sentiment analysis engine, the server generates a list of training modules that are optimal for the user, and combines them to create a personalized training program. The generated training program is sent to the device as JSON format data.

[0325] The device receives the training program from the server and presents it to the user. If the user confirms and agrees with the training content, the training begins. During the training, the device periodically transmits the user's progress information and emotional data to the server.

[0326] The server records the received progress information and emotion data, and generates and provides the next optimal training module based on this information, thereby maintaining an optimal learning environment for the user and enabling effective skill acquisition.

[0327] Specific examples

[0328] Example: Presentation skills training

[0329] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[0330] 2. The device sends the selected training title to the server as JSON data.

[0331] 3. The server retrieves the user information from the database using an SQL query.

[0332] 4. The server loads the TensorFlow model and evaluates the user's skill set.

[0333] 5. The server uses a general emotion recognition API to analyze the user's facial expressions and voice data.

[0334] 6. The server generates a training program based on the evaluation results and creates a personalized program including "Advanced Slide Design" and "Effective Public Speaking."

[0335] 7. The server sends the generated program to the terminal.

[0336] 8. The terminal displays the training program to the user, and the user begins the training.

[0337] 9. As the user progresses through the training, the device periodically sends progress information and emotional data to the server.

[0338] 10. The server records these data and provides the next training module in a timely manner.

[0339] Prompt Sentence Examples

[0340] Prompt 1: Example input to a generative AI model

[0341] "The user has selected a training program to improve their presentation skills. Please suggest the most appropriate learning module based on their past training history, skill assessment, and current job duties. Also, please evaluate the user's emotional state using facial and voice data and take the results into consideration."

[0342] Prompt 2: Example of progress information

[0343] "Please tell us about the current training progress. Please let us know if the user is stressed or motivated, and how well they are progressing."

[0344] This system takes into account the user's emotional state and provides personalized training programs to achieve optimal learning outcomes.

[0345] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0346] Step 1:

[0347] The user starts the application on the terminal and selects the desired program from among a number of training titles.

[0348] Specific operation: The user selects a training title such as "Improve Presentation Skills" from the list of training titles on the screen.

[0349] Input: User selection information

[0350] Output: JSON data containing the selected training titles

[0351] Step 2:

[0352] The terminal transmits the user's selection information to the server.

[0353] Specific operation: The selected training title information is sent to the server in JSON format.

[0354] Input: JSON data containing the selected training titles

[0355] Output: Course title information sent to the server

[0356] Step 3:

[0357] The server acquires the received training title information, the user's past history data, ability evaluation data, and current work data stored in the database.

[0358] What happens next: The server uses an SQL SELECT query to retrieve the relevant user data from the database.

[0359] Input: Training title information, user ID

[0360] Output: Past history data, performance evaluation data, current business data

[0361] Step 4:

[0362] The server uses an artificial intelligence engine to analyze the acquired data and assess the user's skill set and learning style.

[0363] How it works: The server loads the TensorFlow model and inputs the acquired user data into the model to evaluate skill sets and learning styles.

[0364] Input: Past history data, performance evaluation data, current work data

[0365] Output: Evaluation results of user's skill set and learning style

[0366] Step 5:

[0367] The server uses an emotion analysis engine to analyze the user's emotional state.

[0368] Specific operation: The user's facial expression data and voice data sent from the device are input into the emotion recognition API and analyzed.

[0369] Input: facial expression data, voice data

[0370] Output: Evaluation result of the user's emotional state

[0371] Step 6:

[0372] Based on the evaluation results of the artificial intelligence engine and the sentiment analysis engine, the server generates a list of training modules that are optimal for the user and combines them to create a personalized training program.

[0373] Specific operation: Select modules such as "Advanced Slide Design" and "Effective Public Speaking" and combine programs according to the user's condition.

[0374] Input: Skill set assessment results, Learning style assessment results, Emotional state assessment results

[0375] Output: Personalized training program

[0376] Step 7:

[0377] The server transmits the generated training program to the terminal.

[0378] Specific operation: The generated training program is sent to the terminal in JSON format.

[0379] Input: Personalized training program

[0380] Output: Training program sent to the terminal

[0381] Step 8:

[0382] The terminal presents the training program to the user, and the user confirms the contents.

[0383] Specific operation: The training program is displayed on the screen and the user confirms it.

[0384] Input: Training program sent to the terminal

[0385] Output: User confirmation

[0386] Step 9:

[0387] The user starts training and sends progress information and emotion data to the server.

[0388] Specific operation: As the user progresses through each training module, the terminal records progress information, collects emotional data, and sends it to the server.

[0389] Input: Training progress data, emotion data

[0390] Output: Progress and emotion data sent to the server

[0391] Step 10:

[0392] The server records progress information and emotional data, and based on this generates and provides the next optimal training module.

[0393] Specific behavior: The server analyzes the progress and emotion data and adjusts the next training module as needed.

[0394] Input: Progress data, emotion data

[0395] Output: Next training module

[0396] The above are the specific processing steps of the system program.

[0397] (Application example 2)

[0398] 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."

[0399] Traditional training programs are generally provided uniformly and do not take into account the skill sets and emotional states of each user, which can result in reduced learning effectiveness.In addition, there is a lack of methods for conducting on-the-job training efficiently and safely within factories.

[0400] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a means for a user to select a training title on a terminal; a means for transmitting the selected training title to the server; a means for the server to acquire the user's past history data, ability evaluation data, and current work data; a means for the server to analyze the data using an AI engine and evaluate the user's skill set and learning style; a means for generating a personalized training program based on the evaluation; a means for analyzing facial expression data and voice data using an emotion engine and evaluating the user's emotional state; a means for customizing the training program based on the evaluation of the emotional state; a means for transmitting the generated training program to the terminal; a means for the terminal to present the training to the user and start the training; and a means for providing the training program to the user using a robot. This provides a personalized training program tailored to the user's skill set and emotional state, improving learning effectiveness. Furthermore, efficient and safe on-the-job training in factories is possible.

[0401] A "terminal" is a device that a user uses to select a training title and take a training program.

[0402] "Server" refers to the central processing unit that processes user history data and training title information, and generates and provides personalized training programs.

[0403] "Past history data" refers to data relating to the user's past training history and work history.

[0404] "Ability assessment data" is assessment data regarding the user's current skill set and abilities.

[0405] "Current business data" is data relating to the user's current business situation and the work he or she is in charge of.

[0406] An "AI engine" is an artificial intelligence technology that analyzes collected data and evaluates a user's skill set and learning style.

[0407] An "emotion engine" is a technology that analyzes a user's facial expression data and voice data to evaluate their emotional state.

[0408] A "training program" is structured content for users to learn or train.

[0409] "Customizing the training program" means adjusting and optimizing the training content based on the user's emotional state and evaluation results.

[0410] A "robot" is a mechanical device that supports practical training within a factory and provides and guides training programs to users.

[0411] "Facial expression data" refers to data relating to the facial expression of the user.

[0412] "Voice data" is data related to the user's speech.

[0413] "Progress" is information indicating at what stage the user is in the training program.

[0414] A "personalized training program" is training content that is customized based on a user's individual skill set and emotional state.

[0415] The present invention relates to a system for providing personalized training programs for personnel within a factory.

[0416] First, a user (factory employee) uses a terminal to start the training application and select a training title. For example, the user selects the training title "How to set up a CNC machine." This selected training title information is sent from the terminal to the server.

[0417] The server uses the received training title information and the user's ID to retrieve past history data, ability evaluation data, and current work data from the database, thereby understanding the user's learning history and current skill status.

[0418] The server then uses an AI engine to analyze this data and assess the user's skill set and learning style, identifying their current skill level and gaps, and recommending optimal learning content.

[0419] Additionally, an emotion engine is used to analyze the user's facial expression and voice data to assess their emotional state. For example, it can determine whether the user is feeling stressed or highly motivated. This allows the system to add and adjust training modules according to the user's emotional state, as well as the learning content.

[0420] Based on the evaluation results from the AI ​​engine and emotion engine, the server generates a personalized training program, which may include modules such as "basic operation explanations," "safety measures," and even "stress management" and "improving concentration."

[0421] The generated training program is sent to the terminal, which then presents it to the user. The user then checks the training program and begins the training. The training is carried out using a robot. A robot placed in the factory presents the training content to the user as they progress, providing guidance on work procedures and safety measures.

[0422] During the training, the robot continuously monitors the user's facial expressions and speech, and transmits progress information and emotional data to the server, which records this data and uses it to optimize future training programs.

[0423] This allows users to receive personalized training tailored to their skill sets and emotional state, maximizing learning effectiveness. Furthermore, the use of robots enables efficient and safe on-the-job training within factories.

[0424] For example, if a user selects training on "How to set up a CNC machine," the AI ​​engine will determine that basic operations are necessary based on past operation history and evaluation data, and add a module for "Explanation of basic operations." On the other hand, if the emotion engine detects stress from the user's facial expression, modules on relaxation methods and stress management will also be added.

[0425] Furthermore, this system uses a generative AI model to prepare prompts, enabling flexible and intuitive training program generation. For example, the system uses prompts such as:

[0426] Generate optimal training programs based on skill set assessments of how to configure CNC machines and employees' emotional states. Use past work history and facial expression analysis data to personalize the content, including modules on stress management and focus improvement.

[0427] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0428] Step 1:

[0429] The user starts the training application using the terminal and selects a training title. The input is the user's selection operation, and the output is the selected training title information. This information is sent to the server in the next step.

[0430] Step 2:

[0431] The terminal sends the selected training title information and user ID to the server. The input is the training title information and user ID, and the output is the data sent to the server.

[0432] Step 3:

[0433] Based on the training title information and user ID received by the server, past history data, ability evaluation data, and current work data are retrieved from the database. The input is the training title information and user ID, and the output is the retrieved user data.

[0434] Step 4:

[0435] The server uses an AI engine to analyze the acquired data and evaluate the user's skill set and learning style. The input is past history data, ability assessment data, and current work data, and the output is the evaluation results of the user's skill set and learning style.

[0436] Step 5:

[0437] The server uses an emotion engine to analyze the user's facial expression and voice data and evaluate their emotional state. The input is the user's facial expression and voice data, and the output is the evaluation result of their emotional state.

[0438] Step 6:

[0439] The server generates a personalized training program based on the evaluation results of the AI ​​engine and the emotion engine. The inputs are the evaluation results of the skill set and learning style, and the evaluation results of the emotional state, and the output is the generated personalized training program.

[0440] Step 7:

[0441] The server sends the generated training program to the terminal, where the input is the generated training program and the output is the training program sent to the terminal.

[0442] Step 8:

[0443] The terminal presents the training program to the user and starts the training. The input is the training program sent, and the output is instructions for the user to start the training.

[0444] Step 9:

[0445] During the training, the user interacts with the robot. The robot monitors the user's progress and emotional data in real time and sends them to the server. The input is the user's progress and emotional data, and the output is the progress and emotional data sent to the server.

[0446] Step 10:

[0447] The server records the received progress information and emotion data, and optimizes and provides the next training module. The input is the progress information and emotion data, and the output is the next optimized training module.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] [Second embodiment]

[0452] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0453] 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.

[0454] 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).

[0455] 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.

[0456] 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.

[0457] 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).

[0458] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] In the smart glasses 214, 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.

[0463] 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."

[0464] The present invention aims to provide a personalized training program based on the needs of each user. In the system of the present invention, the user selects a training title on the terminal, and the server generates and provides the optimal training program based on the selection. Specifically, the process is as follows:

[0465] First, the user launches the application on their device and selects the desired program from among multiple training titles. This selection is sent to the server via the device. The server then acquires and analyzes the received training title information, as well as the user's past history data, ability evaluation data, and current work data stored in the database.

[0466] The server uses an AI engine to analyze this data and assess the user's current skill set, gaps, and optimal learning style. Based on this assessment, it generates a list of training modules that are best suited to the user and combines them to create a personalized training program.

[0467] The server sends the generated training program to the terminal, which then presents it to the user. The user checks the content of the training program and begins the training if they are satisfied. During the training, the terminal sends the user's progress information to the server, which records this progress. This allows the next training module to be provided in a timely manner.

[0468] It is designed to help users efficiently acquire the skills they need to maximize their learning, and by regularly monitoring their progress, it also helps them maintain and improve their skills over the long term.

[0469] Specific examples

[0470] A specific example is shown below.

[0471] Example 1: Presentation skills training

[0472] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[0473] 2. The terminal sends the selected training title to the server.

[0474] 3. The server retrieves the user's past history data, ability evaluation data, and current work data from the database based on the user ID and the selected training title information.

[0475] 4. The server calls the AI ​​engine and provides these data as input.

[0476] 5. The AI ​​engine analyzes the user's skill set and assesses their skillset and weaknesses. For example, they may be able to create basic slides, but lack effective slide design and audience interaction.

[0477] 6. The server selects training modules based on the results of these evaluations, such as "Advanced Slide Design" and "Effective Public Speaking."

[0478] 7. The server combines the selected modules to create a personalized training program and sends it to the terminal.

[0479] 8. The device presents the training program to the user. The user begins the training and sends progress information to the server as they complete each step.

[0480] 9. The server will record your progress and provide you with the next training content in a timely manner.

[0481] Through this process, users can receive training that is optimized for them, maximizing their learning effect and helping to increase their motivation and continuously improve their skills.

[0482] The processing flow will be explained below.

[0483] Step 1:

[0484] The user starts the application on the terminal and selects the desired training title "improving presentation skills" from among a number of training titles.

[0485] Step 2:

[0486] The device sends request data including the selected training title to the server. For example, the data is sent in JSON format along with the user ID.

[0487] Step 3:

[0488] The server receives the request and accesses a database to obtain the user's history data, performance assessment data, and current job data.

[0489] Step 4:

[0490] The server inputs this acquired data into an AI engine and provides it as parameters for analyzing the user's skill set, skill gaps, and optimal learning style.

[0491] Step 5:

[0492] The AI ​​engine analyzes the data and evaluates the user's skills, such as their current ability to create slides, their ability to interact with the audience, and any gaps in their skills that may be required.

[0493] Step 6:

[0494] The server receives the analysis results from the AI ​​engine and generates a personalized training program based on them, combining modules such as "Advanced Slide Design" and "Effective Public Speaking."

[0495] Step 7:

[0496] The server sends the generated training program to the terminal, which includes details of each module and the order in which they are executed.

[0497] Step 8:

[0498] The terminal presents the received training program to the user, and displays the program content and module configuration.

[0499] Step 9:

[0500] The user checks the presented program and, if satisfied, begins the training by, for example, pressing the "Start" button.

[0501] Step 10:

[0502] The terminal notifies the server of the user's training start action.

[0503] Step 11:

[0504] The server approves the start of the training and provides the necessary training resources (videos, texts, quizzes, etc.).

[0505] Step 12:

[0506] The terminal sequentially displays these resources to the user, and the training program progresses.

[0507] Step 13:

[0508] As the user completes each step, the terminal sends progress information to the server, for example, sending progress data upon completion of each module.

[0509] Step 14:

[0510] The server records the progress and delivers the next training module in a timely manner, and can also flexibly adjust the next step according to the progress.

[0511] Step 15:

[0512] The terminal then presents the user with the next training module, and so on until the entire training program is completed.

[0513] Through these steps, users can receive training programs optimized for them and improve their skills.

[0514] Example 1

[0515] 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."

[0516] Conventional training systems have struggled to provide personalized training programs based on individual user needs. This is due to a lack of technology to comprehensively analyze each user's history data, ability assessment data, and current work data, and automatically generate training programs based on that data. Furthermore, there was no mechanism in place to monitor training progress in real time and provide the next appropriate training module in a timely manner.

[0517] 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.

[0518] In this invention, the server includes means for a user to select a training title on a terminal, means for transmitting the selected training title to the server, means for acquiring the user's past history data, ability assessment data, and current work data, means for analyzing the data using a generative AI model and evaluating the user's skill set and learning style, means for generating a personalized training program based on the evaluation, means for transmitting the generated training program to the terminal, means for the terminal to present the program to the user and start the training, means for transmitting progress information to the server, and means for recording the progress information and providing the next training content in a timely manner. This allows users to receive training programs suited to their individual needs and enables effective skill improvement.

[0519] "User" refers to any individual or legal entity participating in the training program.

[0520] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[0521] "Server" refers to a computer system that performs database access, data analysis, and training program generation and delivery.

[0522] "Training title" refers to the name or theme of the training program selected by the user.

[0523] "Database" refers to an information system that stores users' past history data, performance evaluation data, and current business data.

[0524] "Generative AI model" refers to the artificial intelligence engine that analyzes data and generates personalized training programs.

[0525] A "skill set" refers to the collection of skills and knowledge possessed by a user.

[0526] "Learning style" refers to the method or format in which a user learns optimally.

[0527] "Personalized training program" refers to a learning plan that is customized to meet the user's individual needs.

[0528] "Progress Information" refers to progress data collected as a user progresses through a training program.

[0529] "Training Module" means a separate learning unit or session that forms part of a training program.

[0530] "Real-time" refers to data and information being processed and updated instantly.

[0531] The present invention is a system that provides personalized training programs based on the needs of each user. In this system, the user selects a training title on the terminal, and the server generates and provides the optimal training program based on that selection. The details are explained below.

[0532] First, the user launches the application installed on the terminal and selects the desired program from the multiple training titles provided. For example, if the user selects the training title "Improve Presentation Skills," this information is sent to the server via the terminal. The server retrieves the received training title information, as well as the user's past history data, ability evaluation data, and current work data stored in the database.

[0533] The server collects this data and analyzes it using a generative AI model. Specifically, it evaluates the user's current skill set, gaps, and optimal learning style. Based on this evaluation, the server generates a list of training modules that are optimal for the user and combines them to create a personalized training program.

[0534] The generated training program is again sent from the server to the terminal. The terminal presents this training program to the user, and the user begins the training. As the training progresses, the terminal sends progress information to the server, which records this progress. This allows the next training module to be provided in a timely manner.

[0535] Through this system, users can receive training that is optimized for them, allowing them to efficiently acquire the necessary skills. Furthermore, by regularly monitoring their progress, it is possible to maintain and improve their skills over the long term.

[0536] Specific examples

[0537] A specific example is shown below.

[0538] Example 1: Presentation skills training

[0539] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[0540] 2. The terminal sends the selected training title to the server.

[0541] 3. The server retrieves the user's past history data, ability evaluation data, and current work data from the database based on the user ID and the selected training title information.

[0542] 4. The server invokes the generative AI model, providing these data as input.

[0543] 5. The generative AI model analyzes and evaluates the user's skill set and skills gaps. For example, it may say, "You have basic slide creation skills, but lack effective slide design and audience interaction."

[0544] 6. The server selects training modules based on these evaluation results, such as "Advanced Slide Design" and "Effective Public Speaking."

[0545] 7. The server combines the selected modules to create a personalized training program and sends it to the terminal.

[0546] 8. The device presents the training program to the user. The user begins the training and sends progress information to the server as they complete each step.

[0547] 9. The server will record your progress and provide you with the next training content in a timely manner.

[0548] Through this process, users can receive training that is optimized for them, maximizing their learning effect and helping to increase their motivation and continuously improve their skills.

[0549] Prompt Sentence Examples

[0550] "I am currently seeking training in 'improving presentation skills.' Please select the most appropriate training module for me based on my past and current work data."

[0551] In this way, by using this system, users can receive training programs tailored to their individual needs, enabling them to acquire skills effectively.

[0552] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0553] Step 1:

[0554] The user launches the app on their device and selects a training title. First, the user clicks on the desired training title from the multiple training titles provided. This selection information (training title, user ID, etc.) is entered into the device. The device stores this information in its internal memory.

[0555] Input: User ID, training title

[0556] Output: Selection information

[0557] Step 2:

[0558] The device sends the selected training title to the server. The device creates an API request and sends the selection information to the server using the HTTP POST method. For example, the device constructs the data in JSON format and sends it to the specified endpoint.

[0559] Input: Selection information

[0560] Output: API request

[0561] Step 3:

[0562] The server references the database based on the user ID and training title information to retrieve the required data. Based on the received user ID and training title, the server executes an SQL query to retrieve the following data: The user's past history data, ability evaluation data, and current job data.

[0563] Input: User ID, training title

[0564] Output: Acquired data (history data, performance evaluation data, business data)

[0565] Step 4:

[0566] The server calls the generative AI model to analyze the data. The server provides the acquired data as input to the AI ​​engine. The AI ​​engine analyzes this data and evaluates the user's current skill set, missing skills, and optimal learning style. This evaluation result is generated.

[0567] Input: Acquired data (history data, performance evaluation data, business data)

[0568] Output: Analysis results (skill set, skills gaps, learning style)

[0569] Step 5:

[0570] The server selects the most suitable training module based on the analysis results. The server lists the most suitable training modules based on the analysis results of the AI ​​engine. For example, "Advanced Slide Design" and "Effective Public Speaking" are selected.

[0571] Input: Analysis results

[0572] Output: Selection module

[0573] Step 6:

[0574] The server sends the generated training program to the device. The server combines the selection modules to generate a personalized training program and sends it to the device. It issues an HTTP POST request using the API endpoint.

[0575] Input: Selection module

[0576] Output: Personalized training program

[0577] Step 7:

[0578] The terminal presents the training program to the user. The terminal analyzes the received training program and displays it on the user interface. The user confirms the contents of the training program and starts it.

[0579] Input: Personalized Training Program

[0580] Output: Display training program

[0581] Step 8:

[0582] The user starts the training and sends progress information from the device to the server. As the user progresses through the training, the device periodically sends progress information to the server. For example, progress information is collected each time each step is completed.

[0583] Input: Training progress

[0584] Output: Progress information

[0585] Step 9:

[0586] The server records the progress information and provides the next training content in a timely manner. The server records the received progress information in a database and prepares to provide the next training module based on that information. The next module is sent to the terminal in a timely manner according to the progress.

[0587] Input: Progress information

[0588] Output: Next training module

[0589] Through these steps, users can efficiently receive training that is optimized for them, maximizing the effectiveness of their learning.

[0590] (Application example 1)

[0591] 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."

[0592] In recent years, with the widespread use of robots in factories, improving the skills of operators and maintenance personnel has become increasingly important. However, standardized, one-size-fits-all training programs are difficult to address, making it difficult to efficiently acquire skills. Conventional training programs do not adequately consider users' past work history or on-site requirements, making it difficult to maximize users' learning efficiency. Given this background, there is a need to provide personalized training programs based on each user's skill level and past work history in order to efficiently improve skills.

[0593] 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.

[0594] In this invention, the server includes: means for a user to select a training title on a terminal; means for transmitting the selected training title to the server; means for the server to acquire the user's past history data, ability evaluation data, and current work data; means for analyzing the data using an AI engine and evaluating the user's skill set and learning style; means for generating a personalized training program; means for transmitting the generated training program to the terminal; means for the terminal to present the program to the user and start the training; means for the terminal to provide training titles related to the operation and maintenance of factory robots; means for the server to recommend the next training module required based on the user's current skill level and past work history; and means for recording progress information of the training modules and providing the next module at an appropriate time. This makes it possible to provide an optimal training program based on each user's skill level and work history, thereby efficiently improving skills.

[0595] "Users" refer to factory operators and maintenance personnel who use this system to take training programs.

[0596] A "terminal" is a device that a user operates, and includes tablets and displays built into factory robots.

[0597] "Training Title" refers to the name of a particular training program selected by the user.

[0598] "Server" refers to the central system that manages the information and data selected by the user and analyzes the data using an AI engine.

[0599] "History data" refers to data related to the user's past behavioral history, such as records of tasks and operations performed by the user in the past, and error reports.

[0600] "Ability Assessment Data" refers to assessment data related to a user's skill level and abilities, including past test results and assessment reports.

[0601] "Current work data" refers to data related to the work the user is currently responsible for, including current job duties and project information.

[0602] An "AI engine" refers to a system that uses artificial intelligence technology to analyze data and evaluate a user's skill set and shortcomings.

[0603] A "skill set" refers to the collection of skills and abilities that a user possesses.

[0604] "Learning style" refers to characteristics that indicate how a user learns most effectively.

[0605] "Personalized training program" refers to a training program that is customized based on the user's individual needs and skill level.

[0606] A "factory robot" is an automated machine used in a factory to carry out manufacturing and maintenance processes.

[0607] "Training Module" means a separate learning unit within a training program that provides independent learning content.

[0608] This invention realizes a system that provides personalized training programs for factory robot operators and maintenance personnel. In this system, a user selects a training title on a terminal, and a server generates and provides an optimal training program based on the user's selection.

[0609] In a specific embodiment, the following process is performed. First, the user starts up the terminal and selects a desired program from multiple training titles. This selection is sent to the server via the terminal. The server acquires and analyzes the received training title information, as well as the user's past history data, ability assessment data, and current work data stored in a database. The server analyzes the data using an AI engine (e.g., TensorFlow) and evaluates the user's current skill set, skill gaps, and optimal learning style. Based on the evaluation results, it generates a list of training modules optimal for the user and combines them to create a personalized training program. The generated training program is sent to the terminal, which presents it to the user. The user reviews the content of the presented training program and, if satisfied, begins the training. During the training, the terminal transmits the user's progress information to the server, which records this progress. This allows the next training module to be provided in a timely manner.

[0610] Hardware and software used

[0611] The following hardware and software are used to realize this system.

[0612] Hardware: Android / iOS compatible tablets, displays built into factory robots

[0613] software:

[0614] Server side: Python

[0615] Database Management: MySQL

[0616] AI analysis engine: TensorFlow

[0617] Application frontend: React Native

[0618] Program processing explanation

[0619] The server uses TensorFlow to analyze the user's selected training title, past history data, ability assessment data, and current work data. The analysis evaluates the user's skill set and learning style, and generates optimal training modules based on that. The generated training modules are organized into a personalized training program and sent to the user's device at the appropriate time.

[0620] Specific examples

[0621] For example, if a user selects a training title such as "Precise Operation of a Robot Arm," the server will generate a customized training program that allows the user to learn in stages from "Basic Grip Operation" to "High-Precision Positioning Techniques" based on the frequency of past operational errors and evaluation data.

[0622] Prompt Sentence Examples

[0623] An example of a prompt sentence to input to the generative AI model is as follows:

[0624] "For the training title 'Precision Operation of Robot Arms' selected by user ID 5678, please recommend the next necessary training module based on past operation errors and current evaluation data."

[0625] These prompts allow users to receive training that is optimized for their skill level and needs, enabling them to improve their skills efficiently.

[0626] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0627] Step 1:

[0628] The user starts up the terminal and selects the desired program from among multiple training titles.

[0629] Input: List of training titles

[0630] Output: Selected training title

[0631] Specific operation: The user selects the desired training title from the list of training titles displayed on the device screen by tapping it. The selected training title is then saved in the device.

[0632] Step 2:

[0633] The terminal transmits the selected training title to the server.

[0634] Input: Selected training title

[0635] Output: Training title sent to the server

[0636] Specific operation: The device uses its internal communication function to send the selected training title to the server via the network, along with the user ID and time information.

[0637] Step 3:

[0638] The server acquires the user's past history data, performance evaluation data, and current business data.

[0639] Input: User ID and selected training title

[0640] Output: User's past history data, performance evaluation data, current work data

[0641] Specific operation: The server accesses the database and retrieves past history data (e.g., operation error history), ability evaluation data (e.g., skill evaluation results), and current business data (e.g., information about the project currently in charge) corresponding to the user ID.

[0642] Step 4:

[0643] The server uses an AI engine to analyze the data and assess the user's skill set and learning style.

[0644] Input: User's past history data, performance evaluation data, current work data

[0645] Output: Assessment of user skill sets and learning styles

[0646] How it works: The server launches an AI engine such as TensorFlow to analyze the input data. Specifically, it preprocesses the dataset and inputs it into a model to evaluate the strengths and weaknesses of the user's skills and the optimal learning method.

[0647] Step 5:

[0648] The server generates a personalized training program based on the assessment.

[0649] Input: User skill set and learning style assessment results

[0650] Output: Personalized training program

[0651] Specific operation: Based on the evaluation results, the server selects appropriate training modules (e.g., "basic grip operation" and "high-precision positioning techniques") and combines them to generate a personalized training program.

[0652] Step 6:

[0653] The server transmits the generated training program to the terminal.

[0654] Enter: personalized training programs.

[0655] Output: Training program sent to the device

[0656] Specific operation: The server transmits the generated training program to the terminal via the network, including the program sequence and detailed information.

[0657] Step 7:

[0658] The terminal presents the training program to the user, and the user starts the training.

[0659] Input: Training program sent from the server

[0660] Output: User who started the training

[0661] Specific operation: The device displays the training program on the screen, and the training begins when the user presses the "Start" button. The user proceeds with the learning according to the presented content.

[0662] Step 8:

[0663] The terminal transmits the user's progress information to the server.

[0664] Input: User training progress information

[0665] Output: Progress information sent to the server

[0666] Specific operation: The terminal records the user's training progress (e.g., completed modules, test results) in real time and transmits it to the server in a timely manner.

[0667] Step 9:

[0668] The server records progress information and provides the next training module at the appropriate time.

[0669] Input: User training progress information

[0670] Output: Next training module

[0671] Specific operation: The server stores the received progress information in a database, automatically selects the next required training module, and sends it to the terminal at the appropriate time.

[0672] 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.

[0673] The present invention relates to a system that recognizes a user's emotions and provides a personalized training program based on the results. In this system, the user selects a training title on a terminal, and the server generates and provides an optimal training program based on that selection. The system also analyzes the user's emotional state using an emotion engine. This makes it possible to customize the training program according to the user's emotional state.

[0674] First, the user launches the application on their device and selects the desired program from among multiple training titles. This selection is sent to the server via the device. The server then acquires and analyzes the received training title information, as well as the user's past history data, ability evaluation data, and current work data stored in the database.

[0675] The server uses an AI engine to analyze this data and assess the user's current skill set, gaps, and optimal learning style. It also uses an emotion engine to analyze the user's emotional state. The emotion engine uses facial and voice data to recognize emotions and assess their state.

[0676] Based on the evaluation results from both the AI ​​engine and the emotion engine, the server generates a list of training modules that are optimal for the user and combines them to create a personalized training program. For example, if the user is feeling stressed, a training module for relaxation can be added.

[0677] The server sends the generated training program to the terminal, which then presents it to the user. The user reviews the content of the training program and begins the training if they are satisfied. During the training, the terminal sends the user's progress information and emotional data to the server, which records the progress and emotional state. This allows the next training module to be provided in a timely manner based on the user's emotional state.

[0678] It is designed to help users efficiently acquire the skills necessary to maximize their learning outcomes, and by taking into account the user's emotional state, it can improve learning motivation and manage stress.

[0679] Specific examples

[0680] A specific example is shown below.

[0681] Example 1: Presentation skills training

[0682] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[0683] 2. The terminal sends the selected training title to the server.

[0684] 3. The server retrieves the user's past history data, ability evaluation data, and current work data from the database based on the user ID and the selected training title information.

[0685] 4. The server calls the AI ​​engine, provides this data as input, and evaluates the user's skill set and skills gaps, such as their current ability to create slides, their ability to interact with the audience, and the skills gaps they need.

[0686] 5. The emotion engine analyzes the user's facial expression and voice data to assess whether the user is feeling stressed or highly motivated.

[0687] 6. Based on the evaluation results from the AI ​​engine and emotion engine, the server generates a personalized training program that includes modules on "Advanced Slide Design," "Effective Public Speaking," and stress management.

[0688] 7. The server transmits the generated training program to the terminal.

[0689] 8. The device presents the training program to the user. The user begins the training, and each time the device completes a step, it sends progress information and emotion data to the server.

[0690] 9. The server records the progress and emotional state and provides the next training content in a timely manner.

[0691] This system allows users to receive training tailored to their needs, maximizing learning effectiveness, and by taking into account their emotional state, it can improve their motivation and manage stress.

[0692] The processing flow will be explained below.

[0693] Step 1:

[0694] The user starts the application on the terminal and selects the desired training title "Improve Presentation Skills" from the list of available training titles.

[0695] Step 2:

[0696] The device sends request data including the selected training title to the server. For example, the data is sent in JSON format along with the user ID.

[0697] Step 3:

[0698] The server receives the request and accesses a database to obtain the user's history data, performance assessment data, and current job data.

[0699] Step 4:

[0700] The server inputs this data into the AI ​​engine and emotion engine, providing it as parameters for analyzing the user's skill set, skill gaps, optimal learning style, and emotional state.

[0701] Step 5:

[0702] The emotion engine analyzes the user's facial expression and voice data to assess their emotional state, for example, determining whether they are stressed, relaxed, or motivated.

[0703] Step 6:

[0704] Based on these inputs, the AI ​​engine assesses the user's current skill set, any gaps in skills, and their optimal learning style.

[0705] Step 7:

[0706] The server receives the evaluation results of the AI ​​engine and emotion engine and generates a list of training modules that are optimal for the user's condition. For example, in addition to the modules "Advanced Slide Design" and "Effective Public Speaking," a module for stress management can be added.

[0707] Step 8:

[0708] The server transmits the generated personalized training program to the terminal.

[0709] Step 9:

[0710] The terminal presents the received training program to the user, and displays the program content and module configuration.

[0711] Step 10:

[0712] The user checks the presented program and, if satisfied, begins the training by, for example, pressing the "Start" button.

[0713] Step 11:

[0714] The terminal notifies the server of the user's training start action.

[0715] Step 12:

[0716] The server approves the start of the training and provides the necessary training resources (videos, texts, quizzes, etc.).

[0717] Step 13:

[0718] The terminal sequentially displays these resources to the user, and the training program progresses.

[0719] Step 14:

[0720] Each time the user completes a step, the terminal transmits its progress information and emotional data to the server, for example, sending progress data and emotional state upon completion of each module.

[0721] Step 15:

[0722] The server records the progress and emotional state of the user, and delivers the next training module in a timely manner according to the user's emotional state.

[0723] Step 16:

[0724] The terminal then presents the user with the next training module and repeats this until the entire training program is complete, for example, if the user is feeling stressed, a module on relaxation may be included.

[0725] Through these steps, users can receive personalized training programs and improve their skills. Furthermore, by taking into account the user's emotional state, it is possible to improve motivation and manage stress.

[0726] Example 2

[0727] 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."

[0728] Conventional training systems provided training programs based only on the user's past history and ability evaluation data, making it difficult to provide effective training programs that took into account the emotional state of each individual user.Furthermore, they did not have the functionality to analyze progress information and emotional data in real time and provide the next training content in a timely manner, making it difficult to maximize the learning effect of users.

[0729] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0730] In this invention, the server includes means for acquiring the user's past history data, ability evaluation data, and current work data, means for analyzing the data using an artificial intelligence engine to evaluate the user's skill set and learning style, and means for analyzing the user's emotional state using an emotion analysis engine, thereby enabling the provision of a personalized training program that takes the user's emotional state into consideration.

[0731] A "user" is a person who uses the system to take a training program.

[0732] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0733] The "Training title" is the name of the training program selected by the user, and indicates the specific training content.

[0734] "Server" is the central computer responsible for data processing, generation and distribution of training programs.

[0735] "Past history data" refers to data that records the training programs that the user has previously attended and the user's learning history.

[0736] "Ability evaluation data" is data that includes evaluation results regarding the skills and abilities of a user.

[0737] "Current business data" refers to data that includes information about the user's current job duties and business.

[0738] "Artificial Intelligence Engine" refers to software and algorithms used to analyze acquired data and assess a user's skill set and learning style.

[0739] "Emotion Analysis Engine" refers to software and algorithms for analyzing a user's emotional state.

[0740] A "personalized training program" is a training program that is individually created taking into account the user's skill set and emotional state.

[0741] "Progress information" is data that indicates the progress of a user as they progress through a training program.

[0742] "Emotion data" is data relating to emotions acquired by analyzing the user's facial expressions and voice.

[0743] The present invention relates to a system that recognizes a user's emotions and provides a personalized training program based on the results.

[0744] First, the user launches the application on their device and selects the desired program from among multiple training titles. This selection is sent to the server via the device. The training title information selected by the user is sent to the server as JSON format data.

[0745] The server retrieves the received training title information, as well as the user's past history data, ability evaluation data, and current job data stored in the database. Specifically, it extracts the necessary information using an SQL SELECT query.

[0746] The server then launches an artificial intelligence engine (e.g., TensorFlow) and provides the acquired user data as input. The AI ​​engine uses this data to analyze the user's current skill set and gaps, as well as assess their appropriate learning style.

[0747] Furthermore, the server uses an emotion analysis engine (e.g., a general emotion recognition API) to analyze the user's facial expression and voice data sent from the device. The emotion analysis engine evaluates the user's stress level and motivation state.

[0748] Based on the evaluation results of the AI ​​engine and the sentiment analysis engine, the server generates a list of training modules that are optimal for the user, and combines them to create a personalized training program. The generated training program is sent to the device as JSON format data.

[0749] The device receives the training program from the server and presents it to the user. If the user confirms and agrees with the training content, the training begins. During the training, the device periodically transmits the user's progress information and emotional data to the server.

[0750] The server records the received progress information and emotion data, and generates and provides the next optimal training module based on this information, thereby maintaining an optimal learning environment for the user and enabling effective skill acquisition.

[0751] Specific examples

[0752] Example: Presentation skills training

[0753] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[0754] 2. The device sends the selected training title to the server as JSON data.

[0755] 3. The server retrieves the user information from the database using an SQL query.

[0756] 4. The server loads the TensorFlow model and evaluates the user's skill set.

[0757] 5. The server uses a general emotion recognition API to analyze the user's facial expressions and voice data.

[0758] 6. The server generates a training program based on the evaluation results and creates a personalized program including "Advanced Slide Design" and "Effective Public Speaking."

[0759] 7. The server sends the generated program to the terminal.

[0760] 8. The terminal displays the training program to the user, and the user begins the training.

[0761] 9. As the user progresses through the training, the device periodically sends progress information and emotional data to the server.

[0762] 10. The server records these data and provides the next training module in a timely manner.

[0763] Prompt Sentence Examples

[0764] Prompt 1: Example input to a generative AI model

[0765] "The user has selected a training program to improve their presentation skills. Please suggest the most appropriate learning module based on their past training history, skill assessment, and current job duties. Also, please evaluate the user's emotional state using facial and voice data and take the results into consideration."

[0766] Prompt 2: Example of progress information

[0767] "Please tell us about the current training progress. Please let us know if the user is stressed or motivated, and how well they are progressing."

[0768] This system takes into account the user's emotional state and provides personalized training programs to achieve optimal learning outcomes.

[0769] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0770] Step 1:

[0771] The user starts the application on the terminal and selects the desired program from among a number of training titles.

[0772] Specific operation: The user selects a training title such as "Improve Presentation Skills" from the list of training titles on the screen.

[0773] Input: User selection information

[0774] Output: JSON data containing the selected training titles

[0775] Step 2:

[0776] The terminal transmits the user's selection information to the server.

[0777] Specific operation: The selected training title information is sent to the server in JSON format.

[0778] Input: JSON data containing the selected training titles

[0779] Output: Course title information sent to the server

[0780] Step 3:

[0781] The server acquires the received training title information, the user's past history data, ability evaluation data, and current work data stored in the database.

[0782] What happens next: The server uses an SQL SELECT query to retrieve the relevant user data from the database.

[0783] Input: Training title information, user ID

[0784] Output: Past history data, performance evaluation data, current business data

[0785] Step 4:

[0786] The server uses an artificial intelligence engine to analyze the acquired data and assess the user's skill set and learning style.

[0787] How it works: The server loads the TensorFlow model and inputs the acquired user data into the model to evaluate skill sets and learning styles.

[0788] Input: Past history data, performance evaluation data, current work data

[0789] Output: Evaluation results of user's skill set and learning style

[0790] Step 5:

[0791] The server uses an emotion analysis engine to analyze the user's emotional state.

[0792] Specific operation: The user's facial expression data and voice data sent from the device are input into the emotion recognition API and analyzed.

[0793] Input: facial expression data, voice data

[0794] Output: Evaluation result of the user's emotional state

[0795] Step 6:

[0796] Based on the evaluation results of the artificial intelligence engine and the sentiment analysis engine, the server generates a list of training modules that are optimal for the user and combines them to create a personalized training program.

[0797] Specific operation: Select modules such as "Advanced Slide Design" and "Effective Public Speaking" and combine programs according to the user's condition.

[0798] Input: Skill set assessment results, Learning style assessment results, Emotional state assessment results

[0799] Output: Personalized training program

[0800] Step 7:

[0801] The server transmits the generated training program to the terminal.

[0802] Specific operation: The generated training program is sent to the terminal in JSON format.

[0803] Input: Personalized training program

[0804] Output: Training program sent to the terminal

[0805] Step 8:

[0806] The terminal presents the training program to the user, and the user confirms the contents.

[0807] Specific operation: The training program is displayed on the screen and the user confirms it.

[0808] Input: Training program sent to the terminal

[0809] Output: User confirmation

[0810] Step 9:

[0811] The user starts training and sends progress information and emotion data to the server.

[0812] Specific operation: As the user progresses through each training module, the terminal records progress information, collects emotional data, and sends it to the server.

[0813] Input: Training progress data, emotion data

[0814] Output: Progress and emotion data sent to the server

[0815] Step 10:

[0816] The server records progress information and emotional data, and based on this generates and provides the next optimal training module.

[0817] Specific behavior: The server analyzes the progress and emotion data and adjusts the next training module as needed.

[0818] Input: Progress data, emotion data

[0819] Output: Next training module

[0820] The above are the specific processing steps of the system program.

[0821] (Application example 2)

[0822] 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."

[0823] Traditional training programs are generally provided uniformly and do not take into account the skill sets and emotional states of each user, which can result in reduced learning effectiveness.In addition, there is a lack of methods for conducting on-the-job training efficiently and safely within factories.

[0824] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a means for a user to select a training title on a terminal; a means for transmitting the selected training title to the server; a means for the server to acquire the user's past history data, ability evaluation data, and current work data; a means for the server to analyze the data using an AI engine and evaluate the user's skill set and learning style; a means for generating a personalized training program based on the evaluation; a means for analyzing facial expression data and voice data using an emotion engine and evaluating the user's emotional state; a means for customizing the training program based on the evaluation of the emotional state; a means for transmitting the generated training program to the terminal; a means for the terminal to present the training to the user and start the training; and a means for providing the training program to the user using a robot. This provides a personalized training program tailored to the user's skill set and emotional state, improving learning effectiveness. Furthermore, efficient and safe on-the-job training in factories is possible.

[0825] A "terminal" is a device that a user uses to select a training title and take a training program.

[0826] "Server" refers to the central processing unit that processes user history data and training title information, and generates and provides personalized training programs.

[0827] "Past history data" refers to data relating to the user's past training history and work history.

[0828] "Ability assessment data" is assessment data regarding the user's current skill set and abilities.

[0829] "Current business data" is data relating to the user's current business situation and the work he or she is in charge of.

[0830] An "AI engine" is an artificial intelligence technology that analyzes collected data and evaluates a user's skill set and learning style.

[0831] An "emotion engine" is a technology that analyzes a user's facial expression data and voice data to evaluate their emotional state.

[0832] A "training program" is structured content for users to learn or train.

[0833] "Customizing the training program" means adjusting and optimizing the training content based on the user's emotional state and evaluation results.

[0834] A "robot" is a mechanical device that supports practical training within a factory and provides and guides training programs to users.

[0835] "Facial expression data" refers to data relating to the facial expression of the user.

[0836] "Voice data" is data related to the user's speech.

[0837] "Progress" is information indicating at what stage the user is in the training program.

[0838] A "personalized training program" is training content that is customized based on a user's individual skill set and emotional state.

[0839] The present invention relates to a system for providing personalized training programs for personnel within a factory.

[0840] First, a user (factory employee) uses a terminal to start the training application and select a training title. For example, the user selects the training title "How to set up a CNC machine." This selected training title information is sent from the terminal to the server.

[0841] The server uses the received training title information and the user's ID to retrieve past history data, ability evaluation data, and current work data from the database, thereby understanding the user's learning history and current skill status.

[0842] The server then uses an AI engine to analyze this data and assess the user's skill set and learning style, identifying their current skill level and gaps, and recommending optimal learning content.

[0843] Additionally, an emotion engine is used to analyze the user's facial expression and voice data to assess their emotional state. For example, it can determine whether the user is feeling stressed or highly motivated. This allows the system to add and adjust training modules according to the user's emotional state, as well as the learning content.

[0844] Based on the evaluation results from the AI ​​engine and emotion engine, the server generates a personalized training program, which may include modules such as "basic operation explanations," "safety measures," and even "stress management" and "improving concentration."

[0845] The generated training program is sent to the terminal, which then presents it to the user. The user then checks the training program and begins the training. The training is carried out using a robot. A robot placed in the factory presents the training content to the user as they progress, providing guidance on work procedures and safety measures.

[0846] During the training, the robot continuously monitors the user's facial expressions and speech, and transmits progress information and emotional data to the server, which records this data and uses it to optimize future training programs.

[0847] This allows users to receive personalized training tailored to their skill sets and emotional state, maximizing learning effectiveness. Furthermore, the use of robots enables efficient and safe on-the-job training within factories.

[0848] For example, if a user selects training on "How to set up a CNC machine," the AI ​​engine will determine that basic operations are necessary based on past operation history and evaluation data, and add a module for "Explanation of basic operations." On the other hand, if the emotion engine detects stress from the user's facial expression, modules on relaxation methods and stress management will also be added.

[0849] Furthermore, this system uses a generative AI model to prepare prompts, enabling flexible and intuitive training program generation. For example, the system uses prompts such as:

[0850] Generate optimal training programs based on skill set assessments of how to configure CNC machines and employees' emotional states. Use past work history and facial expression analysis data to personalize the content, including modules on stress management and focus improvement.

[0851] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0852] Step 1:

[0853] The user starts the training application using the terminal and selects a training title. The input is the user's selection operation, and the output is the selected training title information. This information is sent to the server in the next step.

[0854] Step 2:

[0855] The terminal sends the selected training title information and user ID to the server. The input is the training title information and user ID, and the output is the data sent to the server.

[0856] Step 3:

[0857] Based on the training title information and user ID received by the server, past history data, ability evaluation data, and current work data are retrieved from the database. The input is the training title information and user ID, and the output is the retrieved user data.

[0858] Step 4:

[0859] The server uses an AI engine to analyze the acquired data and evaluate the user's skill set and learning style. The input is past history data, ability assessment data, and current work data, and the output is the evaluation results of the user's skill set and learning style.

[0860] Step 5:

[0861] The server uses an emotion engine to analyze the user's facial expression and voice data and evaluate their emotional state. The input is the user's facial expression and voice data, and the output is the evaluation result of their emotional state.

[0862] Step 6:

[0863] The server generates a personalized training program based on the evaluation results of the AI ​​engine and the emotion engine. The inputs are the evaluation results of the skill set and learning style, and the evaluation results of the emotional state, and the output is the generated personalized training program.

[0864] Step 7:

[0865] The server sends the generated training program to the terminal, where the input is the generated training program and the output is the training program sent to the terminal.

[0866] Step 8:

[0867] The terminal presents the training program to the user and starts the training. The input is the training program sent, and the output is instructions for the user to start the training.

[0868] Step 9:

[0869] During the training, the user interacts with the robot. The robot monitors the user's progress and emotional data in real time and sends them to the server. The input is the user's progress and emotional data, and the output is the progress and emotional data sent to the server.

[0870] Step 10:

[0871] The server records the received progress information and emotion data, and optimizes and provides the next training module. The input is the progress information and emotion data, and the output is the next optimized training module.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] [Third embodiment]

[0876] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0877] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0878] 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).

[0879] 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.

[0880] 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.

[0881] 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).

[0882] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] 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."

[0888] The present invention aims to provide a personalized training program based on the needs of each user. In the system of the present invention, the user selects a training title on the terminal, and the server generates and provides the optimal training program based on the selection. Specifically, the process is as follows:

[0889] First, the user launches the application on their device and selects the desired program from among multiple training titles. This selection is sent to the server via the device. The server then acquires and analyzes the received training title information, as well as the user's past history data, ability evaluation data, and current work data stored in the database.

[0890] The server uses an AI engine to analyze this data and assess the user's current skill set, gaps, and optimal learning style. Based on this assessment, it generates a list of training modules that are best suited to the user and combines them to create a personalized training program.

[0891] The server sends the generated training program to the terminal, which then presents it to the user. The user checks the content of the training program and begins the training if they are satisfied. During the training, the terminal sends the user's progress information to the server, which records this progress. This allows the next training module to be provided in a timely manner.

[0892] It is designed to help users efficiently acquire the skills they need to maximize their learning, and by regularly monitoring their progress, it also helps them maintain and improve their skills over the long term.

[0893] Specific examples

[0894] A specific example is shown below.

[0895] Example 1: Presentation skills training

[0896] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[0897] 2. The terminal sends the selected training title to the server.

[0898] 3. The server retrieves the user's past history data, ability evaluation data, and current work data from the database based on the user ID and the selected training title information.

[0899] 4. The server calls the AI ​​engine and provides these data as input.

[0900] 5. The AI ​​engine analyzes the user's skill set and assesses their skillset and weaknesses. For example, they may be able to create basic slides, but lack effective slide design and audience interaction.

[0901] 6. The server selects training modules based on the results of these evaluations, such as "Advanced Slide Design" and "Effective Public Speaking."

[0902] 7. The server combines the selected modules to create a personalized training program and sends it to the terminal.

[0903] 8. The device presents the training program to the user. The user begins the training and sends progress information to the server as they complete each step.

[0904] 9. The server will record your progress and provide you with the next training content in a timely manner.

[0905] Through this process, users can receive training that is optimized for them, maximizing their learning effect and helping to increase their motivation and continuously improve their skills.

[0906] The processing flow will be explained below.

[0907] Step 1:

[0908] The user starts the application on the terminal and selects the desired training title "improving presentation skills" from among a number of training titles.

[0909] Step 2:

[0910] The device sends request data including the selected training title to the server. For example, the data is sent in JSON format along with the user ID.

[0911] Step 3:

[0912] The server receives the request and accesses a database to obtain the user's history data, performance assessment data, and current job data.

[0913] Step 4:

[0914] The server inputs this acquired data into an AI engine and provides it as parameters for analyzing the user's skill set, skill gaps, and optimal learning style.

[0915] Step 5:

[0916] The AI ​​engine analyzes the data and evaluates the user's skills, such as their current ability to create slides, their ability to interact with the audience, and any gaps in their skills that may be required.

[0917] Step 6:

[0918] The server receives the analysis results from the AI ​​engine and generates a personalized training program based on them, combining modules such as "Advanced Slide Design" and "Effective Public Speaking."

[0919] Step 7:

[0920] The server sends the generated training program to the terminal, which includes details of each module and the order in which they are executed.

[0921] Step 8:

[0922] The terminal presents the received training program to the user, and displays the program content and module configuration.

[0923] Step 9:

[0924] The user checks the presented program and, if satisfied, begins the training by, for example, pressing the "Start" button.

[0925] Step 10:

[0926] The terminal notifies the server of the user's training start action.

[0927] Step 11:

[0928] The server approves the start of the training and provides the necessary training resources (videos, texts, quizzes, etc.).

[0929] Step 12:

[0930] The terminal sequentially displays these resources to the user, and the training program progresses.

[0931] Step 13:

[0932] As the user completes each step, the terminal sends progress information to the server, for example, sending progress data upon completion of each module.

[0933] Step 14:

[0934] The server records the progress and delivers the next training module in a timely manner, and can also flexibly adjust the next step according to the progress.

[0935] Step 15:

[0936] The terminal then presents the user with the next training module, and so on until the entire training program is completed.

[0937] Through these steps, users can receive training programs optimized for them and improve their skills.

[0938] Example 1

[0939] 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."

[0940] Conventional training systems have struggled to provide personalized training programs based on individual user needs. This is due to a lack of technology to comprehensively analyze each user's history data, ability assessment data, and current work data, and automatically generate training programs based on that data. Furthermore, there was no mechanism in place to monitor training progress in real time and provide the next appropriate training module in a timely manner.

[0941] 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.

[0942] In this invention, the server includes means for a user to select a training title on a terminal, means for transmitting the selected training title to the server, means for acquiring the user's past history data, ability assessment data, and current work data, means for analyzing the data using a generative AI model and evaluating the user's skill set and learning style, means for generating a personalized training program based on the evaluation, means for transmitting the generated training program to the terminal, means for the terminal to present the program to the user and start the training, means for transmitting progress information to the server, and means for recording the progress information and providing the next training content in a timely manner. This allows users to receive training programs suited to their individual needs and enables effective skill improvement.

[0943] "User" refers to any individual or legal entity participating in the training program.

[0944] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[0945] "Server" refers to a computer system that performs database access, data analysis, and training program generation and delivery.

[0946] "Training title" refers to the name or theme of the training program selected by the user.

[0947] "Database" refers to an information system that stores users' past history data, performance evaluation data, and current business data.

[0948] "Generative AI model" refers to the artificial intelligence engine that analyzes data and generates personalized training programs.

[0949] A "skill set" refers to the collection of skills and knowledge possessed by a user.

[0950] "Learning style" refers to the method or format in which a user learns optimally.

[0951] "Personalized training program" refers to a learning plan that is customized to meet the user's individual needs.

[0952] "Progress Information" refers to progress data collected as a user progresses through a training program.

[0953] "Training Module" means a separate learning unit or session that forms part of a training program.

[0954] "Real-time" refers to data and information being processed and updated instantly.

[0955] The present invention is a system that provides personalized training programs based on the needs of each user. In this system, the user selects a training title on the terminal, and the server generates and provides the optimal training program based on that selection. The details are explained below.

[0956] First, the user launches the application installed on the terminal and selects the desired program from the multiple training titles provided. For example, if the user selects the training title "Improve Presentation Skills," this information is sent to the server via the terminal. The server retrieves the received training title information, as well as the user's past history data, ability evaluation data, and current work data stored in the database.

[0957] The server collects this data and analyzes it using a generative AI model. Specifically, it evaluates the user's current skill set, gaps, and optimal learning style. Based on this evaluation, the server generates a list of training modules that are optimal for the user and combines them to create a personalized training program.

[0958] The generated training program is again sent from the server to the terminal. The terminal presents this training program to the user, and the user begins the training. As the training progresses, the terminal sends progress information to the server, which records this progress. This allows the next training module to be provided in a timely manner.

[0959] Through this system, users can receive training that is optimized for them, allowing them to efficiently acquire the necessary skills. Furthermore, by regularly monitoring their progress, it is possible to maintain and improve their skills over the long term.

[0960] Specific examples

[0961] A specific example is shown below.

[0962] Example 1: Presentation skills training

[0963] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[0964] 2. The terminal sends the selected training title to the server.

[0965] 3. The server retrieves the user's past history data, ability evaluation data, and current work data from the database based on the user ID and the selected training title information.

[0966] 4. The server invokes the generative AI model, providing these data as input.

[0967] 5. The generative AI model analyzes and evaluates the user's skill set and skills gaps. For example, it may say, "You have basic slide creation skills, but lack effective slide design and audience interaction."

[0968] 6. The server selects training modules based on these evaluation results, such as "Advanced Slide Design" and "Effective Public Speaking."

[0969] 7. The server combines the selected modules to create a personalized training program and sends it to the terminal.

[0970] 8. The device presents the training program to the user. The user begins the training and sends progress information to the server as they complete each step.

[0971] 9. The server will record your progress and provide you with the next training content in a timely manner.

[0972] Through this process, users can receive training that is optimized for them, maximizing their learning effect and helping to increase their motivation and continuously improve their skills.

[0973] Prompt Sentence Examples

[0974] "I am currently seeking training in 'improving presentation skills.' Please select the most appropriate training module for me based on my past and current work data."

[0975] In this way, by using this system, users can receive training programs tailored to their individual needs, enabling them to acquire skills effectively.

[0976] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0977] Step 1:

[0978] The user launches the app on their device and selects a training title. First, the user clicks on the desired training title from the multiple training titles provided. This selection information (training title, user ID, etc.) is entered into the device. The device stores this information in its internal memory.

[0979] Input: User ID, training title

[0980] Output: Selection information

[0981] Step 2:

[0982] The device sends the selected training title to the server. The device creates an API request and sends the selection information to the server using the HTTP POST method. For example, the device constructs the data in JSON format and sends it to the specified endpoint.

[0983] Input: Selection information

[0984] Output: API request

[0985] Step 3:

[0986] The server references the database based on the user ID and training title information to retrieve the required data. Based on the received user ID and training title, the server executes an SQL query to retrieve the following data: The user's past history data, ability evaluation data, and current job data.

[0987] Input: User ID, training title

[0988] Output: Acquired data (history data, performance evaluation data, business data)

[0989] Step 4:

[0990] The server calls the generative AI model to analyze the data. The server provides the acquired data as input to the AI ​​engine. The AI ​​engine analyzes this data and evaluates the user's current skill set, missing skills, and optimal learning style. This evaluation result is generated.

[0991] Input: Acquired data (history data, performance evaluation data, business data)

[0992] Output: Analysis results (skill set, skills gaps, learning style)

[0993] Step 5:

[0994] The server selects the most suitable training module based on the analysis results. The server lists the most suitable training modules based on the analysis results of the AI ​​engine. For example, "Advanced Slide Design" and "Effective Public Speaking" are selected.

[0995] Input: Analysis results

[0996] Output: Selection module

[0997] Step 6:

[0998] The server sends the generated training program to the device. The server combines the selection modules to generate a personalized training program and sends it to the device. It issues an HTTP POST request using the API endpoint.

[0999] Input: Selection module

[1000] Output: Personalized training program

[1001] Step 7:

[1002] The terminal presents the training program to the user. The terminal analyzes the received training program and displays it on the user interface. The user confirms the contents of the training program and starts it.

[1003] Input: Personalized Training Program

[1004] Output: Display training program

[1005] Step 8:

[1006] The user starts the training and sends progress information from the device to the server. As the user progresses through the training, the device periodically sends progress information to the server. For example, progress information is collected each time each step is completed.

[1007] Input: Training progress

[1008] Output: Progress information

[1009] Step 9:

[1010] The server records the progress information and provides the next training content in a timely manner. The server records the received progress information in a database and prepares to provide the next training module based on that information. The next module is sent to the terminal in a timely manner according to the progress.

[1011] Input: Progress information

[1012] Output: Next training module

[1013] Through these steps, users can efficiently receive training that is optimized for them, maximizing the effectiveness of their learning.

[1014] (Application example 1)

[1015] 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."

[1016] In recent years, with the widespread use of robots in factories, improving the skills of operators and maintenance personnel has become increasingly important. However, standardized, one-size-fits-all training programs are difficult to address, making it difficult to efficiently acquire skills. Conventional training programs do not adequately consider users' past work history or on-site requirements, making it difficult to maximize users' learning efficiency. Given this background, there is a need to provide personalized training programs based on each user's skill level and past work history in order to efficiently improve skills.

[1017] 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.

[1018] In this invention, the server includes: means for a user to select a training title on a terminal; means for transmitting the selected training title to the server; means for the server to acquire the user's past history data, ability evaluation data, and current work data; means for analyzing the data using an AI engine and evaluating the user's skill set and learning style; means for generating a personalized training program; means for transmitting the generated training program to the terminal; means for the terminal to present the program to the user and start the training; means for the terminal to provide training titles related to the operation and maintenance of factory robots; means for the server to recommend the next training module required based on the user's current skill level and past work history; and means for recording progress information of the training modules and providing the next module at an appropriate time. This makes it possible to provide an optimal training program based on each user's skill level and work history, thereby efficiently improving skills.

[1019] "Users" refer to factory operators and maintenance personnel who use this system to take training programs.

[1020] A "terminal" is a device that a user operates, and includes tablets and displays built into factory robots.

[1021] "Training Title" refers to the name of a particular training program selected by the user.

[1022] "Server" refers to the central system that manages the information and data selected by the user and analyzes the data using an AI engine.

[1023] "History data" refers to data related to the user's past behavioral history, such as records of tasks and operations performed by the user in the past, and error reports.

[1024] "Ability Assessment Data" refers to assessment data related to a user's skill level and abilities, including past test results and assessment reports.

[1025] "Current work data" refers to data related to the work the user is currently responsible for, including current job duties and project information.

[1026] An "AI engine" refers to a system that uses artificial intelligence technology to analyze data and evaluate a user's skill set and shortcomings.

[1027] A "skill set" refers to the collection of skills and abilities that a user possesses.

[1028] "Learning style" refers to characteristics that indicate how a user learns most effectively.

[1029] "Personalized training program" refers to a training program that is customized based on the user's individual needs and skill level.

[1030] A "factory robot" is an automated machine used in a factory to carry out manufacturing and maintenance processes.

[1031] "Training Module" means a separate learning unit within a training program that provides independent learning content.

[1032] This invention realizes a system that provides personalized training programs for factory robot operators and maintenance personnel. In this system, a user selects a training title on a terminal, and a server generates and provides an optimal training program based on the user's selection.

[1033] In a specific embodiment, the following process is performed. First, the user starts up the terminal and selects a desired program from multiple training titles. This selection is sent to the server via the terminal. The server acquires and analyzes the received training title information, as well as the user's past history data, ability assessment data, and current work data stored in a database. The server analyzes the data using an AI engine (e.g., TensorFlow) and evaluates the user's current skill set, skill gaps, and optimal learning style. Based on the evaluation results, it generates a list of training modules optimal for the user and combines them to create a personalized training program. The generated training program is sent to the terminal, which presents it to the user. The user reviews the content of the presented training program and, if satisfied, begins the training. During the training, the terminal transmits the user's progress information to the server, which records this progress. This allows the next training module to be provided in a timely manner.

[1034] Hardware and software used

[1035] The following hardware and software are used to realize this system.

[1036] Hardware: Android / iOS compatible tablets, displays built into factory robots

[1037] software:

[1038] Server side: Python

[1039] Database Management: MySQL

[1040] AI analysis engine: TensorFlow

[1041] Application frontend: React Native

[1042] Program processing explanation

[1043] The server uses TensorFlow to analyze the user's selected training title, past history data, ability assessment data, and current work data. The analysis evaluates the user's skill set and learning style, and generates optimal training modules based on that. The generated training modules are organized into a personalized training program and sent to the user's device at the appropriate time.

[1044] Specific examples

[1045] For example, if a user selects a training title such as "Precise Operation of a Robot Arm," the server will generate a customized training program that allows the user to learn in stages from "Basic Grip Operation" to "High-Precision Positioning Techniques" based on the frequency of past operational errors and evaluation data.

[1046] Prompt Sentence Examples

[1047] An example of a prompt sentence to input to the generative AI model is as follows:

[1048] "For the training title 'Precision Operation of Robot Arms' selected by user ID 5678, please recommend the next necessary training module based on past operation errors and current evaluation data."

[1049] These prompts allow users to receive training that is optimized for their skill level and needs, enabling them to improve their skills efficiently.

[1050] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1051] Step 1:

[1052] The user starts up the terminal and selects the desired program from among multiple training titles.

[1053] Input: List of training titles

[1054] Output: Selected training title

[1055] Specific operation: The user selects the desired training title from the list of training titles displayed on the device screen by tapping it. The selected training title is then saved in the device.

[1056] Step 2:

[1057] The terminal transmits the selected training title to the server.

[1058] Input: Selected training title

[1059] Output: Training title sent to the server

[1060] Specific operation: The device uses its internal communication function to send the selected training title to the server via the network, along with the user ID and time information.

[1061] Step 3:

[1062] The server acquires the user's past history data, performance evaluation data, and current business data.

[1063] Input: User ID and selected training title

[1064] Output: User's past history data, performance evaluation data, current work data

[1065] Specific operation: The server accesses the database and retrieves past history data (e.g., operation error history), ability evaluation data (e.g., skill evaluation results), and current business data (e.g., information about the project currently in charge) corresponding to the user ID.

[1066] Step 4:

[1067] The server uses an AI engine to analyze the data and assess the user's skill set and learning style.

[1068] Input: User's past history data, performance evaluation data, current work data

[1069] Output: Assessment of user skill sets and learning styles

[1070] How it works: The server launches an AI engine such as TensorFlow to analyze the input data. Specifically, it preprocesses the dataset and inputs it into a model to evaluate the strengths and weaknesses of the user's skills and the optimal learning method.

[1071] Step 5:

[1072] The server generates a personalized training program based on the assessment.

[1073] Input: User skill set and learning style assessment results

[1074] Output: Personalized training program

[1075] Specific operation: Based on the evaluation results, the server selects appropriate training modules (e.g., "basic grip operation" and "high-precision positioning techniques") and combines them to generate a personalized training program.

[1076] Step 6:

[1077] The server transmits the generated training program to the terminal.

[1078] Enter: personalized training programs.

[1079] Output: Training program sent to the device

[1080] Specific operation: The server transmits the generated training program to the terminal via the network, including the program sequence and detailed information.

[1081] Step 7:

[1082] The terminal presents the training program to the user, and the user starts the training.

[1083] Input: Training program sent from the server

[1084] Output: User who started the training

[1085] Specific operation: The device displays the training program on the screen, and the training begins when the user presses the "Start" button. The user proceeds with the learning according to the presented content.

[1086] Step 8:

[1087] The terminal transmits the user's progress information to the server.

[1088] Input: User training progress information

[1089] Output: Progress information sent to the server

[1090] Specific operation: The terminal records the user's training progress (e.g., completed modules, test results) in real time and transmits it to the server in a timely manner.

[1091] Step 9:

[1092] The server records progress information and provides the next training module at the appropriate time.

[1093] Input: User training progress information

[1094] Output: Next training module

[1095] Specific operation: The server stores the received progress information in a database, automatically selects the next required training module, and sends it to the terminal at the appropriate time.

[1096] 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.

[1097] The present invention relates to a system that recognizes a user's emotions and provides a personalized training program based on the results. In this system, the user selects a training title on a terminal, and the server generates and provides an optimal training program based on that selection. The system also analyzes the user's emotional state using an emotion engine. This makes it possible to customize the training program according to the user's emotional state.

[1098] First, the user launches the application on their device and selects the desired program from among multiple training titles. This selection is sent to the server via the device. The server then acquires and analyzes the received training title information, as well as the user's past history data, ability evaluation data, and current work data stored in the database.

[1099] The server uses an AI engine to analyze this data and assess the user's current skill set, gaps, and optimal learning style. It also uses an emotion engine to analyze the user's emotional state. The emotion engine uses facial and voice data to recognize emotions and assess their state.

[1100] Based on the evaluation results from both the AI ​​engine and the emotion engine, the server generates a list of training modules that are optimal for the user and combines them to create a personalized training program. For example, if the user is feeling stressed, a training module for relaxation can be added.

[1101] The server sends the generated training program to the terminal, which then presents it to the user. The user reviews the content of the training program and begins the training if they are satisfied. During the training, the terminal sends the user's progress information and emotional data to the server, which records the progress and emotional state. This allows the next training module to be provided in a timely manner based on the user's emotional state.

[1102] It is designed to help users efficiently acquire the skills necessary to maximize their learning outcomes, and by taking into account the user's emotional state, it can improve learning motivation and manage stress.

[1103] Specific examples

[1104] A specific example is shown below.

[1105] Example 1: Presentation skills training

[1106] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[1107] 2. The terminal sends the selected training title to the server.

[1108] 3. The server retrieves the user's past history data, ability evaluation data, and current work data from the database based on the user ID and the selected training title information.

[1109] 4. The server calls the AI ​​engine, provides this data as input, and evaluates the user's skill set and skills gaps, such as their current ability to create slides, their ability to interact with the audience, and the skills gaps they need.

[1110] 5. The emotion engine analyzes the user's facial expression and voice data to assess whether the user is feeling stressed or highly motivated.

[1111] 6. Based on the evaluation results from the AI ​​engine and emotion engine, the server generates a personalized training program that includes modules on "Advanced Slide Design," "Effective Public Speaking," and stress management.

[1112] 7. The server transmits the generated training program to the terminal.

[1113] 8. The device presents the training program to the user. The user begins the training, and each time the device completes a step, it sends progress information and emotion data to the server.

[1114] 9. The server records the progress and emotional state and provides the next training content in a timely manner.

[1115] This system allows users to receive training tailored to their needs, maximizing learning effectiveness, and by taking into account their emotional state, it can improve their motivation and manage stress.

[1116] The processing flow will be explained below.

[1117] Step 1:

[1118] The user starts the application on the terminal and selects the desired training title "Improve Presentation Skills" from the list of available training titles.

[1119] Step 2:

[1120] The device sends request data including the selected training title to the server. For example, the data is sent in JSON format along with the user ID.

[1121] Step 3:

[1122] The server receives the request and accesses a database to obtain the user's history data, performance assessment data, and current job data.

[1123] Step 4:

[1124] The server inputs this data into the AI ​​engine and emotion engine, providing it as parameters for analyzing the user's skill set, skill gaps, optimal learning style, and emotional state.

[1125] Step 5:

[1126] The emotion engine analyzes the user's facial expression and voice data to assess their emotional state, for example, determining whether they are stressed, relaxed, or motivated.

[1127] Step 6:

[1128] Based on these inputs, the AI ​​engine assesses the user's current skill set, any gaps in skills, and their optimal learning style.

[1129] Step 7:

[1130] The server receives the evaluation results of the AI ​​engine and emotion engine and generates a list of training modules that are optimal for the user's condition. For example, in addition to the modules "Advanced Slide Design" and "Effective Public Speaking," a module for stress management can be added.

[1131] Step 8:

[1132] The server transmits the generated personalized training program to the terminal.

[1133] Step 9:

[1134] The terminal presents the received training program to the user, and displays the program content and module configuration.

[1135] Step 10:

[1136] The user checks the presented program and, if satisfied, begins the training by, for example, pressing the "Start" button.

[1137] Step 11:

[1138] The terminal notifies the server of the user's training start action.

[1139] Step 12:

[1140] The server approves the start of the training and provides the necessary training resources (videos, texts, quizzes, etc.).

[1141] Step 13:

[1142] The terminal sequentially displays these resources to the user, and the training program progresses.

[1143] Step 14:

[1144] Each time the user completes a step, the terminal transmits its progress information and emotional data to the server, for example, sending progress data and emotional state upon completion of each module.

[1145] Step 15:

[1146] The server records the progress and emotional state of the user, and delivers the next training module in a timely manner according to the user's emotional state.

[1147] Step 16:

[1148] The terminal then presents the user with the next training module and repeats this until the entire training program is complete, for example, if the user is feeling stressed, a module on relaxation may be included.

[1149] Through these steps, users can receive personalized training programs and improve their skills. Furthermore, by taking into account the user's emotional state, it is possible to improve motivation and manage stress.

[1150] Example 2

[1151] 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."

[1152] Conventional training systems provided training programs based only on the user's past history and ability evaluation data, making it difficult to provide effective training programs that took into account the emotional state of each individual user.Furthermore, they did not have the functionality to analyze progress information and emotional data in real time and provide the next training content in a timely manner, making it difficult to maximize the learning effect of users.

[1153] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1154] In this invention, the server includes means for acquiring the user's past history data, ability evaluation data, and current work data, means for analyzing the data using an artificial intelligence engine to evaluate the user's skill set and learning style, and means for analyzing the user's emotional state using an emotion analysis engine, thereby enabling the provision of a personalized training program that takes the user's emotional state into consideration.

[1155] A "user" is a person who uses the system to take a training program.

[1156] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[1157] The "Training title" is the name of the training program selected by the user, and indicates the specific training content.

[1158] "Server" is the central computer responsible for data processing, generation and distribution of training programs.

[1159] "Past history data" refers to data that records the training programs that the user has previously attended and the user's learning history.

[1160] "Ability evaluation data" is data that includes evaluation results regarding the skills and abilities of a user.

[1161] "Current business data" refers to data that includes information about the user's current job duties and business.

[1162] "Artificial Intelligence Engine" refers to software and algorithms used to analyze acquired data and assess a user's skill set and learning style.

[1163] "Emotion Analysis Engine" refers to software and algorithms for analyzing a user's emotional state.

[1164] A "personalized training program" is a training program that is individually created taking into account the user's skill set and emotional state.

[1165] "Progress information" is data that indicates the progress of a user as they progress through a training program.

[1166] "Emotion data" is data relating to emotions acquired by analyzing the user's facial expressions and voice.

[1167] The present invention relates to a system that recognizes a user's emotions and provides a personalized training program based on the results.

[1168] First, the user launches the application on their device and selects the desired program from among multiple training titles. This selection is sent to the server via the device. The training title information selected by the user is sent to the server as JSON format data.

[1169] The server retrieves the received training title information, as well as the user's past history data, ability evaluation data, and current job data stored in the database. Specifically, it extracts the necessary information using an SQL SELECT query.

[1170] The server then launches an artificial intelligence engine (e.g., TensorFlow) and provides the acquired user data as input. The AI ​​engine uses this data to analyze the user's current skill set and gaps, as well as assess their appropriate learning style.

[1171] Furthermore, the server uses an emotion analysis engine (e.g., a general emotion recognition API) to analyze the user's facial expression and voice data sent from the device. The emotion analysis engine evaluates the user's stress level and motivation state.

[1172] Based on the evaluation results of the AI ​​engine and the sentiment analysis engine, the server generates a list of training modules that are optimal for the user, and combines them to create a personalized training program. The generated training program is sent to the device as JSON format data.

[1173] The device receives the training program from the server and presents it to the user. If the user confirms and agrees with the training content, the training begins. During the training, the device periodically transmits the user's progress information and emotional data to the server.

[1174] The server records the received progress information and emotion data, and generates and provides the next optimal training module based on this information, thereby maintaining an optimal learning environment for the user and enabling effective skill acquisition.

[1175] Specific examples

[1176] Example: Presentation skills training

[1177] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[1178] 2. The device sends the selected training title to the server as JSON data.

[1179] 3. The server retrieves the user information from the database using an SQL query.

[1180] 4. The server loads the TensorFlow model and evaluates the user's skill set.

[1181] 5. The server uses a general emotion recognition API to analyze the user's facial expressions and voice data.

[1182] 6. The server generates a training program based on the evaluation results and creates a personalized program including "Advanced Slide Design" and "Effective Public Speaking."

[1183] 7. The server sends the generated program to the terminal.

[1184] 8. The terminal displays the training program to the user, and the user begins the training.

[1185] 9. As the user progresses through the training, the device periodically sends progress information and emotional data to the server.

[1186] 10. The server records these data and provides the next training module in a timely manner.

[1187] Prompt Sentence Examples

[1188] Prompt 1: Example input to a generative AI model

[1189] "The user has selected a training program to improve their presentation skills. Please suggest the most appropriate learning module based on their past training history, skill assessment, and current job duties. Also, please evaluate the user's emotional state using facial and voice data and take the results into consideration."

[1190] Prompt 2: Example of progress information

[1191] "Please tell us about the current training progress. Please let us know if the user is stressed or motivated, and how well they are progressing."

[1192] This system takes into account the user's emotional state and provides personalized training programs to achieve optimal learning outcomes.

[1193] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1194] Step 1:

[1195] The user starts the application on the terminal and selects the desired program from among a number of training titles.

[1196] Specific operation: The user selects a training title such as "Improve Presentation Skills" from the list of training titles on the screen.

[1197] Input: User selection information

[1198] Output: JSON data containing the selected training titles

[1199] Step 2:

[1200] The terminal transmits the user's selection information to the server.

[1201] Specific operation: The selected training title information is sent to the server in JSON format.

[1202] Input: JSON data containing the selected training titles

[1203] Output: Course title information sent to the server

[1204] Step 3:

[1205] The server acquires the received training title information, the user's past history data, ability evaluation data, and current work data stored in the database.

[1206] What happens next: The server uses an SQL SELECT query to retrieve the relevant user data from the database.

[1207] Input: Training title information, user ID

[1208] Output: Past history data, performance evaluation data, current business data

[1209] Step 4:

[1210] The server uses an artificial intelligence engine to analyze the acquired data and assess the user's skill set and learning style.

[1211] How it works: The server loads the TensorFlow model and inputs the acquired user data into the model to evaluate skill sets and learning styles.

[1212] Input: Past history data, performance evaluation data, current work data

[1213] Output: Evaluation results of user's skill set and learning style

[1214] Step 5:

[1215] The server uses an emotion analysis engine to analyze the user's emotional state.

[1216] Specific operation: The user's facial expression data and voice data sent from the device are input into the emotion recognition API and analyzed.

[1217] Input: facial expression data, voice data

[1218] Output: Evaluation result of the user's emotional state

[1219] Step 6:

[1220] Based on the evaluation results of the artificial intelligence engine and the sentiment analysis engine, the server generates a list of training modules that are optimal for the user and combines them to create a personalized training program.

[1221] Specific operation: Select modules such as "Advanced Slide Design" and "Effective Public Speaking" and combine programs according to the user's condition.

[1222] Input: Skill set assessment results, Learning style assessment results, Emotional state assessment results

[1223] Output: Personalized training program

[1224] Step 7:

[1225] The server transmits the generated training program to the terminal.

[1226] Specific operation: The generated training program is sent to the terminal in JSON format.

[1227] Input: Personalized training program

[1228] Output: Training program sent to the terminal

[1229] Step 8:

[1230] The terminal presents the training program to the user, and the user confirms the contents.

[1231] Specific operation: The training program is displayed on the screen and the user confirms it.

[1232] Input: Training program sent to the terminal

[1233] Output: User confirmation

[1234] Step 9:

[1235] The user starts training and sends progress information and emotion data to the server.

[1236] Specific operation: As the user progresses through each training module, the terminal records progress information, collects emotional data, and sends it to the server.

[1237] Input: Training progress data, emotion data

[1238] Output: Progress and emotion data sent to the server

[1239] Step 10:

[1240] The server records progress information and emotional data, and based on this generates and provides the next optimal training module.

[1241] Specific behavior: The server analyzes the progress and emotion data and adjusts the next training module as needed.

[1242] Input: Progress data, emotion data

[1243] Output: Next training module

[1244] The above are the specific processing steps of the system program.

[1245] (Application example 2)

[1246] 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."

[1247] Traditional training programs are generally provided uniformly and do not take into account the skill sets and emotional states of each user, which can result in reduced learning effectiveness.In addition, there is a lack of methods for conducting on-the-job training efficiently and safely within factories.

[1248] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a means for a user to select a training title on a terminal; a means for transmitting the selected training title to the server; a means for the server to acquire the user's past history data, ability evaluation data, and current work data; a means for the server to analyze the data using an AI engine and evaluate the user's skill set and learning style; a means for generating a personalized training program based on the evaluation; a means for analyzing facial expression data and voice data using an emotion engine and evaluating the user's emotional state; a means for customizing the training program based on the evaluation of the emotional state; a means for transmitting the generated training program to the terminal; a means for the terminal to present the training to the user and start the training; and a means for providing the training program to the user using a robot. This provides a personalized training program tailored to the user's skill set and emotional state, improving learning effectiveness. Furthermore, efficient and safe on-the-job training in factories is possible.

[1249] A "terminal" is a device that a user uses to select a training title and take a training program.

[1250] "Server" refers to the central processing unit that processes user history data and training title information, and generates and provides personalized training programs.

[1251] "Past history data" refers to data relating to the user's past training history and work history.

[1252] "Ability assessment data" is assessment data regarding the user's current skill set and abilities.

[1253] "Current business data" is data relating to the user's current business situation and the work he or she is in charge of.

[1254] An "AI engine" is an artificial intelligence technology that analyzes collected data and evaluates a user's skill set and learning style.

[1255] An "emotion engine" is a technology that analyzes a user's facial expression data and voice data to evaluate their emotional state.

[1256] A "training program" is structured content for users to learn or train.

[1257] "Customizing the training program" means adjusting and optimizing the training content based on the user's emotional state and evaluation results.

[1258] A "robot" is a mechanical device that supports practical training within a factory and provides and guides training programs to users.

[1259] "Facial expression data" refers to data relating to the facial expression of the user.

[1260] "Voice data" is data related to the user's speech.

[1261] "Progress" is information indicating at what stage the user is in the training program.

[1262] A "personalized training program" is training content that is customized based on a user's individual skill set and emotional state.

[1263] The present invention relates to a system for providing personalized training programs for personnel within a factory.

[1264] First, a user (factory employee) uses a terminal to start the training application and select a training title. For example, the user selects the training title "How to set up a CNC machine." This selected training title information is sent from the terminal to the server.

[1265] The server uses the received training title information and the user's ID to retrieve past history data, ability evaluation data, and current work data from the database, thereby understanding the user's learning history and current skill status.

[1266] The server then uses an AI engine to analyze this data and assess the user's skill set and learning style, identifying their current skill level and gaps, and recommending optimal learning content.

[1267] Additionally, an emotion engine is used to analyze the user's facial expression and voice data to assess their emotional state. For example, it can determine whether the user is feeling stressed or highly motivated. This allows the system to add and adjust training modules according to the user's emotional state, as well as the learning content.

[1268] Based on the evaluation results from the AI ​​engine and emotion engine, the server generates a personalized training program, which may include modules such as "basic operation explanations," "safety measures," and even "stress management" and "improving concentration."

[1269] The generated training program is sent to the terminal, which then presents it to the user. The user then checks the training program and begins the training. The training is carried out using a robot. A robot placed in the factory presents the training content to the user as they progress, providing guidance on work procedures and safety measures.

[1270] During the training, the robot continuously monitors the user's facial expressions and speech, and transmits progress information and emotional data to the server, which records this data and uses it to optimize future training programs.

[1271] This allows users to receive personalized training tailored to their skill sets and emotional state, maximizing learning effectiveness. Furthermore, the use of robots enables efficient and safe on-the-job training within factories.

[1272] For example, if a user selects training on "How to set up a CNC machine," the AI ​​engine will determine that basic operations are necessary based on past operation history and evaluation data, and add a module for "Explanation of basic operations." On the other hand, if the emotion engine detects stress from the user's facial expression, modules on relaxation methods and stress management will also be added.

[1273] Furthermore, this system uses a generative AI model to prepare prompts, enabling flexible and intuitive training program generation. For example, the system uses prompts such as:

[1274] Generate optimal training programs based on skill set assessments of how to configure CNC machines and employees' emotional states. Use past work history and facial expression analysis data to personalize the content, including modules on stress management and focus improvement.

[1275] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1276] Step 1:

[1277] The user starts the training application using the terminal and selects a training title. The input is the user's selection operation, and the output is the selected training title information. This information is sent to the server in the next step.

[1278] Step 2:

[1279] The terminal sends the selected training title information and user ID to the server. The input is the training title information and user ID, and the output is the data sent to the server.

[1280] Step 3:

[1281] Based on the training title information and user ID received by the server, past history data, ability evaluation data, and current work data are retrieved from the database. The input is the training title information and user ID, and the output is the retrieved user data.

[1282] Step 4:

[1283] The server uses an AI engine to analyze the acquired data and evaluate the user's skill set and learning style. The input is past history data, ability assessment data, and current work data, and the output is the evaluation results of the user's skill set and learning style.

[1284] Step 5:

[1285] The server uses an emotion engine to analyze the user's facial expression and voice data and evaluate their emotional state. The input is the user's facial expression and voice data, and the output is the evaluation result of their emotional state.

[1286] Step 6:

[1287] The server generates a personalized training program based on the evaluation results of the AI ​​engine and the emotion engine. The inputs are the evaluation results of the skill set and learning style, and the evaluation results of the emotional state, and the output is the generated personalized training program.

[1288] Step 7:

[1289] The server sends the generated training program to the terminal, where the input is the generated training program and the output is the training program sent to the terminal.

[1290] Step 8:

[1291] The terminal presents the training program to the user and starts the training. The input is the training program sent, and the output is instructions for the user to start the training.

[1292] Step 9:

[1293] During the training, the user interacts with the robot. The robot monitors the user's progress and emotional data in real time and sends them to the server. The input is the user's progress and emotional data, and the output is the progress and emotional data sent to the server.

[1294] Step 10:

[1295] The server records the received progress information and emotion data, and optimizes and provides the next training module. The input is the progress information and emotion data, and the output is the next optimized training module.

[1296] 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.

[1297] 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.

[1298] 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.

[1299] [Fourth embodiment]

[1300] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1301] 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.

[1302] 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).

[1303] 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.

[1304] 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.

[1305] 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).

[1306] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1307] 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.

[1308] 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.

[1309] 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.

[1310] 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.

[1311] 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.

[1312] 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."

[1313] The present invention aims to provide a personalized training program based on the needs of each user. In the system of the present invention, the user selects a training title on the terminal, and the server generates and provides the optimal training program based on the selection. Specifically, the process is as follows:

[1314] First, the user launches the application on their device and selects the desired program from among multiple training titles. This selection is sent to the server via the device. The server then acquires and analyzes the received training title information, as well as the user's past history data, ability evaluation data, and current work data stored in the database.

[1315] The server uses an AI engine to analyze this data and assess the user's current skill set, gaps, and optimal learning style. Based on this assessment, it generates a list of training modules that are best suited to the user and combines them to create a personalized training program.

[1316] The server sends the generated training program to the terminal, which then presents it to the user. The user checks the content of the training program and begins the training if they are satisfied. During the training, the terminal sends the user's progress information to the server, which records this progress. This allows the next training module to be provided in a timely manner.

[1317] It is designed to help users efficiently acquire the skills they need to maximize their learning, and by regularly monitoring their progress, it also helps them maintain and improve their skills over the long term.

[1318] Specific examples

[1319] A specific example is shown below.

[1320] Example 1: Presentation skills training

[1321] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[1322] 2. The terminal sends the selected training title to the server.

[1323] 3. The server retrieves the user's past history data, ability evaluation data, and current work data from the database based on the user ID and the selected training title information.

[1324] 4. The server calls the AI ​​engine and provides these data as input.

[1325] 5. The AI ​​engine analyzes the user's skill set and assesses their skillset and weaknesses. For example, they may be able to create basic slides, but lack effective slide design and audience interaction.

[1326] 6. The server selects training modules based on the results of these evaluations, such as "Advanced Slide Design" and "Effective Public Speaking."

[1327] 7. The server combines the selected modules to create a personalized training program and sends it to the terminal.

[1328] 8. The device presents the training program to the user. The user begins the training and sends progress information to the server as they complete each step.

[1329] 9. The server will record your progress and provide you with the next training content in a timely manner.

[1330] Through this process, users can receive training that is optimized for them, maximizing their learning effect and helping to increase their motivation and continuously improve their skills.

[1331] The processing flow will be explained below.

[1332] Step 1:

[1333] The user starts the application on the terminal and selects the desired training title "improving presentation skills" from among a number of training titles.

[1334] Step 2:

[1335] The device sends request data including the selected training title to the server. For example, the data is sent in JSON format along with the user ID.

[1336] Step 3:

[1337] The server receives the request and accesses a database to obtain the user's history data, performance assessment data, and current job data.

[1338] Step 4:

[1339] The server inputs this acquired data into an AI engine and provides it as parameters for analyzing the user's skill set, skill gaps, and optimal learning style.

[1340] Step 5:

[1341] The AI ​​engine analyzes the data and evaluates the user's skills, such as their current ability to create slides, their ability to interact with the audience, and any gaps in their skills that may be required.

[1342] Step 6:

[1343] The server receives the analysis results from the AI ​​engine and generates a personalized training program based on them, combining modules such as "Advanced Slide Design" and "Effective Public Speaking."

[1344] Step 7:

[1345] The server sends the generated training program to the terminal, which includes details of each module and the order in which they are executed.

[1346] Step 8:

[1347] The terminal presents the received training program to the user, and displays the program content and module configuration.

[1348] Step 9:

[1349] The user checks the presented program and, if satisfied, begins the training by, for example, pressing the "Start" button.

[1350] Step 10:

[1351] The terminal notifies the server of the user's training start action.

[1352] Step 11:

[1353] The server approves the start of the training and provides the necessary training resources (videos, texts, quizzes, etc.).

[1354] Step 12:

[1355] The terminal sequentially displays these resources to the user, and the training program progresses.

[1356] Step 13:

[1357] As the user completes each step, the terminal sends progress information to the server, for example, sending progress data upon completion of each module.

[1358] Step 14:

[1359] The server records the progress and delivers the next training module in a timely manner, and can also flexibly adjust the next step according to the progress.

[1360] Step 15:

[1361] The terminal then presents the user with the next training module, and so on until the entire training program is completed.

[1362] Through these steps, users can receive training programs optimized for them and improve their skills.

[1363] Example 1

[1364] 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."

[1365] Conventional training systems have struggled to provide personalized training programs based on individual user needs. This is due to a lack of technology to comprehensively analyze each user's history data, ability assessment data, and current work data, and automatically generate training programs based on that data. Furthermore, there was no mechanism in place to monitor training progress in real time and provide the next appropriate training module in a timely manner.

[1366] 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.

[1367] In this invention, the server includes means for a user to select a training title on a terminal, means for transmitting the selected training title to the server, means for acquiring the user's past history data, ability assessment data, and current work data, means for analyzing the data using a generative AI model and evaluating the user's skill set and learning style, means for generating a personalized training program based on the evaluation, means for transmitting the generated training program to the terminal, means for the terminal to present the program to the user and start the training, means for transmitting progress information to the server, and means for recording the progress information and providing the next training content in a timely manner. This allows users to receive training programs suited to their individual needs and enables effective skill improvement.

[1368] "User" refers to any individual or legal entity participating in the training program.

[1369] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[1370] "Server" refers to a computer system that performs database access, data analysis, and training program generation and delivery.

[1371] "Training title" refers to the name or theme of the training program selected by the user.

[1372] "Database" refers to an information system that stores users' past history data, performance evaluation data, and current business data.

[1373] "Generative AI model" refers to the artificial intelligence engine that analyzes data and generates personalized training programs.

[1374] A "skill set" refers to the collection of skills and knowledge possessed by a user.

[1375] "Learning style" refers to the method or format in which a user learns optimally.

[1376] "Personalized training program" refers to a learning plan that is customized to meet the user's individual needs.

[1377] "Progress Information" refers to progress data collected as a user progresses through a training program.

[1378] "Training Module" means a separate learning unit or session that forms part of a training program.

[1379] "Real-time" refers to data and information being processed and updated instantly.

[1380] The present invention is a system that provides personalized training programs based on the needs of each user. In this system, the user selects a training title on the terminal, and the server generates and provides the optimal training program based on that selection. The details are explained below.

[1381] First, the user launches the application installed on the terminal and selects the desired program from the multiple training titles provided. For example, if the user selects the training title "Improve Presentation Skills," this information is sent to the server via the terminal. The server retrieves the received training title information, as well as the user's past history data, ability evaluation data, and current work data stored in the database.

[1382] The server collects this data and analyzes it using a generative AI model. Specifically, it evaluates the user's current skill set, gaps, and optimal learning style. Based on this evaluation, the server generates a list of training modules that are optimal for the user and combines them to create a personalized training program.

[1383] The generated training program is again sent from the server to the terminal. The terminal presents this training program to the user, and the user begins the training. As the training progresses, the terminal sends progress information to the server, which records this progress. This allows the next training module to be provided in a timely manner.

[1384] Through this system, users can receive training that is optimized for them, allowing them to efficiently acquire the necessary skills. Furthermore, by regularly monitoring their progress, it is possible to maintain and improve their skills over the long term.

[1385] Specific examples

[1386] A specific example is shown below.

[1387] Example 1: Presentation skills training

[1388] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[1389] 2. The terminal sends the selected training title to the server.

[1390] 3. The server retrieves the user's past history data, ability evaluation data, and current work data from the database based on the user ID and the selected training title information.

[1391] 4. The server invokes the generative AI model, providing these data as input.

[1392] 5. The generative AI model analyzes and evaluates the user's skill set and skills gaps. For example, it may say, "You have basic slide creation skills, but lack effective slide design and audience interaction."

[1393] 6. The server selects training modules based on these evaluation results, such as "Advanced Slide Design" and "Effective Public Speaking."

[1394] 7. The server combines the selected modules to create a personalized training program and sends it to the terminal.

[1395] 8. The device presents the training program to the user. The user begins the training and sends progress information to the server as they complete each step.

[1396] 9. The server will record your progress and provide you with the next training content in a timely manner.

[1397] Through this process, users can receive training that is optimized for them, maximizing their learning effect and helping to increase their motivation and continuously improve their skills.

[1398] Prompt Sentence Examples

[1399] "I am currently seeking training in 'improving presentation skills.' Please select the most appropriate training module for me based on my past and current work data."

[1400] In this way, by using this system, users can receive training programs tailored to their individual needs, enabling them to acquire skills effectively.

[1401] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1402] Step 1:

[1403] The user launches the app on their device and selects a training title. First, the user clicks on the desired training title from the multiple training titles provided. This selection information (training title, user ID, etc.) is entered into the device. The device stores this information in its internal memory.

[1404] Input: User ID, training title

[1405] Output: Selection information

[1406] Step 2:

[1407] The device sends the selected training title to the server. The device creates an API request and sends the selection information to the server using the HTTP POST method. For example, the device constructs the data in JSON format and sends it to the specified endpoint.

[1408] Input: Selection information

[1409] Output: API request

[1410] Step 3:

[1411] The server references the database based on the user ID and training title information to retrieve the required data. Based on the received user ID and training title, the server executes an SQL query to retrieve the following data: The user's past history data, ability evaluation data, and current job data.

[1412] Input: User ID, training title

[1413] Output: Acquired data (history data, performance evaluation data, business data)

[1414] Step 4:

[1415] The server calls the generative AI model to analyze the data. The server provides the acquired data as input to the AI ​​engine. The AI ​​engine analyzes this data and evaluates the user's current skill set, missing skills, and optimal learning style. This evaluation result is generated.

[1416] Input: Acquired data (history data, performance evaluation data, business data)

[1417] Output: Analysis results (skill set, skills gaps, learning style)

[1418] Step 5:

[1419] The server selects the most suitable training module based on the analysis results. The server lists the most suitable training modules based on the analysis results of the AI ​​engine. For example, "Advanced Slide Design" and "Effective Public Speaking" are selected.

[1420] Input: Analysis results

[1421] Output: Selection module

[1422] Step 6:

[1423] The server sends the generated training program to the device. The server combines the selection modules to generate a personalized training program and sends it to the device. It issues an HTTP POST request using the API endpoint.

[1424] Input: Selection module

[1425] Output: Personalized training program

[1426] Step 7:

[1427] The terminal presents the training program to the user. The terminal analyzes the received training program and displays it on the user interface. The user confirms the contents of the training program and starts it.

[1428] Input: Personalized Training Program

[1429] Output: Display training program

[1430] Step 8:

[1431] The user starts the training and sends progress information from the device to the server. As the user progresses through the training, the device periodically sends progress information to the server. For example, progress information is collected each time each step is completed.

[1432] Input: Training progress

[1433] Output: Progress information

[1434] Step 9:

[1435] The server records the progress information and provides the next training content in a timely manner. The server records the received progress information in a database and prepares to provide the next training module based on that information. The next module is sent to the terminal in a timely manner according to the progress.

[1436] Input: Progress information

[1437] Output: Next training module

[1438] Through these steps, users can efficiently receive training that is optimized for them, maximizing the effectiveness of their learning.

[1439] (Application example 1)

[1440] 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."

[1441] In recent years, with the widespread use of robots in factories, improving the skills of operators and maintenance personnel has become increasingly important. However, standardized, one-size-fits-all training programs are difficult to address, making it difficult to efficiently acquire skills. Conventional training programs do not adequately consider users' past work history or on-site requirements, making it difficult to maximize users' learning efficiency. Given this background, there is a need to provide personalized training programs based on each user's skill level and past work history in order to efficiently improve skills.

[1442] 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.

[1443] In this invention, the server includes: means for a user to select a training title on a terminal; means for transmitting the selected training title to the server; means for the server to acquire the user's past history data, ability evaluation data, and current work data; means for analyzing the data using an AI engine and evaluating the user's skill set and learning style; means for generating a personalized training program; means for transmitting the generated training program to the terminal; means for the terminal to present the program to the user and start the training; means for the terminal to provide training titles related to the operation and maintenance of factory robots; means for the server to recommend the next training module required based on the user's current skill level and past work history; and means for recording progress information of the training modules and providing the next module at an appropriate time. This makes it possible to provide an optimal training program based on each user's skill level and work history, thereby efficiently improving skills.

[1444] "Users" refer to factory operators and maintenance personnel who use this system to take training programs.

[1445] A "terminal" is a device that a user operates, and includes tablets and displays built into factory robots.

[1446] "Training Title" refers to the name of a particular training program selected by the user.

[1447] "Server" refers to the central system that manages the information and data selected by the user and analyzes the data using an AI engine.

[1448] "History data" refers to data related to the user's past behavioral history, such as records of tasks and operations performed by the user in the past, and error reports.

[1449] "Ability Assessment Data" refers to assessment data related to a user's skill level and abilities, including past test results and assessment reports.

[1450] "Current work data" refers to data related to the work the user is currently responsible for, including current job duties and project information.

[1451] An "AI engine" refers to a system that uses artificial intelligence technology to analyze data and evaluate a user's skill set and shortcomings.

[1452] A "skill set" refers to the collection of skills and abilities that a user possesses.

[1453] "Learning style" refers to characteristics that indicate how a user learns most effectively.

[1454] "Personalized training program" refers to a training program that is customized based on the user's individual needs and skill level.

[1455] A "factory robot" is an automated machine used in a factory to carry out manufacturing and maintenance processes.

[1456] "Training Module" means a separate learning unit within a training program that provides independent learning content.

[1457] This invention realizes a system that provides personalized training programs for factory robot operators and maintenance personnel. In this system, a user selects a training title on a terminal, and a server generates and provides an optimal training program based on the user's selection.

[1458] In a specific embodiment, the following process is performed. First, the user starts up the terminal and selects a desired program from multiple training titles. This selection is sent to the server via the terminal. The server acquires and analyzes the received training title information, as well as the user's past history data, ability assessment data, and current work data stored in a database. The server analyzes the data using an AI engine (e.g., TensorFlow) and evaluates the user's current skill set, skill gaps, and optimal learning style. Based on the evaluation results, it generates a list of training modules optimal for the user and combines them to create a personalized training program. The generated training program is sent to the terminal, which presents it to the user. The user reviews the content of the presented training program and, if satisfied, begins the training. During the training, the terminal transmits the user's progress information to the server, which records this progress. This allows the next training module to be provided in a timely manner.

[1459] Hardware and software used

[1460] The following hardware and software are used to realize this system.

[1461] Hardware: Android / iOS compatible tablets, displays built into factory robots

[1462] software:

[1463] Server side: Python

[1464] Database Management: MySQL

[1465] AI analysis engine: TensorFlow

[1466] Application frontend: React Native

[1467] Program processing explanation

[1468] The server uses TensorFlow to analyze the user's selected training title, past history data, ability assessment data, and current work data. The analysis evaluates the user's skill set and learning style, and generates optimal training modules based on that. The generated training modules are organized into a personalized training program and sent to the user's device at the appropriate time.

[1469] Specific examples

[1470] For example, if a user selects a training title such as "Precise Operation of a Robot Arm," the server will generate a customized training program that allows the user to learn in stages from "Basic Grip Operation" to "High-Precision Positioning Techniques" based on the frequency of past operational errors and evaluation data.

[1471] Prompt Sentence Examples

[1472] An example of a prompt sentence to input to the generative AI model is as follows:

[1473] "For the training title 'Precision Operation of Robot Arms' selected by user ID 5678, please recommend the next necessary training module based on past operation errors and current evaluation data."

[1474] These prompts allow users to receive training that is optimized for their skill level and needs, enabling them to improve their skills efficiently.

[1475] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1476] Step 1:

[1477] The user starts up the terminal and selects the desired program from among multiple training titles.

[1478] Input: List of training titles

[1479] Output: Selected training title

[1480] Specific operation: The user selects the desired training title from the list of training titles displayed on the device screen by tapping it. The selected training title is then saved in the device.

[1481] Step 2:

[1482] The terminal transmits the selected training title to the server.

[1483] Input: Selected training title

[1484] Output: Training title sent to the server

[1485] Specific operation: The device uses its internal communication function to send the selected training title to the server via the network, along with the user ID and time information.

[1486] Step 3:

[1487] The server acquires the user's past history data, performance evaluation data, and current business data.

[1488] Input: User ID and selected training title

[1489] Output: User's past history data, performance evaluation data, current work data

[1490] Specific operation: The server accesses the database and retrieves past history data (e.g., operation error history), ability evaluation data (e.g., skill evaluation results), and current business data (e.g., information about the project currently in charge) corresponding to the user ID.

[1491] Step 4:

[1492] The server uses an AI engine to analyze the data and assess the user's skill set and learning style.

[1493] Input: User's past history data, performance evaluation data, current work data

[1494] Output: Assessment of user skill sets and learning styles

[1495] How it works: The server launches an AI engine such as TensorFlow to analyze the input data. Specifically, it preprocesses the dataset and inputs it into a model to evaluate the strengths and weaknesses of the user's skills and the optimal learning method.

[1496] Step 5:

[1497] The server generates a personalized training program based on the assessment.

[1498] Input: User skill set and learning style assessment results

[1499] Output: Personalized training program

[1500] Specific operation: Based on the evaluation results, the server selects appropriate training modules (e.g., "basic grip operation" and "high-precision positioning techniques") and combines them to generate a personalized training program.

[1501] Step 6:

[1502] The server transmits the generated training program to the terminal.

[1503] Enter: personalized training programs.

[1504] Output: Training program sent to the device

[1505] Specific operation: The server transmits the generated training program to the terminal via the network, including the program sequence and detailed information.

[1506] Step 7:

[1507] The terminal presents the training program to the user, and the user starts the training.

[1508] Input: Training program sent from the server

[1509] Output: User who started the training

[1510] Specific operation: The device displays the training program on the screen, and the training begins when the user presses the "Start" button. The user proceeds with the learning according to the presented content.

[1511] Step 8:

[1512] The terminal transmits the user's progress information to the server.

[1513] Input: User training progress information

[1514] Output: Progress information sent to the server

[1515] Specific operation: The terminal records the user's training progress (e.g., completed modules, test results) in real time and transmits it to the server in a timely manner.

[1516] Step 9:

[1517] The server records progress information and provides the next training module at the appropriate time.

[1518] Input: User training progress information

[1519] Output: Next training module

[1520] Specific operation: The server stores the received progress information in a database, automatically selects the next required training module, and sends it to the terminal at the appropriate time.

[1521] 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.

[1522] The present invention relates to a system that recognizes a user's emotions and provides a personalized training program based on the results. In this system, the user selects a training title on a terminal, and the server generates and provides an optimal training program based on that selection. The system also analyzes the user's emotional state using an emotion engine. This makes it possible to customize the training program according to the user's emotional state.

[1523] First, the user launches the application on their device and selects the desired program from among multiple training titles. This selection is sent to the server via the device. The server then acquires and analyzes the received training title information, as well as the user's past history data, ability evaluation data, and current work data stored in the database.

[1524] The server uses an AI engine to analyze this data and assess the user's current skill set, gaps, and optimal learning style. It also uses an emotion engine to analyze the user's emotional state. The emotion engine uses facial and voice data to recognize emotions and assess their state.

[1525] Based on the evaluation results from both the AI ​​engine and the emotion engine, the server generates a list of training modules that are optimal for the user and combines them to create a personalized training program. For example, if the user is feeling stressed, a training module for relaxation can be added.

[1526] The server sends the generated training program to the terminal, which then presents it to the user. The user reviews the content of the training program and begins the training if they are satisfied. During the training, the terminal sends the user's progress information and emotional data to the server, which records the progress and emotional state. This allows the next training module to be provided in a timely manner based on the user's emotional state.

[1527] It is designed to help users efficiently acquire the skills necessary to maximize their learning outcomes, and by taking into account the user's emotional state, it can improve learning motivation and manage stress.

[1528] Specific examples

[1529] A specific example is shown below.

[1530] Example 1: Presentation skills training

[1531] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[1532] 2. The terminal sends the selected training title to the server.

[1533] 3. The server retrieves the user's past history data, ability evaluation data, and current work data from the database based on the user ID and the selected training title information.

[1534] 4. The server calls the AI ​​engine, provides this data as input, and evaluates the user's skill set and skills gaps, such as their current ability to create slides, their ability to interact with the audience, and the skills gaps they need.

[1535] 5. The emotion engine analyzes the user's facial expression and voice data to assess whether the user is feeling stressed or highly motivated.

[1536] 6. Based on the evaluation results from the AI ​​engine and emotion engine, the server generates a personalized training program that includes modules on "Advanced Slide Design," "Effective Public Speaking," and stress management.

[1537] 7. The server transmits the generated training program to the terminal.

[1538] 8. The device presents the training program to the user. The user begins the training, and each time the device completes a step, it sends progress information and emotion data to the server.

[1539] 9. The server records the progress and emotional state and provides the next training content in a timely manner.

[1540] This system allows users to receive training tailored to their needs, maximizing learning effectiveness, and by taking into account their emotional state, it can improve their motivation and manage stress.

[1541] The processing flow will be explained below.

[1542] Step 1:

[1543] The user starts the application on the terminal and selects the desired training title "Improve Presentation Skills" from the list of available training titles.

[1544] Step 2:

[1545] The device sends request data including the selected training title to the server. For example, the data is sent in JSON format along with the user ID.

[1546] Step 3:

[1547] The server receives the request and accesses a database to obtain the user's history data, performance assessment data, and current job data.

[1548] Step 4:

[1549] The server inputs this data into the AI ​​engine and emotion engine, providing it as parameters for analyzing the user's skill set, skill gaps, optimal learning style, and emotional state.

[1550] Step 5:

[1551] The emotion engine analyzes the user's facial expression and voice data to assess their emotional state, for example, determining whether they are stressed, relaxed, or motivated.

[1552] Step 6:

[1553] Based on these inputs, the AI ​​engine assesses the user's current skill set, any gaps in skills, and their optimal learning style.

[1554] Step 7:

[1555] The server receives the evaluation results of the AI ​​engine and emotion engine and generates a list of training modules that are optimal for the user's condition. For example, in addition to the modules "Advanced Slide Design" and "Effective Public Speaking," a module for stress management can be added.

[1556] Step 8:

[1557] The server transmits the generated personalized training program to the terminal.

[1558] Step 9:

[1559] The terminal presents the received training program to the user, and displays the program content and module configuration.

[1560] Step 10:

[1561] The user checks the presented program and, if satisfied, begins the training by, for example, pressing the "Start" button.

[1562] Step 11:

[1563] The terminal notifies the server of the user's training start action.

[1564] Step 12:

[1565] The server approves the start of the training and provides the necessary training resources (videos, texts, quizzes, etc.).

[1566] Step 13:

[1567] The terminal sequentially displays these resources to the user, and the training program progresses.

[1568] Step 14:

[1569] Each time the user completes a step, the terminal transmits its progress information and emotional data to the server, for example, sending progress data and emotional state upon completion of each module.

[1570] Step 15:

[1571] The server records the progress and emotional state of the user, and delivers the next training module in a timely manner according to the user's emotional state.

[1572] Step 16:

[1573] The terminal then presents the user with the next training module and repeats this until the entire training program is complete, for example, if the user is feeling stressed, a module on relaxation may be included.

[1574] Through these steps, users can receive personalized training programs and improve their skills. Furthermore, by taking into account the user's emotional state, it is possible to improve motivation and manage stress.

[1575] Example 2

[1576] 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."

[1577] Conventional training systems provided training programs based only on the user's past history and ability evaluation data, making it difficult to provide effective training programs that took into account the emotional state of each individual user.Furthermore, they did not have the functionality to analyze progress information and emotional data in real time and provide the next training content in a timely manner, making it difficult to maximize the learning effect of users.

[1578] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1579] In this invention, the server includes means for acquiring the user's past history data, ability evaluation data, and current work data, means for analyzing the data using an artificial intelligence engine to evaluate the user's skill set and learning style, and means for analyzing the user's emotional state using an emotion analysis engine, thereby enabling the provision of a personalized training program that takes the user's emotional state into consideration.

[1580] A "user" is a person who uses the system to take a training program.

[1581] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[1582] The "Training title" is the name of the training program selected by the user, and indicates the specific training content.

[1583] "Server" is the central computer responsible for data processing, generation and distribution of training programs.

[1584] "Past history data" refers to data that records the training programs that the user has previously attended and the user's learning history.

[1585] "Ability evaluation data" is data that includes evaluation results regarding the skills and abilities of a user.

[1586] "Current business data" refers to data that includes information about the user's current job duties and business.

[1587] "Artificial Intelligence Engine" refers to software and algorithms used to analyze acquired data and assess a user's skill set and learning style.

[1588] "Emotion Analysis Engine" refers to software and algorithms for analyzing a user's emotional state.

[1589] A "personalized training program" is a training program that is individually created taking into account the user's skill set and emotional state.

[1590] "Progress information" is data that indicates the progress of a user as they progress through a training program.

[1591] "Emotion data" is data relating to emotions acquired by analyzing the user's facial expressions and voice.

[1592] The present invention relates to a system that recognizes a user's emotions and provides a personalized training program based on the results.

[1593] First, the user launches the application on their device and selects the desired program from among multiple training titles. This selection is sent to the server via the device. The training title information selected by the user is sent to the server as JSON format data.

[1594] The server retrieves the received training title information, as well as the user's past history data, ability evaluation data, and current job data stored in the database. Specifically, it extracts the necessary information using an SQL SELECT query.

[1595] The server then launches an artificial intelligence engine (e.g., TensorFlow) and provides the acquired user data as input. The AI ​​engine uses this data to analyze the user's current skill set and gaps, as well as assess their appropriate learning style.

[1596] Furthermore, the server uses an emotion analysis engine (e.g., a general emotion recognition API) to analyze the user's facial expression and voice data sent from the device. The emotion analysis engine evaluates the user's stress level and motivation state.

[1597] Based on the evaluation results of the AI ​​engine and the sentiment analysis engine, the server generates a list of training modules that are optimal for the user, and combines them to create a personalized training program. The generated training program is sent to the device as JSON format data.

[1598] The device receives the training program from the server and presents it to the user. If the user confirms and agrees with the training content, the training begins. During the training, the device periodically transmits the user's progress information and emotional data to the server.

[1599] The server records the received progress information and emotion data, and generates and provides the next optimal training module based on this information, thereby maintaining an optimal learning environment for the user and enabling effective skill acquisition.

[1600] Specific examples

[1601] Example: Presentation skills training

[1602] 1. The user launches the app on their device and selects the training title "Improve Presentation Skills."

[1603] 2. The device sends the selected training title to the server as JSON data.

[1604] 3. The server retrieves the user information from the database using an SQL query.

[1605] 4. The server loads the TensorFlow model and evaluates the user's skill set.

[1606] 5. The server uses a general emotion recognition API to analyze the user's facial expressions and voice data.

[1607] 6. The server generates a training program based on the evaluation results and creates a personalized program including "Advanced Slide Design" and "Effective Public Speaking."

[1608] 7. The server sends the generated program to the terminal.

[1609] 8. The terminal displays the training program to the user, and the user begins the training.

[1610] 9. As the user progresses through the training, the device periodically sends progress information and emotional data to the server.

[1611] 10. The server records these data and provides the next training module in a timely manner.

[1612] Prompt Sentence Examples

[1613] Prompt 1: Example input to a generative AI model

[1614] "The user has selected a training program to improve their presentation skills. Please suggest the most appropriate learning module based on their past training history, skill assessment, and current job duties. Also, please evaluate the user's emotional state using facial and voice data and take the results into consideration."

[1615] Prompt 2: Example of progress information

[1616] "Please tell us about the current training progress. Please let us know if the user is stressed or motivated, and how well they are progressing."

[1617] This system takes into account the user's emotional state and provides personalized training programs to achieve optimal learning outcomes.

[1618] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1619] Step 1:

[1620] The user starts the application on the terminal and selects the desired program from among a number of training titles.

[1621] Specific operation: The user selects a training title such as "Improve Presentation Skills" from the list of training titles on the screen.

[1622] Input: User selection information

[1623] Output: JSON data containing the selected training titles

[1624] Step 2:

[1625] The terminal transmits the user's selection information to the server.

[1626] Specific operation: The selected training title information is sent to the server in JSON format.

[1627] Input: JSON data containing the selected training titles

[1628] Output: Course title information sent to the server

[1629] Step 3:

[1630] The server acquires the received training title information, the user's past history data, ability evaluation data, and current work data stored in the database.

[1631] What happens next: The server uses an SQL SELECT query to retrieve the relevant user data from the database.

[1632] Input: Training title information, user ID

[1633] Output: Past history data, performance evaluation data, current business data

[1634] Step 4:

[1635] The server uses an artificial intelligence engine to analyze the acquired data and assess the user's skill set and learning style.

[1636] How it works: The server loads the TensorFlow model and inputs the acquired user data into the model to evaluate skill sets and learning styles.

[1637] Input: Past history data, performance evaluation data, current work data

[1638] Output: Evaluation results of user's skill set and learning style

[1639] Step 5:

[1640] The server uses an emotion analysis engine to analyze the user's emotional state.

[1641] Specific operation: The user's facial expression data and voice data sent from the device are input into the emotion recognition API and analyzed.

[1642] Input: facial expression data, voice data

[1643] Output: Evaluation result of the user's emotional state

[1644] Step 6:

[1645] Based on the evaluation results of the artificial intelligence engine and the sentiment analysis engine, the server generates a list of training modules that are optimal for the user and combines them to create a personalized training program.

[1646] Specific operation: Select modules such as "Advanced Slide Design" and "Effective Public Speaking" and combine programs according to the user's condition.

[1647] Input: Skill set assessment results, Learning style assessment results, Emotional state assessment results

[1648] Output: Personalized training program

[1649] Step 7:

[1650] The server transmits the generated training program to the terminal.

[1651] Specific operation: The generated training program is sent to the terminal in JSON format.

[1652] Input: Personalized training program

[1653] Output: Training program sent to the terminal

[1654] Step 8:

[1655] The terminal presents the training program to the user, and the user confirms the contents.

[1656] Specific operation: The training program is displayed on the screen and the user confirms it.

[1657] Input: Training program sent to the terminal

[1658] Output: User confirmation

[1659] Step 9:

[1660] The user starts training and sends progress information and emotion data to the server.

[1661] Specific operation: As the user progresses through each training module, the terminal records progress information, collects emotional data, and sends it to the server.

[1662] Input: Training progress data, emotion data

[1663] Output: Progress and emotion data sent to the server

[1664] Step 10:

[1665] The server records progress information and emotional data, and based on this generates and provides the next optimal training module.

[1666] Specific behavior: The server analyzes the progress and emotion data and adjusts the next training module as needed.

[1667] Input: Progress data, emotion data

[1668] Output: Next training module

[1669] The above are the specific processing steps of the system program.

[1670] (Application example 2)

[1671] 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."

[1672] Traditional training programs are generally provided uniformly and do not take into account the skill sets and emotional states of each user, which can result in reduced learning effectiveness.In addition, there is a lack of methods for conducting on-the-job training efficiently and safely within factories.

[1673] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: a means for a user to select a training title on a terminal; a means for transmitting the selected training title to the server; a means for the server to acquire the user's past history data, ability evaluation data, and current work data; a means for the server to analyze the data using an AI engine and evaluate the user's skill set and learning style; a means for generating a personalized training program based on the evaluation; a means for analyzing facial expression data and voice data using an emotion engine and evaluating the user's emotional state; a means for customizing the training program based on the evaluation of the emotional state; a means for transmitting the generated training program to the terminal; a means for the terminal to present the training to the user and start the training; and a means for providing the training program to the user using a robot. This provides a personalized training program tailored to the user's skill set and emotional state, improving learning effectiveness. Furthermore, efficient and safe on-the-job training in factories is possible.

[1674] A "terminal" is a device that a user uses to select a training title and take a training program.

[1675] "Server" refers to the central processing unit that processes user history data and training title information, and generates and provides personalized training programs.

[1676] "Past history data" refers to data relating to the user's past training history and work history.

[1677] "Ability assessment data" is assessment data regarding the user's current skill set and abilities.

[1678] "Current business data" is data relating to the user's current business situation and the work he or she is in charge of.

[1679] An "AI engine" is an artificial intelligence technology that analyzes collected data and evaluates a user's skill set and learning style.

[1680] An "emotion engine" is a technology that analyzes a user's facial expression data and voice data to evaluate their emotional state.

[1681] A "training program" is structured content for users to learn or train.

[1682] "Customizing the training program" means adjusting and optimizing the training content based on the user's emotional state and evaluation results.

[1683] A "robot" is a mechanical device that supports practical training within a factory and provides and guides training programs to users.

[1684] "Facial expression data" refers to data relating to the facial expression of the user.

[1685] "Voice data" is data related to the user's speech.

[1686] "Progress" is information indicating at what stage the user is in the training program.

[1687] A "personalized training program" is training content that is customized based on a user's individual skill set and emotional state.

[1688] The present invention relates to a system for providing personalized training programs for personnel within a factory.

[1689] First, a user (factory employee) uses a terminal to start the training application and select a training title. For example, the user selects the training title "How to set up a CNC machine." This selected training title information is sent from the terminal to the server.

[1690] The server uses the received training title information and the user's ID to retrieve past history data, ability evaluation data, and current work data from the database, thereby understanding the user's learning history and current skill status.

[1691] The server then uses an AI engine to analyze this data and assess the user's skill set and learning style, identifying their current skill level and gaps, and recommending optimal learning content.

[1692] Additionally, an emotion engine is used to analyze the user's facial expression and voice data to assess their emotional state. For example, it can determine whether the user is feeling stressed or highly motivated. This allows the system to add and adjust training modules according to the user's emotional state, as well as the learning content.

[1693] Based on the evaluation results from the AI ​​engine and emotion engine, the server generates a personalized training program, which may include modules such as "basic operation explanations," "safety measures," and even "stress management" and "improving concentration."

[1694] The generated training program is sent to the terminal, which then presents it to the user. The user then checks the training program and begins the training. The training is carried out using a robot. A robot placed in the factory presents the training content to the user as they progress, providing guidance on work procedures and safety measures.

[1695] During the training, the robot continuously monitors the user's facial expressions and speech, and transmits progress information and emotional data to the server, which records this data and uses it to optimize future training programs.

[1696] This allows users to receive personalized training tailored to their skill sets and emotional state, maximizing learning effectiveness. Furthermore, the use of robots enables efficient and safe on-the-job training within factories.

[1697] For example, if a user selects training on "How to set up a CNC machine," the AI ​​engine will determine that basic operations are necessary based on past operation history and evaluation data, and add a module for "Explanation of basic operations." On the other hand, if the emotion engine detects stress from the user's facial expression, modules on relaxation methods and stress management will also be added.

[1698] Furthermore, this system uses a generative AI model to prepare prompts, enabling flexible and intuitive training program generation. For example, the system uses prompts such as:

[1699] Generate optimal training programs based on skill set assessments of how to configure CNC machines and employees' emotional states. Use past work history and facial expression analysis data to personalize the content, including modules on stress management and focus improvement.

[1700] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1701] Step 1:

[1702] The user starts the training application using the terminal and selects a training title. The input is the user's selection operation, and the output is the selected training title information. This information is sent to the server in the next step.

[1703] Step 2:

[1704] The terminal sends the selected training title information and user ID to the server. The input is the training title information and user ID, and the output is the data sent to the server.

[1705] Step 3:

[1706] Based on the training title information and user ID received by the server, past history data, ability evaluation data, and current work data are retrieved from the database. The input is the training title information and user ID, and the output is the retrieved user data.

[1707] Step 4:

[1708] The server uses an AI engine to analyze the acquired data and evaluate the user's skill set and learning style. The input is past history data, ability assessment data, and current work data, and the output is the evaluation results of the user's skill set and learning style.

[1709] Step 5:

[1710] The server uses an emotion engine to analyze the user's facial expression and voice data and evaluate their emotional state. The input is the user's facial expression and voice data, and the output is the evaluation result of their emotional state.

[1711] Step 6:

[1712] The server generates a personalized training program based on the evaluation results of the AI ​​engine and the emotion engine. The inputs are the evaluation results of the skill set and learning style, and the evaluation results of the emotional state, and the output is the generated personalized training program.

[1713] Step 7:

[1714] The server sends the generated training program to the terminal, where the input is the generated training program and the output is the training program sent to the terminal.

[1715] Step 8:

[1716] The terminal presents the training program to the user and starts the training. The input is the training program sent, and the output is instructions for the user to start the training.

[1717] Step 9:

[1718] During the training, the user interacts with the robot. The robot monitors the user's progress and emotional data in real time and sends them to the server. The input is the user's progress and emotional data, and the output is the progress and emotional data sent to the server.

[1719] Step 10:

[1720] The server records the received progress information and emotion data, and optimizes and provides the next training module. The input is the progress information and emotion data, and the output is the next optimized training module.

[1721] 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.

[1722] 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.

[1723] 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.

[1724] 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.

[1725] 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.

[1726] 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.

[1727] 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).

[1728] 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.

[1729] 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."

[1730] 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.

[1731] 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).

[1732] 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.

[1733] 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.

[1734] 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.

[1735] 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.

[1736] 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.

[1737] 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.

[1738] 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.

[1739] 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.

[1740] 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.

[1741] 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.

[1742] The following is further disclosed regarding the above embodiment.

[1743] (Claim 1)

[1744] A means for a user to select a training title on a terminal;

[1745] means for transmitting the selected training title to a server;

[1746] means for the server to acquire user's past history data, ability evaluation data, and current work data;

[1747] means for the server to analyze the data using an AI engine to assess the user's skill set and learning style;

[1748] means for generating a personalized training program based on said evaluation;

[1749] means for transmitting the generated training program to a terminal;

[1750] The system includes a means for the terminal to present to a user and initiate training.

[1751] (Claim 2)

[1752] 2. The system according to claim 1, wherein the server further comprises means for recording the progress of the training program and delivering the next training content in a timely manner.

[1753] (Claim 3)

[1754] 10. The system of claim 1, wherein the terminal further comprises means for displaying a list of available training titles.

[1755] "Example 1"

[1756] (Claim 1)

[1757] A means for a user to select a training title on a terminal;

[1758] means for transmitting the selected training title to a server;

[1759] means for the server to acquire user's past history data, ability evaluation data, and current work data;

[1760] means for the server to analyze the data using a generative AI model to assess the user's skill set and learning style;

[1761] means for generating a personalized training program based on said evaluation;

[1762] means for transmitting the generated training program to a terminal;

[1763] A means for the terminal to present to the user and start training;

[1764] means for transmitting the progress information to a server;

[1765] The server records progress information and delivers the next training content in a timely manner.

[1766] A system including:

[1767] (Claim 2)

[1768] 2. The system according to claim 1, wherein the server further comprises means for recording the progress of the training program and delivering the next training content in a timely manner.

[1769] (Claim 3)

[1770] 10. The system of claim 1, wherein the terminal further comprises means for displaying a list of available training titles.

[1771] "Application Example 1"

[1772] (Claim 1)

[1773] A means for a user to select a training title on a terminal;

[1774] means for transmitting the selected training title to a server;

[1775] means for the server to acquire user's past history data, ability evaluation data, and current work data;

[1776] means for the server to analyze the data using an AI engine to assess the user's skill set and learning style;

[1777] means for generating a personalized training program based on said evaluation;

[1778] means for transmitting the generated training program to a terminal;

[1779] A means for the terminal to present to the user and start training;

[1780] means for the terminal to provide training titles relating to the operation and maintenance of factory robots;

[1781] A means for the server to recommend the next training module required based on the user's current skill level and past work history;

[1782] a means for recording progress information of the training module and providing the next module at an appropriate time;

[1783] A system including:

[1784] (Claim 2)

[1785] 2. The system according to claim 1, wherein the server further comprises means for recording the progress of the training program and delivering the next training content in a timely manner.

[1786] (Claim 3)

[1787] 10. The system of claim 1, wherein the terminal further comprises means for displaying a training title for the operation and maintenance of a factory robot.

[1788] "Example 2: Combining Emotion Engines"

[1789] (Claim 1)

[1790] A means for a user to select a training title on a terminal;

[1791] means for transmitting the selected training title to a server;

[1792] means for the server to acquire user's past history data, ability evaluation data, and current work data;

[1793] means for the server to analyze the data using an artificial intelligence engine to assess the user's skill set and learning style;

[1794] means for the server to analyze the user's emotional state using an emotion analysis engine;

[1795] means for generating a personalized training program based on the evaluation and sentiment analysis;

[1796] means for transmitting the generated training program to a terminal;

[1797] A means for the terminal to present to the user and start training;

[1798] The system includes a means for users to submit progress information and emotional data during training.

[1799] (Claim 2)

[1800] 2. The system according to claim 1, wherein the server further comprises means for recording the progress of the training program and delivering the next training content in a timely manner.

[1801] (Claim 3)

[1802] 10. The system of claim 1, wherein the terminal further comprises means for displaying a list of available training titles.

[1803] "Application example 2 when combining emotion engines"

[1804] (Claim 1)

[1805] A means for a user to select a training title on a terminal;

[1806] means for transmitting the selected training title to a server;

[1807] means for the server to acquire user's past history data, ability evaluation data, and current work data;

[1808] means for the server to analyze the data using an AI engine to assess the user's skill set and learning style;

[1809] means for generating a personalized training program based on said evaluation;

[1810] a means for analyzing facial expression data and voice data using an emotion engine to assess the user's emotional state;

[1811] means for customizing a training program based on said assessment of emotional state;

[1812] means for transmitting the generated training program to a terminal;

[1813] A means for the terminal to present to the user and start training;

[1814] The system includes means for providing the training program to a user using a robot.

[1815] (Claim 2)

[1816] 2. The system according to claim 1, wherein the server further comprises means for recording the progress of the training program and delivering the next training content in a timely manner.

[1817] (Claim 3)

[1818] 10. The system of claim 1, wherein the terminal further comprises means for displaying a list of available training titles. [Explanation of symbols]

[1819] 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 a user to select a training title on a terminal; means for transmitting the selected training title to a server; means for the server to acquire user's past history data, ability evaluation data, and current work data; means for the server to analyze the data using an AI engine to assess the user's skill set and learning style; means for generating a personalized training program based on said evaluation; means for transmitting the generated training program to a terminal; The system includes a means for the terminal to present to a user and initiate training.

2. 2. The system according to claim 1, wherein the server further comprises means for recording the progress of the training program and delivering the next training content in a timely manner.

3. The system of claim 1 , wherein the terminal further comprises means for displaying a list of available training titles.

Images