system

Abstract

We provide the system. [Solution] A data storage means for saving learning progress data received from a user terminal, A data processing means for generating personalized learning suggestions based on received learning progress data, A data transmission means for sending the generated learning suggestions to the user's terminal, By utilizing accumulated data, we can evolve artificial intelligence agents and optimize business procedures. A simulation method for tracking user operations in real time and virtually reproducing the factory environment, Includes machine learning algorithms to provide the optimal procedure for operation. Business support system.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern business environment, companies have an increasing need to utilize artificial intelligence (AI) and digital transformation (DX). However, employees lack appropriate education and training opportunities to master these technologies and apply them to actual work. As a result, the improvement of business efficiency and the creation of new business opportunities are hindered, and there is a demand to quickly and accurately incorporate AI and DX into business operations.

Means for Solving the Problems

[0005] The present invention provides a business support system comprising data storage means for storing learning progress data received from a user terminal, and processing means for generating personalized learning suggestions based on that data. It also includes communication means for transmitting the generated learning suggestions to the user terminal, and further includes optimization means for evolving an artificial intelligence agent using the accumulated data. This system facilitates practical learning through business-related case studies, promotes knowledge sharing among users, supports the efficient introduction of AI and DX, and contributes to improving business workflows.

[0006] A "user terminal" is an electronic device used by a user to access a specific learning platform.

[0007] "Learning progress data" refers to information that records the learning content and progress achieved by users on the learning platform.

[0008] "Data storage means" refers to a method or apparatus for storing and retaining learning progress data and other related data.

[0009] "Personalized learning suggestions" refer to information that proposes individually optimized learning methods and next learning steps based on the user's learning progress.

[0010] "Processing means" refers to a method or apparatus for performing specific calculations or transformations based on received data.

[0011] "Communication means" refers to a method or device for transmitting data or information to a user's terminal.

[0012] An "artificial intelligence agent" is an AI program that evolves and optimizes to provide business support.

[0013] An "optimization method" is a method or apparatus that analyzes accumulated data to enable artificial intelligence agents to more effectively support tasks. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention is a business support system aimed at improving the operational efficiency of companies by enabling users with specific learning objectives to organically combine knowledge of AI and DX. Below, we will describe the embodiments for carrying out the invention, while showing the roles of each entity in the operation of the system and providing specific examples.

[0036] Server Role

[0037] The server plays a central role in the learning platform, implementing diverse learning content. When a user connects, the server delivers appropriate learning content to the device and constantly tracks the user's learning progress. For example, when a user completes a basic AI course, the server recommends content on DX implementation case studies as the next step. The server also analyzes accumulated data and runs optimization algorithms to improve the performance of artificial intelligence agents, providing specific business advice and suggesting process automation.

[0038] User terminal operation

[0039] The user terminal displays content delivered from the server and provides a learning interface. As the user progresses through the learning process, the terminal quickly reflects their actions and displays feedback. When the user solves practice problems, the terminal displays an answer input form and sends the answer to the server. For example, in a case study exercise on business process improvement, the terminal sends the solution entered by the user to the server in real time and displays feedback.

[0040] User operation

[0041] Users log in to access the learning platform, select courses of interest, and begin learning. During the learning process, users solve specific exercises related to their own work and share information with colleagues using AI collaborative creation notes. For example, when a user works on a project to improve inventory management efficiency using AI, they share notes with other team members and discuss optimal solutions. In this way, users integrate knowledge into their work and generate ideas that directly contribute to their tasks.

[0042] As described above, the present invention provides a system that improves the overall operational efficiency and productivity of a company by having servers, terminals, and users each play a specific role and work together in cooperation.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server prepares the learning platform and accepts user registration information. This information is stored in a database, making it accessible to users.

[0046] Step 2:

[0047] Users log in to the learning platform using their devices and select courses of interest from the provided list of AI and DX courses.

[0048] Step 3:

[0049] The device displays the selected learning content, allowing the user to access the content and begin learning.

[0050] Step 4:

[0051] The server tracks the user's learning progress in real time and records the progress data in a data storage device.

[0052] Step 5:

[0053] Based on the learning progress, the server generates individually optimized learning suggestions and delivers them to the terminal.

[0054] Step 6:

[0055] Users work on practice problems displayed on their devices, enter their answers, and send them to the server.

[0056] Step 7:

[0057] The server analyzes the received answers and automatically records them in an AI collaborative creation notebook. This facilitates knowledge sharing.

[0058] Step 8:

[0059] Users utilize the AI ​​collaborative creation notebook to work with colleagues and discuss specific business improvement measures based on case studies.

[0060] Step 9:

[0061] The server uses the accumulated data to perform optimization processing to improve the performance of the artificial intelligence agent and makes suggestions for improving business efficiency.

[0062] Step 10:

[0063] Users receive advice from AI agents related to their work via their devices and apply it to their actual workflow.

[0064] (Example 1)

[0065] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0066] Conventional learning support systems lack personalized learning suggestions tailored to the user's learning progress, making efficient knowledge acquisition and practical application difficult. Furthermore, effectively utilizing accumulated data to optimize processes and drive business improvement is challenging. There is a need to increase opportunities for efficient information sharing and achieve more advanced business analysis and knowledge utilization.

[0067] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0068] In this invention, the server includes data storage means for storing learning progress information received from a user terminal, information processing means for generating learning recommendations suitable for the user based on the received learning progress information, and communication means for distributing the generated learning recommendations to the user terminal. This makes it possible to provide each user with a personalized learning plan. Furthermore, it enables the enhancement of artificial intelligence and optimization of processes based on the accumulated information, contributing to overall operational efficiency and productivity improvement.

[0069] A "user terminal" is a computing device used by users to access the learning platform and view and interact with its content.

[0070] "Learning progress information" refers to data that shows how far a user has progressed in their learning activities.

[0071] A "data storage means" is a system element that has the function of safely and efficiently storing received information.

[0072] "Information processing means" refers to computational means for analyzing received data and generating optimal learning suggestions for the user.

[0073] "Communication methods" refer to methods and technologies for transmitting data and suggestions between a server and a user's terminal.

[0074] An "artificial intelligence agent" is a program that is ready to use its accumulated knowledge to improve business processes.

[0075] "Optimization methods" refer to methods for making adjustments and improvements to streamline business processes.

[0076] A "generative AI model" is a program that extracts insights from large amounts of data and generates effective strategies and solutions based on new data.

[0077] "Data analysis methods" are techniques used to analyze collected information and derive useful insights and suggestions.

[0078] This business support system has a configuration in which servers, terminals, and users work together in coordination.

[0079] First, the server serves as the core of the business support platform, accepting connections from users. The server uses a database to store and manage learning progress information and selects customized learning content for each user. This process utilizes a generative AI model to analyze accumulated data and optimize the next learning step and its application to business operations. The server also includes data storage capabilities and ensures secure information management.

[0080] Next, the terminal functions as the user's learning interface, displaying content delivered from the server. The terminal efficiently processes user input and communicates with the server in real time. For example, when a user selects a learning task related to AI or DX and proceeds with the learning on the system, the terminal displays answer forms for practice problems and feedback screens.

[0081] Users log into this system and select learning courses relevant to their area of ​​work. Throughout the learning process, users utilize AI collaborative note-taking and share information with colleagues, deepening their knowledge directly applicable to their work. For example, when working on a project to improve inventory management efficiency, a user might use a prompt to the generative AI model—"Analyze sales data and propose the most effective sales strategy"—to plan a specific strategy. This prompt helps users understand market trends and formulate business strategies using the generative AI model.

[0082] In this way, the present invention is a system that leverages the roles of the server, terminal, and user, and organically combines diverse educational materials and information processing capabilities to support users in improving their work efficiency and productivity.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The server receives login information from the user and compares it with the database. It receives the user's ID and password as input and performs authentication by matching them with existing registration data. If authentication is successful, the server generates the user's learning dashboard and prepares it for display as the next step. The output is a customized learning dashboard based on the user profile.

[0086] Step 2:

[0087] The user selects a learning course of interest from the learning dashboard. The input here is the user's selection. The device sends this selection to the server. Based on the selection, the server retrieves relevant learning content (text, videos, exercises) from its database and streams it to the device. As output, the selected learning content is displayed on the user's device.

[0088] Step 3:

[0089] The device allows the user to progress through the learning process using the displayed learning content. Input consists of the user's actions and answers. When the user enters an answer to an exercise problem, the device sends the answer to the server. The server analyzes the answer, determines whether it is correct or incorrect, and generates appropriate feedback. Output is the feedback information displayed on the user's device.

[0090] Step 4:

[0091] The server monitors learning progress and stores learning history in a database. The input is progress information submitted by the user. The server analyzes this data to generate suggestions for the next learning content and advice on more effective learning methods. As output, the user's device displays the next content and methods to be learned.

[0092] Step 5:

[0093] Users use the AI ​​collaborative creation notebook to create projects based on what they've learned and share them with colleagues. Input consists of new information and comments added to the notebook. The device synchronizes the entered information with other users' devices in real time. Output consists of the shared notebook content and feedback from colleagues.

[0094] Step 6:

[0095] The server uses a generative AI model to perform analyses useful for business improvement, based on the accumulated learning data of all users. The input is data collected from the entire system. The server utilizes the generative AI model to analyze the accumulated data and generate insights for improving business efficiency. The output consists of specific business improvement proposals and new strategies using prompt messages.

[0096] (Application Example 1)

[0097] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] Improving the efficiency and ensuring the safety of robot operations within factories are critical challenges. Traditional robot operation training requires on-the-job training, which is costly and risky. Furthermore, insufficient knowledge sharing among workers can prevent the training from leading to actual improvements in work processes. A new training method is needed to address these challenges and achieve both operational efficiency and safety.

[0099] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0100] In this invention, the server includes data storage means, data processing means, data transmission means, optimization means, simulation means, and a machine learning algorithm. This enables the simulation of real-time work conditions in the factory, allowing workers to safely learn robot operation, and further enables the suggestion of optimal operating procedures using AI.

[0101] "Data storage means" refers to a device or program that has the function of saving learning progress data received from a user terminal.

[0102] "Data processing means" refers to a device or program that has the function of generating learning suggestions suitable for the user based on received learning progress data.

[0103] "Data transmission means" refers to a device or program that has the function of transmitting generated learning suggestions to a user terminal.

[0104] An "optimization means" is a device or program that has the function of evolving an artificial intelligence agent using accumulated data and improving work procedures.

[0105] A "simulation means" is a device or program that has the function of tracking user operations in real time and virtually reproducing the factory environment.

[0106] A "machine learning algorithm" is a computational method that analyzes the efficiency of a task based on accumulated data and constructs a learning model to derive the optimal work procedure.

[0107] In implementing this invention, a system is constructed in which a server, terminal, and user each fulfill their respective roles. The server manages learning progress data through data storage, processing, and transmission means. Specifically, it stores the user's learning log in a database and uses that information to execute an algorithm that personalizes learning content. Subsequently, it sends the results to the user terminal to provide real-time feedback. The database used here may be, for example, MySQL® or PostgreSQL, and Unity or Unreal Engine may be used to perform case study simulations.

[0108] The terminal displays learning content based on data received from the server and reflects the user's actions. To conduct simulations in real time, a device equipped with a GPU corresponding to the processing power required by the terminal is used. This allows for the reproduction of complex operating environments such as factory simulations, enabling users to receive training safely.

[0109] Users operate the simulation via a terminal and learn as needed. The AI ​​algorithm analyzes the user's actions in real time and suggests efficient work procedures, which can be useful in actual work. For example, when working in a factory, the system can optimize the assembly procedure of parts in real time and immediately display how to correct any errors, thereby improving work efficiency.

[0110] Furthermore, the system uses a generative AI model to create prompt messages and provide situation-specific advice. An example of a prompt message would be, "Write a program that recreates the factory environment using 3D simulation, tracks worker actions in real time, and advises on the optimal robot operation procedure." In this way, the system is a powerful tool to effectively support users in improving their skills within their work.

[0111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0112] Step 1:

[0113] The server receives learning progress data from the user's terminal and saves this data to a database. In this step, data regarding the user's progress is input, and basic data is output to create the next learning suggestion based on that information. Specifically, information such as the learning modules the user has completed and their scores are recorded as logs.

[0114] Step 2:

[0115] The server analyzes accumulated learning progress data and executes machine learning algorithms to generate personalized learning suggestions. The input is stored learning progress data, and the output is individually optimized learning content based on that data. Specifically, it analyzes the user's past learning history and selects the next content they should work on.

[0116] Step 3:

[0117] The server sends the generated learning suggestions to the user's terminal. In this step, optimized content stored on the server serves as input, and the learning suggestions are output in a format displayed on the user's terminal. Specifically, the server organizes the learning suggestions into packets and sends them to the terminal via the network.

[0118] Step 4:

[0119] The device displays learning suggestions received from the server. The input is learning suggestion data from the server, and the output is content displayed in a form that the user can visually confirm. Specifically, the content is displayed on the device via a UI, guiding the user to the next step.

[0120] Step 5:

[0121] Users interact with learning content on their devices and perform simulations. Inputs consist of learning content provided by the server and user operation data, while output includes the user's operations and learning results. Specifically, users perform work training in a simulation that mimics a factory environment and receive feedback on operational errors and areas for improvement.

[0122] Step 6:

[0123] The terminal tracks user actions in real time and sends user activity data to the server. The input is user action data, and the output is activity log data for analysis by the server. Specifically, the terminal's sensors read user actions and send that data to the server.

[0124] Step 7:

[0125] The server analyzes the received activity data, applies machine learning algorithms to generate optimized operating procedures, and sends them to the user as advice. The input is user activity data, and the output is optimized operating guidance. Specifically, it identifies areas where improvements are needed in specific operations and presents the user with methods for improvement.

[0126] An example of a prompt message is: "Write a program that recreates a factory environment using 3D simulation, tracks worker actions in real time, and advises on the optimal robot operation procedure."

[0127] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0128] This invention is a business support system related to AI and DX, which provides a more personalized learning experience for users by combining it with emotion recognition technology. The following describes specific embodiments for carrying out this invention.

[0129] Server Role

[0130] The server, as the central device of the learning platform, plays the role of centrally processing data from user terminals. Specifically, it receives and stores learning progress data and generates learning suggestions based on the received data. It also has a function to automatically adjust the difficulty level of learning content according to the user's emotional state. For example, if the server detects that the user's emotional data indicates stress, it will switch to easier learning suggestions to reduce the load on the server.

[0131] User terminal operation

[0132] The user terminal is a device that provides the user interface and displays content and feedback sent from the server. The terminal incorporates an emotion engine that analyzes the user's facial expressions and tone of voice to generate emotion data. This data is sent to the server in real time and influences the individual learning experience. For example, if signs of confusion are detected in the user's facial expressions while they are working on an exercise, the terminal sends this information to the server to prompt support.

[0133] User operation

[0134] Users can access the learning platform through their devices and select courses based on AI and DX technologies to proceed with their learning. Because the user's emotional state is reflected in the learning flow, content at an appropriate level is provided, improving learning efficiency. Furthermore, when sharing knowledge with colleagues using digital notes, the emotion engine analyzes the atmosphere of the discussion and offers suggestions to support smooth communication.

[0135] Thus, the system of the present invention supports the improvement of users' skills and work efficiency by analyzing users' emotions in real time and optimizing the learning experience based on those emotions.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The user logs into the learning platform using their device. The device authenticates the user's access and displays a list of available courses.

[0139] Step 2:

[0140] The user selects an AI or DX course that interests them. The selection is sent from the device to the server, which then delivers the corresponding learning content to the device.

[0141] Step 3:

[0142] The server uses data storage to track learning progress and records the user's progress. The data is updated upon completion of each learning step.

[0143] Step 4:

[0144] The device uses a built-in emotion engine to analyze the user's facial expressions and voice, generating emotion data. For example, if the user shows a confused expression while working on a question, that data is collected.

[0145] Step 5:

[0146] The generated sentiment data is sent from the device to the server. The server uses this sentiment data to evaluate the user's current learning progress.

[0147] Step 6:

[0148] The server analyzes emotional data and learning progress data to generate personalized learning suggestions. For example, if a user has a high stress level, it will suggest easier practice problems.

[0149] Step 7:

[0150] The server sends the generated learning suggestions to the terminal for use. The terminal notifies the user of the new suggestions.

[0151] Step 8:

[0152] The user uses their device to continue learning based on suggestions from the server. The device again senses the progress of learning and changes in emotional state, and the processing cycle is repeated.

[0153] Step 9:

[0154] Using the digital note-taking function on their devices, users can record their learning progress and share information with colleagues. During this process, the emotion engine provides advice to support the smooth progress of discussions.

[0155] (Example 2)

[0156] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0157] Conventional learning support systems struggle to provide personalized learning suggestions in real time that take into account each user's emotional state. This leads to users experiencing stress and a decrease in learning efficiency. Furthermore, there are insufficient means to facilitate smooth communication by sharing emotional states.

[0158] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0159] In this invention, the server includes data storage means for storing learning progress data and emotional data received from the user terminal, information processing means for generating personalized learning suggestions based on the received learning progress data and emotional data, and information transmission means for transmitting the generated learning suggestions to the user terminal. This enables real-time automatic adjustment of learning content according to the user's emotional state, allowing for efficient skill improvement while reducing the learning burden.

[0160] A "data storage means" is a device that provides functions for safely and efficiently storing learning progress data and emotional data acquired from a user terminal.

[0161] An "information processing device" is a device that has a mechanism for analyzing learning progress data and sentiment data, and generating optimal learning suggestions based on that analysis.

[0162] "Information transmission means" refers to a device equipped with communication functions for quickly and accurately transmitting generated learning suggestions to the user's terminal.

[0163] An "emotion engine" is a technology that detects and digitizes a user's emotional state by analyzing their facial expressions and tone of voice.

[0164] The "digital note-taking function" is a tool designed to facilitate knowledge sharing among users and support smoother communication that takes emotional states into consideration.

[0165] This invention is a business support system that improves the user's learning experience on a learning platform. This system mainly consists of three elements: a server, a user terminal, and the user, each working together to provide a consistent learning environment.

[0166] Server Role

[0167] The server functions as the central hub of the learning platform, centrally processing learning progress data and sentiment data. The server is equipped with data storage mechanisms, through which learning progress data and sentiment data are securely stored. Furthermore, information processing mechanisms generate personalized learning suggestions based on the received data. These generated learning suggestions are transmitted to the user's terminal using information transmission mechanisms, allowing the user to receive content optimized for their own situation.

[0168] User terminal operation

[0169] The terminal is a device that provides a user interface and displays learning content and feedback sent from the server. The terminal has a built-in emotion engine that analyzes the user's facial expressions and voice tone to generate emotion data in real time. This emotion data is sent to the server and used to optimize the learning experience.

[0170] User operation

[0171] Users can access the learning platform via their devices and select from a variety of courses based on the provided AI and DX technologies. Emotional states are reflected in the learning process, ensuring that content of optimal difficulty is provided and promoting efficient learning. Furthermore, knowledge sharing with other users is possible through the digital note-taking function, which uses an emotion engine to analyze the atmosphere of discussions and facilitate smooth communication.

[0172] Specific example

[0173] For example, when a user is learning a new language, the device may detect a lack of concentration through its camera. In this case, the server may suggest basic review materials or step-by-step instruction. As an example of a prompt, the AI ​​model could be fed the question, "What kind of support is best for the user in this difficult situation?" to suggest specific learning support measures.

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The device uses its camera and microphone to acquire facial and voice data during the user's learning process. This data is analyzed by an emotion engine to generate digital data about the user's current emotional state. The input is the user's visual and auditory information, and the output is the analyzed emotion data. This operation prepares the device to send that emotion data to the server in real time.

[0177] Step 2:

[0178] The device sends generated sentiment data and other learning progress data entered by the user during learning to the server. The input is the sentiment data and learning progress data analyzed on the device, and the output is the data packets sent to the server. The device maintains consistency in the learning experience by delivering this information quickly and accurately.

[0179] Step 3:

[0180] The server stores received emotion data and learning progress data in a data storage device and analyzes the data using an information processing device. The input is data transmitted from the terminal, and the output is the analysis results and learning suggestions based on them. Based on this information, the server identifies the user's current learning status and the support they need.

[0181] Step 4:

[0182] The server generates learning suggestions based on the analysis results and sends the corresponding learning content to the terminal using an information transmission method. The input is the learning suggestion generated on the server, and the output is the personalized learning content transferred to the terminal. This allows the server to provide optimal learning support in real time.

[0183] Step 5:

[0184] Users progress through their learning based on customized learning content displayed on their device. Input is the learning suggestions received by the device, and output is the user's corresponding learning activities and responses. The device continuously tracks sentiment data and learning progress, sending feedback back to the server. This process dynamically optimizes the learning experience.

[0185] (Application Example 2)

[0186] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0187] Conventional learning support systems often provided uniform learning content without considering the individual emotional state of learners. This meant they were unable to respond appropriately when learners experienced stress or confusion, potentially leading to decreased learning efficiency. Furthermore, there was a challenge in optimizing human-machine interaction in home-based educational support.

[0188] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0189] In this invention, the server includes analysis means for analyzing the learner's expressions and acquiring emotional data, adjustment means for dynamically adjusting learning content based on the acquired emotional data, and dialogue means for providing the adjusted learning content while interacting with the learner. This makes it possible to vary the content according to the individual emotional state of the learner and improve learning efficiency.

[0190] "Analysis methods for analyzing learners' expressions and acquiring emotional data" refers to technical means that analyze learners' facial expressions and tone of voice to determine their emotional state in real time.

[0191] "An adjustment means for dynamically adjusting learning content based on acquired emotional data" refers to a technical means that selects and provides content of appropriate difficulty and format according to the learner's state, based on emotional data obtained by an analysis means.

[0192] "Dialogue means for providing tailored learning content in an interactive manner with learners" refers to technical means that use robots or digital interfaces to continuously communicate with learners and flexibly present tailored content.

[0193] The system for implementing this invention aims to improve learning efficiency by analyzing the learner's emotions in real time and providing learning content tailored to their state. There are three main components to this system.

[0194] First, as an analysis method, the device equipped with the emotion engine monitors the learner's facial expressions and voice using a camera and microphone. This emotion engine uses software such as Google® Cloud Vision API or Microsoft® Azure® Emotion API to analyze the learner's emotional state based on the collected data.

[0195] Next, the server, which acts as the adjustment mechanism, uses the emotion data obtained by the analysis mechanism to dynamically adjust the difficulty level and format of the digital content. If the learner is confused, it will switch to easier content.

[0196] Finally, the interactive interface provided by the dialogue means presents the learner with tailored learning content and supports learning through continuous dialogue. This is handled by robots and digital devices, which supplement the content as needed in response to the learner's reactions, helping the learner deepen their understanding.

[0197] As a concrete example, consider a scenario where the system attempts to solve a math problem with a child. If the child faces a difficult problem and shows signs of confusion, the terminal's analysis mechanism reads the child's emotions, and the server's adjustment mechanism selects an easier problem appropriate to the situation. Then, through the dialogue mechanism, the robot presents the problem to the child in an interactive format and adds explanations to support the child's understanding.

[0198] Examples of prompts when using a generative AI model include:

[0199] "Assume you are a learning assistant robot. A child is showing signs of confusion during a math problem. Simplify the problem and offer a step-by-step explanation to help the child understand."

[0200] This prompt sets the AI ​​in the role of an educational assistant, providing guidance to help children learn.

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The device captures the learner's facial expressions and voice through its camera and microphone. The input is video and audio data, and the output generates raw data for analysis by the emotion engine. Specifically, the device collects data in real time and starts emotion analysis processing in the background.

[0204] Step 2:

[0205] The device's emotion engine analyzes video and audio data to generate learner emotion data. The input is the raw data generated in step 1, and the output is data indicating the learner's emotional state (e.g., stress, satisfaction, confusion). Specifically, an emotion recognition algorithm quickly analyzes the data and sends the emotional state to the server based on the results.

[0206] Step 3:

[0207] The server receives emotion data and adjusts the difficulty level of the learning content. The input is the emotion data from step 2, and the output is the adjusted learning content. Specifically, the server's adjustment algorithm selects content based on the emotional state and performs actions such as simplifying problems if the user is feeling stressed.

[0208] Step 4:

[0209] The device provides learners with pre-configured learning content in an interactive format. The input is the learning content from Step 3, and the output is the result of the interaction with the learner. Specifically, the device presents content in text and audio, and determines the next action based on the learner's immediate response. As the interaction continues, supplementary explanations are added as needed to deepen the learner's understanding.

[0210] Step 5:

[0211] The user engages with learning content, and the device records their progress. The input is data on the learner's learning behavior, and the output is recorded data on their learning progress. Specifically, the device records the learner's answers and other information, sends this data to a server, and uses it as basic data for the next learning plan.

[0212] Step 6:

[0213] The server collects and stores progress data, which is then used to generate learning content for subsequent sessions. The input is the progress data from step 5, and the output is updated learner profile data. Specifically, the server saves the data to a database, and the AI ​​agent performs analysis to use it for future learning suggestions.

[0214] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0215] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0220] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0221] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0222] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0223] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0224] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0225] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0227] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0228] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0229] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0230] This invention is a business support system aimed at improving the operational efficiency of companies by enabling users with specific learning objectives to organically combine knowledge of AI and DX. Below, we will describe the embodiments for carrying out the invention, while showing the roles of each entity in the operation of the system and providing specific examples.

[0231] Server Role

[0232] The server plays a central role in the learning platform, implementing diverse learning content. When a user connects, the server delivers appropriate learning content to the device and constantly tracks the user's learning progress. For example, when a user completes a basic AI course, the server recommends content on DX implementation case studies as the next step. The server also analyzes accumulated data and runs optimization algorithms to improve the performance of artificial intelligence agents, providing specific business advice and suggesting process automation.

[0233] User terminal operation

[0234] The user terminal displays content delivered from the server and provides a learning interface. As the user progresses through the learning process, the terminal quickly reflects their actions and displays feedback. When the user solves practice problems, the terminal displays an answer input form and sends the answer to the server. For example, in a case study exercise on business process improvement, the terminal sends the solution entered by the user to the server in real time and displays feedback.

[0235] User operation

[0236] Users log in to access the learning platform, select courses of interest, and begin learning. During the learning process, users solve specific exercises related to their own work and share information with colleagues using AI collaborative creation notes. For example, when a user works on a project to improve inventory management efficiency using AI, they share notes with other team members and discuss optimal solutions. In this way, users integrate knowledge into their work and generate ideas that directly contribute to their tasks.

[0237] As described above, the present invention provides a system that improves the overall operational efficiency and productivity of a company by having servers, terminals, and users each play a specific role and work together in cooperation.

[0238] The following describes the processing flow.

[0239] Step 1:

[0240] The server prepares the learning platform and accepts user registration information. This information is stored in a database, making it accessible to users.

[0241] Step 2:

[0242] Users log in to the learning platform using their devices and select courses of interest from the provided list of AI and DX courses.

[0243] Step 3:

[0244] The device displays the selected learning content, allowing the user to access the content and begin learning.

[0245] Step 4:

[0246] The server tracks the user's learning progress in real time and records the progress data in a data storage device.

[0247] Step 5:

[0248] Based on the learning progress, the server generates individually optimized learning suggestions and delivers them to the terminal.

[0249] Step 6:

[0250] Users work on practice problems displayed on their devices, enter their answers, and send them to the server.

[0251] Step 7:

[0252] The server analyzes the received answers and automatically records them in an AI collaborative creation notebook. This facilitates knowledge sharing.

[0253] Step 8:

[0254] Users utilize the AI ​​collaborative creation notebook to work with colleagues and discuss specific business improvement measures based on case studies.

[0255] Step 9:

[0256] The server uses the accumulated data to perform optimization processing to improve the performance of the artificial intelligence agent and makes suggestions for improving business efficiency.

[0257] Step 10:

[0258] Users receive advice from AI agents related to their work via their devices and apply it to their actual workflow.

[0259] (Example 1)

[0260] Next, we will describe Example 1. 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."

[0261] Conventional learning support systems lack personalized learning suggestions tailored to the user's learning progress, making efficient knowledge acquisition and practical application difficult. Furthermore, effectively utilizing accumulated data to optimize processes and drive business improvement is challenging. There is a need to increase opportunities for efficient information sharing and achieve more advanced business analysis and knowledge utilization.

[0262] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0263] In this invention, the server includes data storage means for storing learning progress information received from a user terminal, information processing means for generating learning recommendations suitable for the user based on the received learning progress information, and communication means for distributing the generated learning recommendations to the user terminal. This makes it possible to provide each user with a personalized learning plan. Furthermore, it enables the enhancement of artificial intelligence and optimization of processes based on the accumulated information, contributing to overall operational efficiency and productivity improvement.

[0264] A "user terminal" is a computing device used by users to access the learning platform and view and interact with its content.

[0265] "Learning progress information" refers to data that shows how far a user has progressed in their learning activities.

[0266] A "data storage means" is a system element that has the function of safely and efficiently storing received information.

[0267] "Information processing means" refers to computational means for analyzing received data and generating optimal learning suggestions for the user.

[0268] "Communication methods" refer to methods and technologies for transmitting data and suggestions between a server and a user's terminal.

[0269] An "artificial intelligence agent" is a program that is ready to use its accumulated knowledge to improve business processes.

[0270] "Optimization methods" refer to methods for making adjustments and improvements to streamline business processes.

[0271] A "generative AI model" is a program that extracts insights from large amounts of data and generates effective strategies and solutions based on new data.

[0272] "Data analysis methods" are techniques used to analyze collected information and derive useful insights and suggestions.

[0273] This business support system has a configuration in which servers, terminals, and users work together in coordination.

[0274] First, the server serves as the core of the business support platform, accepting connections from users. The server uses a database to store and manage learning progress information and selects customized learning content for each user. This process utilizes a generative AI model to analyze accumulated data and optimize the next learning step and its application to business operations. The server also includes data storage capabilities and ensures secure information management.

[0275] Next, the terminal functions as the user's learning interface, displaying content delivered from the server. The terminal efficiently processes user input and communicates with the server in real time. For example, when a user selects a learning task related to AI or DX and proceeds with the learning on the system, the terminal displays answer forms for practice problems and feedback screens.

[0276] Users log into this system and select learning courses relevant to their area of ​​work. Throughout the learning process, users utilize AI collaborative note-taking and share information with colleagues, deepening their knowledge directly applicable to their work. For example, when working on a project to improve inventory management efficiency, a user might use a prompt to the generative AI model—"Analyze sales data and propose the most effective sales strategy"—to plan a specific strategy. This prompt helps users understand market trends and formulate business strategies using the generative AI model.

[0277] In this way, the present invention is a system that leverages the roles of the server, terminal, and user, and organically combines diverse educational materials and information processing capabilities to support users in improving their work efficiency and productivity.

[0278] The flow of the specific process in Example 1 will be described with reference to FIG. 11.

[0279] Step 1:

[0280] The server receives login information from the user and verifies it against the database. It receives the user ID and password as input, and matches this with the existing registered data for authentication. If the authentication is successful, the server generates the user's learning dashboard and prepares it to be displayable as the next step. The output is a customized learning dashboard based on the user profile.

[0281] Step 2:

[0282] The user selects a learning course of interest from the learning dashboard. The input here is the user's selection operation. The terminal sends that selection to the server. The server retrieves relevant learning content (text, video, practice questions) from the database based on that selection and streams it to the terminal. As output, the selected learning content is displayed on the user's terminal.

[0283] Step 3:

[0284] The terminal proceeds with learning using the learning content displayed to the user. The input is the user's operation or answer. When the user enters an answer to a practice question, the terminal sends that answer to the server. The server analyzes the answer, makes a correct / incorrect determination, and then generates appropriate feedback. The output is the feedback information displayed on the user's terminal.

[0285] Step 4:

[0286] The server monitors the learning progress and saves the learning history in a database. The input is the progress information sent from the user. The server analyzes this data and generates proposals for the next learning content and advice on more effective learning methods. As output, the content and methods to be learned next are presented to the user's terminal.

[0287] Step 5:

[0288] The user creates a project based on the learned content using the AI collaborative creation note and shares it with colleagues. The input is the new information and comments described in the note. The terminal synchronizes the input information with the terminals of other users in real time. The output is the shared note content and feedback from colleagues on it.

[0289] Step 6:

[0290] Based on the learning data of all accumulated users, the server uses a generative AI model to perform analysis useful for business improvement. The input is the data collected from the entire system. The server utilizes the generative AI model to analyze the accumulated data and generate insights for improving business efficiency. The output is specific business improvement plans and new strategies using prompt sentences.

[0291] (Application Example 1)

[0292] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0293] Improving the efficiency and ensuring the safety of robot operations in the factory are important issues. In conventional robot operation education, on-site training is required, which involves costs and risks. Also, due to insufficient knowledge sharing among workers, it may not lead to actual business improvement. There is a need for a new educational method to solve such problems and achieve business efficiency and safety.

[0294] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0295] In this invention, the server includes data storage means, data processing means, data transmission means, optimization means, simulation means, and a machine learning algorithm. This enables the simulation of real-time work conditions in the factory, allowing workers to safely learn robot operation, and further enables the suggestion of optimal operating procedures using AI.

[0296] "Data storage means" refers to a device or program that has the function of saving learning progress data received from a user terminal.

[0297] "Data processing means" refers to a device or program that has the function of generating learning suggestions suitable for the user based on received learning progress data.

[0298] "Data transmission means" refers to a device or program that has the function of transmitting generated learning suggestions to a user terminal.

[0299] An "optimization means" is a device or program that has the function of evolving an artificial intelligence agent using accumulated data and improving work procedures.

[0300] A "simulation means" is a device or program that has the function of tracking user operations in real time and virtually reproducing the factory environment.

[0301] A "machine learning algorithm" is a computational method that analyzes the efficiency of a task based on accumulated data and constructs a learning model to derive the optimal work procedure.

[0302] In implementing this invention, a system is constructed in which a server, terminal, and user each fulfill their respective roles. The server manages learning progress data through data storage, processing, and transmission means. Specifically, it stores the user's learning log in a database and uses that information to execute an algorithm that personalizes learning content. Subsequently, it sends the results to the user terminal to provide real-time feedback. The database used here may be, for example, MySQL or PostgreSQL, and Unity or Unreal Engine may be used to perform case study simulations.

[0303] The terminal displays learning content based on data received from the server and reflects the user's actions. To conduct simulations in real time, a device equipped with a GPU corresponding to the processing power required by the terminal is used. This allows for the reproduction of complex operating environments such as factory simulations, enabling users to receive training safely.

[0304] Users operate the simulation via a terminal and learn as needed. The AI ​​algorithm analyzes the user's actions in real time and suggests efficient work procedures, which can be useful in actual work. For example, when working in a factory, the system can optimize the assembly procedure of parts in real time and immediately display how to correct any errors, thereby improving work efficiency.

[0305] Furthermore, the system uses a generative AI model to create prompt messages and provide situation-specific advice. An example of a prompt message would be, "Write a program that recreates the factory environment using 3D simulation, tracks worker actions in real time, and advises on the optimal robot operation procedure." In this way, the system is a powerful tool to effectively support users in improving their skills within their work.

[0306] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0307] Step 1:

[0308] The server receives learning progress data from the user terminal and stores the data in the database. In this step, data regarding the user's progress situation is input, and based on this information, basic data for creating the next learning proposal is output. Specifically, information such as the learning modules completed by the user and scores is recorded as a log.

[0309] Step 2:

[0310] The server analyzes the accumulated learning progress data and executes a machine learning algorithm to generate a personalized learning proposal. As input, the stored learning progress data is used, and the output is individually optimized learning content based on this. Specifically, the server analyzes the user's past learning history and selects the content to be tackled next.

[0311] Step 3:

[0312] The server sends the generated learning proposal to the user terminal. In this step, the optimized content stored in the server serves as the input, and the learning proposal is output in a form that can be displayed on the user terminal. Specifically, the server composes the learning proposal as a packet and sends it to the terminal via the network.

[0313] Step 4:

[0314] The terminal displays the learning proposal received from the server. The input is the learning proposal data from the server, and the output is the display of the content in a form that the user can visually confirm. Specifically, the content is displayed on the terminal via the UI, guiding the user to the next step.

[0315] Step 5:

[0316] Users interact with learning content on their devices and perform simulations. Inputs consist of learning content provided by the server and user operation data, while output includes the user's operations and learning results. Specifically, users perform work training in a simulation that mimics a factory environment and receive feedback on operational errors and areas for improvement.

[0317] Step 6:

[0318] The terminal tracks user actions in real time and sends user activity data to the server. The input is user action data, and the output is activity log data for analysis by the server. Specifically, the terminal's sensors read user actions and send that data to the server.

[0319] Step 7:

[0320] The server analyzes the received activity data, applies machine learning algorithms to generate optimized operating procedures, and sends them to the user as advice. The input is user activity data, and the output is optimized operating guidance. Specifically, it identifies areas where improvements are needed in specific operations and presents the user with methods for improvement.

[0321] An example of a prompt message is: "Write a program that recreates a factory environment using 3D simulation, tracks worker actions in real time, and advises on the optimal robot operation procedure."

[0322] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0323] This invention is a business support system related to AI and DX, which provides a more personalized learning experience for users by combining it with emotion recognition technology. The following describes specific embodiments for carrying out this invention.

[0324] Server Role

[0325] The server, as the central device of the learning platform, plays the role of centrally processing data from user terminals. Specifically, it receives and stores learning progress data and generates learning suggestions based on the received data. It also has a function to automatically adjust the difficulty level of learning content according to the user's emotional state. For example, if the server detects that the user's emotional data indicates stress, it will switch to easier learning suggestions to reduce the load on the server.

[0326] User terminal operation

[0327] The user terminal is a device that provides the user interface and displays content and feedback sent from the server. The terminal incorporates an emotion engine that analyzes the user's facial expressions and tone of voice to generate emotion data. This data is sent to the server in real time and influences the individual learning experience. For example, if signs of confusion are detected in the user's facial expressions while they are working on an exercise, the terminal sends this information to the server to prompt support.

[0328] User operation

[0329] Users can access the learning platform through their devices and select courses based on AI and DX technologies to proceed with their learning. Because the user's emotional state is reflected in the learning flow, content at an appropriate level is provided, improving learning efficiency. Furthermore, when sharing knowledge with colleagues using digital notes, the emotion engine analyzes the atmosphere of the discussion and offers suggestions to support smooth communication.

[0330] Thus, the system of the present invention supports the improvement of users' skills and work efficiency by analyzing users' emotions in real time and optimizing the learning experience based on those emotions.

[0331] The following describes the processing flow.

[0332] Step 1:

[0333] The user logs into the learning platform using their device. The device authenticates the user's access and displays a list of available courses.

[0334] Step 2:

[0335] The user selects an AI or DX course that interests them. The selection is sent from the device to the server, which then delivers the corresponding learning content to the device.

[0336] Step 3:

[0337] The server uses data storage to track learning progress and records the user's progress. The data is updated upon completion of each learning step.

[0338] Step 4:

[0339] The device uses a built-in emotion engine to analyze the user's facial expressions and voice, generating emotion data. For example, if the user shows a confused expression while working on a question, that data is collected.

[0340] Step 5:

[0341] The generated sentiment data is sent from the device to the server. The server uses this sentiment data to evaluate the user's current learning progress.

[0342] Step 6:

[0343] The server analyzes emotional data and learning progress data to generate personalized learning suggestions. For example, if a user has a high stress level, it will suggest easier practice problems.

[0344] Step 7:

[0345] The server sends the generated learning suggestions to the terminal for use. The terminal notifies the user of the new suggestions.

[0346] Step 8:

[0347] The user uses their device to continue learning based on suggestions from the server. The device again senses the progress of learning and changes in emotional state, and the processing cycle is repeated.

[0348] Step 9:

[0349] Using the digital note-taking function on their devices, users can record their learning progress and share information with colleagues. During this process, the emotion engine provides advice to support the smooth progress of discussions.

[0350] (Example 2)

[0351] Next, we will describe Example 2. 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".

[0352] Conventional learning support systems struggle to provide personalized learning suggestions in real time that take into account each user's emotional state. This leads to users experiencing stress and a decrease in learning efficiency. Furthermore, there are insufficient means to facilitate smooth communication by sharing emotional states.

[0353] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0354] In this invention, the server includes data storage means for storing learning progress data and emotional data received from the user terminal, information processing means for generating personalized learning suggestions based on the received learning progress data and emotional data, and information transmission means for transmitting the generated learning suggestions to the user terminal. This enables real-time automatic adjustment of learning content according to the user's emotional state, allowing for efficient skill improvement while reducing the learning burden.

[0355] A "data storage means" is a device that provides functions for safely and efficiently storing learning progress data and emotional data acquired from a user terminal.

[0356] An "information processing device" is a device that has a mechanism for analyzing learning progress data and sentiment data, and generating optimal learning suggestions based on that analysis.

[0357] "Information transmission means" refers to a device equipped with communication functions for quickly and accurately transmitting generated learning suggestions to the user's terminal.

[0358] An "emotion engine" is a technology that detects and digitizes a user's emotional state by analyzing their facial expressions and tone of voice.

[0359] The "digital note-taking function" is a tool designed to facilitate knowledge sharing among users and support smoother communication that takes emotional states into consideration.

[0360] This invention is a business support system that improves the user's learning experience on a learning platform. This system mainly consists of three elements: a server, a user terminal, and the user, each working together to provide a consistent learning environment.

[0361] Server Role

[0362] The server functions as the central hub of the learning platform, centrally processing learning progress data and sentiment data. The server is equipped with data storage mechanisms, through which learning progress data and sentiment data are securely stored. Furthermore, information processing mechanisms generate personalized learning suggestions based on the received data. These generated learning suggestions are transmitted to the user's terminal using information transmission mechanisms, allowing the user to receive content optimized for their own situation.

[0363] User terminal operation

[0364] The terminal is a device that provides a user interface and displays learning content and feedback sent from the server. The terminal has a built-in emotion engine that analyzes the user's facial expressions and voice tone to generate emotion data in real time. This emotion data is sent to the server and used to optimize the learning experience.

[0365] User operation

[0366] Users can access the learning platform via their devices and select from a variety of courses based on the provided AI and DX technologies. Emotional states are reflected in the learning process, ensuring that content of optimal difficulty is provided and promoting efficient learning. Furthermore, knowledge sharing with other users is possible through the digital note-taking function, which uses an emotion engine to analyze the atmosphere of discussions and facilitate smooth communication.

[0367] Specific example

[0368] For example, when a user is learning a new language, the device may detect a lack of concentration through its camera. In this case, the server may suggest basic review materials or step-by-step instruction. As an example of a prompt, the AI ​​model could be fed the question, "What kind of support is best for the user in this difficult situation?" to suggest specific learning support measures.

[0369] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0370] Step 1:

[0371] The device uses its camera and microphone to acquire facial and voice data during the user's learning process. This data is analyzed by an emotion engine to generate digital data about the user's current emotional state. The input is the user's visual and auditory information, and the output is the analyzed emotion data. This operation prepares the device to send that emotion data to the server in real time.

[0372] Step 2:

[0373] The device sends generated sentiment data and other learning progress data entered by the user during learning to the server. The input is the sentiment data and learning progress data analyzed on the device, and the output is the data packets sent to the server. The device maintains consistency in the learning experience by delivering this information quickly and accurately.

[0374] Step 3:

[0375] The server stores received emotion data and learning progress data in a data storage device and analyzes the data using an information processing device. The input is data transmitted from the terminal, and the output is the analysis results and learning suggestions based on them. Based on this information, the server identifies the user's current learning status and the support they need.

[0376] Step 4:

[0377] The server generates learning suggestions based on the analysis results and sends the corresponding learning content to the terminal using an information transmission method. The input is the learning suggestion generated on the server, and the output is the personalized learning content transferred to the terminal. This allows the server to provide optimal learning support in real time.

[0378] Step 5:

[0379] Users progress through their learning based on customized learning content displayed on their device. Input is the learning suggestions received by the device, and output is the user's corresponding learning activities and responses. The device continuously tracks sentiment data and learning progress, sending feedback back to the server. This process dynamically optimizes the learning experience.

[0380] (Application Example 2)

[0381] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0382] Conventional learning support systems often provided uniform learning content without considering the individual emotional state of learners. This meant they were unable to respond appropriately when learners experienced stress or confusion, potentially leading to decreased learning efficiency. Furthermore, there was a challenge in optimizing human-machine interaction in home-based educational support.

[0383] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0384] In this invention, the server includes analysis means for analyzing the learner's expressions and acquiring emotional data, adjustment means for dynamically adjusting learning content based on the acquired emotional data, and dialogue means for providing the adjusted learning content while interacting with the learner. This makes it possible to vary the content according to the individual emotional state of the learner and improve learning efficiency.

[0385] "Analysis methods for analyzing learners' expressions and acquiring emotional data" refers to technical means that analyze learners' facial expressions and tone of voice to determine their emotional state in real time.

[0386] "An adjustment means for dynamically adjusting learning content based on acquired emotional data" refers to a technical means that selects and provides content of appropriate difficulty and format according to the learner's state, based on emotional data obtained by an analysis means.

[0387] "Dialogue means for providing tailored learning content in an interactive manner with learners" refers to technical means that use robots or digital interfaces to continuously communicate with learners and flexibly present tailored content.

[0388] The system for implementing this invention aims to improve learning efficiency by analyzing the learner's emotions in real time and providing learning content tailored to their state. There are three main components to this system.

[0389] First, as an analysis method, the device equipped with the emotion engine monitors the learner's facial expressions and voice using a camera and microphone. This emotion engine uses software such as Google Cloud Vision API or Microsoft Azure Emotion API to analyze the learner's emotional state based on the collected data.

[0390] Next, the server, which acts as the adjustment mechanism, uses the emotion data obtained by the analysis mechanism to dynamically adjust the difficulty level and format of the digital content. If the learner is confused, it will switch to easier content.

[0391] Finally, the interactive interface provided by the dialogue means presents the learner with tailored learning content and supports learning through continuous dialogue. This is handled by robots and digital devices, which supplement the content as needed in response to the learner's reactions, helping the learner deepen their understanding.

[0392] As a concrete example, consider a scenario where the system attempts to solve a math problem with a child. If the child faces a difficult problem and shows signs of confusion, the terminal's analysis mechanism reads the child's emotions, and the server's adjustment mechanism selects an easier problem appropriate to the situation. Then, through the dialogue mechanism, the robot presents the problem to the child in an interactive format and adds explanations to support the child's understanding.

[0393] Examples of prompts when using a generative AI model include:

[0394] "Assume you are a learning assistant robot. A child is showing signs of confusion during a math problem. Simplify the problem and offer a step-by-step explanation to help the child understand."

[0395] This prompt sets the AI ​​in the role of an educational assistant, providing guidance to help children learn.

[0396] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0397] Step 1:

[0398] The device captures the learner's facial expressions and voice through its camera and microphone. The input is video and audio data, and the output generates raw data for analysis by the emotion engine. Specifically, the device collects data in real time and starts emotion analysis processing in the background.

[0399] Step 2:

[0400] The device's emotion engine analyzes video and audio data to generate learner emotion data. The input is the raw data generated in step 1, and the output is data indicating the learner's emotional state (e.g., stress, satisfaction, confusion). Specifically, an emotion recognition algorithm quickly analyzes the data and sends the emotional state to the server based on the results.

[0401] Step 3:

[0402] The server receives emotion data and adjusts the difficulty level of the learning content. The input is the emotion data from step 2, and the output is the adjusted learning content. Specifically, the server's adjustment algorithm selects content based on the emotional state and performs actions such as simplifying problems if the user is feeling stressed.

[0403] Step 4:

[0404] The device provides learners with pre-configured learning content in an interactive format. The input is the learning content from Step 3, and the output is the result of the interaction with the learner. Specifically, the device presents content in text and audio, and determines the next action based on the learner's immediate response. As the interaction continues, supplementary explanations are added as needed to deepen the learner's understanding.

[0405] Step 5:

[0406] The user engages with learning content, and the device records their progress. The input is data on the learner's learning behavior, and the output is recorded data on their learning progress. Specifically, the device records the learner's answers and other information, sends this data to a server, and uses it as basic data for the next learning plan.

[0407] Step 6:

[0408] The server collects and stores progress data, which is then used to generate learning content for subsequent sessions. The input is the progress data from step 5, and the output is updated learner profile data. Specifically, the server saves the data to a database, and the AI ​​agent performs analysis to use it for future learning suggestions.

[0409] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0410] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0411] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0412] [Third Embodiment]

[0413] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0414] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0415] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0416] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0417] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0418] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0419] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0420] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0421] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0422] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0423] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0424] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0425] This invention is a business support system aimed at improving the operational efficiency of companies by enabling users with specific learning objectives to organically combine knowledge of AI and DX. Below, we will describe the embodiments for carrying out the invention, while showing the roles of each entity in the operation of the system and providing specific examples.

[0426] Server Role

[0427] The server plays a central role in the learning platform, implementing diverse learning content. When a user connects, the server delivers appropriate learning content to the device and constantly tracks the user's learning progress. For example, when a user completes a basic AI course, the server recommends content on DX implementation case studies as the next step. The server also analyzes accumulated data and runs optimization algorithms to improve the performance of artificial intelligence agents, providing specific business advice and suggesting process automation.

[0428] User terminal operation

[0429] The user terminal displays content delivered from the server and provides a learning interface. As the user progresses through the learning process, the terminal quickly reflects their actions and displays feedback. When the user solves practice problems, the terminal displays an answer input form and sends the answer to the server. For example, in a case study exercise on business process improvement, the terminal sends the solution entered by the user to the server in real time and displays feedback.

[0430] User operation

[0431] Users log in to access the learning platform, select courses of interest, and begin learning. During the learning process, users solve specific exercises related to their own work and share information with colleagues using AI collaborative creation notes. For example, when a user works on a project to improve inventory management efficiency using AI, they share notes with other team members and discuss optimal solutions. In this way, users integrate knowledge into their work and generate ideas that directly contribute to their tasks.

[0432] As described above, the present invention provides a system that improves the overall operational efficiency and productivity of a company by having servers, terminals, and users each play a specific role and work together in cooperation.

[0433] The following describes the processing flow.

[0434] Step 1:

[0435] The server prepares the learning platform and accepts user registration information. This information is stored in a database, making it accessible to users.

[0436] Step 2:

[0437] Users log in to the learning platform using their devices and select courses of interest from the provided list of AI and DX courses.

[0438] Step 3:

[0439] The device displays the selected learning content, allowing the user to access the content and begin learning.

[0440] Step 4:

[0441] The server tracks the user's learning progress in real time and records the progress data in a data storage device.

[0442] Step 5:

[0443] Based on the learning progress, the server generates individually optimized learning suggestions and delivers them to the terminal.

[0444] Step 6:

[0445] Users work on practice problems displayed on their devices, enter their answers, and send them to the server.

[0446] Step 7:

[0447] The server analyzes the received answers and automatically records them in an AI collaborative creation notebook. This facilitates knowledge sharing.

[0448] Step 8:

[0449] Users utilize the AI ​​collaborative creation notebook to work with colleagues and discuss specific business improvement measures based on case studies.

[0450] Step 9:

[0451] The server uses the accumulated data to perform optimization processing to improve the performance of the artificial intelligence agent and makes suggestions for improving business efficiency.

[0452] Step 10:

[0453] Users receive advice from AI agents related to their work via their devices and apply it to their actual workflow.

[0454] (Example 1)

[0455] Next, we will describe Example 1. 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."

[0456] Conventional learning support systems lack personalized learning suggestions tailored to the user's learning progress, making efficient knowledge acquisition and practical application difficult. Furthermore, effectively utilizing accumulated data to optimize processes and drive business improvement is challenging. There is a need to increase opportunities for efficient information sharing and achieve more advanced business analysis and knowledge utilization.

[0457] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0458] In this invention, the server includes data storage means for storing learning progress information received from a user terminal, information processing means for generating learning recommendations suitable for the user based on the received learning progress information, and communication means for distributing the generated learning recommendations to the user terminal. This makes it possible to provide each user with a personalized learning plan. Furthermore, it enables the enhancement of artificial intelligence and optimization of processes based on the accumulated information, contributing to overall operational efficiency and productivity improvement.

[0459] A "user terminal" is a computing device used by users to access the learning platform and view and interact with its content.

[0460] "Learning progress information" refers to data that shows how far a user has progressed in their learning activities.

[0461] A "data storage means" is a system element that has the function of safely and efficiently storing received information.

[0462] "Information processing means" refers to computational means for analyzing received data and generating optimal learning suggestions for the user.

[0463] "Communication methods" refer to methods and technologies for transmitting data and suggestions between a server and a user's terminal.

[0464] An "artificial intelligence agent" is a program that is ready to use its accumulated knowledge to improve business processes.

[0465] "Optimization methods" refer to methods for making adjustments and improvements to streamline business processes.

[0466] A "generative AI model" is a program that extracts insights from large amounts of data and generates effective strategies and solutions based on new data.

[0467] "Data analysis methods" are techniques used to analyze collected information and derive useful insights and suggestions.

[0468] This business support system has a configuration in which servers, terminals, and users work together in coordination.

[0469] First, the server serves as the core of the business support platform, accepting connections from users. The server uses a database to store and manage learning progress information and selects customized learning content for each user. This process utilizes a generative AI model to analyze accumulated data and optimize the next learning step and its application to business operations. The server also includes data storage capabilities and ensures secure information management.

[0470] Next, the terminal functions as the user's learning interface, displaying content delivered from the server. The terminal efficiently processes user input and communicates with the server in real time. For example, when a user selects a learning task related to AI or DX and proceeds with the learning on the system, the terminal displays answer forms for practice problems and feedback screens.

[0471] Users log into this system and select learning courses relevant to their area of ​​work. Throughout the learning process, users utilize AI collaborative note-taking and share information with colleagues, deepening their knowledge directly applicable to their work. For example, when working on a project to improve inventory management efficiency, a user might use a prompt to the generative AI model—"Analyze sales data and propose the most effective sales strategy"—to plan a specific strategy. This prompt helps users understand market trends and formulate business strategies using the generative AI model.

[0472] In this way, the present invention is a system that leverages the roles of the server, terminal, and user, and organically combines diverse educational materials and information processing capabilities to support users in improving their work efficiency and productivity.

[0473] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0474] Step 1:

[0475] The server receives login information from the user and compares it with the database. It receives the user's ID and password as input and performs authentication by matching them with existing registration data. If authentication is successful, the server generates the user's learning dashboard and prepares it for display as the next step. The output is a customized learning dashboard based on the user profile.

[0476] Step 2:

[0477] The user selects a learning course of interest from the learning dashboard. The input here is the user's selection. The device sends this selection to the server. Based on the selection, the server retrieves relevant learning content (text, videos, exercises) from its database and streams it to the device. As output, the selected learning content is displayed on the user's device.

[0478] Step 3:

[0479] The device allows the user to progress through the learning process using the displayed learning content. Input consists of the user's actions and answers. When the user enters an answer to an exercise problem, the device sends the answer to the server. The server analyzes the answer, determines whether it is correct or incorrect, and generates appropriate feedback. Output is the feedback information displayed on the user's device.

[0480] Step 4:

[0481] The server monitors learning progress and stores learning history in a database. The input is progress information submitted by the user. The server analyzes this data to generate suggestions for the next learning content and advice on more effective learning methods. As output, the user's device displays the next content and methods to be learned.

[0482] Step 5:

[0483] Users use the AI ​​collaborative creation notebook to create projects based on what they've learned and share them with colleagues. Input consists of new information and comments added to the notebook. The device synchronizes the entered information with other users' devices in real time. Output consists of the shared notebook content and feedback from colleagues.

[0484] Step 6:

[0485] The server uses a generative AI model to perform analyses useful for business improvement, based on the accumulated learning data of all users. The input is data collected from the entire system. The server utilizes the generative AI model to analyze the accumulated data and generate insights for improving business efficiency. The output consists of specific business improvement proposals and new strategies using prompt messages.

[0486] (Application Example 1)

[0487] Next, we will explain Application Example 1. In the following explanation, 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."

[0488] Improving the efficiency and ensuring the safety of robot operations within factories are critical challenges. Traditional robot operation training requires on-the-job training, which is costly and risky. Furthermore, insufficient knowledge sharing among workers can prevent the training from leading to actual improvements in work processes. A new training method is needed to address these challenges and achieve both operational efficiency and safety.

[0489] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0490] In this invention, the server includes data storage means, data processing means, data transmission means, optimization means, simulation means, and a machine learning algorithm. This enables the simulation of real-time work conditions in the factory, allowing workers to safely learn robot operation, and further enables the suggestion of optimal operating procedures using AI.

[0491] "Data storage means" refers to a device or program that has the function of saving learning progress data received from a user terminal.

[0492] "Data processing means" refers to a device or program that has the function of generating learning suggestions suitable for the user based on received learning progress data.

[0493] "Data transmission means" refers to a device or program that has the function of transmitting generated learning suggestions to a user terminal.

[0494] An "optimization means" is a device or program that has the function of evolving an artificial intelligence agent using accumulated data and improving work procedures.

[0495] A "simulation means" is a device or program that has the function of tracking user operations in real time and virtually reproducing the factory environment.

[0496] A "machine learning algorithm" is a computational method that analyzes the efficiency of a task based on accumulated data and constructs a learning model to derive the optimal work procedure.

[0497] In implementing this invention, a system is constructed in which a server, terminal, and user each fulfill their respective roles. The server manages learning progress data through data storage, processing, and transmission means. Specifically, it stores the user's learning log in a database and uses that information to execute an algorithm that personalizes learning content. Subsequently, it sends the results to the user terminal to provide real-time feedback. The database used here may be, for example, MySQL or PostgreSQL, and Unity or Unreal Engine may be used to perform case study simulations.

[0498] The terminal displays learning content based on data received from the server and reflects the user's actions. To conduct simulations in real time, a device equipped with a GPU corresponding to the processing power required by the terminal is used. This allows for the reproduction of complex operating environments such as factory simulations, enabling users to receive training safely.

[0499] Users operate the simulation via a terminal and learn as needed. The AI ​​algorithm analyzes the user's actions in real time and suggests efficient work procedures, which can be useful in actual work. For example, when working in a factory, the system can optimize the assembly procedure of parts in real time and immediately display how to correct any errors, thereby improving work efficiency.

[0500] Furthermore, the system uses a generative AI model to create prompt messages and provide situation-specific advice. An example of a prompt message would be, "Write a program that recreates the factory environment using 3D simulation, tracks worker actions in real time, and advises on the optimal robot operation procedure." In this way, the system is a powerful tool to effectively support users in improving their skills within their work.

[0501] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0502] Step 1:

[0503] The server receives learning progress data from the user's terminal and saves this data to a database. In this step, data regarding the user's progress is input, and basic data is output to create the next learning suggestion based on that information. Specifically, information such as the learning modules the user has completed and their scores are recorded as logs.

[0504] Step 2:

[0505] The server analyzes accumulated learning progress data and executes machine learning algorithms to generate personalized learning suggestions. The input is stored learning progress data, and the output is individually optimized learning content based on that data. Specifically, it analyzes the user's past learning history and selects the next content they should work on.

[0506] Step 3:

[0507] The server sends the generated learning suggestions to the user's terminal. In this step, optimized content stored on the server serves as input, and the learning suggestions are output in a format displayed on the user's terminal. Specifically, the server organizes the learning suggestions into packets and sends them to the terminal via the network.

[0508] Step 4:

[0509] The device displays learning suggestions received from the server. The input is learning suggestion data from the server, and the output is content displayed in a form that the user can visually confirm. Specifically, the content is displayed on the device via a UI, guiding the user to the next step.

[0510] Step 5:

[0511] Users interact with learning content on their devices and perform simulations. Inputs consist of learning content provided by the server and user operation data, while output includes the user's operations and learning results. Specifically, users perform work training in a simulation that mimics a factory environment and receive feedback on operational errors and areas for improvement.

[0512] Step 6:

[0513] The terminal tracks user actions in real time and sends user activity data to the server. The input is user action data, and the output is activity log data for analysis by the server. Specifically, the terminal's sensors read user actions and send that data to the server.

[0514] Step 7:

[0515] The server analyzes the received activity data, applies machine learning algorithms to generate optimized operating procedures, and sends them to the user as advice. The input is user activity data, and the output is optimized operating guidance. Specifically, it identifies areas where improvements are needed in specific operations and presents the user with methods for improvement.

[0516] An example of a prompt message is: "Write a program that recreates a factory environment using 3D simulation, tracks worker actions in real time, and advises on the optimal robot operation procedure."

[0517] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0518] This invention is a business support system related to AI and DX, which provides a more personalized learning experience for users by combining it with emotion recognition technology. The following describes specific embodiments for carrying out this invention.

[0519] Server Role

[0520] The server, as the central device of the learning platform, plays the role of centrally processing data from user terminals. Specifically, it receives and stores learning progress data and generates learning suggestions based on the received data. It also has a function to automatically adjust the difficulty level of learning content according to the user's emotional state. For example, if the server detects that the user's emotional data indicates stress, it will switch to easier learning suggestions to reduce the load on the server.

[0521] User terminal operation

[0522] The user terminal is a device that provides the user interface and displays content and feedback sent from the server. The terminal incorporates an emotion engine that analyzes the user's facial expressions and tone of voice to generate emotion data. This data is sent to the server in real time and influences the individual learning experience. For example, if signs of confusion are detected in the user's facial expressions while they are working on an exercise, the terminal sends this information to the server to prompt support.

[0523] User operation

[0524] Users can access the learning platform through their devices and select courses based on AI and DX technologies to proceed with their learning. Because the user's emotional state is reflected in the learning flow, content at an appropriate level is provided, improving learning efficiency. Furthermore, when sharing knowledge with colleagues using digital notes, the emotion engine analyzes the atmosphere of the discussion and offers suggestions to support smooth communication.

[0525] Thus, the system of the present invention supports the improvement of users' skills and work efficiency by analyzing users' emotions in real time and optimizing the learning experience based on those emotions.

[0526] The following describes the processing flow.

[0527] Step 1:

[0528] The user logs into the learning platform using their device. The device authenticates the user's access and displays a list of available courses.

[0529] Step 2:

[0530] The user selects an AI or DX course that interests them. The selection is sent from the device to the server, which then delivers the corresponding learning content to the device.

[0531] Step 3:

[0532] The server uses data storage to track learning progress and records the user's progress. The data is updated upon completion of each learning step.

[0533] Step 4:

[0534] The device uses a built-in emotion engine to analyze the user's facial expressions and voice, generating emotion data. For example, if the user shows a confused expression while working on a question, that data is collected.

[0535] Step 5:

[0536] The generated sentiment data is sent from the device to the server. The server uses this sentiment data to evaluate the user's current learning progress.

[0537] Step 6:

[0538] The server analyzes emotional data and learning progress data to generate personalized learning suggestions. For example, if a user has a high stress level, it will suggest easier practice problems.

[0539] Step 7:

[0540] The server sends the generated learning suggestions to the terminal for use. The terminal notifies the user of the new suggestions.

[0541] Step 8:

[0542] The user uses their device to continue learning based on suggestions from the server. The device again senses the progress of learning and changes in emotional state, and the processing cycle is repeated.

[0543] Step 9:

[0544] Using the digital note-taking function on their devices, users can record their learning progress and share information with colleagues. During this process, the emotion engine provides advice to support the smooth progress of discussions.

[0545] (Example 2)

[0546] Next, we will describe Example 2. 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."

[0547] Conventional learning support systems struggle to provide personalized learning suggestions in real time that take into account each user's emotional state. This leads to users experiencing stress and a decrease in learning efficiency. Furthermore, there are insufficient means to facilitate smooth communication by sharing emotional states.

[0548] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0549] In this invention, the server includes data storage means for storing learning progress data and emotional data received from the user terminal, information processing means for generating personalized learning suggestions based on the received learning progress data and emotional data, and information transmission means for transmitting the generated learning suggestions to the user terminal. This enables real-time automatic adjustment of learning content according to the user's emotional state, allowing for efficient skill improvement while reducing the learning burden.

[0550] A "data storage means" is a device that provides functions for safely and efficiently storing learning progress data and emotional data acquired from a user terminal.

[0551] An "information processing device" is a device that has a mechanism for analyzing learning progress data and sentiment data, and generating optimal learning suggestions based on that analysis.

[0552] "Information transmission means" refers to a device equipped with communication functions for quickly and accurately transmitting generated learning suggestions to the user's terminal.

[0553] An "emotion engine" is a technology that detects and digitizes a user's emotional state by analyzing their facial expressions and tone of voice.

[0554] The "digital note-taking function" is a tool designed to facilitate knowledge sharing among users and support smoother communication that takes emotional states into consideration.

[0555] This invention is a business support system that improves the user's learning experience on a learning platform. This system mainly consists of three elements: a server, a user terminal, and the user, each working together to provide a consistent learning environment.

[0556] Server Role

[0557] The server functions as the central hub of the learning platform, centrally processing learning progress data and sentiment data. The server is equipped with data storage mechanisms, through which learning progress data and sentiment data are securely stored. Furthermore, information processing mechanisms generate personalized learning suggestions based on the received data. These generated learning suggestions are transmitted to the user's terminal using information transmission mechanisms, allowing the user to receive content optimized for their own situation.

[0558] User terminal operation

[0559] The terminal is a device that provides a user interface and displays learning content and feedback sent from the server. The terminal has a built-in emotion engine that analyzes the user's facial expressions and voice tone to generate emotion data in real time. This emotion data is sent to the server and used to optimize the learning experience.

[0560] User operation

[0561] Users can access the learning platform via their devices and select from a variety of courses based on the provided AI and DX technologies. Emotional states are reflected in the learning process, ensuring that content of optimal difficulty is provided and promoting efficient learning. Furthermore, knowledge sharing with other users is possible through the digital note-taking function, which uses an emotion engine to analyze the atmosphere of discussions and facilitate smooth communication.

[0562] Specific example

[0563] For example, when a user is learning a new language, the device may detect a lack of concentration through its camera. In this case, the server may suggest basic review materials or step-by-step instruction. As an example of a prompt, the AI ​​model could be fed the question, "What kind of support is best for the user in this difficult situation?" to suggest specific learning support measures.

[0564] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0565] Step 1:

[0566] The device uses its camera and microphone to acquire facial and voice data during the user's learning process. This data is analyzed by an emotion engine to generate digital data about the user's current emotional state. The input is the user's visual and auditory information, and the output is the analyzed emotion data. This operation prepares the device to send that emotion data to the server in real time.

[0567] Step 2:

[0568] The device sends generated sentiment data and other learning progress data entered by the user during learning to the server. The input is the sentiment data and learning progress data analyzed on the device, and the output is the data packets sent to the server. The device maintains consistency in the learning experience by delivering this information quickly and accurately.

[0569] Step 3:

[0570] The server stores received emotion data and learning progress data in a data storage device and analyzes the data using an information processing device. The input is data transmitted from the terminal, and the output is the analysis results and learning suggestions based on them. Based on this information, the server identifies the user's current learning status and the support they need.

[0571] Step 4:

[0572] The server generates learning suggestions based on the analysis results and sends the corresponding learning content to the terminal using an information transmission method. The input is the learning suggestion generated on the server, and the output is the personalized learning content transferred to the terminal. This allows the server to provide optimal learning support in real time.

[0573] Step 5:

[0574] Users progress through their learning based on customized learning content displayed on their device. Input is the learning suggestions received by the device, and output is the user's corresponding learning activities and responses. The device continuously tracks sentiment data and learning progress, sending feedback back to the server. This process dynamically optimizes the learning experience.

[0575] (Application Example 2)

[0576] Next, we will explain application example 2. In the following explanation, 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."

[0577] Conventional learning support systems often provided uniform learning content without considering the individual emotional state of learners. This meant they were unable to respond appropriately when learners experienced stress or confusion, potentially leading to decreased learning efficiency. Furthermore, there was a challenge in optimizing human-machine interaction in home-based educational support.

[0578] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0579] In this invention, the server includes analysis means for analyzing the learner's expressions and acquiring emotional data, adjustment means for dynamically adjusting learning content based on the acquired emotional data, and dialogue means for providing the adjusted learning content while interacting with the learner. This makes it possible to vary the content according to the individual emotional state of the learner and improve learning efficiency.

[0580] "Analysis methods for analyzing learners' expressions and acquiring emotional data" refers to technical means that analyze learners' facial expressions and tone of voice to determine their emotional state in real time.

[0581] "An adjustment means for dynamically adjusting learning content based on acquired emotional data" refers to a technical means that selects and provides content of appropriate difficulty and format according to the learner's state, based on emotional data obtained by an analysis means.

[0582] "Dialogue means for providing tailored learning content in an interactive manner with learners" refers to technical means that use robots or digital interfaces to continuously communicate with learners and flexibly present tailored content.

[0583] The system for implementing this invention aims to improve learning efficiency by analyzing the learner's emotions in real time and providing learning content tailored to their state. There are three main components to this system.

[0584] First, as an analysis method, the device equipped with the emotion engine monitors the learner's facial expressions and voice using a camera and microphone. This emotion engine uses software such as Google Cloud Vision API or Microsoft Azure Emotion API to analyze the learner's emotional state based on the collected data.

[0585] Next, the server, which acts as the adjustment mechanism, uses the emotion data obtained by the analysis mechanism to dynamically adjust the difficulty level and format of the digital content. If the learner is confused, it will switch to easier content.

[0586] Finally, the interactive interface provided by the dialogue means presents the learner with tailored learning content and supports learning through continuous dialogue. This is handled by robots and digital devices, which supplement the content as needed in response to the learner's reactions, helping the learner deepen their understanding.

[0587] As a concrete example, consider a scenario where the system attempts to solve a math problem with a child. If the child faces a difficult problem and shows signs of confusion, the terminal's analysis mechanism reads the child's emotions, and the server's adjustment mechanism selects an easier problem appropriate to the situation. Then, through the dialogue mechanism, the robot presents the problem to the child in an interactive format and adds explanations to support the child's understanding.

[0588] Examples of prompts when using a generative AI model include:

[0589] "Assume you are a learning assistant robot. A child is showing signs of confusion during a math problem. Simplify the problem and offer a step-by-step explanation to help the child understand."

[0590] This prompt sets the AI ​​in the role of an educational assistant, providing guidance to help children learn.

[0591] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0592] Step 1:

[0593] The device captures the learner's facial expressions and voice through its camera and microphone. The input is video and audio data, and the output generates raw data for analysis by the emotion engine. Specifically, the device collects data in real time and starts emotion analysis processing in the background.

[0594] Step 2:

[0595] The device's emotion engine analyzes video and audio data to generate learner emotion data. The input is the raw data generated in step 1, and the output is data indicating the learner's emotional state (e.g., stress, satisfaction, confusion). Specifically, an emotion recognition algorithm quickly analyzes the data and sends the emotional state to the server based on the results.

[0596] Step 3:

[0597] The server receives emotion data and adjusts the difficulty level of the learning content. The input is the emotion data from step 2, and the output is the adjusted learning content. Specifically, the server's adjustment algorithm selects content based on the emotional state and performs actions such as simplifying problems if the user is feeling stressed.

[0598] Step 4:

[0599] The device provides learners with pre-configured learning content in an interactive format. The input is the learning content from Step 3, and the output is the result of the interaction with the learner. Specifically, the device presents content in text and audio, and determines the next action based on the learner's immediate response. As the interaction continues, supplementary explanations are added as needed to deepen the learner's understanding.

[0600] Step 5:

[0601] The user engages with learning content, and the device records their progress. The input is data on the learner's learning behavior, and the output is recorded data on their learning progress. Specifically, the device records the learner's answers and other information, sends this data to a server, and uses it as basic data for the next learning plan.

[0602] Step 6:

[0603] The server collects and stores progress data, which is then used to generate learning content for subsequent sessions. The input is the progress data from step 5, and the output is updated learner profile data. Specifically, the server saves the data to a database, and the AI ​​agent performs analysis to use it for future learning suggestions.

[0604] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0605] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0606] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0607] [Fourth Embodiment]

[0608] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0609] As shown in Figure 7, the 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.

[0610] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0611] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0612] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0613] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0614] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0615] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0616] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0617] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0618] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0619] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0620] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0621] This invention is a business support system aimed at improving the operational efficiency of companies by enabling users with specific learning objectives to organically combine knowledge of AI and DX. Below, we will describe the embodiments for carrying out the invention, while showing the roles of each entity in the operation of the system and providing specific examples.

[0622] Server Role

[0623] The server plays a central role in the learning platform, implementing diverse learning content. When a user connects, the server delivers appropriate learning content to the device and constantly tracks the user's learning progress. For example, when a user completes a basic AI course, the server recommends content on DX implementation case studies as the next step. The server also analyzes accumulated data and runs optimization algorithms to improve the performance of artificial intelligence agents, providing specific business advice and suggesting process automation.

[0624] User terminal operation

[0625] The user terminal displays content delivered from the server and provides a learning interface. As the user progresses through the learning process, the terminal quickly reflects their actions and displays feedback. When the user solves practice problems, the terminal displays an answer input form and sends the answer to the server. For example, in a case study exercise on business process improvement, the terminal sends the solution entered by the user to the server in real time and displays feedback.

[0626] User operation

[0627] Users log in to access the learning platform, select courses of interest, and begin learning. During the learning process, users solve specific exercises related to their own work and share information with colleagues using AI collaborative creation notes. For example, when a user works on a project to improve inventory management efficiency using AI, they share notes with other team members and discuss optimal solutions. In this way, users integrate knowledge into their work and generate ideas that directly contribute to their tasks.

[0628] As described above, the present invention provides a system that improves the overall operational efficiency and productivity of a company by having servers, terminals, and users each play a specific role and work together in cooperation.

[0629] The following describes the processing flow.

[0630] Step 1:

[0631] The server prepares the learning platform and accepts user registration information. This information is stored in a database, making it accessible to users.

[0632] Step 2:

[0633] Users log in to the learning platform using their devices and select courses of interest from the provided list of AI and DX courses.

[0634] Step 3:

[0635] The device displays the selected learning content, allowing the user to access the content and begin learning.

[0636] Step 4:

[0637] The server tracks the user's learning progress in real time and records the progress data in a data storage device.

[0638] Step 5:

[0639] Based on the learning progress, the server generates individually optimized learning suggestions and delivers them to the terminal.

[0640] Step 6:

[0641] Users work on practice problems displayed on their devices, enter their answers, and send them to the server.

[0642] Step 7:

[0643] The server analyzes the received answers and automatically records them in an AI collaborative creation notebook. This facilitates knowledge sharing.

[0644] Step 8:

[0645] Users utilize the AI ​​collaborative creation notebook to work with colleagues and discuss specific business improvement measures based on case studies.

[0646] Step 9:

[0647] The server uses the accumulated data to perform optimization processing to improve the performance of the artificial intelligence agent and makes suggestions for improving business efficiency.

[0648] Step 10:

[0649] Users receive advice from AI agents related to their work via their devices and apply it to their actual workflow.

[0650] (Example 1)

[0651] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0652] Conventional learning support systems lack personalized learning suggestions tailored to the user's learning progress, making efficient knowledge acquisition and practical application difficult. Furthermore, effectively utilizing accumulated data to optimize processes and drive business improvement is challenging. There is a need to increase opportunities for efficient information sharing and achieve more advanced business analysis and knowledge utilization.

[0653] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0654] In this invention, the server includes data storage means for storing learning progress information received from a user terminal, information processing means for generating learning recommendations suitable for the user based on the received learning progress information, and communication means for distributing the generated learning recommendations to the user terminal. This makes it possible to provide each user with a personalized learning plan. Furthermore, it enables the enhancement of artificial intelligence and optimization of processes based on the accumulated information, contributing to overall operational efficiency and productivity improvement.

[0655] A "user terminal" is a computing device used by users to access the learning platform and view and interact with its content.

[0656] "Learning progress information" refers to data that shows how far a user has progressed in their learning activities.

[0657] A "data storage means" is a system element that has the function of safely and efficiently storing received information.

[0658] "Information processing means" refers to computational means for analyzing received data and generating optimal learning suggestions for the user.

[0659] "Communication methods" refer to methods and technologies for transmitting data and suggestions between a server and a user's terminal.

[0660] An "artificial intelligence agent" is a program that is ready to use its accumulated knowledge to improve business processes.

[0661] "Optimization methods" refer to methods for making adjustments and improvements to streamline business processes.

[0662] A "generative AI model" is a program that extracts insights from large amounts of data and generates effective strategies and solutions based on new data.

[0663] "Data analysis methods" are techniques used to analyze collected information and derive useful insights and suggestions.

[0664] This business support system has a configuration in which servers, terminals, and users work together in coordination.

[0665] First, the server serves as the core of the business support platform, accepting connections from users. The server uses a database to store and manage learning progress information and selects customized learning content for each user. This process utilizes a generative AI model to analyze accumulated data and optimize the next learning step and its application to business operations. The server also includes data storage capabilities and ensures secure information management.

[0666] Next, the terminal functions as the user's learning interface, displaying content delivered from the server. The terminal efficiently processes user input and communicates with the server in real time. For example, when a user selects a learning task related to AI or DX and proceeds with the learning on the system, the terminal displays answer forms for practice problems and feedback screens.

[0667] Users log into this system and select learning courses relevant to their area of ​​work. Throughout the learning process, users utilize AI collaborative note-taking and share information with colleagues, deepening their knowledge directly applicable to their work. For example, when working on a project to improve inventory management efficiency, a user might use a prompt to the generative AI model—"Analyze sales data and propose the most effective sales strategy"—to plan a specific strategy. This prompt helps users understand market trends and formulate business strategies using the generative AI model.

[0668] In this way, the present invention is a system that leverages the roles of the server, terminal, and user, and organically combines diverse educational materials and information processing capabilities to support users in improving their work efficiency and productivity.

[0669] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0670] Step 1:

[0671] The server receives login information from the user and compares it with the database. It receives the user's ID and password as input and performs authentication by matching them with existing registration data. If authentication is successful, the server generates the user's learning dashboard and prepares it for display as the next step. The output is a customized learning dashboard based on the user profile.

[0672] Step 2:

[0673] The user selects a learning course of interest from the learning dashboard. The input here is the user's selection. The device sends this selection to the server. Based on the selection, the server retrieves relevant learning content (text, videos, exercises) from its database and streams it to the device. As output, the selected learning content is displayed on the user's device.

[0674] Step 3:

[0675] The device allows the user to progress through the learning process using the displayed learning content. Input consists of the user's actions and answers. When the user enters an answer to an exercise problem, the device sends the answer to the server. The server analyzes the answer, determines whether it is correct or incorrect, and generates appropriate feedback. Output is the feedback information displayed on the user's device.

[0676] Step 4:

[0677] The server monitors learning progress and stores learning history in a database. The input is progress information submitted by the user. The server analyzes this data to generate suggestions for the next learning content and advice on more effective learning methods. As output, the user's device displays the next content and methods to be learned.

[0678] Step 5:

[0679] Users use the AI ​​collaborative creation notebook to create projects based on what they've learned and share them with colleagues. Input consists of new information and comments added to the notebook. The device synchronizes the entered information with other users' devices in real time. Output consists of the shared notebook content and feedback from colleagues.

[0680] Step 6:

[0681] The server uses a generative AI model to perform analyses useful for business improvement, based on the accumulated learning data of all users. The input is data collected from the entire system. The server utilizes the generative AI model to analyze the accumulated data and generate insights for improving business efficiency. The output consists of specific business improvement proposals and new strategies using prompt messages.

[0682] (Application Example 1)

[0683] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0684] Improving the efficiency and ensuring the safety of robot operations within factories are critical challenges. Traditional robot operation training requires on-the-job training, which is costly and risky. Furthermore, insufficient knowledge sharing among workers can prevent the training from leading to actual improvements in work processes. A new training method is needed to address these challenges and achieve both operational efficiency and safety.

[0685] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0686] In this invention, the server includes data storage means, data processing means, data transmission means, optimization means, simulation means, and a machine learning algorithm. This enables the simulation of real-time work conditions in the factory, allowing workers to safely learn robot operation, and further enables the suggestion of optimal operating procedures using AI.

[0687] "Data storage means" refers to a device or program that has the function of saving learning progress data received from a user terminal.

[0688] "Data processing means" refers to a device or program that has the function of generating learning suggestions suitable for the user based on received learning progress data.

[0689] "Data transmission means" refers to a device or program that has the function of transmitting generated learning suggestions to a user terminal.

[0690] An "optimization means" is a device or program that has the function of evolving an artificial intelligence agent using accumulated data and improving work procedures.

[0691] A "simulation means" is a device or program that has the function of tracking user operations in real time and virtually reproducing the factory environment.

[0692] A "machine learning algorithm" is a computational method that analyzes the efficiency of a task based on accumulated data and constructs a learning model to derive the optimal work procedure.

[0693] In implementing this invention, a system is constructed in which a server, terminal, and user each fulfill their respective roles. The server manages learning progress data through data storage, processing, and transmission means. Specifically, it stores the user's learning log in a database and uses that information to execute an algorithm that personalizes learning content. Subsequently, it sends the results to the user terminal to provide real-time feedback. The database used here may be, for example, MySQL or PostgreSQL, and Unity or Unreal Engine may be used to perform case study simulations.

[0694] The terminal displays learning content based on data received from the server and reflects the user's actions. To conduct simulations in real time, a device equipped with a GPU corresponding to the processing power required by the terminal is used. This allows for the reproduction of complex operating environments such as factory simulations, enabling users to receive training safely.

[0695] Users operate the simulation via a terminal and learn as needed. The AI ​​algorithm analyzes the user's actions in real time and suggests efficient work procedures, which can be useful in actual work. For example, when working in a factory, the system can optimize the assembly procedure of parts in real time and immediately display how to correct any errors, thereby improving work efficiency.

[0696] Furthermore, the system uses a generative AI model to create prompt messages and provide situation-specific advice. An example of a prompt message would be, "Write a program that recreates the factory environment using 3D simulation, tracks worker actions in real time, and advises on the optimal robot operation procedure." In this way, the system is a powerful tool to effectively support users in improving their skills within their work.

[0697] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0698] Step 1:

[0699] The server receives learning progress data from the user's terminal and saves this data to a database. In this step, data regarding the user's progress is input, and basic data is output to create the next learning suggestion based on that information. Specifically, information such as the learning modules the user has completed and their scores are recorded as logs.

[0700] Step 2:

[0701] The server analyzes accumulated learning progress data and executes machine learning algorithms to generate personalized learning suggestions. The input is stored learning progress data, and the output is individually optimized learning content based on that data. Specifically, it analyzes the user's past learning history and selects the next content they should work on.

[0702] Step 3:

[0703] The server sends the generated learning suggestions to the user's terminal. In this step, optimized content stored on the server serves as input, and the learning suggestions are output in a format displayed on the user's terminal. Specifically, the server organizes the learning suggestions into packets and sends them to the terminal via the network.

[0704] Step 4:

[0705] The device displays learning suggestions received from the server. The input is learning suggestion data from the server, and the output is content displayed in a form that the user can visually confirm. Specifically, the content is displayed on the device via a UI, guiding the user to the next step.

[0706] Step 5:

[0707] Users interact with learning content on their devices and perform simulations. Inputs consist of learning content provided by the server and user operation data, while output includes the user's operations and learning results. Specifically, users perform work training in a simulation that mimics a factory environment and receive feedback on operational errors and areas for improvement.

[0708] Step 6:

[0709] The terminal tracks user actions in real time and sends user activity data to the server. The input is user action data, and the output is activity log data for analysis by the server. Specifically, the terminal's sensors read user actions and send that data to the server.

[0710] Step 7:

[0711] The server analyzes the received activity data, applies machine learning algorithms to generate optimized operating procedures, and sends them to the user as advice. The input is user activity data, and the output is optimized operating guidance. Specifically, it identifies areas where improvements are needed in specific operations and presents the user with methods for improvement.

[0712] An example of a prompt message is: "Write a program that recreates a factory environment using 3D simulation, tracks worker actions in real time, and advises on the optimal robot operation procedure."

[0713] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0714] This invention is a business support system related to AI and DX, which provides a more personalized learning experience for users by combining it with emotion recognition technology. The following describes specific embodiments for carrying out this invention.

[0715] Server Role

[0716] The server, as the central device of the learning platform, plays the role of centrally processing data from user terminals. Specifically, it receives and stores learning progress data and generates learning suggestions based on the received data. It also has a function to automatically adjust the difficulty level of learning content according to the user's emotional state. For example, if the server detects that the user's emotional data indicates stress, it will switch to easier learning suggestions to reduce the load on the server.

[0717] User terminal operation

[0718] The user terminal is a device that provides the user interface and displays content and feedback sent from the server. The terminal incorporates an emotion engine that analyzes the user's facial expressions and tone of voice to generate emotion data. This data is sent to the server in real time and influences the individual learning experience. For example, if signs of confusion are detected in the user's facial expressions while they are working on an exercise, the terminal sends this information to the server to prompt support.

[0719] User operation

[0720] Users can access the learning platform through their devices and select courses based on AI and DX technologies to proceed with their learning. Because the user's emotional state is reflected in the learning flow, content at an appropriate level is provided, improving learning efficiency. Furthermore, when sharing knowledge with colleagues using digital notes, the emotion engine analyzes the atmosphere of the discussion and offers suggestions to support smooth communication.

[0721] Thus, the system of the present invention supports the improvement of users' skills and work efficiency by analyzing users' emotions in real time and optimizing the learning experience based on those emotions.

[0722] The following describes the processing flow.

[0723] Step 1:

[0724] The user logs into the learning platform using their device. The device authenticates the user's access and displays a list of available courses.

[0725] Step 2:

[0726] The user selects an AI or DX course that interests them. The selection is sent from the device to the server, which then delivers the corresponding learning content to the device.

[0727] Step 3:

[0728] The server uses data storage to track learning progress and records the user's progress. The data is updated upon completion of each learning step.

[0729] Step 4:

[0730] The device uses a built-in emotion engine to analyze the user's facial expressions and voice, generating emotion data. For example, if the user shows a confused expression while working on a question, that data is collected.

[0731] Step 5:

[0732] The generated sentiment data is sent from the device to the server. The server uses this sentiment data to evaluate the user's current learning progress.

[0733] Step 6:

[0734] The server analyzes emotional data and learning progress data to generate personalized learning suggestions. For example, if a user has a high stress level, it will suggest easier practice problems.

[0735] Step 7:

[0736] The server sends the generated learning suggestions to the terminal for use. The terminal notifies the user of the new suggestions.

[0737] Step 8:

[0738] The user uses their device to continue learning based on suggestions from the server. The device again senses the progress of learning and changes in emotional state, and the processing cycle is repeated.

[0739] Step 9:

[0740] Using the digital note-taking function on their devices, users can record their learning progress and share information with colleagues. During this process, the emotion engine provides advice to support the smooth progress of discussions.

[0741] (Example 2)

[0742] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0743] Conventional learning support systems struggle to provide personalized learning suggestions in real time that take into account each user's emotional state. This leads to users experiencing stress and a decrease in learning efficiency. Furthermore, there are insufficient means to facilitate smooth communication by sharing emotional states.

[0744] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0745] In this invention, the server includes data storage means for storing learning progress data and emotional data received from the user terminal, information processing means for generating personalized learning suggestions based on the received learning progress data and emotional data, and information transmission means for transmitting the generated learning suggestions to the user terminal. This enables real-time automatic adjustment of learning content according to the user's emotional state, allowing for efficient skill improvement while reducing the learning burden.

[0746] A "data storage means" is a device that provides functions for safely and efficiently storing learning progress data and emotional data acquired from a user terminal.

[0747] An "information processing device" is a device that has a mechanism for analyzing learning progress data and sentiment data, and generating optimal learning suggestions based on that analysis.

[0748] "Information transmission means" refers to a device equipped with communication functions for quickly and accurately transmitting generated learning suggestions to the user's terminal.

[0749] An "emotion engine" is a technology that detects and digitizes a user's emotional state by analyzing their facial expressions and tone of voice.

[0750] The "digital note-taking function" is a tool designed to facilitate knowledge sharing among users and support smoother communication that takes emotional states into consideration.

[0751] This invention is a business support system that improves the user's learning experience on a learning platform. This system mainly consists of three elements: a server, a user terminal, and the user, each working together to provide a consistent learning environment.

[0752] Server Role

[0753] The server functions as the central hub of the learning platform, centrally processing learning progress data and sentiment data. The server is equipped with data storage mechanisms, through which learning progress data and sentiment data are securely stored. Furthermore, information processing mechanisms generate personalized learning suggestions based on the received data. These generated learning suggestions are transmitted to the user's terminal using information transmission mechanisms, allowing the user to receive content optimized for their own situation.

[0754] User terminal operation

[0755] The terminal is a device that provides a user interface and displays learning content and feedback sent from the server. The terminal has a built-in emotion engine that analyzes the user's facial expressions and voice tone to generate emotion data in real time. This emotion data is sent to the server and used to optimize the learning experience.

[0756] User operation

[0757] Users can access the learning platform via their devices and select from a variety of courses based on the provided AI and DX technologies. Emotional states are reflected in the learning process, ensuring that content of optimal difficulty is provided and promoting efficient learning. Furthermore, knowledge sharing with other users is possible through the digital note-taking function, which uses an emotion engine to analyze the atmosphere of discussions and facilitate smooth communication.

[0758] Specific example

[0759] For example, when a user is learning a new language, the device may detect a lack of concentration through its camera. In this case, the server may suggest basic review materials or step-by-step instruction. As an example of a prompt, the AI ​​model could be fed the question, "What kind of support is best for the user in this difficult situation?" to suggest specific learning support measures.

[0760] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0761] Step 1:

[0762] The device uses its camera and microphone to acquire facial and voice data during the user's learning process. This data is analyzed by an emotion engine to generate digital data about the user's current emotional state. The input is the user's visual and auditory information, and the output is the analyzed emotion data. This operation prepares the device to send that emotion data to the server in real time.

[0763] Step 2:

[0764] The device sends generated sentiment data and other learning progress data entered by the user during learning to the server. The input is the sentiment data and learning progress data analyzed on the device, and the output is the data packets sent to the server. The device maintains consistency in the learning experience by delivering this information quickly and accurately.

[0765] Step 3:

[0766] The server stores received emotion data and learning progress data in a data storage device and analyzes the data using an information processing device. The input is data transmitted from the terminal, and the output is the analysis results and learning suggestions based on them. Based on this information, the server identifies the user's current learning status and the support they need.

[0767] Step 4:

[0768] The server generates learning suggestions based on the analysis results and sends the corresponding learning content to the terminal using an information transmission method. The input is the learning suggestion generated on the server, and the output is the personalized learning content transferred to the terminal. This allows the server to provide optimal learning support in real time.

[0769] Step 5:

[0770] Users progress through their learning based on customized learning content displayed on their device. Input is the learning suggestions received by the device, and output is the user's corresponding learning activities and responses. The device continuously tracks sentiment data and learning progress, sending feedback back to the server. This process dynamically optimizes the learning experience.

[0771] (Application Example 2)

[0772] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0773] Conventional learning support systems often provided uniform learning content without considering the individual emotional state of learners. This meant they were unable to respond appropriately when learners experienced stress or confusion, potentially leading to decreased learning efficiency. Furthermore, there was a challenge in optimizing human-machine interaction in home-based educational support.

[0774] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0775] In this invention, the server includes analysis means for analyzing the learner's expressions and acquiring emotional data, adjustment means for dynamically adjusting learning content based on the acquired emotional data, and dialogue means for providing the adjusted learning content while interacting with the learner. This makes it possible to vary the content according to the individual emotional state of the learner and improve learning efficiency.

[0776] "Analysis methods for analyzing learners' expressions and acquiring emotional data" refers to technical means that analyze learners' facial expressions and tone of voice to determine their emotional state in real time.

[0777] "An adjustment means for dynamically adjusting learning content based on acquired emotional data" refers to a technical means that selects and provides content of appropriate difficulty and format according to the learner's state, based on emotional data obtained by an analysis means.

[0778] "Dialogue means for providing tailored learning content in an interactive manner with learners" refers to technical means that use robots or digital interfaces to continuously communicate with learners and flexibly present tailored content.

[0779] The system for implementing this invention aims to improve learning efficiency by analyzing the learner's emotions in real time and providing learning content tailored to their state. There are three main components to this system.

[0780] First, as an analysis method, the device equipped with the emotion engine monitors the learner's facial expressions and voice using a camera and microphone. This emotion engine uses software such as Google Cloud Vision API or Microsoft Azure Emotion API to analyze the learner's emotional state based on the collected data.

[0781] Next, the server, which acts as the adjustment mechanism, uses the emotion data obtained by the analysis mechanism to dynamically adjust the difficulty level and format of the digital content. If the learner is confused, it will switch to easier content.

[0782] Finally, the interactive interface provided by the dialogue means presents the learner with tailored learning content and supports learning through continuous dialogue. This is handled by robots and digital devices, which supplement the content as needed in response to the learner's reactions, helping the learner deepen their understanding.

[0783] As a concrete example, consider a scenario where the system attempts to solve a math problem with a child. If the child faces a difficult problem and shows signs of confusion, the terminal's analysis mechanism reads the child's emotions, and the server's adjustment mechanism selects an easier problem appropriate to the situation. Then, through the dialogue mechanism, the robot presents the problem to the child in an interactive format and adds explanations to support the child's understanding.

[0784] Examples of prompts when using a generative AI model include:

[0785] "Assume you are a learning assistant robot. A child is showing signs of confusion during a math problem. Simplify the problem and offer a step-by-step explanation to help the child understand."

[0786] This prompt sets the AI ​​in the role of an educational assistant, providing guidance to help children learn.

[0787] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0788] Step 1:

[0789] The device captures the learner's facial expressions and voice through its camera and microphone. The input is video and audio data, and the output generates raw data for analysis by the emotion engine. Specifically, the device collects data in real time and starts emotion analysis processing in the background.

[0790] Step 2:

[0791] The device's emotion engine analyzes video and audio data to generate learner emotion data. The input is the raw data generated in step 1, and the output is data indicating the learner's emotional state (e.g., stress, satisfaction, confusion). Specifically, an emotion recognition algorithm quickly analyzes the data and sends the emotional state to the server based on the results.

[0792] Step 3:

[0793] The server receives emotion data and adjusts the difficulty level of the learning content. The input is the emotion data from step 2, and the output is the adjusted learning content. Specifically, the server's adjustment algorithm selects content based on the emotional state and performs actions such as simplifying problems if the user is feeling stressed.

[0794] Step 4:

[0795] The device provides learners with pre-configured learning content in an interactive format. The input is the learning content from Step 3, and the output is the result of the interaction with the learner. Specifically, the device presents content in text and audio, and determines the next action based on the learner's immediate response. As the interaction continues, supplementary explanations are added as needed to deepen the learner's understanding.

[0796] Step 5:

[0797] The user engages with learning content, and the device records their progress. The input is data on the learner's learning behavior, and the output is recorded data on their learning progress. Specifically, the device records the learner's answers and other information, sends this data to a server, and uses it as basic data for the next learning plan.

[0798] Step 6:

[0799] The server collects and stores progress data, which is then used to generate learning content for subsequent sessions. The input is the progress data from step 5, and the output is updated learner profile data. Specifically, the server saves the data to a database, and the AI ​​agent performs analysis to use it for future learning suggestions.

[0800] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0801] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0802] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0803] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0804] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0805] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0806] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0807] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0808] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0809] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0810] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0811] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0812] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0813] 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.

[0814] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0815] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0816] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0817] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0818] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0819] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0820] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0821] The following is further disclosed regarding the embodiments described above.

[0822] (Claim 1)

[0823] A data storage means for saving learning progress data received from a user terminal,

[0824] A processing means for generating personalized learning suggestions based on received learning progress data,

[0825] A communication means for sending the generated learning suggestions to the user's terminal,

[0826] This includes using accumulated data to evolve artificial intelligence agents and optimization methods to improve business workflows.

[0827] Business support system.

[0828] (Claim 2)

[0829] A business support system according to claim 1, which generates practice problems based on user input and provides them in conjunction with business-related case studies.

[0830] (Claim 3)

[0831] The business support system according to claim 1, comprising an educational support means that incorporates a digital note-taking function to facilitate knowledge sharing among users.

[0832] "Example 1"

[0833] (Claim 1)

[0834] A data storage means for saving learning progress information received from a user terminal,

[0835] Information processing means for generating learning recommendations suitable for the user based on received learning progress information,

[0836] A communication means for delivering the generated learning recommendations to the user's terminal,

[0837] Using accumulated information to enhance artificial intelligence agents and improve business processes,

[0838] A system that includes data analysis tools to support business analysis by utilizing generative AI models.

[0839] (Claim 2)

[0840] The system according to claim 1, which creates practice problems based on user input information and provides them as business-related case studies.

[0841] (Claim 3)

[0842] The system according to claim 1, comprising an educational support means that incorporates a digital note-taking function to facilitate information sharing among users.

[0843] "Application Example 1"

[0844] (Claim 1)

[0845] A data storage means for saving learning progress data received from a user terminal,

[0846] A data processing means for generating personalized learning suggestions based on received learning progress data,

[0847] A data transmission means for sending the generated learning suggestions to the user's terminal,

[0848] By utilizing accumulated data, we can evolve artificial intelligence agents and optimize business procedures.

[0849] A simulation method for tracking user operations in real time and virtually reproducing the factory environment,

[0850] Includes machine learning algorithms to provide the optimal procedure for operation.

[0851] Business support system.

[0852] (Claim 2)

[0853] The system according to claim 1, which generates practice problems based on user input and provides them in connection with business-related issues.

[0854] (Claim 3)

[0855] The system according to claim 1, comprising a training support means that incorporates an electronic note-taking function for promoting knowledge sharing among users.

[0856] "Example 2 of combining an emotion engine"

[0857] (Claim 1)

[0858] A data storage means for storing learning progress data and emotion data received from a user terminal,

[0859] Information processing means for generating personalized learning suggestions based on received learning progress data and sentiment data,

[0860] Information transmission means for sending the generated learning suggestions to the user's terminal,

[0861] A system that includes automated means for automatically adjusting the difficulty level of learning content according to the user's emotional state.

[0862] (Claim 2)

[0863] The system according to claim 1, which is equipped with an emotion engine that analyzes the user's facial expressions and tone of voice, and adjusts learning suggestions based on the analysis results for the purpose of stress reduction and concentration improvement.

[0864] (Claim 3)

[0865] The system according to claim 1, which incorporates an educational support means that facilitates knowledge sharing through a digital note-taking function that takes into account the emotional state of the user.

[0866] "Application example 2 when combining with an emotional engine"

[0867] (Claim 1)

[0868] An analytical means for analyzing learners' expressions and obtaining emotional data,

[0869] An adjustment mechanism for dynamically adjusting learning content based on acquired emotional data,

[0870] A dialogue mechanism for providing tailored learning content in an interactive manner with learners,

[0871] A data storage means for saving learning progress data received from a user terminal,

[0872] A processing means for generating personalized learning suggestions based on received learning progress data,

[0873] A communication means for sending the generated learning suggestions to the user's terminal,

[0874] This includes developing intelligent agents using accumulated data and optimization methods to improve business procedures.

[0875] system.

[0876] (Claim 2)

[0877] The system according to claim 1, which detects changes in learners' emotions and modifies appropriate practice problems to an easier level, and provides them in conjunction with case studies related to education.

[0878] (Claim 3)

[0879] The system according to claim 1, which includes collaborative support means incorporating an atmosphere analysis function using emotion analysis to facilitate information sharing among learners. [Explanation of symbols]

[0880] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A data storage means for saving learning progress data received from a user terminal, A data processing means for generating personalized learning suggestions based on received learning progress data, A data transmission means for sending the generated learning suggestions to the user's terminal, By utilizing accumulated data, we can evolve artificial intelligence agents and optimize business procedures. A simulation method for tracking user operations in real time and virtually reproducing the factory environment, Includes machine learning algorithms to provide the optimal procedure for operation. system.

2. The system according to claim 1, which generates practice problems based on user input and provides them in connection with business-related tasks.

3. The system according to claim 1, comprising a training support means that incorporates an electronic note-taking function to facilitate knowledge sharing among users.

Images