system

Abstract

Provide a system. 【Solution means】 Analysis means for collecting the user's learner information and analyzing the user's learning level based on the information, Plan generation means for generating an optimized learning plan according to the user's learning goal, Support means for providing real-time learning support and feedback based on the generated learning plan, Evaluation means for conducting simulation training in a virtual business environment and evaluating the activities of the user during the training, Response means for receiving inquiries from the user, generating responses and providing them, Feedback means for analyzing the user's learning progress and generating visual feedback, Evaluation means for providing a simulation scenario from the user's perspective in real time and evaluating the language ability, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society where globalization is progressing, individuals and companies are facing the need to effectively cultivate international talents. However, it takes a great deal of time and cost to acquire language skills and cross-cultural understanding, and it is difficult to provide individually optimized support according to the needs and levels of individual learners. Furthermore, in order to develop practical business skills, training assuming daily business scenes is essential, but there is a lack of an environment to effectively conduct this. There is a need for means to provide a more efficient and effective learning experience for these problems of current solutions.

Means for Solving the Problems

[0005] This invention relates to a system that collects learner information from users and analyzes their language level and cross-cultural understanding based on that information. Based on the analysis results, this system generates an optimized learning plan for each user and provides real-time learning support and feedback. This process includes simulation training using a virtual business environment, allowing users to hone their practical skills. It also includes an immediate response function to user questions, supporting continuous learning. Each of the above means uses machine learning to analyze learning progress and enables continuous improvement of the individual learning experience. Through the above series of functions, this invention effectively solves conventional problems related to global human resource development and supports the improvement of users' international communication skills and business skills.

[0006] "User information" refers to personal data related to a user's learning, including language level, learning goals, and past learning history.

[0007] "Analysis means" refers to a data processing process that uses collected user information to identify the user's current skills and learning needs.

[0008] The "plan generation method" is a function that creates learning plans and curricula tailored to each individual user based on the analysis results.

[0009] "Real-time support" is a process in which the user and the system respond to each other instantly, providing continuous learning support and feedback.

[0010] An "evaluation method" is a mechanism that measures and analyzes user performance during simulation training to quantify learning effectiveness and comprehension.

[0011] A "response mechanism" is an information processing function aimed at generating and providing quick and appropriate answers to user inquiries.

[0012] A "feedback mechanism" is a function that allows a system to understand a user's learning progress and provide it to the user as visual or numerical information to help them decide on their next learning step.

[0013] A "machine learning algorithm" is a set of computational methods in which a computer learns from data and automatically improves the performance of the system based on the results of analyzing the collected data.

[0014] A "virtual business environment" is a virtual space that mimics actual business scenarios and is a simulation environment used by users to train their business skills. [Brief explanation of the drawing]

[0015] [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] 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.

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

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

[0019] 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.

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

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] The system of the present invention operates on a platform accessible to users via a network. The system mainly consists of a server and user terminals and is equipped with various functions to support user learning. The method of implementing the present invention will be described in detail below.

[0037] Server operation

[0038] The server first collects user information and stores it in a database. This information includes the user's language level, learning history, and individual learning goals. Based on this information, the server uses natural language processing technology to analyze the user's skill level.

[0039] Based on the analysis results, the server generates a learning plan optimized for each user. For example, it selects topics and practice exercises to improve specific language skills. Furthermore, the server sets up a virtual business environment, allowing users to practice their skills in specific scenarios.

[0040] Terminal operation

[0041] The device displays learning plans and exercises sent from the server to the user. Through the interface, users can access content related to language practice and intercultural understanding, and receive real-time feedback from the server. In particular, the pronunciation practice feature provides immediate feedback and correction suggestions via voice input.

[0042] Furthermore, the device supports simulation training within a virtual business environment, allowing users to conduct training that mimics real-world business scenarios. Within this environment, the device observes user behavior and provides immediate feedback to support skill improvement.

[0043] User actions

[0044] Users log in to the system via their device and view their personalized learning dashboard. This dashboard displays their ongoing learning plan and achievement goals, and users proceed with their studies accordingly. At any step, users can send questions to the server via their device, and the server provides a prompt response.

[0045] This allows users to gain a personalized learning experience and efficiently acquire the language skills and cross-cultural understanding required in the international job market.

[0046] Specific example

[0047] For example, if User A wants to improve their English business conversation skills, the server analyzes User A's current English proficiency and generates a learning plan specifically tailored to business conversations. This plan includes specific industry terminology, conversation scenarios, and even practical exercises based on simulations. The user can practice using their device and refine their skills while incorporating feedback from the server.

[0048] By using the system, each user can effectively improve their language and intercultural understanding skills at their own pace, and cultivate the ability to apply those skills in real-world situations.

[0049] The following describes the processing flow.

[0050] Step 1:

[0051] The server collects user information. When a user enters personal learning data through their device, the server receives it and stores it in a database. The collected information includes language level, learning goals, and past learning history.

[0052] Step 2:

[0053] The server uses natural language processing technology to analyze the user's skill level. Based on the collected data, it identifies the user's current proficiency and needs, and evaluates their user level.

[0054] Step 3:

[0055] The server generates an optimized learning plan. Based on the analyzed user data, it selects learning materials and practice problems tailored to individual learning goals and determines the specific learning content.

[0056] Step 4:

[0057] The server sends the generated learning plan to the device. The device then displays a learning dashboard on the user interface, providing the user with the suggested learning schedule and content.

[0058] Step 5:

[0059] The user begins practicing through their device. They access the presented learning content and study language skills exercises and topics related to intercultural understanding. They receive real-time feedback from the server.

[0060] Step 6:

[0061] The device analyzes the user's pronunciation and input. Based on the data collected in real time, it provides feedback on accuracy and areas for improvement, offering specific suggestions and advice to the user.

[0062] Step 7:

[0063] The server creates a virtual business environment. When the user selects simulation training, the server sets up exercises in a virtual business scenario and provides corresponding scenarios and dialogues.

[0064] Step 8:

[0065] Users conduct training in a virtual business environment. They practice negotiations and presentations according to scenarios presented on their devices and receive immediate behavioral feedback.

[0066] Step 9:

[0067] The server collects and analyzes user progress. It uses machine learning algorithms to analyze user activity data and visualizes learning progress based on pre-defined metrics.

[0068] Step 10:

[0069] The device presents the analysis results to the user. Progress and achievement feedback are displayed in visual formats such as graphs and charts to help the user self-evaluate.

[0070] (Example 1)

[0071] 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."

[0072] Traditional learning systems often struggled to provide learning plans optimized for individual learners' abilities and goals, frequently offering only general content and feedback. This made it difficult for learners to efficiently improve their skills. Furthermore, they lacked sufficient real-time support and practical training simulating specific scenarios.

[0073] 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.

[0074] In this invention, the server includes means for collecting user information and analyzing the user's abilities based on said information, means for generating an optimized plan according to the user's goals, and means for providing support and feedback in real time based on the generated plan. This enables the provision of an optimized learning plan for each individual learner, allowing for efficient skill improvement. Furthermore, practical skills can be acquired through simulation training in a virtual environment.

[0075] "Means for collecting information" refers to devices or methods for collecting and storing data provided by users and for understanding the characteristics of users based on that data.

[0076] "Means of analyzing capabilities" refers to methods for processing collected data and evaluating the user's current capabilities and condition.

[0077] "Means for generating plans" refers to methods for creating optimal learning plans and action guidelines for users based on analysis results.

[0078] "Means of providing support and feedback in real time" refers to a device or method that provides functions for immediate guidance, correction, and evaluation in response to the user's activities.

[0079] "Means for conducting simulation training in a virtual environment" refers to a method that reproduces a situation close to reality in a virtual space, enabling users to conduct practical training within that space.

[0080] "Means of evaluating behavior" are methods for observing a user's activities and responses and measuring their abilities and progress based on those observations.

[0081] "Means of generating and providing responses" refers to methods for providing appropriate information and solutions to inquiries from users.

[0082] "Means for analyzing progress and generating visual feedback" refers to a device or method for tracking and analyzing a user's learning progress and displaying the results clearly using diagrams or graphs.

[0083] "Methods for checking pronunciation using voice analysis technology" refer to technologies that analyze voice data and evaluate the accuracy and areas for improvement of the speech.

[0084] "Methods for improving plans using generative AI technology" refer to methods that use machine learning algorithms to generate optimized plans from current data and continuously improve them.

[0085] "Means of supporting skill practice using multiple computing devices" refers to methods of assisting users in improving their practical skills by using multiple devices that provide computing power.

[0086] This invention is a system that operates on a platform accessible to users via a network. The system mainly consists of a server and user terminals and provides a variety of functions to support learning.

[0087] The server collects and stores user information using a database system. The user's language level, learning history, and learning goals are stored in data storage connected to the server. The server analyzes this data using a natural language processing library implemented in Python to assess the user's skill level. Based on this analysis, it generates a learning plan optimized for the learner using natural language processing techniques.

[0088] After generating a learning plan, the server uses generative AI technology to select the most suitable content for each user and configures a virtual environment. Since the virtual environment is built using technologies such as WebGL, users can practice their skills in specific scenarios. Training conducted in an environment that mimics real business scenarios influences user behavior and helps improve skills.

[0089] The device displays learning plans and simulation content sent from the server to the user. Users can access the content and receive real-time feedback through an interface built with React. Specifically, a speech input analysis function using the Google® Cloud Speech-to-Text API immediately provides suggested corrections to the user's pronunciation.

[0090] Furthermore, the terminal supports simulation training, allowing users to perform activities within a virtual business environment. During this process, user activity data is sent to a server and analyzed as needed. The analysis results are then returned to the user as real-time feedback.

[0091] Users can check their current learning progress and achievement goals through a dashboard provided on their device. As they progress according to their learning plan, they can directly ask questions to the server about anything they are unsure of during their studies. This allows for efficient skill improvement through a learning experience tailored to the individual needs of each user.

[0092] For example, if a user wants to improve their business conversation skills, the server analyzes the user's current language proficiency and creates a learning plan specifically tailored to business conversations. This plan includes specific industry terminology, conversation scenarios, and practical exercises based on simulations. Based on this plan, the user can progress through the learning process and refine their skills while receiving feedback from the server.

[0093] An example of a prompt to input into a generative AI model is, "Please provide a specific learning plan for the user to improve their business conversational skills." This allows for the more accurate generation of relevant information and the provision of appropriate responses.

[0094] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0095] Step 1:

[0096] The server receives login information submitted by the user. This input includes the username and password. Using this information, the server accesses the database and authenticates the user. If authentication is successful, the user's past learning history and settings are retrieved from the database. The output includes information such as the user's learning history, learning level, and individual learning goals.

[0097] Step 2:

[0098] The server uses the acquired user information to analyze skill levels using natural language processing techniques. The input is the user's past learning data, and a natural language processing library implemented in Python is used for the analysis. This process identifies the current skill level and areas of weakness. The output is the analyzed skill data.

[0099] Step 3:

[0100] The server generates a learning plan based on the analysis results. The input is the analyzed skill data, and the plan generation process is performed by a generative AI model. This model outputs a plan that includes specific topics, practice problems, and hypothetical scenarios. The final output is a learning plan optimized for the user.

[0101] Step 4:

[0102] The server delivers the generated learning plan to the terminal. The input is the generated learning plan, which the server sends to the terminal using a communication protocol. The terminal displays the received learning plan and waits for user input. The output is the learning plan presented on the user interface.

[0103] Step 5:

[0104] The device provides the functionality to accept voice input in real time and perform speech analysis. The user's voice is treated as input, and the Google Cloud Speech-to-Text API performs the analysis. Based on the analysis results, pronunciation evaluations and areas for improvement are immediately output and presented to the user.

[0105] Step 6:

[0106] The terminal performs simulation training within a virtual environment. Using scenario data sent from the server as input, it generates a virtual business environment using WebGL technology. Evaluation based on user operations and selected actions is performed in real time, and the terminal outputs feedback.

[0107] Step 7:

[0108] The user submits a question about something they've encountered within the system. The input is the user's question, which is transmitted to the server via the terminal. The server uses a database and AI models to generate the best possible response to the question and resends it to the terminal. The output is the answer presented to the user.

[0109] (Application Example 1)

[0110] 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."

[0111] For users to communicate effectively in an international business environment, appropriate cross-cultural communication skills and high language proficiency are required. However, acquiring these skills efficiently in a short period of time is currently difficult. Therefore, there is a need to provide a learning environment in which users can improve their abilities in real time and receive feedback.

[0112] 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.

[0113] In this invention, the server includes means for collecting user learner information and analyzing the user's learning level based on said information; means for generating an optimized learning plan according to the user's learning goals; and means for providing a simulation scenario from the user's perspective in real time and evaluating language ability. This enables users to improve their multicultural communication skills in a real-time simulation environment and refine their language skills through immediate feedback.

[0114] A "user" refers to an individual or organization that uses the system to engage in learning activities according to a learning plan.

[0115] "Learner information" refers to a collection of data that includes the user's language proficiency, learning history, and learning objectives.

[0116] "Analysis means" refers to systems and functions for evaluating a user's current learning level and skills based on collected learner information.

[0117] A "plan generation method" refers to a system or function for creating optimized learning programs and assignments based on the user's learning objectives.

[0118] "Support measures" refer to systems and functions that provide users with the necessary learning content and feedback in real time, according to the generated learning plan.

[0119] "Evaluation means" refers to systems and functions for monitoring and evaluating user activity during simulations conducted in virtual business environments, etc.

[0120] A "response mechanism" refers to a system or function that provides quick answers to questions and inquiries from users.

[0121] A "feedback tool" is a system or function that generates visual feedback and improvement suggestions based on the user's learning progress.

[0122] A "simulation scenario" is a training setting in a virtual environment where users experience specific roles and situations.

[0123] "Language proficiency" refers to a user's ability to understand and communicate appropriately using a specific language.

[0124] The system for realizing this invention mainly consists of a server and terminals. The server collects learner information registered by users and stores it in a database. The server uses natural language processing technology to analyze the user's learning level from this information. Based on the analysis results, the server generates an optimized learning plan for each user. This plan includes topics and tasks for improving language proficiency.

[0125] The terminal displays learning plans and exercises sent from the server to the user. The application running on the terminal allows the user to access content related to language practice and cross-cultural understanding, and can receive real-time feedback from the server. In particular, for pronunciation practice, it uses a voice input function to immediately provide the user with corrections and suggestions.

[0126] Furthermore, the device supports simulation training in a virtual business environment. Users experience scenarios in a virtual environment and their language skills are evaluated. Real-time simulation scenarios are presented from the user's perspective using wearable devices such as smart glasses. User behavior data is collected, and immediate feedback is provided through evaluation tools.

[0127] For example, if a user requests training to facilitate smooth conversation at an international conference, the server analyzes the user's current language proficiency and provides a customized business conversation simulation based on the results. This simulation is performed in real time on the terminal, allowing the user to receive immediate feedback.

[0128] An example of a prompt incorporating a generative AI model is: "In the following scenario, explain security to an English-speaking customer. Use appropriate terminology and be careful not to cause misunderstandings." The goal of following this prompt is for users to acquire the skills to confidently respond in real-world situations.

[0129] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0130] Step 1:

[0131] The server collects and stores learner information registered by users in a database. This learner information includes the user's language proficiency, learning history, and goals. The input is new user information, and the output is the information stored in the database. At this stage, data processing is performed to appropriately organize the information and prepare it for subsequent analysis.

[0132] Step 2:

[0133] The server analyzes the collected learner information using natural language processing technology to evaluate the user's learning level. The input is the user information stored in step 1, and the output is the evaluation result of the learning level based on that information. In this process, an analysis algorithm is used to perform data calculations, and the learning level is calculated as a numerical value or indicator.

[0134] Step 3:

[0135] The server generates an optimized learning plan based on the user's learning goals and analyzed learning level. The input is the analysis results and learning goals, and the output is a individually customized learning plan. This uses a generative AI model, which generates creative learning scenarios and tasks based on prompts.

[0136] Step 4:

[0137] The terminal receives the learning plan and exercise content sent from the server and presents it to the user. The input is the learning plan from the server, and the output is the learning content displayed on the user interface. The terminal visualizes this data and provides it to the user in an intuitively easy-to-understand format.

[0138] Step 5:

[0139] Users conduct simulation training in a virtual business environment using a terminal. The input is a virtual situation presented as a scenario, and the output is user behavior data. Users practice their skills through the simulation, and a generated AI model operates during this process, providing real-time feedback.

[0140] Step 6:

[0141] The server analyzes user behavior data during the simulation, generates immediate feedback, and sends it to the terminal. The input is user behavior data, and the output is feedback information. This feedback evaluates the user's actions and points out shortcomings and areas for improvement in detail. This allows users to receive specific guidance to enhance their ability to apply the concepts in real-world environments.

[0142] 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.

[0143] This invention relates to a learning support system that incorporates an emotion engine that recognizes the user's emotional state and dynamically adjusts the learning plan and feedback accordingly. This system is accessible to users via a network and mainly consists of a server, a user terminal, and the emotion engine.

[0144] Server operation

[0145] The server first collects the user's learner information and stores it in a database. This information includes learning goals, current skill level, and past learning history. Based on this information, the server analyzes the user's learning level and generates an optimal learning plan.

[0146] Furthermore, this system incorporates an emotion engine, and the server analyzes the user's emotional data obtained from the emotion engine. By adjusting the learning plan and feedback content in real time according to the emotional state, the system improves the user's learning experience.

[0147] Terminal operation

[0148] The terminal functions as a user interface, displaying learning plans and other content provided by the server. Through the terminal, users can access learning content and perform practice exercises and simulation training.

[0149] The emotion engine analyzes the user's facial expressions and voice, and transmits their emotional state to the device in real time. Based on this emotional data, the device dynamically adjusts visual and auditory feedback to provide optimal support for maintaining motivation.

[0150] User actions

[0151] Users log in using their devices and operate the learning dashboard. Analysis results from the emotion engine are provided as feedback, allowing them to monitor their own emotional state and learn according to a plan tailored to their learning progress.

[0152] Specifically, for example, if the emotion engine determines that a user is in a "fatigued" state, the server will temporarily reduce the learning plan and provide content that encourages refreshment. Similarly, if a "high-stress" state is detected, the device will attempt to reduce stress through appropriate relaxation music and interactive feedback.

[0153] This system is expected to appropriately reflect user emotions in the learning process, significantly improving overall learning effectiveness and user satisfaction.

[0154] The following describes the processing flow.

[0155] Step 1:

[0156] The user logs into the system via their device. The device obtains the user's authentication information and sends it to the server. Based on this information, the server authenticates the user.

[0157] Step 2:

[0158] The server generates an appropriate learning plan based on the user's learner information. The server refers to past learning history and learning goals to determine individually customized learning content.

[0159] Step 3:

[0160] The device displays the generated learning plan to the user. The user accesses the provided content and starts the selected learning module.

[0161] Step 4:

[0162] The emotion engine uses the user's facial recognition and voice analysis capabilities to evaluate the user's emotional state in real time.

[0163] Step 5:

[0164] The emotion engine sends the collected emotion data to the server. The server receives this data and incorporates adjustments to the learning plan based on the user's emotional state.

[0165] Step 6:

[0166] The server adjusts learning content or methods based on emotional data. For example, if a user is detected as fatigued, the server may lower the difficulty of the task or recommend content that encourages breaks.

[0167] Step 7:

[0168] The device updates its display content and feedback in real time, providing visual and auditory support to maintain user motivation.

[0169] Step 8:

[0170] Users continue learning while receiving feedback. If their emotional state improves, they can return to more challenging content.

[0171] Step 9:

[0172] The server continuously monitors the user's learning progress and analyzes the data using machine learning algorithms. This allows for improvements to future learning plans.

[0173] Step 10:

[0174] The device provides users with visual feedback on their progress and achievements. This allows users to understand their learning status and further increase their motivation to learn.

[0175] (Example 2)

[0176] 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".

[0177] There is a need to provide effective learning plans and feedback tailored to the individual needs and emotional states of learners to maximize learning effectiveness, but current systems struggle to do this in real time. Furthermore, there is a lack of flexible educational support platforms that can dynamically adjust learning content based on learners' emotional states and progress.

[0178] 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.

[0179] In this invention, the server includes an analysis means for collecting user attribute data and analyzing the user's level of understanding based on said data; a content generation means for generating personalized educational content based on the user's goals; and an adjustment means for analyzing the user's emotional state and dynamically adjusting the educational content and feedback according to that state. This makes it possible to provide an optimal learning experience tailored to the individual circumstances of each learner in real time.

[0180] "Attribute data" refers to information about the user, including learning goals, level of understanding, and emotional state.

[0181] "Comprehension level" is an indicator that shows how accurately users understand the learning material.

[0182] "Personalized educational content" refers to learning materials and curricula that are optimized based on each user's individual learning needs and level of understanding.

[0183] "Emotional state" refers to information that indicates the user's psychological state, and includes, for example, fatigue, excitement, and the presence or absence of concentration.

[0184] "Analysis means" refers to methods and technologies that allow a server to analyze user attribute data and determine an appropriate learning plan.

[0185] "Content generation methods" refer to technologies and methods for creating optimal educational content based on the user's learning objectives and level of understanding.

[0186] "Adjustment means" refers to methods or technologies for dynamically changing educational content and feedback based on the user's real-time emotional state.

[0187] This invention is designed as a learning support system to improve the user's learning experience. The system mainly consists of a server, terminals, and an emotion analysis engine, and each component works in cooperation with the others.

[0188] The server first collects user attribute data when a user accesses the learning platform. This data includes learning goals, current skill level, past learning history, and even real-time emotional state. Using this information, the server employs AI algorithms to generate personalized educational content for each user. The educational content is customized according to the user's goals and skills. Specifically, an AI module using a neural network is used for emotion analysis.

[0189] The device acts as a user interface, displaying educational content provided by the server. Users learn through the device, and their state is monitored by an emotion analysis engine. The device uses a camera and microphone to collect the user's facial expressions and voice, which the emotion analysis engine analyzes in real time. For example, if the user is feeling fatigued, the device will play relaxing music, and the server will temporarily reduce the learning load.

[0190] Furthermore, the system utilizes generative AI models to continuously improve educational content based on learning progress and user feedback. This process incorporates a function that analyzes each user's behavioral data and automatically updates the plan.

[0191] For example, a prompt might say, "Please suggest the type of feedback to provide if the user is determined to be in a high-stress state." Based on this prompt, the AI ​​formulates appropriate feedback for the user.

[0192] In this way, the present invention can provide optimal learning support tailored to the user's emotional state and individual learning needs.

[0193] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0194] Step 1:

[0195] The server collects user attribute data when a user logs into the learning platform. Input includes the user's learning goals, skill level, and past learning history. This data is used to construct a user profile and store it in a database. Specifically, it performs queries on the database and stores the user information.

[0196] Step 2:

[0197] The server analyzes collected attribute data and generates optimized educational content using AI algorithms. It utilizes user profile information as input and processes the data using a generation AI model. This results in the creation of user-specific curricula and learning plans. Specifically, the content generation engine calculates a new plan based on the AI ​​model's training data.

[0198] Step 3:

[0199] The terminal displays educational content provided by the server to the user. It receives educational content data from the server as input and presents learning materials and practice problems on the screen as output. Specifically, it visually formats the content via the user interface and displays it in a user-accessible format.

[0200] Step 4:

[0201] The device uses its camera and microphone to transmit the user's facial expressions and voice to an emotion analysis engine. It takes in voice and image data as input, performs data calculations using AI, and outputs an assessment of the user's emotional state. Specifically, it uses voice recognition software to convert voice data into text and image processing algorithms to identify emotions from facial expressions.

[0202] Step 5:

[0203] The server receives output data from the emotion analysis engine and dynamically adjusts the learning plan and feedback. It uses user emotion state data as input and updates the learning plan using a content adjustment algorithm. The output obtained here is the adjusted learning materials and new feedback. Specifically, it modifies the learning plan in real time, making adjustments based on the user.

[0204] Step 6:

[0205] Users use their devices to actually learn from the provided, pre-adjusted educational content. They receive the adjusted content as input and obtain their own learning progress and skill improvement as output. Specifically, they perform self-assessments by answering practice problems and completing simulations, and record their progress.

[0206] (Application Example 2)

[0207] 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 device 14 will be referred to as the "terminal."

[0208] Improving safety within facilities requires a rapid response to unexpected behaviors and conditions of visitors and staff. In particular, detecting changes in emotions and anticipating a deterioration of the situation is crucial for safety management. However, current systems lack the means to capture such changes in emotional states in real time and respond quickly.

[0209] 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.

[0210] In this invention, the server includes means for collecting user learner information and analyzing the user's learning stage based on said information; means for generating an optimized learning plan according to the user's learning goals; means for providing learning support and feedback in real time based on the generated learning plan; and warning means for analyzing the emotional state of people in the facility through facial expressions and voice and issuing an alarm when a suspicious emotional state is detected. This makes it possible to improve safety within the facility by monitoring the emotional state of users and people in the facility in real time and issuing appropriate alarms.

[0211] "Learner information" refers to data that includes the user's learning goals, progress, and past history.

[0212] "Analysis means" refers to a device or program that has the function of analyzing collected data and identifying the user's learning stage and the support they need.

[0213] A "plan generation means" is a device or program that automatically creates an optimal learning plan based on the user's learning objectives.

[0214] A "support system" is a system that supports the progress of learning according to the plan and provides real-time feedback as needed.

[0215] A "warning device" is a device or program that analyzes the emotional state of people within a facility from their facial expressions and voice, and promptly issues an alarm when a suspicious emotional state is detected.

[0216] The invention will now be described in terms of embodiments. This system mainly consists of a server, a terminal, and an emotion engine with emotion recognition capabilities.

[0217] First, the server collects learner information from users and stores it in a database. This information includes learning goals, current ability level, and past learning history. The server analyzes this data to generate an optimal learning plan. Furthermore, the server has an integrated emotion engine that analyzes facial expressions and voice data to identify the user's emotional state.

[0218] Next, the device functions as a user interface, displaying learning plans and other content created on the server. The device receives emotional data in real time from the emotion engine and dynamically adjusts visual and auditory feedback based on this data to help maintain the user's motivation and learning efficiency. For example, if the device determines that the user is tired, it will present lighter learning content or interactive content for refreshment.

[0219] As an example of facility security applications, the devices are used as smartphones or smart glasses to monitor the emotional states of visitors and staff within the facility. This process employs a system that analyzes emotions from facial expressions and voices using an emotion recognition library (e.g., MediaPipe). If a suspicious emotional state is detected, an immediate alert is sent to security personnel, enabling a swift response.

[0220] A concrete example of its use is a scenario where, upon detecting a visitor in a shopping mall who appears anxious, security personnel would check the visitor's surroundings and take necessary action. An example of an input prompt for the generating AI model would be: "Create a program that analyzes a visitor's video and detects signs of tension or anxiety. Based on the analysis results, it should issue an alarm."

[0221] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0222] Step 1:

[0223] The server collects learner information from users. Specifically, it retrieves data such as learning goals, current ability level, and past learning history from a database. Based on this input data, it analyzes the user's learning stage and prepares the basic information necessary to generate appropriate feedback.

[0224] Step 2:

[0225] The server analyzes the collected learner information and generates a learning plan optimized for each user. The input data includes learning goals and ability levels, and by sending this to the analysis engine, it outputs an individually optimized learning plan and proposes the next course of action.

[0226] Step 3:

[0227] The terminal visually displays the learning plan received from the server to the user. Here, an interface is dynamically generated and displayed to make the plan easy to understand and to support user interaction. The output includes a visualization of the plan and a corresponding feedback mechanism.

[0228] Step 4:

[0229] The server uses an emotion engine to analyze the user's emotional state from their facial expressions and voice. It collects the user's emotional data, and through this analysis, outputs data to identify the emotional state in real time, providing foundational information for feedback adjustment. For example, it might use libraries such as MediaPipe.

[0230] Step 5:

[0231] The device dynamically adjusts visual and auditory feedback based on the analyzed emotional state. It receives real-time emotional assessments as input data, and outputs feedback tailored to the user's state, presented as specific actions to facilitate the learning experience.

[0232] Step 6:

[0233] Users progress through their learning based on the provided plan and feedback. They initiate learning activities through the interface and execute the plan while monitoring their progress through voluntary actions. The output is improved efficiency and satisfaction.

[0234] Step 7:

[0235] The server monitors the emotional state within the facility and immediately issues an alarm if an anomaly is detected. It receives emotional data transmitted from terminals as input, analyzes this data using a machine learning model to recognize specific patterns, and determines an alarm signal and corresponding action as output.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] [Second Embodiment]

[0240] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0241] 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.

[0242] 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).

[0243] 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.

[0244] 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.

[0245] 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).

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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.

[0251] 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".

[0252] The system of the present invention operates on a platform accessible to users via a network. The system mainly consists of a server and user terminals and is equipped with various functions to support user learning. The method of implementing the present invention will be described in detail below.

[0253] Server operation

[0254] The server first collects user information and stores it in a database. This information includes the user's language level, learning history, and individual learning goals. Based on this information, the server uses natural language processing technology to analyze the user's skill level.

[0255] Based on the analysis results, the server generates a learning plan optimized for each user. For example, it selects topics and practice exercises to improve specific language skills. Furthermore, the server sets up a virtual business environment, allowing users to practice their skills in specific scenarios.

[0256] Terminal operation

[0257] The device displays learning plans and exercises sent from the server to the user. Through the interface, users can access content related to language practice and intercultural understanding, and receive real-time feedback from the server. In particular, the pronunciation practice feature provides immediate feedback and correction suggestions via voice input.

[0258] Furthermore, the device supports simulation training within a virtual business environment, allowing users to conduct training that mimics real-world business scenarios. Within this environment, the device observes user behavior and provides immediate feedback to support skill improvement.

[0259] User actions

[0260] Users log in to the system via their device and view their personalized learning dashboard. This dashboard displays their ongoing learning plan and achievement goals, and users proceed with their studies accordingly. At any step, users can send questions to the server via their device, and the server provides a prompt response.

[0261] This allows users to gain a personalized learning experience and efficiently acquire the language skills and cross-cultural understanding required in the international job market.

[0262] Specific example

[0263] For example, if User A wants to improve their English business conversation skills, the server analyzes User A's current English proficiency and generates a learning plan specifically tailored to business conversations. This plan includes specific industry terminology, conversation scenarios, and even practical exercises based on simulations. The user can practice using their device and refine their skills while incorporating feedback from the server.

[0264] By using the system, each user can effectively improve their language and intercultural understanding skills at their own pace, and cultivate the ability to apply those skills in real-world situations.

[0265] The following describes the processing flow.

[0266] Step 1:

[0267] The server collects user information. When a user enters personal learning data through their device, the server receives it and stores it in a database. The collected information includes language level, learning goals, and past learning history.

[0268] Step 2:

[0269] The server uses natural language processing technology to analyze the user's skill level. Based on the collected data, it identifies the user's current proficiency and needs, and evaluates their user level.

[0270] Step 3:

[0271] The server generates an optimized learning plan. Based on the analyzed user data, it selects learning materials and practice problems tailored to individual learning goals and determines the specific learning content.

[0272] Step 4:

[0273] The server sends the learning plan it generated to the terminal. The terminal displays a learning dashboard on the user interface and provides the proposed learning schedule and content to the user.

[0274] Step 5:

[0275] The user starts practicing through the terminal. Access the presented learning content and learn language skill exercises and topics on cross - cultural understanding. Receive feedback from the server in real - time.

[0276] Step 6:

[0277] The terminal analyzes the user's pronunciation and input. Based on the data collected in real - time, it provides feedback on accuracy and areas for improvement, presenting specific points and advice to the user.

[0278] Step 7:

[0279] The server constructs a virtual business environment. When the user selects simulation training, the server sets up exercises in a virtual business scenario and provides corresponding scenarios and dialogues.

[0280] Step 8:

[0281] The user conducts training in the virtual business environment. Practice negotiations and presentations along the scenarios presented on the terminal and receive immediate action feedback.

[0282] Step 9:

[0283] The server collects and analyzes the user's progress. Using machine - learning algorithms, it analyzes the user's activity data and visualizes the progress of learning based on pre - set metrics.

[0284] Step 10:

[0285] The terminal presents the analysis results to the user. It displays feedback on progress and achievement in a visual format such as graphs or charts to assist the user in self-evaluation.

[0286] (Example 1)

[0287] Next, 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".

[0288] Conventional learning systems have difficulty providing learning plans optimized for each learner's abilities and goals, and often only general content and feedback can be obtained. Therefore, it has been difficult for learners to improve their skills efficiently. There is also a problem that real-time support and practical training assuming specific scenarios cannot be sufficiently carried out.

[0289] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0290] In this invention, the server includes means for collecting user information, analyzing the user's ability based on the information, generating a plan optimized according to the user's goal, and providing real-time support and feedback based on the generated plan. This enables the provision of a learning plan optimized for each learner, making efficient skill improvement possible. Furthermore, practical skills can be acquired through simulation training in a virtual environment.

[0291] The "means for collecting information" is a device or method for collecting, storing data provided by the user, and grasping the user's characteristics based on it.

[0292] The "means for analyzing ability" is a method for processing the collected data and evaluating the user's current ability and state.

[0293] "Means for generating plans" refers to methods for creating optimal learning plans and action guidelines for users based on analysis results.

[0294] "Means of providing support and feedback in real time" refers to a device or method that provides functions for immediate guidance, correction, and evaluation in response to the user's activities.

[0295] "Means for conducting simulation training in a virtual environment" refers to a method that reproduces a situation close to reality in a virtual space, enabling users to conduct practical training within that space.

[0296] "Means of evaluating behavior" are methods for observing a user's activities and responses and measuring their abilities and progress based on those observations.

[0297] "Means of generating and providing responses" refers to methods for providing appropriate information and solutions to inquiries from users.

[0298] "Means for analyzing progress and generating visual feedback" refers to a device or method for tracking and analyzing a user's learning progress and displaying the results clearly using diagrams or graphs.

[0299] "Methods for checking pronunciation using voice analysis technology" refer to technologies that analyze voice data and evaluate the accuracy and areas for improvement of the speech.

[0300] "Methods for improving plans using generative AI technology" refer to methods that use machine learning algorithms to generate optimized plans from current data and continuously improve them.

[0301] "Means of supporting skill practice using multiple computing devices" refers to methods of assisting users in improving their practical skills by using multiple devices that provide computing power.

[0302] This invention is a system that operates on a platform accessible to users via a network. The system mainly consists of a server and user terminals and provides a variety of functions to support learning.

[0303] The server collects and stores user information using a database system. The user's language level, learning history, and learning goals are stored in data storage connected to the server. The server analyzes this data using a natural language processing library implemented in Python to assess the user's skill level. Based on this analysis, it generates a learning plan optimized for the learner using natural language processing techniques.

[0304] After generating a learning plan, the server uses generative AI technology to select the most suitable content for each user and configures a virtual environment. Since the virtual environment is built using technologies such as WebGL, users can practice their skills in specific scenarios. Training conducted in an environment that mimics real business scenarios influences user behavior and helps improve skills.

[0305] The device displays learning plans and simulation content sent from the server to the user. Users can access the content and receive real-time feedback through an interface built with React. Specifically, a speech input analysis function using the Google Cloud Speech-to-Text API provides immediate suggestions for correcting the user's pronunciation.

[0306] Furthermore, the terminal supports simulation training, allowing users to perform activities within a virtual business environment. During this process, user activity data is sent to a server and analyzed as needed. The analysis results are then returned to the user as real-time feedback.

[0307] Users can check their current learning status and achievement goals through the dashboard provided on the terminal. While progressing according to the learning plan, users can directly ask questions about their learning doubts to the server. Through this, efficient skill improvement can be expected through a learning experience tailored to the individual needs of the users.

[0308] As a specific example, when a user wants to improve their business conversation ability, the server analyzes the user's current language ability and creates a learning plan specialized for business conversations. This plan includes specific industry terms, conversation scenarios, and practical exercises based on simulations. Based on this content, users can proceed with their learning and hone their skills while receiving feedback from the server.

[0309] As an example of a prompt sentence to input into the generative AI model, "Please show a specific learning plan for the user to improve their conversation ability in business." can be considered. This enables more accurate generation of highly relevant information and appropriate responses.

[0310] The flow of the specific process in Example 1 will be described using FIG. 11.

[0311] Step 1:

[0312] The server receives the login information sent from the user. The input includes the username and password. Using this information, the server accesses the database and authenticates the user. If the authentication is successful, the user's past learning history and settings are retrieved from the database. As output, information such as the user's learning history, learning level, and individual learning goals can be obtained.

[0313] Step 2:

[0314] The server uses the acquired user information to analyze skill levels using natural language processing techniques. The input is the user's past learning data, and a natural language processing library implemented in Python is used for the analysis. This process identifies the current skill level and areas of weakness. The output is the analyzed skill data.

[0315] Step 3:

[0316] The server generates a learning plan based on the analysis results. The input is the analyzed skill data, and the plan generation process is performed by a generative AI model. This model outputs a plan that includes specific topics, practice problems, and hypothetical scenarios. The final output is a learning plan optimized for the user.

[0317] Step 4:

[0318] The server delivers the generated learning plan to the terminal. The input is the generated learning plan, which the server sends to the terminal using a communication protocol. The terminal displays the received learning plan and waits for user input. The output is the learning plan presented on the user interface.

[0319] Step 5:

[0320] The device provides the functionality to accept voice input in real time and perform speech analysis. The user's voice is treated as input, and the Google Cloud Speech-to-Text API performs the analysis. Based on the analysis results, pronunciation evaluations and areas for improvement are immediately output and presented to the user.

[0321] Step 6:

[0322] The terminal performs simulation training within a virtual environment. Using scenario data sent from the server as input, it generates a virtual business environment using WebGL technology. Evaluation based on user operations and selected actions is performed in real time, and the terminal outputs feedback.

[0323] Step 7:

[0324] The user submits a question about something they've encountered within the system. The input is the user's question, which is transmitted to the server via the terminal. The server uses a database and AI models to generate the best possible response to the question and resends it to the terminal. The output is the answer presented to the user.

[0325] (Application Example 1)

[0326] 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 glasses 214 will be referred to as the "terminal."

[0327] For users to communicate effectively in an international business environment, appropriate cross-cultural communication skills and high language proficiency are required. However, acquiring these skills efficiently in a short period of time is currently difficult. Therefore, there is a need to provide a learning environment in which users can improve their abilities in real time and receive feedback.

[0328] 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.

[0329] In this invention, the server includes means for collecting user learner information and analyzing the user's learning level based on said information; means for generating an optimized learning plan according to the user's learning goals; and means for providing a simulation scenario from the user's perspective in real time and evaluating language ability. This enables users to improve their multicultural communication skills in a real-time simulation environment and refine their language skills through immediate feedback.

[0330] A "user" refers to an individual or organization that uses the system to engage in learning activities according to a learning plan.

[0331] "Learner information" refers to a collection of data that includes the user's language proficiency, learning history, and learning objectives.

[0332] "Analysis means" refers to systems and functions for evaluating a user's current learning level and skills based on collected learner information.

[0333] A "plan generation method" refers to a system or function for creating optimized learning programs and assignments based on the user's learning objectives.

[0334] "Support measures" refer to systems and functions that provide users with the necessary learning content and feedback in real time, according to the generated learning plan.

[0335] "Evaluation means" refers to systems and functions for monitoring and evaluating user activity during simulations conducted in virtual business environments, etc.

[0336] A "response mechanism" refers to a system or function that provides quick answers to questions and inquiries from users.

[0337] A "feedback tool" is a system or function that generates visual feedback and improvement suggestions based on the user's learning progress.

[0338] A "simulation scenario" is a training setting in a virtual environment where users experience specific roles and situations.

[0339] "Language proficiency" refers to a user's ability to understand and communicate appropriately using a specific language.

[0340] The system for realizing this invention mainly consists of a server and terminals. The server collects learner information registered by users and stores it in a database. The server uses natural language processing technology to analyze the user's learning level from this information. Based on the analysis results, the server generates an optimized learning plan for each user. This plan includes topics and tasks for improving language proficiency.

[0341] The terminal displays learning plans and exercises sent from the server to the user. The application running on the terminal allows the user to access content related to language practice and cross-cultural understanding, and can receive real-time feedback from the server. In particular, for pronunciation practice, it uses a voice input function to immediately provide the user with corrections and suggestions.

[0342] Furthermore, the device supports simulation training in a virtual business environment. Users experience scenarios in a virtual environment and their language skills are evaluated. Real-time simulation scenarios are presented from the user's perspective using wearable devices such as smart glasses. User behavior data is collected, and immediate feedback is provided through evaluation tools.

[0343] For example, if a user requests training to facilitate smooth conversation at an international conference, the server analyzes the user's current language proficiency and provides a customized business conversation simulation based on the results. This simulation is performed in real time on the terminal, allowing the user to receive immediate feedback.

[0344] An example of a prompt incorporating a generative AI model is: "In the following scenario, explain security to an English-speaking customer. Use appropriate terminology and be careful not to cause misunderstandings." The goal of following this prompt is for users to acquire the skills to confidently respond in real-world situations.

[0345] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0346] Step 1:

[0347] The server collects and stores learner information registered by users in a database. This learner information includes the user's language proficiency, learning history, and goals. The input is new user information, and the output is the information stored in the database. At this stage, data processing is performed to appropriately organize the information and prepare it for subsequent analysis.

[0348] Step 2:

[0349] The server analyzes the collected learner information using natural language processing technology to evaluate the user's learning level. The input is the user information stored in step 1, and the output is the evaluation result of the learning level based on that information. In this process, an analysis algorithm is used to perform data calculations, and the learning level is calculated as a numerical value or indicator.

[0350] Step 3:

[0351] The server generates an optimized learning plan based on the user's learning goals and analyzed learning level. The input is the analysis results and learning goals, and the output is a individually customized learning plan. This uses a generative AI model, which generates creative learning scenarios and tasks based on prompts.

[0352] Step 4:

[0353] The terminal receives the learning plan and exercise content sent from the server and presents it to the user. The input is the learning plan from the server, and the output is the learning content displayed on the user interface. The terminal visualizes this data and provides it to the user in an intuitively easy-to-understand format.

[0354] Step 5:

[0355] Users conduct simulation training in a virtual business environment using a terminal. The input is a virtual situation presented as a scenario, and the output is user behavior data. Users practice their skills through the simulation, and a generated AI model operates during this process, providing real-time feedback.

[0356] Step 6:

[0357] The server analyzes user behavior data during the simulation, generates immediate feedback, and sends it to the terminal. The input is user behavior data, and the output is feedback information. This feedback evaluates the user's actions and points out shortcomings and areas for improvement in detail. This allows users to receive specific guidance to enhance their ability to apply the concepts in real-world environments.

[0358] 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.

[0359] This invention relates to a learning support system that incorporates an emotion engine that recognizes the user's emotional state and dynamically adjusts the learning plan and feedback accordingly. This system is accessible to users via a network and mainly consists of a server, a user terminal, and the emotion engine.

[0360] Server operation

[0361] The server first collects the user's learner information and stores it in a database. This information includes learning goals, current skill level, and past learning history. Based on this information, the server analyzes the user's learning level and generates an optimal learning plan.

[0362] Furthermore, this system incorporates an emotion engine, and the server analyzes the user's emotional data obtained from the emotion engine. By adjusting the learning plan and feedback content in real time according to the emotional state, the system improves the user's learning experience.

[0363] Terminal operation

[0364] The terminal functions as a user interface, displaying learning plans and other content provided by the server. Through the terminal, users can access learning content and perform practice exercises and simulation training.

[0365] The emotion engine analyzes the user's facial expressions and voice, and transmits their emotional state to the device in real time. Based on this emotional data, the device dynamically adjusts visual and auditory feedback to provide optimal support for maintaining motivation.

[0366] User actions

[0367] Users log in using their devices and operate the learning dashboard. Analysis results from the emotion engine are provided as feedback, allowing them to monitor their own emotional state and learn according to a plan tailored to their learning progress.

[0368] Specifically, for example, if the emotion engine determines that a user is in a "fatigued" state, the server will temporarily reduce the learning plan and provide content that encourages refreshment. Similarly, if a "high-stress" state is detected, the device will attempt to reduce stress through appropriate relaxation music and interactive feedback.

[0369] This system is expected to appropriately reflect user emotions in the learning process, significantly improving overall learning effectiveness and user satisfaction.

[0370] The following describes the processing flow.

[0371] Step 1:

[0372] The user logs into the system via their device. The device obtains the user's authentication information and sends it to the server. Based on this information, the server authenticates the user.

[0373] Step 2:

[0374] The server generates an appropriate learning plan based on the user's learner information. The server refers to past learning history and learning goals to determine individually customized learning content.

[0375] Step 3:

[0376] The device displays the generated learning plan to the user. The user accesses the provided content and starts the selected learning module.

[0377] Step 4:

[0378] The emotion engine uses the user's facial recognition and voice analysis capabilities to evaluate the user's emotional state in real time.

[0379] Step 5:

[0380] The emotion engine sends the collected emotion data to the server. The server receives this data and incorporates adjustments to the learning plan based on the user's emotional state.

[0381] Step 6:

[0382] The server adjusts learning content or methods based on emotional data. For example, if a user is detected as fatigued, the server may lower the difficulty of the task or recommend content that encourages breaks.

[0383] Step 7:

[0384] The device updates its display content and feedback in real time, providing visual and auditory support to maintain user motivation.

[0385] Step 8:

[0386] Users continue learning while receiving feedback. If their emotional state improves, they can return to more challenging content.

[0387] Step 9:

[0388] The server continuously monitors the user's learning progress and analyzes the data using machine learning algorithms. This allows for improvements to future learning plans.

[0389] Step 10:

[0390] The device provides users with visual feedback on their progress and achievements. This allows users to understand their learning status and further increase their motivation to learn.

[0391] (Example 2)

[0392] 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".

[0393] There is a need to provide effective learning plans and feedback tailored to the individual needs and emotional states of learners to maximize learning effectiveness, but current systems struggle to do this in real time. Furthermore, there is a lack of flexible educational support platforms that can dynamically adjust learning content based on learners' emotional states and progress.

[0394] 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.

[0395] In this invention, the server includes an analysis means for collecting user attribute data and analyzing the user's level of understanding based on said data; a content generation means for generating personalized educational content based on the user's goals; and an adjustment means for analyzing the user's emotional state and dynamically adjusting the educational content and feedback according to that state. This makes it possible to provide an optimal learning experience tailored to the individual circumstances of each learner in real time.

[0396] "Attribute data" refers to information about the user, including learning goals, level of understanding, and emotional state.

[0397] "Comprehension level" is an indicator that shows how accurately users understand the learning material.

[0398] "Personalized educational content" refers to learning materials and curricula that are optimized based on each user's individual learning needs and level of understanding.

[0399] "Emotional state" refers to information that indicates the user's psychological state, and includes, for example, fatigue, excitement, and the presence or absence of concentration.

[0400] "Analysis means" refers to methods and technologies that allow a server to analyze user attribute data and determine an appropriate learning plan.

[0401] "Content generation methods" refer to technologies and methods for creating optimal educational content based on the user's learning objectives and level of understanding.

[0402] "Adjustment means" refers to methods or technologies for dynamically changing educational content and feedback based on the user's real-time emotional state.

[0403] This invention is designed as a learning support system to improve the user's learning experience. The system mainly consists of a server, terminals, and an emotion analysis engine, and each component works in cooperation with the others.

[0404] The server first collects user attribute data when a user accesses the learning platform. This data includes learning goals, current skill level, past learning history, and even real-time emotional state. Using this information, the server employs AI algorithms to generate personalized educational content for each user. The educational content is customized according to the user's goals and skills. Specifically, an AI module using a neural network is used for emotion analysis.

[0405] The device acts as a user interface, displaying educational content provided by the server. Users learn through the device, and their state is monitored by an emotion analysis engine. The device uses a camera and microphone to collect the user's facial expressions and voice, which the emotion analysis engine analyzes in real time. For example, if the user is feeling fatigued, the device will play relaxing music, and the server will temporarily reduce the learning load.

[0406] Furthermore, the system utilizes generative AI models to continuously improve educational content based on learning progress and user feedback. This process incorporates a function that analyzes each user's behavioral data and automatically updates the plan.

[0407] For example, a prompt might say, "Please suggest the type of feedback to provide if the user is determined to be in a high-stress state." Based on this prompt, the AI ​​formulates appropriate feedback for the user.

[0408] In this way, the present invention can provide optimal learning support tailored to the user's emotional state and individual learning needs.

[0409] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0410] Step 1:

[0411] The server collects user attribute data when a user logs into the learning platform. Input includes the user's learning goals, skill level, and past learning history. This data is used to construct a user profile and store it in a database. Specifically, it performs queries on the database and stores the user information.

[0412] Step 2:

[0413] The server analyzes collected attribute data and generates optimized educational content using AI algorithms. It utilizes user profile information as input and processes the data using a generation AI model. This results in the creation of user-specific curricula and learning plans. Specifically, the content generation engine calculates a new plan based on the AI ​​model's training data.

[0414] Step 3:

[0415] The terminal displays educational content provided by the server to the user. It receives educational content data from the server as input and presents learning materials and practice problems on the screen as output. Specifically, it visually formats the content via the user interface and displays it in a user-accessible format.

[0416] Step 4:

[0417] The device uses its camera and microphone to transmit the user's facial expressions and voice to an emotion analysis engine. It takes in voice and image data as input, performs data calculations using AI, and outputs an assessment of the user's emotional state. Specifically, it uses voice recognition software to convert voice data into text and image processing algorithms to identify emotions from facial expressions.

[0418] Step 5:

[0419] The server receives output data from the emotion analysis engine and dynamically adjusts the learning plan and feedback. It uses user emotion state data as input and updates the learning plan using a content adjustment algorithm. The output obtained here is the adjusted learning materials and new feedback. Specifically, it modifies the learning plan in real time, making adjustments based on the user.

[0420] Step 6:

[0421] Users use their devices to actually learn from the provided, pre-adjusted educational content. They receive the adjusted content as input and obtain their own learning progress and skill improvement as output. Specifically, they perform self-assessments by answering practice problems and completing simulations, and record their progress.

[0422] (Application Example 2)

[0423] 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."

[0424] Improving safety within facilities requires a rapid response to unexpected behaviors and conditions of visitors and staff. In particular, detecting changes in emotions and anticipating a deterioration of the situation is crucial for safety management. However, current systems lack the means to capture such changes in emotional states in real time and respond quickly.

[0425] 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.

[0426] In this invention, the server includes means for collecting user learner information and analyzing the user's learning stage based on said information; means for generating an optimized learning plan according to the user's learning goals; means for providing learning support and feedback in real time based on the generated learning plan; and warning means for analyzing the emotional state of people in the facility through facial expressions and voice and issuing an alarm when a suspicious emotional state is detected. This makes it possible to improve safety within the facility by monitoring the emotional state of users and people in the facility in real time and issuing appropriate alarms.

[0427] "Learner information" refers to data that includes the user's learning goals, progress, and past history.

[0428] "Analysis means" refers to a device or program that has the function of analyzing collected data and identifying the user's learning stage and the support they need.

[0429] A "plan generation means" is a device or program that automatically creates an optimal learning plan based on the user's learning objectives.

[0430] A "support system" is a system that supports the progress of learning according to the plan and provides real-time feedback as needed.

[0431] A "warning device" is a device or program that analyzes the emotional state of people within a facility from their facial expressions and voice, and promptly issues an alarm when a suspicious emotional state is detected.

[0432] The invention will now be described in terms of embodiments. This system mainly consists of a server, a terminal, and an emotion engine with emotion recognition capabilities.

[0433] First, the server collects learner information from users and stores it in a database. This information includes learning goals, current ability level, and past learning history. The server analyzes this data to generate an optimal learning plan. Furthermore, the server has an integrated emotion engine that analyzes facial expressions and voice data to identify the user's emotional state.

[0434] Next, the device functions as a user interface, displaying learning plans and other content created on the server. The device receives emotional data in real time from the emotion engine and dynamically adjusts visual and auditory feedback based on this data to help maintain the user's motivation and learning efficiency. For example, if the device determines that the user is tired, it will present lighter learning content or interactive content for refreshment.

[0435] As an example of facility security applications, the devices are used as smartphones or smart glasses to monitor the emotional states of visitors and staff within the facility. This process employs a system that analyzes emotions from facial expressions and voices using an emotion recognition library (e.g., MediaPipe). If a suspicious emotional state is detected, an immediate alert is sent to security personnel, enabling a swift response.

[0436] A concrete example of its use is a scenario where, upon detecting a visitor in a shopping mall who appears anxious, security personnel would check the visitor's surroundings and take necessary action. An example of an input prompt for the generating AI model would be: "Create a program that analyzes a visitor's video and detects signs of tension or anxiety. Based on the analysis results, it should issue an alarm."

[0437] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0438] Step 1:

[0439] The server collects learner information from users. Specifically, it retrieves data such as learning goals, current ability level, and past learning history from a database. Based on this input data, it analyzes the user's learning stage and prepares the basic information necessary to generate appropriate feedback.

[0440] Step 2:

[0441] The server analyzes the collected learner information and generates a learning plan optimized for each user. The input data includes learning goals and ability levels, and by sending this to the analysis engine, it outputs an individually optimized learning plan and proposes the next course of action.

[0442] Step 3:

[0443] The terminal visually displays the learning plan received from the server to the user. Here, an interface is dynamically generated and displayed to make the plan easy to understand and to support user interaction. The output includes a visualization of the plan and a corresponding feedback mechanism.

[0444] Step 4:

[0445] The server uses an emotion engine to analyze the user's emotional state from their facial expressions and voice. It collects the user's emotional data, and through this analysis, outputs data to identify the emotional state in real time, providing foundational information for feedback adjustment. For example, it might use libraries such as MediaPipe.

[0446] Step 5:

[0447] The device dynamically adjusts visual and auditory feedback based on the analyzed emotional state. It receives real-time emotional assessments as input data, and outputs feedback tailored to the user's state, presented as specific actions to facilitate the learning experience.

[0448] Step 6:

[0449] Users progress through their learning based on the provided plan and feedback. They initiate learning activities through the interface and execute the plan while monitoring their progress through voluntary actions. The output is improved efficiency and satisfaction.

[0450] Step 7:

[0451] The server monitors the emotional state within the facility and immediately issues an alarm if an anomaly is detected. It receives emotional data transmitted from terminals as input, analyzes this data using a machine learning model to recognize specific patterns, and determines an alarm signal and corresponding action as output.

[0452] 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.

[0453] 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.

[0454] 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.

[0455] [Third Embodiment]

[0456] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0457] 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.

[0458] 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).

[0459] 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.

[0460] 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.

[0461] 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).

[0462] 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.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] 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".

[0468] The system of the present invention operates on a platform accessible to users via a network. The system mainly consists of a server and user terminals and is equipped with various functions to support user learning. The method of implementing the present invention will be described in detail below.

[0469] Server operation

[0470] The server first collects user information and stores it in a database. This information includes the user's language level, learning history, and individual learning goals. Based on this information, the server uses natural language processing technology to analyze the user's skill level.

[0471] Based on the analysis results, the server generates a learning plan optimized for each user. For example, it selects topics and practice exercises to improve specific language skills. Furthermore, the server sets up a virtual business environment, allowing users to practice their skills in specific scenarios.

[0472] Terminal operation

[0473] The device displays learning plans and exercises sent from the server to the user. Through the interface, users can access content related to language practice and intercultural understanding, and receive real-time feedback from the server. In particular, the pronunciation practice feature provides immediate feedback and correction suggestions via voice input.

[0474] Furthermore, the device supports simulation training within a virtual business environment, allowing users to conduct training that mimics real-world business scenarios. Within this environment, the device observes user behavior and provides immediate feedback to support skill improvement.

[0475] User actions

[0476] Users log in to the system via their device and view their personalized learning dashboard. This dashboard displays their ongoing learning plan and achievement goals, and users proceed with their studies accordingly. At any step, users can send questions to the server via their device, and the server provides a prompt response.

[0477] This allows users to gain a personalized learning experience and efficiently acquire the language skills and cross-cultural understanding required in the international job market.

[0478] Specific example

[0479] For example, if User A wants to improve their English business conversation skills, the server analyzes User A's current English proficiency and generates a learning plan specifically tailored to business conversations. This plan includes specific industry terminology, conversation scenarios, and even practical exercises based on simulations. The user can practice using their device and refine their skills while incorporating feedback from the server.

[0480] By using the system, each user can effectively improve their language and intercultural understanding skills at their own pace, and cultivate the ability to apply those skills in real-world situations.

[0481] The following describes the processing flow.

[0482] Step 1:

[0483] The server collects user information. When a user enters personal learning data through their device, the server receives it and stores it in a database. The collected information includes language level, learning goals, and past learning history.

[0484] Step 2:

[0485] The server uses natural language processing technology to analyze the user's skill level. Based on the collected data, it identifies the user's current proficiency and needs, and evaluates their user level.

[0486] Step 3:

[0487] The server generates an optimized learning plan. Based on the analyzed user data, it selects learning materials and practice problems tailored to individual learning goals and determines the specific learning content.

[0488] Step 4:

[0489] The server sends the generated learning plan to the device. The device then displays a learning dashboard on the user interface, providing the user with the suggested learning schedule and content.

[0490] Step 5:

[0491] The user begins practicing through their device. They access the presented learning content and study language skills exercises and topics related to intercultural understanding. They receive real-time feedback from the server.

[0492] Step 6:

[0493] The device analyzes the user's pronunciation and input. Based on the data collected in real time, it provides feedback on accuracy and areas for improvement, offering specific suggestions and advice to the user.

[0494] Step 7:

[0495] The server creates a virtual business environment. When the user selects simulation training, the server sets up exercises in a virtual business scenario and provides corresponding scenarios and dialogues.

[0496] Step 8:

[0497] Users conduct training in a virtual business environment. They practice negotiations and presentations according to scenarios presented on their devices and receive immediate behavioral feedback.

[0498] Step 9:

[0499] The server collects and analyzes user progress. It uses machine learning algorithms to analyze user activity data and visualizes learning progress based on pre-defined metrics.

[0500] Step 10:

[0501] The device presents the analysis results to the user. Progress and achievement feedback are displayed in visual formats such as graphs and charts to help the user self-evaluate.

[0502] (Example 1)

[0503] 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."

[0504] Traditional learning systems often struggled to provide learning plans optimized for individual learners' abilities and goals, frequently offering only general content and feedback. This made it difficult for learners to efficiently improve their skills. Furthermore, they lacked sufficient real-time support and practical training simulating specific scenarios.

[0505] 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.

[0506] In this invention, the server includes means for collecting user information and analyzing the user's abilities based on said information, means for generating an optimized plan according to the user's goals, and means for providing support and feedback in real time based on the generated plan. This enables the provision of an optimized learning plan for each individual learner, allowing for efficient skill improvement. Furthermore, practical skills can be acquired through simulation training in a virtual environment.

[0507] "Means for collecting information" refers to devices or methods for collecting and storing data provided by users and for understanding the characteristics of users based on that data.

[0508] "Means of analyzing capabilities" refers to methods for processing collected data and evaluating the user's current capabilities and condition.

[0509] "Means for generating plans" refers to methods for creating optimal learning plans and action guidelines for users based on analysis results.

[0510] "Means of providing support and feedback in real time" refers to a device or method that provides functions for immediate guidance, correction, and evaluation in response to the user's activities.

[0511] "Means for conducting simulation training in a virtual environment" refers to a method that reproduces a situation close to reality in a virtual space, enabling users to conduct practical training within that space.

[0512] "Means of evaluating behavior" are methods for observing a user's activities and responses and measuring their abilities and progress based on those observations.

[0513] "Means of generating and providing responses" refers to methods for providing appropriate information and solutions to inquiries from users.

[0514] "Means for analyzing progress and generating visual feedback" refers to a device or method for tracking and analyzing a user's learning progress and displaying the results clearly using diagrams or graphs.

[0515] "Methods for checking pronunciation using voice analysis technology" refer to technologies that analyze voice data and evaluate the accuracy and areas for improvement of the speech.

[0516] "Methods for improving plans using generative AI technology" refer to methods that use machine learning algorithms to generate optimized plans from current data and continuously improve them.

[0517] "Means of supporting skill practice using multiple computing devices" refers to methods of assisting users in improving their practical skills by using multiple devices that provide computing power.

[0518] This invention is a system that operates on a platform accessible to users via a network. The system mainly consists of a server and user terminals and provides a variety of functions to support learning.

[0519] The server collects and stores user information using a database system. The user's language level, learning history, and learning goals are stored in data storage connected to the server. The server analyzes this data using a natural language processing library implemented in Python to assess the user's skill level. Based on this analysis, it generates a learning plan optimized for the learner using natural language processing techniques.

[0520] After generating a learning plan, the server uses generative AI technology to select the most suitable content for each user and configures a virtual environment. Since the virtual environment is built using technologies such as WebGL, users can practice their skills in specific scenarios. Training conducted in an environment that mimics real business scenarios influences user behavior and helps improve skills.

[0521] The device displays learning plans and simulation content sent from the server to the user. Users can access the content and receive real-time feedback through an interface built with React. Specifically, a speech input analysis function using the Google Cloud Speech-to-Text API provides immediate suggestions for correcting the user's pronunciation.

[0522] Furthermore, the terminal supports simulation training, allowing users to perform activities within a virtual business environment. During this process, user activity data is sent to a server and analyzed as needed. The analysis results are then returned to the user as real-time feedback.

[0523] Users can check their current learning progress and achievement goals through a dashboard provided on their device. As they progress according to their learning plan, they can directly ask questions to the server about anything they are unsure of during their studies. This allows for efficient skill improvement through a learning experience tailored to the individual needs of each user.

[0524] For example, if a user wants to improve their business conversation skills, the server analyzes the user's current language proficiency and creates a learning plan specifically tailored to business conversations. This plan includes specific industry terminology, conversation scenarios, and practical exercises based on simulations. Based on this plan, the user can progress through the learning process and refine their skills while receiving feedback from the server.

[0525] An example of a prompt to input into a generative AI model is, "Please provide a specific learning plan for the user to improve their business conversational skills." This allows for the more accurate generation of relevant information and the provision of appropriate responses.

[0526] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0527] Step 1:

[0528] The server receives login information submitted by the user. This input includes the username and password. Using this information, the server accesses the database and authenticates the user. If authentication is successful, the user's past learning history and settings are retrieved from the database. The output includes information such as the user's learning history, learning level, and individual learning goals.

[0529] Step 2:

[0530] The server uses the acquired user information to analyze skill levels using natural language processing techniques. The input is the user's past learning data, and a natural language processing library implemented in Python is used for the analysis. This process identifies the current skill level and areas of weakness. The output is the analyzed skill data.

[0531] Step 3:

[0532] The server generates a learning plan based on the analysis results. The input is the analyzed skill data, and the plan generation process is performed by a generative AI model. This model outputs a plan that includes specific topics, practice problems, and hypothetical scenarios. The final output is a learning plan optimized for the user.

[0533] Step 4:

[0534] The server delivers the generated learning plan to the terminal. The input is the generated learning plan, which the server sends to the terminal using a communication protocol. The terminal displays the received learning plan and waits for user input. The output is the learning plan presented on the user interface.

[0535] Step 5:

[0536] The device provides the functionality to accept voice input in real time and perform speech analysis. The user's voice is treated as input, and the Google Cloud Speech-to-Text API performs the analysis. Based on the analysis results, pronunciation evaluations and areas for improvement are immediately output and presented to the user.

[0537] Step 6:

[0538] The terminal performs simulation training within a virtual environment. Using scenario data sent from the server as input, it generates a virtual business environment using WebGL technology. Evaluation based on user operations and selected actions is performed in real time, and the terminal outputs feedback.

[0539] Step 7:

[0540] The user submits a question about something they've encountered within the system. The input is the user's question, which is transmitted to the server via the terminal. The server uses a database and AI models to generate the best possible response to the question and resends it to the terminal. The output is the answer presented to the user.

[0541] (Application Example 1)

[0542] 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."

[0543] For users to communicate effectively in an international business environment, appropriate cross-cultural communication skills and high language proficiency are required. However, acquiring these skills efficiently in a short period of time is currently difficult. Therefore, there is a need to provide a learning environment in which users can improve their abilities in real time and receive feedback.

[0544] 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.

[0545] In this invention, the server includes means for collecting user learner information and analyzing the user's learning level based on said information; means for generating an optimized learning plan according to the user's learning goals; and means for providing a simulation scenario from the user's perspective in real time and evaluating language ability. This enables users to improve their multicultural communication skills in a real-time simulation environment and refine their language skills through immediate feedback.

[0546] A "user" refers to an individual or organization that uses the system to engage in learning activities according to a learning plan.

[0547] "Learner information" refers to a collection of data that includes the user's language proficiency, learning history, and learning objectives.

[0548] "Analysis means" refers to systems and functions for evaluating a user's current learning level and skills based on collected learner information.

[0549] A "plan generation method" refers to a system or function for creating optimized learning programs and assignments based on the user's learning objectives.

[0550] "Support measures" refer to systems and functions that provide users with the necessary learning content and feedback in real time, according to the generated learning plan.

[0551] "Evaluation means" refers to systems and functions for monitoring and evaluating user activity during simulations conducted in virtual business environments, etc.

[0552] A "response mechanism" refers to a system or function that provides quick answers to questions and inquiries from users.

[0553] A "feedback tool" is a system or function that generates visual feedback and improvement suggestions based on the user's learning progress.

[0554] A "simulation scenario" is a training setting in a virtual environment where users experience specific roles and situations.

[0555] "Language proficiency" refers to a user's ability to understand and communicate appropriately using a specific language.

[0556] The system for realizing this invention mainly consists of a server and terminals. The server collects learner information registered by users and stores it in a database. The server uses natural language processing technology to analyze the user's learning level from this information. Based on the analysis results, the server generates an optimized learning plan for each user. This plan includes topics and tasks for improving language proficiency.

[0557] The terminal displays learning plans and exercises sent from the server to the user. The application running on the terminal allows the user to access content related to language practice and cross-cultural understanding, and can receive real-time feedback from the server. In particular, for pronunciation practice, it uses a voice input function to immediately provide the user with corrections and suggestions.

[0558] Furthermore, the device supports simulation training in a virtual business environment. Users experience scenarios in a virtual environment and their language skills are evaluated. Real-time simulation scenarios are presented from the user's perspective using wearable devices such as smart glasses. User behavior data is collected, and immediate feedback is provided through evaluation tools.

[0559] For example, if a user requests training to facilitate smooth conversation at an international conference, the server analyzes the user's current language proficiency and provides a customized business conversation simulation based on the results. This simulation is performed in real time on the terminal, allowing the user to receive immediate feedback.

[0560] An example of a prompt incorporating a generative AI model is: "In the following scenario, explain security to an English-speaking customer. Use appropriate terminology and be careful not to cause misunderstandings." The goal of following this prompt is for users to acquire the skills to confidently respond in real-world situations.

[0561] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0562] Step 1:

[0563] The server collects and stores learner information registered by users in a database. This learner information includes the user's language proficiency, learning history, and goals. The input is new user information, and the output is the information stored in the database. At this stage, data processing is performed to appropriately organize the information and prepare it for subsequent analysis.

[0564] Step 2:

[0565] The server analyzes the collected learner information using natural language processing technology to evaluate the user's learning level. The input is the user information stored in step 1, and the output is the evaluation result of the learning level based on that information. In this process, an analysis algorithm is used to perform data calculations, and the learning level is calculated as a numerical value or indicator.

[0566] Step 3:

[0567] The server generates an optimized learning plan based on the user's learning goals and analyzed learning level. The input is the analysis results and learning goals, and the output is a individually customized learning plan. This uses a generative AI model, which generates creative learning scenarios and tasks based on prompts.

[0568] Step 4:

[0569] The terminal receives the learning plan and exercise content sent from the server and presents it to the user. The input is the learning plan from the server, and the output is the learning content displayed on the user interface. The terminal visualizes this data and provides it to the user in an intuitively easy-to-understand format.

[0570] Step 5:

[0571] Users conduct simulation training in a virtual business environment using a terminal. The input is a virtual situation presented as a scenario, and the output is user behavior data. Users practice their skills through the simulation, and a generated AI model operates during this process, providing real-time feedback.

[0572] Step 6:

[0573] The server analyzes user behavior data during the simulation, generates immediate feedback, and sends it to the terminal. The input is user behavior data, and the output is feedback information. This feedback evaluates the user's actions and points out shortcomings and areas for improvement in detail. This allows users to receive specific guidance to enhance their ability to apply the concepts in real-world environments.

[0574] 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.

[0575] This invention relates to a learning support system that incorporates an emotion engine that recognizes the user's emotional state and dynamically adjusts the learning plan and feedback accordingly. This system is accessible to users via a network and mainly consists of a server, a user terminal, and the emotion engine.

[0576] Server operation

[0577] The server first collects the user's learner information and stores it in a database. This information includes learning goals, current skill level, and past learning history. Based on this information, the server analyzes the user's learning level and generates an optimal learning plan.

[0578] Furthermore, this system incorporates an emotion engine, and the server analyzes the user's emotional data obtained from the emotion engine. By adjusting the learning plan and feedback content in real time according to the emotional state, the system improves the user's learning experience.

[0579] Terminal operation

[0580] The terminal functions as a user interface, displaying learning plans and other content provided by the server. Through the terminal, users can access learning content and perform practice exercises and simulation training.

[0581] The emotion engine analyzes the user's facial expressions and voice, and transmits their emotional state to the device in real time. Based on this emotional data, the device dynamically adjusts visual and auditory feedback to provide optimal support for maintaining motivation.

[0582] User actions

[0583] Users log in using their devices and operate the learning dashboard. Analysis results from the emotion engine are provided as feedback, allowing them to monitor their own emotional state and learn according to a plan tailored to their learning progress.

[0584] Specifically, for example, if the emotion engine determines that a user is in a "fatigued" state, the server will temporarily reduce the learning plan and provide content that encourages refreshment. Similarly, if a "high-stress" state is detected, the device will attempt to reduce stress through appropriate relaxation music and interactive feedback.

[0585] This system is expected to appropriately reflect user emotions in the learning process, significantly improving overall learning effectiveness and user satisfaction.

[0586] The following describes the processing flow.

[0587] Step 1:

[0588] The user logs into the system via their device. The device obtains the user's authentication information and sends it to the server. Based on this information, the server authenticates the user.

[0589] Step 2:

[0590] The server generates an appropriate learning plan based on the user's learner information. The server refers to past learning history and learning goals to determine individually customized learning content.

[0591] Step 3:

[0592] The device displays the generated learning plan to the user. The user accesses the provided content and starts the selected learning module.

[0593] Step 4:

[0594] The emotion engine uses the user's facial recognition and voice analysis capabilities to evaluate the user's emotional state in real time.

[0595] Step 5:

[0596] The emotion engine sends the collected emotion data to the server. The server receives this data and incorporates adjustments to the learning plan based on the user's emotional state.

[0597] Step 6:

[0598] The server adjusts learning content or methods based on emotional data. For example, if a user is detected as fatigued, the server may lower the difficulty of the task or recommend content that encourages breaks.

[0599] Step 7:

[0600] The device updates its display content and feedback in real time, providing visual and auditory support to maintain user motivation.

[0601] Step 8:

[0602] Users continue learning while receiving feedback. If their emotional state improves, they can return to more challenging content.

[0603] Step 9:

[0604] The server continuously monitors the user's learning progress and analyzes the data using machine learning algorithms. This allows for improvements to future learning plans.

[0605] Step 10:

[0606] The device provides users with visual feedback on their progress and achievements. This allows users to understand their learning status and further increase their motivation to learn.

[0607] (Example 2)

[0608] 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."

[0609] There is a need to provide effective learning plans and feedback tailored to the individual needs and emotional states of learners to maximize learning effectiveness, but current systems struggle to do this in real time. Furthermore, there is a lack of flexible educational support platforms that can dynamically adjust learning content based on learners' emotional states and progress.

[0610] 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.

[0611] In this invention, the server includes an analysis means for collecting user attribute data and analyzing the user's level of understanding based on said data; a content generation means for generating personalized educational content based on the user's goals; and an adjustment means for analyzing the user's emotional state and dynamically adjusting the educational content and feedback according to that state. This makes it possible to provide an optimal learning experience tailored to the individual circumstances of each learner in real time.

[0612] "Attribute data" refers to information about the user, including learning goals, level of understanding, and emotional state.

[0613] "Comprehension level" is an indicator that shows how accurately users understand the learning material.

[0614] "Personalized educational content" refers to learning materials and curricula that are optimized based on each user's individual learning needs and level of understanding.

[0615] "Emotional state" refers to information that indicates the user's psychological state, and includes, for example, fatigue, excitement, and the presence or absence of concentration.

[0616] "Analysis means" refers to methods and technologies that allow a server to analyze user attribute data and determine an appropriate learning plan.

[0617] "Content generation methods" refer to technologies and methods for creating optimal educational content based on the user's learning objectives and level of understanding.

[0618] "Adjustment means" refers to methods or technologies for dynamically changing educational content and feedback based on the user's real-time emotional state.

[0619] This invention is designed as a learning support system to improve the user's learning experience. The system mainly consists of a server, terminals, and an emotion analysis engine, and each component works in cooperation with the others.

[0620] The server first collects user attribute data when a user accesses the learning platform. This data includes learning goals, current skill level, past learning history, and even real-time emotional state. Using this information, the server employs AI algorithms to generate personalized educational content for each user. The educational content is customized according to the user's goals and skills. Specifically, an AI module using a neural network is used for emotion analysis.

[0621] The device acts as a user interface, displaying educational content provided by the server. Users learn through the device, and their state is monitored by an emotion analysis engine. The device uses a camera and microphone to collect the user's facial expressions and voice, which the emotion analysis engine analyzes in real time. For example, if the user is feeling fatigued, the device will play relaxing music, and the server will temporarily reduce the learning load.

[0622] Furthermore, the system utilizes generative AI models to continuously improve educational content based on learning progress and user feedback. This process incorporates a function that analyzes each user's behavioral data and automatically updates the plan.

[0623] For example, a prompt might say, "Please suggest the type of feedback to provide if the user is determined to be in a high-stress state." Based on this prompt, the AI ​​formulates appropriate feedback for the user.

[0624] In this way, the present invention can provide optimal learning support tailored to the user's emotional state and individual learning needs.

[0625] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0626] Step 1:

[0627] The server collects user attribute data when a user logs into the learning platform. Input includes the user's learning goals, skill level, and past learning history. This data is used to construct a user profile and store it in a database. Specifically, it performs queries on the database and stores the user information.

[0628] Step 2:

[0629] The server analyzes collected attribute data and generates optimized educational content using AI algorithms. It utilizes user profile information as input and processes the data using a generation AI model. This results in the creation of user-specific curricula and learning plans. Specifically, the content generation engine calculates a new plan based on the AI ​​model's training data.

[0630] Step 3:

[0631] The terminal displays educational content provided by the server to the user. It receives educational content data from the server as input and presents learning materials and practice problems on the screen as output. Specifically, it visually formats the content via the user interface and displays it in a user-accessible format.

[0632] Step 4:

[0633] The device uses its camera and microphone to transmit the user's facial expressions and voice to an emotion analysis engine. It takes in voice and image data as input, performs data calculations using AI, and outputs an assessment of the user's emotional state. Specifically, it uses voice recognition software to convert voice data into text and image processing algorithms to identify emotions from facial expressions.

[0634] Step 5:

[0635] The server receives output data from the emotion analysis engine and dynamically adjusts the learning plan and feedback. It uses user emotion state data as input and updates the learning plan using a content adjustment algorithm. The output obtained here is the adjusted learning materials and new feedback. Specifically, it modifies the learning plan in real time, making adjustments based on the user.

[0636] Step 6:

[0637] Users use their devices to actually learn from the provided, pre-adjusted educational content. They receive the adjusted content as input and obtain their own learning progress and skill improvement as output. Specifically, they perform self-assessments by answering practice problems and completing simulations, and record their progress.

[0638] (Application Example 2)

[0639] 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."

[0640] Improving safety within facilities requires a rapid response to unexpected behaviors and conditions of visitors and staff. In particular, detecting changes in emotions and anticipating a deterioration of the situation is crucial for safety management. However, current systems lack the means to capture such changes in emotional states in real time and respond quickly.

[0641] 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.

[0642] In this invention, the server includes means for collecting user learner information and analyzing the user's learning stage based on said information; means for generating an optimized learning plan according to the user's learning goals; means for providing learning support and feedback in real time based on the generated learning plan; and warning means for analyzing the emotional state of people in the facility through facial expressions and voice and issuing an alarm when a suspicious emotional state is detected. This makes it possible to improve safety within the facility by monitoring the emotional state of users and people in the facility in real time and issuing appropriate alarms.

[0643] "Learner information" refers to data that includes the user's learning goals, progress, and past history.

[0644] "Analysis means" refers to a device or program that has the function of analyzing collected data and identifying the user's learning stage and the support they need.

[0645] A "plan generation means" is a device or program that automatically creates an optimal learning plan based on the user's learning objectives.

[0646] A "support system" is a system that supports the progress of learning according to the plan and provides real-time feedback as needed.

[0647] A "warning device" is a device or program that analyzes the emotional state of people within a facility from their facial expressions and voice, and promptly issues an alarm when a suspicious emotional state is detected.

[0648] The invention will now be described in terms of embodiments. This system mainly consists of a server, a terminal, and an emotion engine with emotion recognition capabilities.

[0649] First, the server collects learner information from users and stores it in a database. This information includes learning goals, current ability level, and past learning history. The server analyzes this data to generate an optimal learning plan. Furthermore, the server has an integrated emotion engine that analyzes facial expressions and voice data to identify the user's emotional state.

[0650] Next, the device functions as a user interface, displaying learning plans and other content created on the server. The device receives emotional data in real time from the emotion engine and dynamically adjusts visual and auditory feedback based on this data to help maintain the user's motivation and learning efficiency. For example, if the device determines that the user is tired, it will present lighter learning content or interactive content for refreshment.

[0651] As an example of facility security applications, the devices are used as smartphones or smart glasses to monitor the emotional states of visitors and staff within the facility. This process employs a system that analyzes emotions from facial expressions and voices using an emotion recognition library (e.g., MediaPipe). If a suspicious emotional state is detected, an immediate alert is sent to security personnel, enabling a swift response.

[0652] A concrete example of its use is a scenario where, upon detecting a visitor in a shopping mall who appears anxious, security personnel would check the visitor's surroundings and take necessary action. An example of an input prompt for the generating AI model would be: "Create a program that analyzes a visitor's video and detects signs of tension or anxiety. Based on the analysis results, it should issue an alarm."

[0653] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0654] Step 1:

[0655] The server collects learner information from users. Specifically, it retrieves data such as learning goals, current ability level, and past learning history from a database. Based on this input data, it analyzes the user's learning stage and prepares the basic information necessary to generate appropriate feedback.

[0656] Step 2:

[0657] The server analyzes the collected learner information and generates a learning plan optimized for each user. The input data includes learning goals and ability levels, and by sending this to the analysis engine, it outputs an individually optimized learning plan and proposes the next course of action.

[0658] Step 3:

[0659] The terminal visually displays the learning plan received from the server to the user. Here, an interface is dynamically generated and displayed to make the plan easy to understand and to support user interaction. The output includes a visualization of the plan and a corresponding feedback mechanism.

[0660] Step 4:

[0661] The server uses an emotion engine to analyze the user's emotional state from their facial expressions and voice. It collects the user's emotional data, and through this analysis, outputs data to identify the emotional state in real time, providing foundational information for feedback adjustment. For example, it might use libraries such as MediaPipe.

[0662] Step 5:

[0663] The device dynamically adjusts visual and auditory feedback based on the analyzed emotional state. It receives real-time emotional assessments as input data, and outputs feedback tailored to the user's state, presented as specific actions to facilitate the learning experience.

[0664] Step 6:

[0665] Users progress through their learning based on the provided plan and feedback. They initiate learning activities through the interface and execute the plan while monitoring their progress through voluntary actions. The output is improved efficiency and satisfaction.

[0666] Step 7:

[0667] The server monitors the emotional state within the facility and immediately issues an alarm if an anomaly is detected. It receives emotional data transmitted from terminals as input, analyzes this data using a machine learning model to recognize specific patterns, and determines an alarm signal and corresponding action as output.

[0668] 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.

[0669] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An 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.

[0670] 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.

[0671] [Fourth Embodiment]

[0672] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0673] 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.

[0674] 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).

[0675] 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.

[0676] 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.

[0677] 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).

[0678] 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.

[0679] 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.

[0680] 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.

[0681] 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.

[0682] 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.

[0683] 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.

[0684] 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".

[0685] The system of the present invention operates on a platform accessible to users via a network. The system mainly consists of a server and user terminals and is equipped with various functions to support user learning. The method of implementing the present invention will be described in detail below.

[0686] Server operation

[0687] The server first collects user information and stores it in a database. This information includes the user's language level, learning history, and individual learning goals. Based on this information, the server uses natural language processing technology to analyze the user's skill level.

[0688] Based on the analysis results, the server generates a learning plan optimized for each user. For example, it selects topics and practice exercises to improve specific language skills. Furthermore, the server sets up a virtual business environment, allowing users to practice their skills in specific scenarios.

[0689] Terminal operation

[0690] The device displays learning plans and exercises sent from the server to the user. Through the interface, users can access content related to language practice and intercultural understanding, and receive real-time feedback from the server. In particular, the pronunciation practice feature provides immediate feedback and correction suggestions via voice input.

[0691] Furthermore, the device supports simulation training within a virtual business environment, allowing users to conduct training that mimics real-world business scenarios. Within this environment, the device observes user behavior and provides immediate feedback to support skill improvement.

[0692] User actions

[0693] Users log in to the system via their device and view their personalized learning dashboard. This dashboard displays their ongoing learning plan and achievement goals, and users proceed with their studies accordingly. At any step, users can send questions to the server via their device, and the server provides a prompt response.

[0694] This allows users to gain a personalized learning experience and efficiently acquire the language skills and cross-cultural understanding required in the international job market.

[0695] Specific example

[0696] For example, if User A wants to improve their English business conversation skills, the server analyzes User A's current English proficiency and generates a learning plan specifically tailored to business conversations. This plan includes specific industry terminology, conversation scenarios, and even practical exercises based on simulations. The user can practice using their device and refine their skills while incorporating feedback from the server.

[0697] By using the system, each user can effectively improve their language and intercultural understanding skills at their own pace, and cultivate the ability to apply those skills in real-world situations.

[0698] The following describes the processing flow.

[0699] Step 1:

[0700] The server collects user information. When a user enters personal learning data through their device, the server receives it and stores it in a database. The collected information includes language level, learning goals, and past learning history.

[0701] Step 2:

[0702] The server uses natural language processing technology to analyze the user's skill level. Based on the collected data, it identifies the user's current proficiency and needs, and evaluates their user level.

[0703] Step 3:

[0704] The server generates an optimized learning plan. Based on the analyzed user data, it selects learning materials and practice problems tailored to individual learning goals and determines the specific learning content.

[0705] Step 4:

[0706] The server sends the generated learning plan to the device. The device then displays a learning dashboard on the user interface, providing the user with the suggested learning schedule and content.

[0707] Step 5:

[0708] The user begins practicing through their device. They access the presented learning content and study language skills exercises and topics related to intercultural understanding. They receive real-time feedback from the server.

[0709] Step 6:

[0710] The device analyzes the user's pronunciation and input. Based on the data collected in real time, it provides feedback on accuracy and areas for improvement, offering specific suggestions and advice to the user.

[0711] Step 7:

[0712] The server creates a virtual business environment. When the user selects simulation training, the server sets up exercises in a virtual business scenario and provides corresponding scenarios and dialogues.

[0713] Step 8:

[0714] Users conduct training in a virtual business environment. They practice negotiations and presentations according to scenarios presented on their devices and receive immediate behavioral feedback.

[0715] Step 9:

[0716] The server collects and analyzes user progress. It uses machine learning algorithms to analyze user activity data and visualizes learning progress based on pre-defined metrics.

[0717] Step 10:

[0718] The device presents the analysis results to the user. Progress and achievement feedback are displayed in visual formats such as graphs and charts to help the user self-evaluate.

[0719] (Example 1)

[0720] 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".

[0721] Traditional learning systems often struggled to provide learning plans optimized for individual learners' abilities and goals, frequently offering only general content and feedback. This made it difficult for learners to efficiently improve their skills. Furthermore, they lacked sufficient real-time support and practical training simulating specific scenarios.

[0722] 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.

[0723] In this invention, the server includes means for collecting user information and analyzing the user's abilities based on said information, means for generating an optimized plan according to the user's goals, and means for providing support and feedback in real time based on the generated plan. This enables the provision of an optimized learning plan for each individual learner, allowing for efficient skill improvement. Furthermore, practical skills can be acquired through simulation training in a virtual environment.

[0724] "Means for collecting information" refers to devices or methods for collecting and storing data provided by users and for understanding the characteristics of users based on that data.

[0725] "Means of analyzing capabilities" refers to methods for processing collected data and evaluating the user's current capabilities and condition.

[0726] "Means for generating plans" refers to methods for creating optimal learning plans and action guidelines for users based on analysis results.

[0727] "Means of providing support and feedback in real time" refers to a device or method that provides functions for immediate guidance, correction, and evaluation in response to the user's activities.

[0728] "Means for conducting simulation training in a virtual environment" refers to a method that reproduces a situation close to reality in a virtual space, enabling users to conduct practical training within that space.

[0729] "Means of evaluating behavior" are methods for observing a user's activities and responses and measuring their abilities and progress based on those observations.

[0730] "Means of generating and providing responses" refers to methods for providing appropriate information and solutions to inquiries from users.

[0731] "Means for analyzing progress and generating visual feedback" refers to a device or method for tracking and analyzing a user's learning progress and displaying the results clearly using diagrams or graphs.

[0732] "Methods for checking pronunciation using voice analysis technology" refer to technologies that analyze voice data and evaluate the accuracy and areas for improvement of the speech.

[0733] "Methods for improving plans using generative AI technology" refer to methods that use machine learning algorithms to generate optimized plans from current data and continuously improve them.

[0734] "Means of supporting skill practice using multiple computing devices" refers to methods of assisting users in improving their practical skills by using multiple devices that provide computing power.

[0735] This invention is a system that operates on a platform accessible to users via a network. The system mainly consists of a server and user terminals and provides a variety of functions to support learning.

[0736] The server collects and stores user information using a database system. The user's language level, learning history, and learning goals are stored in data storage connected to the server. The server analyzes this data using a natural language processing library implemented in Python to assess the user's skill level. Based on this analysis, it generates a learning plan optimized for the learner using natural language processing techniques.

[0737] After generating a learning plan, the server uses generative AI technology to select the most suitable content for each user and configures a virtual environment. Since the virtual environment is built using technologies such as WebGL, users can practice their skills in specific scenarios. Training conducted in an environment that mimics real business scenarios influences user behavior and helps improve skills.

[0738] The device displays learning plans and simulation content sent from the server to the user. Users can access the content and receive real-time feedback through an interface built with React. Specifically, a speech input analysis function using the Google Cloud Speech-to-Text API provides immediate suggestions for correcting the user's pronunciation.

[0739] Furthermore, the terminal supports simulation training, allowing users to perform activities within a virtual business environment. During this process, user activity data is sent to a server and analyzed as needed. The analysis results are then returned to the user as real-time feedback.

[0740] Users can check their current learning progress and achievement goals through a dashboard provided on their device. As they progress according to their learning plan, they can directly ask questions to the server about anything they are unsure of during their studies. This allows for efficient skill improvement through a learning experience tailored to the individual needs of each user.

[0741] For example, if a user wants to improve their business conversation skills, the server analyzes the user's current language proficiency and creates a learning plan specifically tailored to business conversations. This plan includes specific industry terminology, conversation scenarios, and practical exercises based on simulations. Based on this plan, the user can progress through the learning process and refine their skills while receiving feedback from the server.

[0742] An example of a prompt to input into a generative AI model is, "Please provide a specific learning plan for the user to improve their business conversational skills." This allows for the more accurate generation of relevant information and the provision of appropriate responses.

[0743] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0744] Step 1:

[0745] The server receives login information submitted by the user. This input includes the username and password. Using this information, the server accesses the database and authenticates the user. If authentication is successful, the user's past learning history and settings are retrieved from the database. The output includes information such as the user's learning history, learning level, and individual learning goals.

[0746] Step 2:

[0747] The server uses the acquired user information to analyze skill levels using natural language processing techniques. The input is the user's past learning data, and a natural language processing library implemented in Python is used for the analysis. This process identifies the current skill level and areas of weakness. The output is the analyzed skill data.

[0748] Step 3:

[0749] The server generates a learning plan based on the analysis results. The input is the analyzed skill data, and the plan generation process is performed by a generative AI model. This model outputs a plan that includes specific topics, practice problems, and hypothetical scenarios. The final output is a learning plan optimized for the user.

[0750] Step 4:

[0751] The server delivers the generated learning plan to the terminal. The input is the generated learning plan, which the server sends to the terminal using a communication protocol. The terminal displays the received learning plan and waits for user input. The output is the learning plan presented on the user interface.

[0752] Step 5:

[0753] The device provides the functionality to accept voice input in real time and perform speech analysis. The user's voice is treated as input, and the Google Cloud Speech-to-Text API performs the analysis. Based on the analysis results, pronunciation evaluations and areas for improvement are immediately output and presented to the user.

[0754] Step 6:

[0755] The terminal performs simulation training within a virtual environment. Using scenario data sent from the server as input, it generates a virtual business environment using WebGL technology. Evaluation based on user operations and selected actions is performed in real time, and the terminal outputs feedback.

[0756] Step 7:

[0757] The user submits a question about something they've encountered within the system. The input is the user's question, which is transmitted to the server via the terminal. The server uses a database and AI models to generate the best possible response to the question and resends it to the terminal. The output is the answer presented to the user.

[0758] (Application Example 1)

[0759] 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".

[0760] For users to communicate effectively in an international business environment, appropriate cross-cultural communication skills and high language proficiency are required. However, acquiring these skills efficiently in a short period of time is currently difficult. Therefore, there is a need to provide a learning environment in which users can improve their abilities in real time and receive feedback.

[0761] 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.

[0762] In this invention, the server includes means for collecting user learner information and analyzing the user's learning level based on said information; means for generating an optimized learning plan according to the user's learning goals; and means for providing a simulation scenario from the user's perspective in real time and evaluating language ability. This enables users to improve their multicultural communication skills in a real-time simulation environment and refine their language skills through immediate feedback.

[0763] A "user" refers to an individual or organization that uses the system to engage in learning activities according to a learning plan.

[0764] "Learner information" refers to a collection of data that includes the user's language proficiency, learning history, and learning objectives.

[0765] "Analysis means" refers to systems and functions for evaluating a user's current learning level and skills based on collected learner information.

[0766] A "plan generation method" refers to a system or function for creating optimized learning programs and assignments based on the user's learning objectives.

[0767] "Support measures" refer to systems and functions that provide users with the necessary learning content and feedback in real time, according to the generated learning plan.

[0768] "Evaluation means" refers to systems and functions for monitoring and evaluating user activity during simulations conducted in virtual business environments, etc.

[0769] A "response mechanism" refers to a system or function that provides quick answers to questions and inquiries from users.

[0770] A "feedback tool" is a system or function that generates visual feedback and improvement suggestions based on the user's learning progress.

[0771] A "simulation scenario" is a training setting in a virtual environment where users experience specific roles and situations.

[0772] "Language proficiency" refers to a user's ability to understand and communicate appropriately using a specific language.

[0773] The system for realizing this invention mainly consists of a server and terminals. The server collects learner information registered by users and stores it in a database. The server uses natural language processing technology to analyze the user's learning level from this information. Based on the analysis results, the server generates an optimized learning plan for each user. This plan includes topics and tasks for improving language proficiency.

[0774] The terminal displays learning plans and exercises sent from the server to the user. The application running on the terminal allows the user to access content related to language practice and cross-cultural understanding, and can receive real-time feedback from the server. In particular, for pronunciation practice, it uses a voice input function to immediately provide the user with corrections and suggestions.

[0775] Furthermore, the device supports simulation training in a virtual business environment. Users experience scenarios in a virtual environment and their language skills are evaluated. Real-time simulation scenarios are presented from the user's perspective using wearable devices such as smart glasses. User behavior data is collected, and immediate feedback is provided through evaluation tools.

[0776] For example, if a user requests training to facilitate smooth conversation at an international conference, the server analyzes the user's current language proficiency and provides a customized business conversation simulation based on the results. This simulation is performed in real time on the terminal, allowing the user to receive immediate feedback.

[0777] An example of a prompt incorporating a generative AI model is: "In the following scenario, explain security to an English-speaking customer. Use appropriate terminology and be careful not to cause misunderstandings." The goal of following this prompt is for users to acquire the skills to confidently respond in real-world situations.

[0778] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0779] Step 1:

[0780] The server collects and stores learner information registered by users in a database. This learner information includes the user's language proficiency, learning history, and goals. The input is new user information, and the output is the information stored in the database. At this stage, data processing is performed to appropriately organize the information and prepare it for subsequent analysis.

[0781] Step 2:

[0782] The server analyzes the collected learner information using natural language processing technology to evaluate the user's learning level. The input is the user information stored in step 1, and the output is the evaluation result of the learning level based on that information. In this process, an analysis algorithm is used to perform data calculations, and the learning level is calculated as a numerical value or indicator.

[0783] Step 3:

[0784] The server generates an optimized learning plan based on the user's learning goals and analyzed learning level. The input is the analysis results and learning goals, and the output is a individually customized learning plan. This uses a generative AI model, which generates creative learning scenarios and tasks based on prompts.

[0785] Step 4:

[0786] The terminal receives the learning plan and exercise content sent from the server and presents it to the user. The input is the learning plan from the server, and the output is the learning content displayed on the user interface. The terminal visualizes this data and provides it to the user in an intuitively easy-to-understand format.

[0787] Step 5:

[0788] Users conduct simulation training in a virtual business environment using a terminal. The input is a virtual situation presented as a scenario, and the output is user behavior data. Users practice their skills through the simulation, and a generated AI model operates during this process, providing real-time feedback.

[0789] Step 6:

[0790] The server analyzes user behavior data during the simulation, generates immediate feedback, and sends it to the terminal. The input is user behavior data, and the output is feedback information. This feedback evaluates the user's actions and points out shortcomings and areas for improvement in detail. This allows users to receive specific guidance to enhance their ability to apply the concepts in real-world environments.

[0791] 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.

[0792] This invention relates to a learning support system that incorporates an emotion engine that recognizes the user's emotional state and dynamically adjusts the learning plan and feedback accordingly. This system is accessible to users via a network and mainly consists of a server, a user terminal, and the emotion engine.

[0793] Server operation

[0794] The server first collects the user's learner information and stores it in a database. This information includes learning goals, current skill level, and past learning history. Based on this information, the server analyzes the user's learning level and generates an optimal learning plan.

[0795] Furthermore, this system incorporates an emotion engine, and the server analyzes the user's emotional data obtained from the emotion engine. By adjusting the learning plan and feedback content in real time according to the emotional state, the system improves the user's learning experience.

[0796] Terminal operation

[0797] The terminal functions as a user interface, displaying learning plans and other content provided by the server. Through the terminal, users can access learning content and perform practice exercises and simulation training.

[0798] The emotion engine analyzes the user's facial expressions and voice, and transmits their emotional state to the device in real time. Based on this emotional data, the device dynamically adjusts visual and auditory feedback to provide optimal support for maintaining motivation.

[0799] User actions

[0800] Users log in using their devices and operate the learning dashboard. Analysis results from the emotion engine are provided as feedback, allowing them to monitor their own emotional state and learn according to a plan tailored to their learning progress.

[0801] Specifically, for example, if the emotion engine determines that a user is in a "fatigued" state, the server will temporarily reduce the learning plan and provide content that encourages refreshment. Similarly, if a "high-stress" state is detected, the device will attempt to reduce stress through appropriate relaxation music and interactive feedback.

[0802] This system is expected to appropriately reflect user emotions in the learning process, significantly improving overall learning effectiveness and user satisfaction.

[0803] The following describes the processing flow.

[0804] Step 1:

[0805] The user logs into the system via their device. The device obtains the user's authentication information and sends it to the server. Based on this information, the server authenticates the user.

[0806] Step 2:

[0807] The server generates an appropriate learning plan based on the user's learner information. The server refers to past learning history and learning goals to determine individually customized learning content.

[0808] Step 3:

[0809] The device displays the generated learning plan to the user. The user accesses the provided content and starts the selected learning module.

[0810] Step 4:

[0811] The emotion engine uses the user's facial recognition and voice analysis capabilities to evaluate the user's emotional state in real time.

[0812] Step 5:

[0813] The emotion engine sends the collected emotion data to the server. The server receives this data and incorporates adjustments to the learning plan based on the user's emotional state.

[0814] Step 6:

[0815] The server adjusts learning content or methods based on emotional data. For example, if a user is detected as fatigued, the server may lower the difficulty of the task or recommend content that encourages breaks.

[0816] Step 7:

[0817] The device updates its display content and feedback in real time, providing visual and auditory support to maintain user motivation.

[0818] Step 8:

[0819] Users continue learning while receiving feedback. If their emotional state improves, they can return to more challenging content.

[0820] Step 9:

[0821] The server continuously monitors the user's learning progress and analyzes the data using machine learning algorithms. This allows for improvements to future learning plans.

[0822] Step 10:

[0823] The device provides users with visual feedback on their progress and achievements. This allows users to understand their learning status and further increase their motivation to learn.

[0824] (Example 2)

[0825] 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".

[0826] There is a need to provide effective learning plans and feedback tailored to the individual needs and emotional states of learners to maximize learning effectiveness, but current systems struggle to do this in real time. Furthermore, there is a lack of flexible educational support platforms that can dynamically adjust learning content based on learners' emotional states and progress.

[0827] 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.

[0828] In this invention, the server includes an analysis means for collecting user attribute data and analyzing the user's level of understanding based on said data; a content generation means for generating personalized educational content based on the user's goals; and an adjustment means for analyzing the user's emotional state and dynamically adjusting the educational content and feedback according to that state. This makes it possible to provide an optimal learning experience tailored to the individual circumstances of each learner in real time.

[0829] "Attribute data" refers to information about the user, including learning goals, level of understanding, and emotional state.

[0830] "Comprehension level" is an indicator that shows how accurately users understand the learning material.

[0831] "Personalized educational content" refers to learning materials and curricula that are optimized based on each user's individual learning needs and level of understanding.

[0832] "Emotional state" refers to information that indicates the user's psychological state, and includes, for example, fatigue, excitement, and the presence or absence of concentration.

[0833] "Analysis means" refers to methods and technologies that allow a server to analyze user attribute data and determine an appropriate learning plan.

[0834] "Content generation methods" refer to technologies and methods for creating optimal educational content based on the user's learning objectives and level of understanding.

[0835] "Adjustment means" refers to methods or technologies for dynamically changing educational content and feedback based on the user's real-time emotional state.

[0836] This invention is designed as a learning support system to improve the user's learning experience. The system mainly consists of a server, terminals, and an emotion analysis engine, and each component works in cooperation with the others.

[0837] The server first collects user attribute data when a user accesses the learning platform. This data includes learning goals, current skill level, past learning history, and even real-time emotional state. Using this information, the server employs AI algorithms to generate personalized educational content for each user. The educational content is customized according to the user's goals and skills. Specifically, an AI module using a neural network is used for emotion analysis.

[0838] The device acts as a user interface, displaying educational content provided by the server. Users learn through the device, and their state is monitored by an emotion analysis engine. The device uses a camera and microphone to collect the user's facial expressions and voice, which the emotion analysis engine analyzes in real time. For example, if the user is feeling fatigued, the device will play relaxing music, and the server will temporarily reduce the learning load.

[0839] Furthermore, the system utilizes generative AI models to continuously improve educational content based on learning progress and user feedback. This process incorporates a function that analyzes each user's behavioral data and automatically updates the plan.

[0840] For example, a prompt might say, "Please suggest the type of feedback to provide if the user is determined to be in a high-stress state." Based on this prompt, the AI ​​formulates appropriate feedback for the user.

[0841] In this way, the present invention can provide optimal learning support tailored to the user's emotional state and individual learning needs.

[0842] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0843] Step 1:

[0844] The server collects user attribute data when a user logs into the learning platform. Input includes the user's learning goals, skill level, and past learning history. This data is used to construct a user profile and store it in a database. Specifically, it performs queries on the database and stores the user information.

[0845] Step 2:

[0846] The server analyzes collected attribute data and generates optimized educational content using AI algorithms. It utilizes user profile information as input and processes the data using a generation AI model. This results in the creation of user-specific curricula and learning plans. Specifically, the content generation engine calculates a new plan based on the AI ​​model's training data.

[0847] Step 3:

[0848] The terminal displays educational content provided by the server to the user. It receives educational content data from the server as input and presents learning materials and practice problems on the screen as output. Specifically, it visually formats the content via the user interface and displays it in a user-accessible format.

[0849] Step 4:

[0850] The device uses its camera and microphone to transmit the user's facial expressions and voice to an emotion analysis engine. It takes in voice and image data as input, performs data calculations using AI, and outputs an assessment of the user's emotional state. Specifically, it uses voice recognition software to convert voice data into text and image processing algorithms to identify emotions from facial expressions.

[0851] Step 5:

[0852] The server receives output data from the emotion analysis engine and dynamically adjusts the learning plan and feedback. It uses user emotion state data as input and updates the learning plan using a content adjustment algorithm. The output obtained here is the adjusted learning materials and new feedback. Specifically, it modifies the learning plan in real time, making adjustments based on the user.

[0853] Step 6:

[0854] Users use their devices to actually learn from the provided, pre-adjusted educational content. They receive the adjusted content as input and obtain their own learning progress and skill improvement as output. Specifically, they perform self-assessments by answering practice problems and completing simulations, and record their progress.

[0855] (Application Example 2)

[0856] 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".

[0857] Improving safety within facilities requires a rapid response to unexpected behaviors and conditions of visitors and staff. In particular, detecting changes in emotions and anticipating a deterioration of the situation is crucial for safety management. However, current systems lack the means to capture such changes in emotional states in real time and respond quickly.

[0858] 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.

[0859] In this invention, the server includes means for collecting user learner information and analyzing the user's learning stage based on said information; means for generating an optimized learning plan according to the user's learning goals; means for providing learning support and feedback in real time based on the generated learning plan; and warning means for analyzing the emotional state of people in the facility through facial expressions and voice and issuing an alarm when a suspicious emotional state is detected. This makes it possible to improve safety within the facility by monitoring the emotional state of users and people in the facility in real time and issuing appropriate alarms.

[0860] "Learner information" refers to data that includes the user's learning goals, progress, and past history.

[0861] "Analysis means" refers to a device or program that has the function of analyzing collected data and identifying the user's learning stage and the support they need.

[0862] A "plan generation means" is a device or program that automatically creates an optimal learning plan based on the user's learning objectives.

[0863] A "support system" is a system that supports the progress of learning according to the plan and provides real-time feedback as needed.

[0864] A "warning device" is a device or program that analyzes the emotional state of people within a facility from their facial expressions and voice, and promptly issues an alarm when a suspicious emotional state is detected.

[0865] The invention will now be described in terms of embodiments. This system mainly consists of a server, a terminal, and an emotion engine with emotion recognition capabilities.

[0866] First, the server collects learner information from users and stores it in a database. This information includes learning goals, current ability level, and past learning history. The server analyzes this data to generate an optimal learning plan. Furthermore, the server has an integrated emotion engine that analyzes facial expressions and voice data to identify the user's emotional state.

[0867] Next, the device functions as a user interface, displaying learning plans and other content created on the server. The device receives emotional data in real time from the emotion engine and dynamically adjusts visual and auditory feedback based on this data to help maintain the user's motivation and learning efficiency. For example, if the device determines that the user is tired, it will present lighter learning content or interactive content for refreshment.

[0868] As an example of facility security applications, the devices are used as smartphones or smart glasses to monitor the emotional states of visitors and staff within the facility. This process employs a system that analyzes emotions from facial expressions and voices using an emotion recognition library (e.g., MediaPipe). If a suspicious emotional state is detected, an immediate alert is sent to security personnel, enabling a swift response.

[0869] A concrete example of its use is a scenario where, upon detecting a visitor in a shopping mall who appears anxious, security personnel would check the visitor's surroundings and take necessary action. An example of an input prompt for the generating AI model would be: "Create a program that analyzes a visitor's video and detects signs of tension or anxiety. Based on the analysis results, it should issue an alarm."

[0870] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0871] Step 1:

[0872] The server collects learner information from users. Specifically, it retrieves data such as learning goals, current ability level, and past learning history from a database. Based on this input data, it analyzes the user's learning stage and prepares the basic information necessary to generate appropriate feedback.

[0873] Step 2:

[0874] The server analyzes the collected learner information and generates a learning plan optimized for each user. The input data includes learning goals and ability levels, and by sending this to the analysis engine, it outputs an individually optimized learning plan and proposes the next course of action.

[0875] Step 3:

[0876] The terminal visually displays the learning plan received from the server to the user. Here, an interface is dynamically generated and displayed to make the plan easy to understand and to support user interaction. The output includes a visualization of the plan and a corresponding feedback mechanism.

[0877] Step 4:

[0878] The server uses an emotion engine to analyze the user's emotional state from their facial expressions and voice. It collects the user's emotional data, and through this analysis, outputs data to identify the emotional state in real time, providing foundational information for feedback adjustment. For example, it might use libraries such as MediaPipe.

[0879] Step 5:

[0880] The device dynamically adjusts visual and auditory feedback based on the analyzed emotional state. It receives real-time emotional assessments as input data, and outputs feedback tailored to the user's state, presented as specific actions to facilitate the learning experience.

[0881] Step 6:

[0882] Users progress through their learning based on the provided plan and feedback. They initiate learning activities through the interface and execute the plan while monitoring their progress through voluntary actions. The output is improved efficiency and satisfaction.

[0883] Step 7:

[0884] The server monitors the emotional state within the facility and immediately issues an alarm if an anomaly is detected. It receives emotional data transmitted from terminals as input, analyzes this data using a machine learning model to recognize specific patterns, and determines an alarm signal and corresponding action as output.

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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."

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] 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.

[0905] 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.

[0906] The following is further disclosed regarding the embodiments described above.

[0907] (Claim 1)

[0908] An analytical means for collecting user learner information and analyzing the user's learning level based on said information,

[0909] A plan generation means that generates a learning plan optimized according to the user's learning objectives,

[0910] A support system that provides real-time learning support and feedback based on the generated learning plan,

[0911] An evaluation method for conducting simulation training in a virtual business environment and evaluating the user's activities during said training,

[0912] A response system that receives inquiries from users, generates and provides responses,

[0913] A feedback system that analyzes the user's learning progress and generates visual feedback,

[0914] A system that includes this.

[0915] (Claim 2)

[0916] The system according to claim 1, further comprising means for analyzing the user's pronunciation in real time and providing feedback.

[0917] (Claim 3)

[0918] The system according to claim 1, further comprising means for collecting user activity data and continuously improving the learning plan using machine learning algorithms.

[0919] "Example 1"

[0920] (Claim 1)

[0921] An analytical means for collecting user information and analyzing the user's abilities based on said information,

[0922] A plan generation means that generates a plan optimized according to the user's goals,

[0923] A support system that provides real-time support and feedback based on the generated plan,

[0924] An evaluation means for conducting simulation training in a virtual environment and evaluating the user's behavior during said training,

[0925] A response means that receives inquiries from users, generates and provides responses,

[0926] A feedback mechanism that analyzes user progress and generates visual feedback,

[0927] A means of using voice analysis technology to check the user's pronunciation and providing improvement suggestions based on the analysis results,

[0928] A means of collecting user behavior data and continuously improving plans using generational AI technology,

[0929] A means of supporting the practice of skills using multiple computing devices and enhancing capabilities in practical situations,

[0930] A system that includes this.

[0931] (Claim 2)

[0932] The system according to claim 1, further comprising means for processing user input and providing individually optimized feedback using data analysis techniques.

[0933] (Claim 3)

[0934] The system according to claim 1, further comprising means for analyzing data obtained via an information processing device using machine learning techniques to continuously improve the user's plan.

[0935] "Application Example 1"

[0936] (Claim 1)

[0937] An analytical means for collecting user learner information and analyzing the user's learning level based on said information,

[0938] A plan generation means that generates a learning plan optimized according to the user's learning objectives,

[0939] A support system that provides real-time learning support and feedback based on the generated learning plan,

[0940] An evaluation method for conducting simulation training in a virtual business environment and evaluating the user's activities during said training,

[0941] A response system that receives inquiries from users, generates and provides responses,

[0942] A feedback system that analyzes the user's learning progress and generates visual feedback,

[0943] An evaluation method that provides simulation scenarios from the user's perspective in real time and evaluates language ability,

[0944] A system that includes this.

[0945] (Claim 2)

[0946] The system according to claim 1, further comprising means for analyzing the user's pronunciation in real time and providing feedback.

[0947] (Claim 3)

[0948] The system according to claim 1, further comprising means for collecting user activity data and continuously improving the learning plan using machine learning algorithms.

[0949] "Example 2 of combining an emotion engine"

[0950] (Claim 1)

[0951] An analytical means for collecting user attribute data and analyzing the user's level of understanding based on said data,

[0952] A content generation method that generates personalized educational content based on the user's goals,

[0953] An adjustment mechanism that analyzes the user's emotional state and dynamically adjusts educational content and feedback according to that state,

[0954] An evaluation means that uses online technology to conduct training in a virtual environment and evaluates the user's behavior during said training,

[0955] A means of handling inquiries from users, generating and providing answers,

[0956] A presentation means that analyzes the user's learning progress and provides visual and auditory feedback,

[0957] A system that includes this.

[0958] (Claim 2)

[0959] The system according to claim 1, further comprising means for analyzing a user's voice data in real time and returning feedback based on the analysis results.

[0960] (Claim 3)

[0961] The system according to claim 1, further comprising means for collecting user behavior data and continuously improving educational content using data analysis techniques.

[0962] "Application example 2 when combining with an emotional engine"

[0963] (Claim 1)

[0964] An analytical means for collecting user learner information and analyzing the user's learning stage based on said information,

[0965] A plan generation means that generates a learning plan optimized according to the user's learning objectives,

[0966] A support system that provides real-time learning support and feedback based on the generated learning plan,

[0967] An evaluation means for conducting simulated training in a virtual work environment and evaluating the user's behavior during said training,

[0968] A response means that receives inquiries from users, generates and provides responses,

[0969] A feedback system that analyzes the user's learning progress and generates visual feedback,

[0970] A warning system that analyzes the emotional state of people within the facility through facial expressions and voice, and issues an alarm when a suspicious emotional state is detected,

[0971] A system that includes this.

[0972] (Claim 2)

[0973] The system according to claim 1, further comprising a function for analyzing the user's pronunciation in real time and providing feedback.

[0974] (Claim 3)

[0975] The system according to claim 1, further comprising a method for collecting user behavior data and continuously improving the learning plan using a machine learning algorithm. [Explanation of Symbols]

[0976] 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. An analytical means for collecting user learner information and analyzing the user's learning level based on said information, A plan generation means that generates a learning plan optimized according to the user's learning objectives, A support system that provides real-time learning support and feedback based on the generated learning plan, An evaluation method for conducting simulation training in a virtual business environment and evaluating the user's activities during said training, A response system that receives inquiries from users, generates and provides responses, A feedback system that analyzes the user's learning progress and generates visual feedback, An evaluation method that provides simulation scenarios from the user's perspective in real time and evaluates language ability, A system that includes this.

2. The system according to claim 1, further comprising means for analyzing the user's pronunciation in real time and providing feedback.

3. The system according to claim 1, further comprising means for collecting user activity data and continuously improving the learning plan using machine learning algorithms.

Images