system

Abstract

We provide the system. [Solution] A means of receiving task data in text format from users, A means for selecting highly relevant literature based on the aforementioned problem data and generating recommendation information, Based on the aforementioned recommendation information, a generation means for facilitating dialogue between the user and the literature, A learning support system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

[0003] , ,

[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, the method 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 the self-improvement and skill acquisition of working people, traditional self-study is lonely and inefficient, and it takes time and effort to appropriately select and promote the understanding of the information to be learned, which is a problem. Furthermore, in order to effectively utilize the unique know-how and experience of an individual and sell it as an e-book, a high-level text creation technique is required, so there is a problem that it is difficult to execute.

Means for Solving the Problems

[0005] This invention provides a means for receiving text-based task data from users and selecting and recommending highly relevant literature based on this data, thereby enabling efficient information selection. In addition, it includes a generation means for facilitating dialogue between users and literature, making learning easier. Furthermore, it generates simulation results corresponding to conditions provided by users, supporting the concretization of learning. Moreover, by providing a means for analyzing unique information provided by users and generating electronic publications, it supports the provision of personal know-how as commercially-grade ebooks.

[0006] A "user" is an individual or legal entity that receives learning support or information through this system.

[0007] "Challenge data" refers to information that expresses the content users want to learn or the problems they want to solve in text format.

[0008] "Literature" refers to a general term for electronically available information sources, books, and articles, including content intended for learning and information dissemination.

[0009] "Recommendation information" refers to information used to identify and suggest the most suitable literature based on the task data entered by the user.

[0010] "Generation means" refers to a function that uses AI technology to generate and transform information in order to facilitate dialogue between users and literature.

[0011] "Simulation results" refer to the output of information or a virtual model generated based on the user's specific conditions, which is useful for solving real-world problems or making situational judgments.

[0012] "Electronic publications" are documents such as books and articles that are provided in digital format and can be sold or distributed online. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] 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 a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] 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.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention provides a learning support system that offers means for users to efficiently advance their learning. This system comprises a server, terminals, and a generative AI. The following describes each component in natural language.

[0035] server

[0036] The server handles the central processing of this system and has the function of selecting appropriate literature based on the assignment data received from the user. It accesses the literature database, analyzes keywords and themes, and extracts highly relevant literature. The server also works in conjunction with the generation AI to generate dialogue responses and simulation results based on the literature, and sends them to the terminal.

[0037] terminal

[0038] The device functions as an interface for users to input assignment data and questions. When a user enters text, it is sent to the server, and the results returned from the server are displayed to the user. The displayed information includes recommendations, conversational responses, and simulation results. The device features a user-friendly UI to support a smooth learning experience.

[0039] user

[0040] Through this system, users specify the topics they want to learn and the business problems they want to solve, enabling them to efficiently acquire information and deepen their knowledge. Users input problem data using their terminals, receive responses from the server, and review their interactions with literature and simulation results. Furthermore, they contribute their own expertise and participate in the process of generating electronic publications.

[0041] Specific example

[0042] For example, if a user wants to obtain information on "building sustainable business models," the user enters their question into the terminal. The terminal sends the entered information to the server, which then recommends relevant literature. Furthermore, based on the user's conditions, it generates simulation results regarding sustainability and provides interactive responses. In this way, the user can acquire concrete and practical knowledge.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] Users access the device's interface and input what they want to learn or the business problems they want to solve in text format.

[0046] Step 2:

[0047] The terminal prepares to send the entered text data to the server and sends the data to the server using the appropriate communication protocol.

[0048] Step 3:

[0049] The server analyzes the received assignment data using a text analysis module and extracts keywords and main themes.

[0050] Step 4:

[0051] The server searches the literature database based on the analyzed data and applies algorithms to identify highly relevant literature.

[0052] Step 5:

[0053] The server combines relevant bibliographic information, generates recommendation information, and sends the results to the terminal.

[0054] Step 6:

[0055] The terminal displays recommendation information received from the server to the user and provides them with literature options.

[0056] Step 7:

[0057] The user selects literature of interest from the provided options and enters further text for questions or more detailed discussions.

[0058] Step 8:

[0059] The terminal sends the user's input back to the server and requests the generation of an interactive response.

[0060] Step 9:

[0061] The server uses generative AI to generate conversational responses based on selected literature, creating specific answers to questions.

[0062] Step 10:

[0063] The server sends the generated response back to the terminal and continues the interaction with the user.

[0064] Step 11:

[0065] Users deepen their learning by interacting with the literature using the displayed information, and input new challenges or questions as needed.

[0066] Step 12:

[0067] If a user wishes to provide their own expertise to the system, they can send the information through their terminal, and the process of converting it into an electronic publication will begin.

[0068] Step 13:

[0069] The server analyzes the information provided by the user and performs configuration and proofreading for the creation of electronic publications.

[0070] Step 14:

[0071] The server generates commercial-grade electronic publications based on the processed information and provides the finished product to the user as a preview via a terminal.

[0072] (Example 1)

[0073] 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."

[0074] Modern learners are required to find the most relevant information from a vast amount of data and to learn efficiently. However, conventional learning support systems have shortcomings in selecting relevant information and generating in-depth, interactive responses, making it difficult to improve learning efficiency. Furthermore, there is a need for rapid and accurate responses in generating simulation results based on specific conditions and creating publications based on user information.

[0075] 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.

[0076] In this invention, the server includes means for acquiring task data by a device for inputting information from a user, means for accessing literature information sources based on the task data and selecting highly relevant information, and means for creating an interactive response using a generative AI model based on the selected information. This enables learners to efficiently and effectively acquire the necessary information and gain a deep understanding.

[0077] "Users" refers to individuals or groups who use the system to obtain information and attempt to learn or solve problems.

[0078] "Devices for inputting information" refers to electronic devices such as computers and smartphones that users use to input task data and conditions.

[0079] "Problem data" refers to information such as text and keywords entered by users to solve problems, and serves as the basic data for the system to process based on that content.

[0080] "Literature information sources" refer to collections of information that provide relevant information, such as books, articles, and databases.

[0081] "Highly relevant information" refers to information that is deemed to be highly useful or suitable for the problem data.

[0082] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to automatically generate conversational responses based on input information.

[0083] "Dialogue-based responses" refer to the presentation of information in the form of questions and answers, which is provided in a way that is easy for users to understand.

[0084] "Simulation" refers to the process of virtually reproducing how a certain phenomenon or system operates based on specific conditions.

[0085] "Digital publications" refer to publications that are provided electronically, such as ebooks and online reports.

[0086] The learning support system of the present invention provides advanced functions for efficiently acquiring information and promoting learning. This system is primarily implemented by hardware and software, including servers, terminals, and generative AI models. The following details each component and its operation.

[0087] server

[0088] The server handles the core processing of this system. Specifically, it analyzes received task data and searches for highly relevant information. The technologies used here include a database management system, from which it accesses literature sources. Furthermore, it utilizes a generative AI model to generate dialogue-based responses based on the literature. The generative AI model used for this purpose uses natural language processing techniques to automatically construct appropriate responses from the input information.

[0089] terminal

[0090] The terminal functions as an interface for users to input information. Users input task data and requirements on the terminal, and this data is sent to the server. The terminal displays the received information to the user and accepts further questions through interaction. The terminal interface is intuitive and designed for smooth user operation.

[0091] user

[0092] Users input what they want to learn or their business challenges into the system via their devices. Based on the information returned from the server, users proceed with their learning. Furthermore, the information provided by users is also used to create digital publications and is widely utilized.

[0093] Specific example

[0094] For example, suppose a user wants to obtain information on "building sustainable business models." In this case, the user enters keywords such as "sustainability, high profitability" into their device, and the server selects relevant literature based on those keywords. Furthermore, a generative AI model is used to create responses that show "specific examples of highly sustainable business models" and "the advantages of adopting them."

[0095] Example of a prompt

[0096] "Based on relevant literature on building sustainable business models, please generate AI simulation results and provide countermeasures in a conversational format."

[0097] This system aims to provide users with effective learning support and deepen their knowledge. By using specific prompts, the generative AI model provides appropriate information tailored to the user's needs.

[0098] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0099] Step 1:

[0100] The terminal receives task data from the user as input. The user enters what they want to learn or a specific business task in text format into the terminal's input field and presses the submit button. The terminal sends this input data to the server.

[0101] Step 2:

[0102] The server receives assignment data from the terminal as input and performs analysis. Using a database access module, it searches for literature sources and selects literature relevant to the assignment data. The selected literature data is stored on the server.

[0103] Step 3:

[0104] The server passes the selected literature as input to the generative AI model. The generative AI model uses natural language processing techniques to generate conversational responses based on the literature. The generated responses are formatted in a way that is easy for the user to understand.

[0105] Step 4:

[0106] The server sends the generated interactive response as output to the terminal. The terminal displays this response to the user. A user-friendly interface is used to provide information in a visually clear and easy-to-understand manner.

[0107] Step 5:

[0108] The user continues learning based on the displayed information. They can also enter additional questions into their device as needed and receive responses from the server again. The server processes the input again, continuing to provide the information the user requests.

[0109] The above outlines the specific processing steps of the system program.

[0110] (Application Example 1)

[0111] 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."

[0112] In training for operating interconnected machinery in factories, there is a need for a safe and efficient way for users to learn how to operate the machines without relying on the actual equipment. Furthermore, a challenge lies in the difficulty of obtaining concrete feedback derived from on-site practice.

[0113] 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.

[0114] In this invention, the server includes means for receiving operation tasks in natural language format from a user, means for generating virtual operations of a collaborative machine based on the operation tasks, means for providing an environment in which the user can interactively experience the generated virtual operations, and means for analyzing the user's inquiries and generating appropriate dialogue responses. This enables the user to safely learn how to operate a machine in a virtual environment without relying on a real machine, and to learn efficiently and concretely.

[0115] A "user" is an entity that uses the system to learn operational tasks.

[0116] "Natural language forms" refer to the forms of language that humans use on a daily basis, including text as an example.

[0117] "Operational tasks" are assignments designed to teach the specific operating methods and procedures of the linked machines.

[0118] "Cooperative machinery" refers to industrial equipment and robots used in factories and work sites.

[0119] "Virtual operation" refers to a simulation environment that simulates actual machine operation, allowing learners to experience it firsthand.

[0120] An "interactive learning environment" refers to a virtual learning environment where users can interact with the system in a two-way manner while progressing through their learning.

[0121] A "question" refers to any statement made by a user to the system that includes questions or requests for confirmation.

[0122] "Appropriate dialogue response" refers to a contextually appropriate response generated by the system in response to a user's question.

[0123] To realize this application, the server first receives an operational task from the user in natural language format. This may include prompts such as, "Please tell me the steps to efficiently program a transport robot." After receiving the task, the server analyzes it and prepares data to generate the relevant virtual operation. The virtual operation is provided as a simulation environment that mimics Tanli's industrial robots, and users can access this environment via smartphones or head-mounted displays to conduct training without relying on actual equipment.

[0124] On the user side, the device provides an interface, enabling an interactive experience based on received virtual operation data. The generative AI model generates appropriate responses to user inquiries in real time, organizing and presenting relevant information in response to inputs called prompts to facilitate two-way communication. This allows users to gain efficient and deep learning.

[0125] As a concrete example, users can learn how to program transport robots using their smartphones. In this process, the generating AI will respond to specific questions provided by the user with relevant information and procedures as needed. Possible prompts include questions such as, "Please tell me the steps to efficiently program a transport robot."

[0126] The hardware used includes a smartphone, a head-mounted display, and a computer system capable of running virtual operations. The software utilizes machine learning libraries such as TENSORFLOW® and PyTorch for data analysis. This enables a learning support system that integrates virtual operations and interactive responses.

[0127] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0128] Step 1:

[0129] The terminal receives an operational task from the user in the form of a prompt. This prompt is treated as input data for natural language processing.

[0130] Step 2:

[0131] The server analyzes the prompt text and extracts relevant information using a generative AI model. Specifically, it extracts keywords from the input data using natural language processing techniques and then uses these keywords to obtain relevant information from a literature database (e.g., an industrial robot operation manual). At this stage, it prepares the data necessary to generate a relevant virtual operation simulation.

[0132] Step 3:

[0133] The server generates a virtual operation based on the acquired information and constructs it as data for an interactive learning environment. Here, the simulation data necessary for the virtual operation is integrated and sent to the terminal as a single package. This package also includes dialogue response data from the generated AI model.

[0134] Step 4:

[0135] The terminal interactively displays and provides the user with the received virtual operation data. Through this, the user virtually experiences operating the robot. The terminal uses a head-mounted display or smartphone and reproduces the virtual environment using advanced graphics technology.

[0136] Step 5:

[0137] The user interacts with the AI ​​model through virtual operation and, as needed, sends additional prompt messages via the terminal. These additional prompt messages are entered by the user based on their understanding of the current situation and the steps they wish to learn more about.

[0138] Step 6:

[0139] The server generates a response to the received additional prompt using the AI ​​model and sends it back to the user in real time. At that time, it provides more specific information about operation methods and precautions based on the virtual operation status.

[0140] This process will enable users to learn how to operate the robot safely and effectively.

[0141] 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.

[0142] This invention provides an effective learning experience tailored to the user's emotions by combining an emotion engine with a learning support system. The system comprises a server, a terminal, a generative AI, and an emotion engine. Each component is described below.

[0143] server

[0144] The server is the central processing component that receives task data and input information from users. The server uses an analysis module to extract keywords and main themes from the task data and selects relevant literature from a literature database. Furthermore, it uses an emotion engine to analyze the user's emotional state and optimizes recommendation information and dialogue content based on this analysis. Another role of the server is to generate responses that facilitate interaction with the user using generative AI and send them to the terminal.

[0145] terminal

[0146] The terminal functions as an interface where users input tasks and questions, and data, including emotional triggers, is collected. The terminal sends the collected information to a server, and the information returned from the server (recommendations and conversation content) is displayed to the user. The terminal also monitors user interaction in real time through the UI and feeds back to the system using emotional changes as triggers.

[0147] User

[0148] Users begin the learning process by setting individual learning goals using this system and inputting assignment data into their terminal. The user's emotional state is also transmitted to the system as part of the input information, optimizing each individual learning experience. Specifically, when a user shows interest or is confused, the server automatically adjusts its conversational responses and provides information in a format that is easy for the user to understand.

[0149] Specific example

[0150] For example, if a user wishes to learn about "improving project management skills," they would input relevant assignments as initial input and begin learning. The user would ask questions about topics of interest, while the system simultaneously recognizes their emotions. The server uses an emotion engine to analyze the user's interests and understanding, and if, for example, the user appears confused, it would provide more specific and visual information or offer additional hints to clarify the conversation. In this way, the user can learn at an optimal pace and with the most relevant content.

[0151] The following describes the processing flow.

[0152] Step 1:

[0153] Users use the device's interface to input the topics they want to learn about or the problems they want to solve in text format.

[0154] Step 2:

[0155] The terminal sends the entered text data to the server, and at the same time, it also collects information necessary for emotion analysis, such as the user's facial expressions and voice data.

[0156] Step 3:

[0157] The server analyzes the received issue data using an analysis module and extracts key keywords and themes.

[0158] Step 4:

[0159] The server searches the literature database and selects highly relevant literature based on the extracted keywords.

[0160] Step 5:

[0161] The server utilizes an emotion engine to generate recommendation information that takes into account the individual emotional state of each user, based on the selected literature information.

[0162] Step 6:

[0163] The server sends the generated recommendation information to the terminal and suggests appropriate learning content to the user.

[0164] Step 7:

[0165] The terminal displays received recommendation information to the user and provides an interface to make it easier for the user to select literature.

[0166] Step 8:

[0167] Users select literature of interest from the recommended selections and provide additional input to prompt further questions or discussions.

[0168] Step 9:

[0169] The terminal then sends the user's additional input back to the server and requests the generation of the dialogue content.

[0170] Step 10:

[0171] The server uses generative AI to generate conversational responses based on selected literature and the user's emotional state, including visualizations and concrete examples of information as needed.

[0172] Step 11:

[0173] The server sends the generated dialogue response back to the terminal, providing information in a format that is easy for the user to understand.

[0174] Step 12:

[0175] Users utilize the presented information and, through interaction, progress through the learning process, sending emotional feedback to the system.

[0176] Step 13:

[0177] The server receives emotional feedback from users and makes adjustments to reflect this feedback in the conversation and future recommendations.

[0178] Step 14:

[0179] When a user provides their own expertise, the process begins by inputting the information using a terminal and generating it as an electronic publication.

[0180] Step 15:

[0181] The server analyzes the provided information, generates appropriate electronic publications that take emotional feedback into consideration, and presents the results to the user for confirmation.

[0182] (Example 2)

[0183] 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".

[0184] Conventional learning support systems have struggled to provide personalized learning experiences tailored to users' emotional states, often remaining limited to providing fixed information. Furthermore, they lacked the flexibility to appropriately respond to changes in user challenges and circumstances. This resulted in limited effectiveness and efficiency of learning.

[0185] 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.

[0186] In this invention, the server includes a device for receiving linguistic task information from a user, a device for analyzing semantic elements related to the task information, a device for selecting relevant documents and generating recommended information based on the analysis results, a generation device for facilitating dialogue between the user and information resources based on the generated recommended information, and a device for recognizing the user's emotional state and making adjustments to optimize the learning experience. This makes it possible to provide a flexible learning experience that is tailored to the individual state and needs of the user.

[0187] "User" refers to an individual or group of people who use the system to acquire, input, or engage in learning activities related to information.

[0188] "Language morphology challenge information" refers to natural language data, including text and audio, submitted by users to the system.

[0189] "Device" refers to hardware or software elements arranged or programmed to perform a specific function.

[0190] "Semantic elements" refer to important keywords and concepts contained in the information provided by the user.

[0191] "Analyzing" refers to the act of breaking down data or information and evaluating its constituent elements and interrelationships.

[0192] "Relevant documents" refer to literature and materials that are selected based on the user's problem information and are highly suitable and useful.

[0193] "Recommended information" refers to helpful advice and guidelines provided to users based on the analysis results.

[0194] A "generation device" refers to a component of a system designed to construct new content or responses based on specific data.

[0195] "Information resources" refer to digital content, including databases and knowledge bases, that are used to support users' learning and information gathering.

[0196] "Emotional state" refers to data or indicators that represent the user's current psychological or emotional condition.

[0197] "Making adjustments" refers to the process of modifying the system's output and operation according to the user's situation and needs.

[0198] A "flexible learning experience" refers to customized educational activities that adapt to the individual needs and circumstances of the users.

[0199] This invention is a system that utilizes information processing equipment and sentiment analysis technology to optimize the user's learning experience. The system comprises a server, a terminal, a generative AI, and a sentiment engine.

[0200] The server plays a central role in information processing. Using analysis modules, the server processes task data and questions provided by users. Specifically, it receives task information in linguistic form and extracts semantic elements such as keywords and main themes. Furthermore, the server selects relevant documents from a database and generates recommendation information. In this process, utilizing generative AI models makes it possible to provide effective interactive responses. Additionally, an emotion engine is used to analyze the user's emotional state and make adjustments to optimize the learning experience.

[0201] The terminal functions as an interface for users to input tasks and questions. Users begin the learning process by inputting tasks aligned with their learning goals. The terminal sends the input information to the server and displays the information returned from the server. The terminal also incorporates emotion recognition capabilities, using the camera and microphone to analyze the user's facial expressions and voice to determine their emotions, and then feeds that data back to the server.

[0202] Users set specific learning themes and communicate their interests and questions to the system along the way. For example, if a user enters a prompt such as "I want to learn about the latest project management techniques" into the terminal, the system will provide literature and visual materials related to that theme. Furthermore, if the server detects that the user is showing interest or is confused, it will adjust accordingly to provide more easily understandable information. This creates an environment where users can learn efficiently at their own pace.

[0203] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0204] Step 1:

[0205] The user enters assignment information about the content or topic they want to learn into the terminal. The entered text or audio data is acquired through the terminal's interface. For example, the user might enter the prompt "I want to learn about the latest project management techniques." The terminal then sends this information to the server as input data.

[0206] Step 2:

[0207] The server processes the issue information received from the terminal using an analysis module. First, the information is broken down into semantic elements, and keywords and main themes are extracted. This generates basic data for finding related content. Specifically, natural language processing technology is used to extract terms related to project management.

[0208] Step 3:

[0209] The server uses a generative AI model to select literature related to the extracted keywords from the database. It then generates information resources to present to the user as recommendations. This process efficiently scans a large database and filters out highly relevant materials. The output includes lists of visual materials and documents.

[0210] Step 4:

[0211] The server uses an emotion engine to analyze the user's emotional state. Emotional data is obtained based on information fed back from the device. This allows the server to measure the user's level of interest and confusion, and adjust the learning experience to be more personalized. For example, if the server determines that the user is confused, additional visual materials and detailed explanatory information will be generated.

[0212] Step 5:

[0213] The server sends the generated recommendations and adjusted content to the terminal. The terminal displays this information on its interface and presents it to the user. The user can learn based on the presented information, resolve questions at their own pace, and efficiently deepen their knowledge. The server continues to monitor the user's responses, and if new input is received, the process from step 2 is repeated.

[0214] (Application Example 2)

[0215] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0216] In modern manufacturing environments, improving work efficiency and managing worker health are crucial issues. However, current systems fail to provide adequate feedback that takes into account workers' emotional states and biometric data. As a result, it is difficult to obtain appropriate feedback that responds to workers' emotions, making it challenging to create an efficient work environment.

[0217] 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.

[0218] In this invention, the server includes a device for receiving task data in text format from a user; a device for selecting highly relevant materials based on the task data and generating recommendation information; a generation device for facilitating interaction between the user and the materials based on the recommendation information; a device for monitoring the user's biometric data and analyzing their emotional state; and a device for providing feedback to improve the user's work efficiency based on their emotional state. This enables efficient work support and health management in response to the analysis of the customer's emotional state based on their biometric data.

[0219] A "user" is a person who operates the system and provides information.

[0220] "Issue data" refers to information about problems or themes that users input into the system.

[0221] "Documents" refer to a collection of documents or data that contain information related to the assigned data.

[0222] "Recommended information" refers to highly relevant information selected and presented by the system based on the problem data provided by the user.

[0223] A "generation device" is a device that supports the interaction between users and materials based on recommendation information.

[0224] "Biometric data" refers to digital data collected from the user's body, such as heart rate and skin electrical activity.

[0225] "Emotional state" refers to the user's mental or emotional condition, as analyzed based on biometric data.

[0226] "Feedback" refers to advice or suggestions given to a user based on their emotional state.

[0227] This invention incorporates several functional components to realize a learning support system that provides feedback while taking into account the user's emotional state. Its main components and functions are described below.

[0228] The server receives text-based task data from the user and selects highly relevant materials from a literature database based on this data. Based on the selected materials, it generates recommendation information and uses an AI module to create responses that facilitate interaction between the user and the materials. Furthermore, the server uses a biometric data collection module to analyze the user's biometric data, such as heart rate and skin electrical activity, and uses an emotion engine to evaluate their emotional state. This provides a more effective learning experience by combining feedback based on the user's emotional state.

[0229] The terminal functions as an interface for users to input task data and send it to the server. The terminal also collects the user's biometric data in real time and monitors changes, providing a trigger for the system to provide appropriate feedback if the user is in an unfavorable state.

[0230] For example, if the user's heart rate, as received from the terminal, is higher than normal, the server will determine this to be a stressed state and provide feedback to the user such as, "We recommend you take a short break." In this way, it becomes possible to provide information tailored to each user's individual condition, thereby improving the user's work efficiency and mental health.

[0231] An example of a prompt message could be: "Please tell me the data points to consider when determining that a user is fatigued. Also, please suggest appropriate feedback for that situation." This is how one might instruct the generating AI.

[0232] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0233] Step 1:

[0234] The terminal receives task data in text format from the user as input. This data contains information about problems or themes that the user wants to solve. The terminal then sends the received task data to the server.

[0235] Step 2:

[0236] The server takes the received assignment data as input and selects highly relevant materials from the literature database. In this process, the analysis module extracts keywords and main themes, and then performs a material search based on them to output highly relevant materials.

[0237] Step 3:

[0238] The server generates recommendation information using selected materials. This recommendation information is the optimal collection of materials to provide knowledge to the user. The server uses a generative AI model to create responses that facilitate interaction between the materials and the user, and sends these responses to the terminal.

[0239] Step 4:

[0240] The terminal receives recommendation information and responses sent from the server and presents them to the user. The user uses this information to engage in learning activities and can input additional assignment data or questions as needed.

[0241] Step 5:

[0242] The device collects the user's biometric data in real time. Specifically, it acquires heart rate and skin electrical activity as input from devices such as smartwatches and smart bands, and sends this data to a server.

[0243] Step 6:

[0244] The server uses the received biometric data as input to analyze it with an emotion engine and evaluate the user's emotional state. For example, if the heart rate is higher than normal, it determines that the user is under stress. Based on this analysis, it generates optimal feedback for the user and sends it to the device.

[0245] Step 7:

[0246] The device receives feedback sent from the server and presents it to the user. This allows the user to receive advice and suggestions tailored to their emotional state, which can help improve their learning and work efficiency.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] [Second Embodiment]

[0251] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0252] 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.

[0253] 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).

[0254] 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.

[0255] 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.

[0256] 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).

[0257] 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.

[0258] 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.

[0259] 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.

[0260] 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.

[0261] 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.

[0262] 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".

[0263] This invention provides a learning support system that offers means for users to efficiently advance their learning. This system comprises a server, terminals, and a generative AI. The following describes each component in natural language.

[0264] server

[0265] The server handles the central processing of this system and has the function of selecting appropriate literature based on the assignment data received from the user. It accesses the literature database, analyzes keywords and themes, and extracts highly relevant literature. The server also works in conjunction with the generation AI to generate dialogue responses and simulation results based on the literature, and sends them to the terminal.

[0266] terminal

[0267] The device functions as an interface for users to input assignment data and questions. When a user enters text, it is sent to the server, and the results returned from the server are displayed to the user. The displayed information includes recommendations, conversational responses, and simulation results. The device features a user-friendly UI to support a smooth learning experience.

[0268] user

[0269] Through this system, users specify the topics they want to learn and the business problems they want to solve, enabling them to efficiently acquire information and deepen their knowledge. Users input problem data using their terminals, receive responses from the server, and review their interactions with literature and simulation results. Furthermore, they contribute their own expertise and participate in the process of generating electronic publications.

[0270] Specific example

[0271] For example, if a user wants to obtain information on "building sustainable business models," the user enters their question into the terminal. The terminal sends the entered information to the server, which then recommends relevant literature. Furthermore, based on the user's conditions, it generates simulation results regarding sustainability and provides interactive responses. In this way, the user can acquire concrete and practical knowledge.

[0272] The following describes the processing flow.

[0273] Step 1:

[0274] The user accesses the interface of the terminal and inputs in text form the content they want to learn or the business issues they want to solve.

[0275] Step 2:

[0276] The terminal prepares to send the input text data to the server and uses an appropriate communication protocol to send the data to the server.

[0277] Step 3:

[0278] The server analyzes the received issue data using a text analysis module and extracts keywords and main themes.

[0279] Step 4:

[0280] The server searches the literature database based on the analyzed data and applies an algorithm to identify relevant literature.

[0281] Step 5:

[0282] The server combines the relevant literature information, generates recommendation information, and sends the result to the terminal.

[0283] Step 6:

[0284] The terminal displays the recommendation information received from the server to the user and provides literature options.

[0285] Step 7:

[0286] The user selects the literature they are interested in from the provided options and enters further text for questions or detailed conversations.

[0287] Step 8:

[0288] The terminal sends the user's input back to the server and requests the generation of an interactive response.

[0289] Step 9:

[0290] The server uses generative AI to generate conversational responses based on selected literature, creating specific answers to questions.

[0291] Step 10:

[0292] The server sends the generated response back to the terminal and continues the interaction with the user.

[0293] Step 11:

[0294] Users deepen their learning by interacting with the literature using the displayed information, and input new challenges or questions as needed.

[0295] Step 12:

[0296] If a user wishes to provide their own expertise to the system, they can send the information through their terminal, and the process of converting it into an electronic publication will begin.

[0297] Step 13:

[0298] The server analyzes the information provided by the user and performs configuration and proofreading for the creation of electronic publications.

[0299] Step 14:

[0300] The server generates commercial-grade electronic publications based on the processed information and provides the finished product to the user as a preview via a terminal.

[0301] (Example 1)

[0302] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0303] Modern learners are required to find the most relevant information from a vast amount of information and proceed with learning efficiently. On the other hand, conventional learning support systems have problems such as insufficient selection of relevant information and generation of responses in a deep dialogue format, making it difficult to improve learning efficiency. Furthermore, in the generation of simulation results according to conditions and the creation of publications based on user information, prompt and accurate responses are also required.

[0304] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Example 1 is realized by the following means.

[0305] In this invention, the server includes means for acquiring problem data by a device for inputting information from a user, means for accessing a literature information source based on the problem data and selecting highly relevant information, and means for creating a response in a dialogue format using a generated AI model based on the selected information. Thereby, learners can acquire necessary information efficiently and effectively and gain a deep understanding.

[0306] The "user" refers to an individual or group that uses the system to acquire information and attempts learning or problem-solving.

[0307] The "device for inputting information" refers to an electronic device such as a computer or smartphone that a user uses to input problem data and conditions.

[0308] The "problem data" is information such as text or keywords that a user inputs for solution, and is the basic data for the system to perform processing based on its content.

[0309] The "literature information source" refers to an aggregation of information such as books, papers, databases, etc. that provides relevant information. [[ID=2...]]

[0310] The "highly relevant information" refers to information that is judged to have high usefulness and suitability for the problem data.

[0311] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to automatically generate conversational responses based on input information.

[0312] "Dialogue-based responses" refer to the presentation of information in the form of questions and answers, which is provided in a way that is easy for users to understand.

[0313] "Simulation" refers to the process of virtually reproducing how a certain phenomenon or system operates based on specific conditions.

[0314] "Digital publications" refer to publications that are provided electronically, such as ebooks and online reports.

[0315] The learning support system of the present invention provides advanced functions for efficiently acquiring information and promoting learning. This system is primarily implemented by hardware and software, including servers, terminals, and generative AI models. The following details each component and its operation.

[0316] server

[0317] The server handles the core processing of this system. Specifically, it analyzes received task data and searches for highly relevant information. The technologies used here include a database management system, from which it accesses literature sources. Furthermore, it utilizes a generative AI model to generate dialogue-based responses based on the literature. The generative AI model used for this purpose uses natural language processing techniques to automatically construct appropriate responses from the input information.

[0318] terminal

[0319] The terminal functions as an interface for users to input information. Users input task data and requirements on the terminal, and this data is sent to the server. The terminal displays the received information to the user and accepts further questions through interaction. The terminal interface is intuitive and designed for smooth user operation.

[0320] user

[0321] Users input what they want to learn or their business challenges into the system via their devices. Based on the information returned from the server, users proceed with their learning. Furthermore, the information provided by users is also used to create digital publications and is widely utilized.

[0322] Specific example

[0323] For example, suppose a user wants to obtain information on "building sustainable business models." In this case, the user enters keywords such as "sustainability, high profitability" into their device, and the server selects relevant literature based on those keywords. Furthermore, a generative AI model is used to create responses that show "specific examples of highly sustainable business models" and "the advantages of adopting them."

[0324] Example of a prompt

[0325] "Based on relevant literature on building sustainable business models, please generate AI simulation results and provide countermeasures in a conversational format."

[0326] This system aims to provide users with effective learning support and deepen their knowledge. By using specific prompts, the generative AI model provides appropriate information tailored to the user's needs.

[0327] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0328] Step 1:

[0329] The terminal receives task data from the user as input. The user enters what they want to learn or a specific business task in text format into the terminal's input field and presses the submit button. The terminal sends this input data to the server.

[0330] Step 2:

[0331] The server receives assignment data from the terminal as input and performs analysis. Using a database access module, it searches for literature sources and selects literature relevant to the assignment data. The selected literature data is stored on the server.

[0332] Step 3:

[0333] The server passes the selected literature as input to the generative AI model. The generative AI model uses natural language processing techniques to generate conversational responses based on the literature. The generated responses are formatted in a way that is easy for the user to understand.

[0334] Step 4:

[0335] The server sends the generated interactive response as output to the terminal. The terminal displays this response to the user. A user-friendly interface is used to provide information in a visually clear and easy-to-understand manner.

[0336] Step 5:

[0337] The user continues learning based on the displayed information. They can also enter additional questions into their device as needed and receive responses from the server again. The server processes the input again, continuing to provide the information the user requests.

[0338] The above outlines the specific processing steps of the system program.

[0339] (Application Example 1)

[0340] 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."

[0341] In training for operating interconnected machinery in factories, there is a need for a safe and efficient way for users to learn how to operate the machines without relying on the actual equipment. Furthermore, a challenge lies in the difficulty of obtaining concrete feedback derived from on-site practice.

[0342] 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.

[0343] In this invention, the server includes means for receiving operation tasks in natural language format from a user, means for generating virtual operations of a collaborative machine based on the operation tasks, means for providing an environment in which the user can interactively experience the generated virtual operations, and means for analyzing the user's inquiries and generating appropriate dialogue responses. This enables the user to safely learn how to operate a machine in a virtual environment without relying on a real machine, and to learn efficiently and concretely.

[0344] A "user" is an entity that uses the system to learn operational tasks.

[0345] "Natural language forms" refer to the forms of language that humans use on a daily basis, including text as an example.

[0346] "Operational tasks" are assignments designed to teach the specific operating methods and procedures of the linked machines.

[0347] "Cooperative machinery" refers to industrial equipment and robots used in factories and work sites.

[0348] "Virtual operation" refers to a simulation environment that simulates actual machine operation, allowing learners to experience it firsthand.

[0349] An "interactive learning environment" refers to a virtual learning environment where users can interact with the system in a two-way manner while progressing through their learning.

[0350] A "question" refers to any statement made by a user to the system that includes questions or requests for confirmation.

[0351] "Appropriate dialogue response" refers to a contextually appropriate response generated by the system in response to a user's question.

[0352] To realize this application, the server first receives an operational task from the user in natural language format. This may include prompts such as, "Please tell me the steps to efficiently program a transport robot." After receiving the task, the server analyzes it and prepares data to generate the relevant virtual operation. The virtual operation is provided as a simulation environment that mimics Tanli's industrial robots, and users can access this environment via smartphones or head-mounted displays to conduct training without relying on actual equipment.

[0353] On the user side, the device provides an interface, enabling an interactive experience based on received virtual operation data. The generative AI model generates appropriate responses to user inquiries in real time, organizing and presenting relevant information in response to inputs called prompts to facilitate two-way communication. This allows users to gain efficient and deep learning.

[0354] As a concrete example, users can learn how to program transport robots using their smartphones. In this process, the generating AI will respond to specific questions provided by the user with relevant information and procedures as needed. Possible prompts include questions such as, "Please tell me the steps to efficiently program a transport robot."

[0355] The hardware used includes smartphones, head-mounted displays, and a computer system capable of running virtual operations, while the software utilizes machine learning libraries such as TensorFlow and PyTorch for data analysis. This enables a learning support system that integrates virtual operations and interactive responses.

[0356] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0357] Step 1:

[0358] The terminal receives an operational task from the user in the form of a prompt. This prompt is treated as input data for natural language processing.

[0359] Step 2:

[0360] The server analyzes the prompt text and extracts relevant information using a generative AI model. Specifically, it extracts keywords from the input data using natural language processing techniques and then uses these keywords to obtain relevant information from a literature database (e.g., an industrial robot operation manual). At this stage, it prepares the data necessary to generate a relevant virtual operation simulation.

[0361] Step 3:

[0362] The server generates a virtual operation based on the acquired information and constructs it as data for an interactive learning environment. Here, the simulation data necessary for the virtual operation is integrated and sent to the terminal as a single package. This package also includes dialogue response data from the generated AI model.

[0363] Step 4:

[0364] The terminal interactively displays and provides the user with the received virtual operation data. Through this, the user virtually experiences operating the robot. The terminal uses a head-mounted display or smartphone and reproduces the virtual environment using advanced graphics technology.

[0365] Step 5:

[0366] The user interacts with the AI ​​model through virtual operation and, as needed, sends additional prompt messages via the terminal. These additional prompt messages are entered by the user based on their understanding of the current situation and the steps they wish to learn more about.

[0367] Step 6:

[0368] The server generates a response to the received additional prompt using the AI ​​model and sends it back to the user in real time. At that time, it provides more specific information about operation methods and precautions based on the virtual operation status.

[0369] This process will enable users to learn how to operate the robot safely and effectively.

[0370] 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.

[0371] This invention provides an effective learning experience tailored to the user's emotions by combining an emotion engine with a learning support system. The system comprises a server, a terminal, a generative AI, and an emotion engine. Each component is described below.

[0372] server

[0373] The server is the central processing component that receives task data and input information from users. The server uses an analysis module to extract keywords and main themes from the task data and selects relevant literature from a literature database. Furthermore, it uses an emotion engine to analyze the user's emotional state and optimizes recommendation information and dialogue content based on this analysis. Another role of the server is to generate responses that facilitate interaction with the user using generative AI and send them to the terminal.

[0374] terminal

[0375] The terminal functions as an interface where users input tasks and questions, and data, including emotional triggers, is collected. The terminal sends the collected information to a server, and the information returned from the server (recommendations and conversation content) is displayed to the user. The terminal also monitors user interaction in real time through the UI and feeds back to the system using emotional changes as triggers.

[0376] User

[0377] Users begin the learning process by setting individual learning goals using this system and inputting assignment data into their terminal. The user's emotional state is also transmitted to the system as part of the input information, optimizing each individual learning experience. Specifically, when a user shows interest or is confused, the server automatically adjusts its conversational responses and provides information in a format that is easy for the user to understand.

[0378] Specific example

[0379] For example, if a user wishes to learn about "improving project management skills," they would input relevant assignments as initial input and begin learning. The user would ask questions about topics of interest, while the system simultaneously recognizes their emotions. The server uses an emotion engine to analyze the user's interests and understanding, and if, for example, the user appears confused, it would provide more specific and visual information or offer additional hints to clarify the conversation. In this way, the user can learn at an optimal pace and with the most relevant content.

[0380] The following describes the processing flow.

[0381] Step 1:

[0382] Users use the device's interface to input the topics they want to learn about or the problems they want to solve in text format.

[0383] Step 2:

[0384] The terminal sends the entered text data to the server, and at the same time, it also collects information necessary for emotion analysis, such as the user's facial expressions and voice data.

[0385] Step 3:

[0386] The server analyzes the received issue data using an analysis module and extracts key keywords and themes.

[0387] Step 4:

[0388] The server searches the literature database and selects highly relevant literature based on the extracted keywords.

[0389] Step 5:

[0390] The server utilizes an emotion engine to generate recommendation information that takes into account the individual emotional state of each user, based on the selected literature information.

[0391] Step 6:

[0392] The server sends the generated recommendation information to the terminal and suggests appropriate learning content to the user.

[0393] Step 7:

[0394] The terminal displays received recommendation information to the user and provides an interface to make it easier for the user to select literature.

[0395] Step 8:

[0396] Users select literature of interest from the recommended selections and provide additional input to prompt further questions or discussions.

[0397] Step 9:

[0398] The terminal then sends the user's additional input back to the server and requests the generation of the dialogue content.

[0399] Step 10:

[0400] The server uses generative AI to generate conversational responses based on selected literature and the user's emotional state, including visualizations and concrete examples of information as needed.

[0401] Step 11:

[0402] The server sends the generated dialogue response back to the terminal, providing information in a format that is easy for the user to understand.

[0403] Step 12:

[0404] Users utilize the presented information and, through interaction, progress through the learning process, sending emotional feedback to the system.

[0405] Step 13:

[0406] The server receives emotional feedback from users and makes adjustments to reflect this feedback in the conversation and future recommendations.

[0407] Step 14:

[0408] When a user provides their own expertise, the process begins by inputting the information using a terminal and generating it as an electronic publication.

[0409] Step 15:

[0410] The server analyzes the provided information, generates appropriate electronic publications that take emotional feedback into consideration, and presents the results to the user for confirmation.

[0411] (Example 2)

[0412] 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".

[0413] Conventional learning support systems have struggled to provide personalized learning experiences tailored to users' emotional states, often remaining limited to providing fixed information. Furthermore, they lacked the flexibility to appropriately respond to changes in user challenges and circumstances. This resulted in limited effectiveness and efficiency of learning.

[0414] 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.

[0415] In this invention, the server includes a device for receiving linguistic task information from a user, a device for analyzing semantic elements related to the task information, a device for selecting relevant documents and generating recommended information based on the analysis results, a generation device for facilitating dialogue between the user and information resources based on the generated recommended information, and a device for recognizing the user's emotional state and making adjustments to optimize the learning experience. This makes it possible to provide a flexible learning experience that is tailored to the individual state and needs of the user.

[0416] "User" refers to an individual or group of people who use the system to acquire, input, or engage in learning activities related to information.

[0417] "Language morphology challenge information" refers to natural language data, including text and audio, submitted by users to the system.

[0418] "Device" refers to hardware or software elements arranged or programmed to perform a specific function.

[0419] "Semantic elements" refer to important keywords and concepts contained in the information provided by the user.

[0420] "Analyzing" refers to the act of breaking down data or information and evaluating its constituent elements and interrelationships.

[0421] "Relevant documents" refer to literature and materials that are selected based on the user's problem information and are highly suitable and useful.

[0422] "Recommended information" refers to helpful advice and guidelines provided to users based on the analysis results.

[0423] A "generation device" refers to a component of a system designed to construct new content or responses based on specific data.

[0424] "Information resources" refer to digital content, including databases and knowledge bases, that are used to support users' learning and information gathering.

[0425] "Emotional state" refers to data or indicators that represent the user's current psychological or emotional condition.

[0426] "Making adjustments" refers to the process of modifying the system's output and operation according to the user's situation and needs.

[0427] A "flexible learning experience" refers to customized educational activities that adapt to the individual needs and circumstances of the users.

[0428] This invention is a system that utilizes information processing equipment and sentiment analysis technology to optimize the user's learning experience. The system comprises a server, a terminal, a generative AI, and a sentiment engine.

[0429] The server plays a central role in information processing. Using analysis modules, the server processes task data and questions provided by users. Specifically, it receives task information in linguistic form and extracts semantic elements such as keywords and main themes. Furthermore, the server selects relevant documents from a database and generates recommendation information. In this process, utilizing generative AI models makes it possible to provide effective interactive responses. Additionally, an emotion engine is used to analyze the user's emotional state and make adjustments to optimize the learning experience.

[0430] The terminal functions as an interface for users to input tasks and questions. Users begin the learning process by inputting tasks aligned with their learning goals. The terminal sends the input information to the server and displays the information returned from the server. The terminal also incorporates emotion recognition capabilities, using the camera and microphone to analyze the user's facial expressions and voice to determine their emotions, and then feeds that data back to the server.

[0431] Users set specific learning themes and communicate their interests and questions to the system along the way. For example, if a user enters a prompt such as "I want to learn about the latest project management techniques" into the terminal, the system will provide literature and visual materials related to that theme. Furthermore, if the server detects that the user is showing interest or is confused, it will adjust accordingly to provide more easily understandable information. This creates an environment where users can learn efficiently at their own pace.

[0432] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0433] Step 1:

[0434] The user enters assignment information about the content or topic they want to learn into the terminal. The entered text or audio data is acquired through the terminal's interface. For example, the user might enter the prompt "I want to learn about the latest project management techniques." The terminal then sends this information to the server as input data.

[0435] Step 2:

[0436] The server processes the issue information received from the terminal using an analysis module. First, the information is broken down into semantic elements, and keywords and main themes are extracted. This generates basic data for finding related content. Specifically, natural language processing technology is used to extract terms related to project management.

[0437] Step 3:

[0438] The server uses a generative AI model to select literature related to the extracted keywords from the database. It then generates information resources to present to the user as recommendations. This process efficiently scans a large database and filters out highly relevant materials. The output includes lists of visual materials and documents.

[0439] Step 4:

[0440] The server uses an emotion engine to analyze the user's emotional state. Emotional data is obtained based on information fed back from the device. This allows the server to measure the user's level of interest and confusion, and adjust the learning experience to be more personalized. For example, if the server determines that the user is confused, additional visual materials and detailed explanatory information will be generated.

[0441] Step 5:

[0442] The server sends the generated recommendations and adjusted content to the terminal. The terminal displays this information on its interface and presents it to the user. The user can learn based on the presented information, resolve questions at their own pace, and efficiently deepen their knowledge. The server continues to monitor the user's responses, and if new input is received, the process from step 2 is repeated.

[0443] (Application Example 2)

[0444] 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."

[0445] In modern manufacturing environments, improving work efficiency and managing worker health are crucial issues. However, current systems fail to provide adequate feedback that takes into account workers' emotional states and biometric data. As a result, it is difficult to obtain appropriate feedback that responds to workers' emotions, making it challenging to create an efficient work environment.

[0446] 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.

[0447] In this invention, the server includes a device for receiving task data in text format from a user; a device for selecting highly relevant materials based on the task data and generating recommendation information; a generation device for facilitating interaction between the user and the materials based on the recommendation information; a device for monitoring the user's biometric data and analyzing their emotional state; and a device for providing feedback to improve the user's work efficiency based on their emotional state. This enables efficient work support and health management in response to the analysis of the customer's emotional state based on their biometric data.

[0448] A "user" is a person who operates the system and provides information.

[0449] "Issue data" refers to information about problems or themes that users input into the system.

[0450] "Documents" refer to a collection of documents or data that contain information related to the assigned data.

[0451] "Recommended information" refers to highly relevant information selected and presented by the system based on the problem data provided by the user.

[0452] A "generation device" is a device that supports the interaction between users and materials based on recommendation information.

[0453] "Biometric data" refers to digital data collected from the user's body, such as heart rate and skin electrical activity.

[0454] "Emotional state" refers to the user's mental or emotional condition, as analyzed based on biometric data.

[0455] "Feedback" refers to advice or suggestions given to a user based on their emotional state.

[0456] This invention incorporates several functional components to realize a learning support system that provides feedback while taking into account the user's emotional state. Its main components and functions are described below.

[0457] The server receives text-based task data from the user and selects highly relevant materials from a literature database based on this data. Based on the selected materials, it generates recommendation information and uses an AI module to create responses that facilitate interaction between the user and the materials. Furthermore, the server uses a biometric data collection module to analyze the user's biometric data, such as heart rate and skin electrical activity, and uses an emotion engine to evaluate their emotional state. This provides a more effective learning experience by combining feedback based on the user's emotional state.

[0458] The terminal functions as an interface for users to input task data and send it to the server. The terminal also collects the user's biometric data in real time and monitors changes, providing a trigger for the system to provide appropriate feedback if the user is in an unfavorable state.

[0459] For example, if the user's heart rate, as received from the terminal, is higher than normal, the server will determine this to be a stressed state and provide feedback to the user such as, "We recommend you take a short break." In this way, it becomes possible to provide information tailored to each user's individual condition, thereby improving the user's work efficiency and mental health.

[0460] An example of a prompt message could be: "Please tell me the data points to consider when determining that a user is fatigued. Also, please suggest appropriate feedback for that situation." This is how one might instruct the generating AI.

[0461] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0462] Step 1:

[0463] The terminal receives task data in text format from the user as input. This data contains information about problems or themes that the user wants to solve. The terminal then sends the received task data to the server.

[0464] Step 2:

[0465] The server takes the received assignment data as input and selects highly relevant materials from the literature database. In this process, the analysis module extracts keywords and main themes, and then performs a material search based on them to output highly relevant materials.

[0466] Step 3:

[0467] The server generates recommendation information using selected materials. This recommendation information is the optimal collection of materials to provide knowledge to the user. The server uses a generative AI model to create responses that facilitate interaction between the materials and the user, and sends these responses to the terminal.

[0468] Step 4:

[0469] The terminal receives recommendation information and responses sent from the server and presents them to the user. The user uses this information to engage in learning activities and can input additional assignment data or questions as needed.

[0470] Step 5:

[0471] The device collects the user's biometric data in real time. Specifically, it acquires heart rate and skin electrical activity as input from devices such as smartwatches and smart bands, and sends this data to a server.

[0472] Step 6:

[0473] The server uses the received biometric data as input to analyze it with an emotion engine and evaluate the user's emotional state. For example, if the heart rate is higher than normal, it determines that the user is under stress. Based on this analysis, it generates optimal feedback for the user and sends it to the device.

[0474] Step 7:

[0475] The device receives feedback sent from the server and presents it to the user. This allows the user to receive advice and suggestions tailored to their emotional state, which can help improve their learning and work efficiency.

[0476] 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.

[0477] 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.

[0478] 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.

[0479] [Third Embodiment]

[0480] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0481] 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.

[0482] 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).

[0483] 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.

[0484] 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.

[0485] 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).

[0486] 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.

[0487] 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.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] 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".

[0492] This invention provides a learning support system that offers means for users to efficiently advance their learning. This system comprises a server, terminals, and a generative AI. The following describes each component in natural language.

[0493] server

[0494] The server handles the central processing of this system and has the function of selecting appropriate literature based on the assignment data received from the user. It accesses the literature database, analyzes keywords and themes, and extracts highly relevant literature. The server also works in conjunction with the generation AI to generate dialogue responses and simulation results based on the literature, and sends them to the terminal.

[0495] terminal

[0496] The device functions as an interface for users to input assignment data and questions. When a user enters text, it is sent to the server, and the results returned from the server are displayed to the user. The displayed information includes recommendations, conversational responses, and simulation results. The device features a user-friendly UI to support a smooth learning experience.

[0497] user

[0498] Through this system, users specify the topics they want to learn and the business problems they want to solve, enabling them to efficiently acquire information and deepen their knowledge. Users input problem data using their terminals, receive responses from the server, and review their interactions with literature and simulation results. Furthermore, they contribute their own expertise and participate in the process of generating electronic publications.

[0499] Specific example

[0500] For example, if a user wants to obtain information on "building sustainable business models," the user enters their question into the terminal. The terminal sends the entered information to the server, which then recommends relevant literature. Furthermore, based on the user's conditions, it generates simulation results regarding sustainability and provides interactive responses. In this way, the user can acquire concrete and practical knowledge.

[0501] The following describes the processing flow.

[0502] Step 1:

[0503] Users access the device's interface and input what they want to learn or the business problems they want to solve in text format.

[0504] Step 2:

[0505] The terminal prepares to send the entered text data to the server and sends the data to the server using the appropriate communication protocol.

[0506] Step 3:

[0507] The server analyzes the received assignment data using a text analysis module and extracts keywords and main themes.

[0508] Step 4:

[0509] The server searches the literature database based on the analyzed data and applies algorithms to identify highly relevant literature.

[0510] Step 5:

[0511] The server combines relevant bibliographic information, generates recommendation information, and sends the results to the terminal.

[0512] Step 6:

[0513] The terminal displays recommendation information received from the server to the user and provides them with literature options.

[0514] Step 7:

[0515] The user selects literature of interest from the provided options and enters further text for questions or more detailed discussions.

[0516] Step 8:

[0517] The terminal sends the user's input back to the server and requests the generation of an interactive response.

[0518] Step 9:

[0519] The server uses generative AI to generate conversational responses based on selected literature, creating specific answers to questions.

[0520] Step 10:

[0521] The server sends the generated response back to the terminal and continues the interaction with the user.

[0522] Step 11:

[0523] Users deepen their learning by interacting with the literature using the displayed information, and input new challenges or questions as needed.

[0524] Step 12:

[0525] If a user wishes to provide their own expertise to the system, they can send the information through their terminal, and the process of converting it into an electronic publication will begin.

[0526] Step 13:

[0527] The server analyzes the information provided by the user and performs configuration and proofreading for the creation of electronic publications.

[0528] Step 14:

[0529] The server generates commercial-grade electronic publications based on the processed information and provides the finished product to the user as a preview via a terminal.

[0530] (Example 1)

[0531] 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."

[0532] Modern learners are required to find the most relevant information from a vast amount of data and to learn efficiently. However, conventional learning support systems have shortcomings in selecting relevant information and generating in-depth, interactive responses, making it difficult to improve learning efficiency. Furthermore, there is a need for rapid and accurate responses in generating simulation results based on specific conditions and creating publications based on user information.

[0533] 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.

[0534] In this invention, the server includes means for acquiring task data by a device for inputting information from a user, means for accessing literature information sources based on the task data and selecting highly relevant information, and means for creating an interactive response using a generative AI model based on the selected information. This enables learners to efficiently and effectively acquire the necessary information and gain a deep understanding.

[0535] "Users" refers to individuals or groups who use the system to obtain information and attempt to learn or solve problems.

[0536] "Devices for inputting information" refers to electronic devices such as computers and smartphones that users use to input task data and conditions.

[0537] "Problem data" refers to information such as text and keywords entered by users to solve problems, and serves as the basic data for the system to process based on that content.

[0538] "Literature information sources" refer to collections of information that provide relevant information, such as books, articles, and databases.

[0539] "Highly relevant information" refers to information that is deemed to be highly useful or suitable for the problem data.

[0540] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to automatically generate conversational responses based on input information.

[0541] "Dialogue-based responses" refer to the presentation of information in the form of questions and answers, which is provided in a way that is easy for users to understand.

[0542] "Simulation" refers to the process of virtually reproducing how a certain phenomenon or system operates based on specific conditions.

[0543] "Digital publications" refer to publications that are provided electronically, such as ebooks and online reports.

[0544] The learning support system of the present invention provides advanced functions for efficiently acquiring information and promoting learning. This system is primarily implemented by hardware and software, including servers, terminals, and generative AI models. The following details each component and its operation.

[0545] server

[0546] The server handles the core processing of this system. Specifically, it analyzes received task data and searches for highly relevant information. The technologies used here include a database management system, from which it accesses literature sources. Furthermore, it utilizes a generative AI model to generate dialogue-based responses based on the literature. The generative AI model used for this purpose uses natural language processing techniques to automatically construct appropriate responses from the input information.

[0547] terminal

[0548] The terminal functions as an interface for users to input information. Users input task data and requirements on the terminal, and this data is sent to the server. The terminal displays the received information to the user and accepts further questions through interaction. The terminal interface is intuitive and designed for smooth user operation.

[0549] user

[0550] Users input what they want to learn or their business challenges into the system via their devices. Based on the information returned from the server, users proceed with their learning. Furthermore, the information provided by users is also used to create digital publications and is widely utilized.

[0551] Specific example

[0552] For example, suppose a user wants to obtain information on "building sustainable business models." In this case, the user enters keywords such as "sustainability, high profitability" into their device, and the server selects relevant literature based on those keywords. Furthermore, a generative AI model is used to create responses that show "specific examples of highly sustainable business models" and "the advantages of adopting them."

[0553] Example of a prompt

[0554] "Based on relevant literature on building sustainable business models, please generate AI simulation results and provide countermeasures in a conversational format."

[0555] This system aims to provide users with effective learning support and deepen their knowledge. By using specific prompts, the generative AI model provides appropriate information tailored to the user's needs.

[0556] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0557] Step 1:

[0558] The terminal receives task data from the user as input. The user enters what they want to learn or a specific business task in text format into the terminal's input field and presses the submit button. The terminal sends this input data to the server.

[0559] Step 2:

[0560] The server receives assignment data from the terminal as input and performs analysis. Using a database access module, it searches for literature sources and selects literature relevant to the assignment data. The selected literature data is stored on the server.

[0561] Step 3:

[0562] The server passes the selected literature as input to the generative AI model. The generative AI model uses natural language processing techniques to generate conversational responses based on the literature. The generated responses are formatted in a way that is easy for the user to understand.

[0563] Step 4:

[0564] The server sends the generated interactive response as output to the terminal. The terminal displays this response to the user. A user-friendly interface is used to provide information in a visually clear and easy-to-understand manner.

[0565] Step 5:

[0566] The user continues learning based on the displayed information. They can also enter additional questions into their device as needed and receive responses from the server again. The server processes the input again, continuing to provide the information the user requests.

[0567] The above outlines the specific processing steps of the system program.

[0568] (Application Example 1)

[0569] 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."

[0570] In training for operating interconnected machinery in factories, there is a need for a safe and efficient way for users to learn how to operate the machines without relying on the actual equipment. Furthermore, a challenge lies in the difficulty of obtaining concrete feedback derived from on-site practice.

[0571] 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.

[0572] In this invention, the server includes means for receiving operation tasks in natural language format from a user, means for generating virtual operations of a collaborative machine based on the operation tasks, means for providing an environment in which the user can interactively experience the generated virtual operations, and means for analyzing the user's inquiries and generating appropriate dialogue responses. This enables the user to safely learn how to operate a machine in a virtual environment without relying on a real machine, and to learn efficiently and concretely.

[0573] A "user" is an entity that uses the system to learn operational tasks.

[0574] "Natural language forms" refer to the forms of language that humans use on a daily basis, including text as an example.

[0575] "Operational tasks" are assignments designed to teach the specific operating methods and procedures of the linked machines.

[0576] "Cooperative machinery" refers to industrial equipment and robots used in factories and work sites.

[0577] "Virtual operation" refers to a simulation environment that simulates actual machine operation, allowing learners to experience it firsthand.

[0578] An "interactive learning environment" refers to a virtual learning environment where users can interact with the system in a two-way manner while progressing through their learning.

[0579] A "question" refers to any statement made by a user to the system that includes questions or requests for confirmation.

[0580] "Appropriate dialogue response" refers to a contextually appropriate response generated by the system in response to a user's question.

[0581] To realize this application, the server first receives an operational task from the user in natural language format. This may include prompts such as, "Please tell me the steps to efficiently program a transport robot." After receiving the task, the server analyzes it and prepares data to generate the relevant virtual operation. The virtual operation is provided as a simulation environment that mimics Tanli's industrial robots, and users can access this environment via smartphones or head-mounted displays to conduct training without relying on actual equipment.

[0582] On the user side, the device provides an interface, enabling an interactive experience based on received virtual operation data. The generative AI model generates appropriate responses to user inquiries in real time, organizing and presenting relevant information in response to inputs called prompts to facilitate two-way communication. This allows users to gain efficient and deep learning.

[0583] As a concrete example, users can learn how to program transport robots using their smartphones. In this process, the generating AI will respond to specific questions provided by the user with relevant information and procedures as needed. Possible prompts include questions such as, "Please tell me the steps to efficiently program a transport robot."

[0584] The hardware used includes smartphones, head-mounted displays, and a computer system capable of running virtual operations, while the software utilizes machine learning libraries such as TensorFlow and PyTorch for data analysis. This enables a learning support system that integrates virtual operations and interactive responses.

[0585] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0586] Step 1:

[0587] The terminal receives an operational task from the user in the form of a prompt. This prompt is treated as input data for natural language processing.

[0588] Step 2:

[0589] The server analyzes the prompt text and extracts relevant information using a generative AI model. Specifically, it extracts keywords from the input data using natural language processing techniques and then uses these keywords to obtain relevant information from a literature database (e.g., an industrial robot operation manual). At this stage, it prepares the data necessary to generate a relevant virtual operation simulation.

[0590] Step 3:

[0591] The server generates a virtual operation based on the acquired information and constructs it as data for an interactive learning environment. Here, the simulation data necessary for the virtual operation is integrated and sent to the terminal as a single package. This package also includes dialogue response data from the generated AI model.

[0592] Step 4:

[0593] The terminal interactively displays and provides the user with the received virtual operation data. Through this, the user virtually experiences operating the robot. The terminal uses a head-mounted display or smartphone and reproduces the virtual environment using advanced graphics technology.

[0594] Step 5:

[0595] The user interacts with the AI ​​model through virtual operation and, as needed, sends additional prompt messages via the terminal. These additional prompt messages are entered by the user based on their understanding of the current situation and the steps they wish to learn more about.

[0596] Step 6:

[0597] The server generates a response to the received additional prompt using the AI ​​model and sends it back to the user in real time. At that time, it provides more specific information about operation methods and precautions based on the virtual operation status.

[0598] This process will enable users to learn how to operate the robot safely and effectively.

[0599] 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.

[0600] This invention provides an effective learning experience tailored to the user's emotions by combining an emotion engine with a learning support system. The system comprises a server, a terminal, a generative AI, and an emotion engine. Each component is described below.

[0601] server

[0602] The server is the central processing component that receives task data and input information from users. The server uses an analysis module to extract keywords and main themes from the task data and selects relevant literature from a literature database. Furthermore, it uses an emotion engine to analyze the user's emotional state and optimizes recommendation information and dialogue content based on this analysis. Another role of the server is to generate responses that facilitate interaction with the user using generative AI and send them to the terminal.

[0603] terminal

[0604] The terminal functions as an interface where users input tasks and questions, and data, including emotional triggers, is collected. The terminal sends the collected information to a server, and the information returned from the server (recommendations and conversation content) is displayed to the user. The terminal also monitors user interaction in real time through the UI and feeds back to the system using emotional changes as triggers.

[0605] User

[0606] Users begin the learning process by setting individual learning goals using this system and inputting assignment data into their terminal. The user's emotional state is also transmitted to the system as part of the input information, optimizing each individual learning experience. Specifically, when a user shows interest or is confused, the server automatically adjusts its conversational responses and provides information in a format that is easy for the user to understand.

[0607] Specific example

[0608] For example, if a user wishes to learn about "improving project management skills," they would input relevant assignments as initial input and begin learning. The user would ask questions about topics of interest, while the system simultaneously recognizes their emotions. The server uses an emotion engine to analyze the user's interests and understanding, and if, for example, the user appears confused, it would provide more specific and visual information or offer additional hints to clarify the conversation. In this way, the user can learn at an optimal pace and with the most relevant content.

[0609] The following describes the processing flow.

[0610] Step 1:

[0611] Users use the device's interface to input the topics they want to learn about or the problems they want to solve in text format.

[0612] Step 2:

[0613] The terminal sends the entered text data to the server, and at the same time, it also collects information necessary for emotion analysis, such as the user's facial expressions and voice data.

[0614] Step 3:

[0615] The server analyzes the received issue data using an analysis module and extracts key keywords and themes.

[0616] Step 4:

[0617] The server searches the literature database and selects highly relevant literature based on the extracted keywords.

[0618] Step 5:

[0619] The server utilizes an emotion engine to generate recommendation information that takes into account the individual emotional state of each user, based on the selected literature information.

[0620] Step 6:

[0621] The server sends the generated recommendation information to the terminal and suggests appropriate learning content to the user.

[0622] Step 7:

[0623] The terminal displays received recommendation information to the user and provides an interface to make it easier for the user to select literature.

[0624] Step 8:

[0625] Users select literature of interest from the recommended selections and provide additional input to prompt further questions or discussions.

[0626] Step 9:

[0627] The terminal then sends the user's additional input back to the server and requests the generation of the dialogue content.

[0628] Step 10:

[0629] The server uses generative AI to generate conversational responses based on selected literature and the user's emotional state, including visualizations and concrete examples of information as needed.

[0630] Step 11:

[0631] The server sends the generated dialogue response back to the terminal, providing information in a format that is easy for the user to understand.

[0632] Step 12:

[0633] Users utilize the presented information and, through interaction, progress through the learning process, sending emotional feedback to the system.

[0634] Step 13:

[0635] The server receives emotional feedback from users and makes adjustments to reflect this feedback in the conversation and future recommendations.

[0636] Step 14:

[0637] When a user provides their own expertise, the process begins by inputting the information using a terminal and generating it as an electronic publication.

[0638] Step 15:

[0639] The server analyzes the provided information, generates appropriate electronic publications that take emotional feedback into consideration, and presents the results to the user for confirmation.

[0640] (Example 2)

[0641] 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."

[0642] Conventional learning support systems have struggled to provide personalized learning experiences tailored to users' emotional states, often remaining limited to providing fixed information. Furthermore, they lacked the flexibility to appropriately respond to changes in user challenges and circumstances. This resulted in limited effectiveness and efficiency of learning.

[0643] 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.

[0644] In this invention, the server includes a device for receiving linguistic task information from a user, a device for analyzing semantic elements related to the task information, a device for selecting relevant documents and generating recommended information based on the analysis results, a generation device for facilitating dialogue between the user and information resources based on the generated recommended information, and a device for recognizing the user's emotional state and making adjustments to optimize the learning experience. This makes it possible to provide a flexible learning experience that is tailored to the individual state and needs of the user.

[0645] "User" refers to an individual or group of people who use the system to acquire, input, or engage in learning activities related to information.

[0646] "Language morphology challenge information" refers to natural language data, including text and audio, submitted by users to the system.

[0647] "Device" refers to hardware or software elements arranged or programmed to perform a specific function.

[0648] "Semantic elements" refer to important keywords and concepts contained in the information provided by the user.

[0649] "Analyzing" refers to the act of breaking down data or information and evaluating its constituent elements and interrelationships.

[0650] "Relevant documents" refer to literature and materials that are selected based on the user's problem information and are highly suitable and useful.

[0651] "Recommended information" refers to helpful advice and guidelines provided to users based on the analysis results.

[0652] A "generation device" refers to a component of a system designed to construct new content or responses based on specific data.

[0653] "Information resources" refer to digital content, including databases and knowledge bases, that are used to support users' learning and information gathering.

[0654] "Emotional state" refers to data or indicators that represent the user's current psychological or emotional condition.

[0655] "Making adjustments" refers to the process of modifying the system's output and operation according to the user's situation and needs.

[0656] A "flexible learning experience" refers to customized educational activities that adapt to the individual needs and circumstances of the users.

[0657] This invention is a system that utilizes information processing equipment and sentiment analysis technology to optimize the user's learning experience. The system comprises a server, a terminal, a generative AI, and a sentiment engine.

[0658] The server plays a central role in information processing. Using analysis modules, the server processes task data and questions provided by users. Specifically, it receives task information in linguistic form and extracts semantic elements such as keywords and main themes. Furthermore, the server selects relevant documents from a database and generates recommendation information. In this process, utilizing generative AI models makes it possible to provide effective interactive responses. Additionally, an emotion engine is used to analyze the user's emotional state and make adjustments to optimize the learning experience.

[0659] The terminal functions as an interface for users to input tasks and questions. Users begin the learning process by inputting tasks aligned with their learning goals. The terminal sends the input information to the server and displays the information returned from the server. The terminal also incorporates emotion recognition capabilities, using the camera and microphone to analyze the user's facial expressions and voice to determine their emotions, and then feeds that data back to the server.

[0660] Users set specific learning themes and communicate their interests and questions to the system along the way. For example, if a user enters a prompt such as "I want to learn about the latest project management techniques" into the terminal, the system will provide literature and visual materials related to that theme. Furthermore, if the server detects that the user is showing interest or is confused, it will adjust accordingly to provide more easily understandable information. This creates an environment where users can learn efficiently at their own pace.

[0661] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0662] Step 1:

[0663] The user enters assignment information about the content or topic they want to learn into the terminal. The entered text or audio data is acquired through the terminal's interface. For example, the user might enter the prompt "I want to learn about the latest project management techniques." The terminal then sends this information to the server as input data.

[0664] Step 2:

[0665] The server processes the issue information received from the terminal using an analysis module. First, the information is broken down into semantic elements, and keywords and main themes are extracted. This generates basic data for finding related content. Specifically, natural language processing technology is used to extract terms related to project management.

[0666] Step 3:

[0667] The server uses a generative AI model to select literature related to the extracted keywords from the database. It then generates information resources to present to the user as recommendations. This process efficiently scans a large database and filters out highly relevant materials. The output includes lists of visual materials and documents.

[0668] Step 4:

[0669] The server uses an emotion engine to analyze the user's emotional state. Emotional data is obtained based on information fed back from the device. This allows the server to measure the user's level of interest and confusion, and adjust the learning experience to be more personalized. For example, if the server determines that the user is confused, additional visual materials and detailed explanatory information will be generated.

[0670] Step 5:

[0671] The server sends the generated recommendations and adjusted content to the terminal. The terminal displays this information on its interface and presents it to the user. The user can learn based on the presented information, resolve questions at their own pace, and efficiently deepen their knowledge. The server continues to monitor the user's responses, and if new input is received, the process from step 2 is repeated.

[0672] (Application Example 2)

[0673] 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."

[0674] In modern manufacturing environments, improving work efficiency and managing worker health are crucial issues. However, current systems fail to provide adequate feedback that takes into account workers' emotional states and biometric data. As a result, it is difficult to obtain appropriate feedback that responds to workers' emotions, making it challenging to create an efficient work environment.

[0675] 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.

[0676] In this invention, the server includes a device for receiving task data in text format from a user; a device for selecting highly relevant materials based on the task data and generating recommendation information; a generation device for facilitating interaction between the user and the materials based on the recommendation information; a device for monitoring the user's biometric data and analyzing their emotional state; and a device for providing feedback to improve the user's work efficiency based on their emotional state. This enables efficient work support and health management in response to the analysis of the customer's emotional state based on their biometric data.

[0677] A "user" is a person who operates the system and provides information.

[0678] "Issue data" refers to information about problems or themes that users input into the system.

[0679] "Documents" refer to a collection of documents or data that contain information related to the assigned data.

[0680] "Recommended information" refers to highly relevant information selected and presented by the system based on the problem data provided by the user.

[0681] A "generation device" is a device that supports the interaction between users and materials based on recommendation information.

[0682] "Biometric data" refers to digital data collected from the user's body, such as heart rate and skin electrical activity.

[0683] "Emotional state" refers to the user's mental or emotional condition, as analyzed based on biometric data.

[0684] "Feedback" refers to advice or suggestions given to a user based on their emotional state.

[0685] This invention incorporates several functional components to realize a learning support system that provides feedback while taking into account the user's emotional state. Its main components and functions are described below.

[0686] The server receives text-based task data from the user and selects highly relevant materials from a literature database based on this data. Based on the selected materials, it generates recommendation information and uses an AI module to create responses that facilitate interaction between the user and the materials. Furthermore, the server uses a biometric data collection module to analyze the user's biometric data, such as heart rate and skin electrical activity, and uses an emotion engine to evaluate their emotional state. This provides a more effective learning experience by combining feedback based on the user's emotional state.

[0687] The terminal functions as an interface for users to input task data and send it to the server. The terminal also collects the user's biometric data in real time and monitors changes, providing a trigger for the system to provide appropriate feedback if the user is in an unfavorable state.

[0688] For example, if the user's heart rate, as received from the terminal, is higher than normal, the server will determine this to be a stressed state and provide feedback to the user such as, "We recommend you take a short break." In this way, it becomes possible to provide information tailored to each user's individual condition, thereby improving the user's work efficiency and mental health.

[0689] An example of a prompt message could be: "Please tell me the data points to consider when determining that a user is fatigued. Also, please suggest appropriate feedback for that situation." This is how one might instruct the generating AI.

[0690] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0691] Step 1:

[0692] The terminal receives task data in text format from the user as input. This data contains information about problems or themes that the user wants to solve. The terminal then sends the received task data to the server.

[0693] Step 2:

[0694] The server takes the received assignment data as input and selects highly relevant materials from the literature database. In this process, the analysis module extracts keywords and main themes, and then performs a material search based on them to output highly relevant materials.

[0695] Step 3:

[0696] The server generates recommendation information using selected materials. This recommendation information is the optimal collection of materials to provide knowledge to the user. The server uses a generative AI model to create responses that facilitate interaction between the materials and the user, and sends these responses to the terminal.

[0697] Step 4:

[0698] The terminal receives recommendation information and responses sent from the server and presents them to the user. The user uses this information to engage in learning activities and can input additional assignment data or questions as needed.

[0699] Step 5:

[0700] The device collects the user's biometric data in real time. Specifically, it acquires heart rate and skin electrical activity as input from devices such as smartwatches and smart bands, and sends this data to a server.

[0701] Step 6:

[0702] The server uses the received biometric data as input to analyze it with an emotion engine and evaluate the user's emotional state. For example, if the heart rate is higher than normal, it determines that the user is under stress. Based on this analysis, it generates optimal feedback for the user and sends it to the device.

[0703] Step 7:

[0704] The device receives feedback sent from the server and presents it to the user. This allows the user to receive advice and suggestions tailored to their emotional state, which can help improve their learning and work efficiency.

[0705] 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.

[0706] 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.

[0707] 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.

[0708] [Fourth Embodiment]

[0709] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0710] 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.

[0711] 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).

[0712] 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.

[0713] 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.

[0714] 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).

[0715] 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.

[0716] 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 in 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.

[0717] 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.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] 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".

[0722] This invention provides a learning support system that offers means for users to efficiently advance their learning. This system comprises a server, terminals, and a generative AI. The following describes each component in natural language.

[0723] server

[0724] The server handles the central processing of this system and has the function of selecting appropriate literature based on the assignment data received from the user. It accesses the literature database, analyzes keywords and themes, and extracts highly relevant literature. The server also works in conjunction with the generation AI to generate dialogue responses and simulation results based on the literature, and sends them to the terminal.

[0725] terminal

[0726] The device functions as an interface for users to input assignment data and questions. When a user enters text, it is sent to the server, and the results returned from the server are displayed to the user. The displayed information includes recommendations, conversational responses, and simulation results. The device features a user-friendly UI to support a smooth learning experience.

[0727] user

[0728] Through this system, users specify the topics they want to learn and the business problems they want to solve, enabling them to efficiently acquire information and deepen their knowledge. Users input problem data using their terminals, receive responses from the server, and review their interactions with literature and simulation results. Furthermore, they contribute their own expertise and participate in the process of generating electronic publications.

[0729] Specific example

[0730] For example, if a user wants to obtain information on "building sustainable business models," the user enters their question into the terminal. The terminal sends the entered information to the server, which then recommends relevant literature. Furthermore, based on the user's conditions, it generates simulation results regarding sustainability and provides interactive responses. In this way, the user can acquire concrete and practical knowledge.

[0731] The following describes the processing flow.

[0732] Step 1:

[0733] Users access the device's interface and input what they want to learn or the business problems they want to solve in text format.

[0734] Step 2:

[0735] The terminal prepares to send the entered text data to the server and sends the data to the server using the appropriate communication protocol.

[0736] Step 3:

[0737] The server analyzes the received assignment data using a text analysis module and extracts keywords and main themes.

[0738] Step 4:

[0739] The server searches the literature database based on the analyzed data and applies algorithms to identify highly relevant literature.

[0740] Step 5:

[0741] The server combines relevant bibliographic information, generates recommendation information, and sends the results to the terminal.

[0742] Step 6:

[0743] The terminal displays recommendation information received from the server to the user and provides them with literature options.

[0744] Step 7:

[0745] The user selects literature of interest from the provided options and enters further text for questions or more detailed discussions.

[0746] Step 8:

[0747] The terminal sends the user's input back to the server and requests the generation of an interactive response.

[0748] Step 9:

[0749] The server uses generative AI to generate conversational responses based on selected literature, creating specific answers to questions.

[0750] Step 10:

[0751] The server sends the generated response back to the terminal and continues the interaction with the user.

[0752] Step 11:

[0753] Users deepen their learning by interacting with the literature using the displayed information, and input new challenges or questions as needed.

[0754] Step 12:

[0755] If a user wishes to provide their own expertise to the system, they can send the information through their terminal, and the process of converting it into an electronic publication will begin.

[0756] Step 13:

[0757] The server analyzes the information provided by the user and performs configuration and proofreading for the creation of electronic publications.

[0758] Step 14:

[0759] The server generates commercial-grade electronic publications based on the processed information and provides the finished product to the user as a preview via a terminal.

[0760] (Example 1)

[0761] 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".

[0762] Modern learners are required to find the most relevant information from a vast amount of data and to learn efficiently. However, conventional learning support systems have shortcomings in selecting relevant information and generating in-depth, interactive responses, making it difficult to improve learning efficiency. Furthermore, there is a need for rapid and accurate responses in generating simulation results based on specific conditions and creating publications based on user information.

[0763] 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.

[0764] In this invention, the server includes means for acquiring task data by a device for inputting information from a user, means for accessing literature information sources based on the task data and selecting highly relevant information, and means for creating an interactive response using a generative AI model based on the selected information. This enables learners to efficiently and effectively acquire the necessary information and gain a deep understanding.

[0765] "Users" refers to individuals or groups who use the system to obtain information and attempt to learn or solve problems.

[0766] "Devices for inputting information" refers to electronic devices such as computers and smartphones that users use to input task data and conditions.

[0767] "Problem data" refers to information such as text and keywords entered by users to solve problems, and serves as the basic data for the system to process based on that content.

[0768] "Literature information sources" refer to collections of information that provide relevant information, such as books, articles, and databases.

[0769] "Highly relevant information" refers to information that is deemed to be highly useful or suitable for the problem data.

[0770] A "generative AI model" refers to an algorithm or system that uses artificial intelligence technology to automatically generate conversational responses based on input information.

[0771] "Dialogue-based responses" refer to the presentation of information in the form of questions and answers, which is provided in a way that is easy for users to understand.

[0772] "Simulation" refers to the process of virtually reproducing how a certain phenomenon or system operates based on specific conditions.

[0773] "Digital publications" refer to publications that are provided electronically, such as ebooks and online reports.

[0774] The learning support system of the present invention provides advanced functions for efficiently acquiring information and promoting learning. This system is primarily implemented by hardware and software, including servers, terminals, and generative AI models. The following details each component and its operation.

[0775] server

[0776] The server handles the core processing of this system. Specifically, it analyzes received task data and searches for highly relevant information. The technologies used here include a database management system, from which it accesses literature sources. Furthermore, it utilizes a generative AI model to generate dialogue-based responses based on the literature. The generative AI model used for this purpose uses natural language processing techniques to automatically construct appropriate responses from the input information.

[0777] terminal

[0778] The terminal functions as an interface for users to input information. Users input task data and requirements on the terminal, and this data is sent to the server. The terminal displays the received information to the user and accepts further questions through interaction. The terminal interface is intuitive and designed for smooth user operation.

[0779] user

[0780] Users input what they want to learn or their business challenges into the system via their devices. Based on the information returned from the server, users proceed with their learning. Furthermore, the information provided by users is also used to create digital publications and is widely utilized.

[0781] Specific example

[0782] For example, suppose a user wants to obtain information on "building sustainable business models." In this case, the user enters keywords such as "sustainability, high profitability" into their device, and the server selects relevant literature based on those keywords. Furthermore, a generative AI model is used to create responses that show "specific examples of highly sustainable business models" and "the advantages of adopting them."

[0783] Example of a prompt

[0784] "Based on relevant literature on building sustainable business models, please generate AI simulation results and provide countermeasures in a conversational format."

[0785] This system aims to provide users with effective learning support and deepen their knowledge. By using specific prompts, the generative AI model provides appropriate information tailored to the user's needs.

[0786] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0787] Step 1:

[0788] The terminal receives task data from the user as input. The user enters what they want to learn or a specific business task in text format into the terminal's input field and presses the submit button. The terminal sends this input data to the server.

[0789] Step 2:

[0790] The server receives assignment data from the terminal as input and performs analysis. Using a database access module, it searches for literature sources and selects literature relevant to the assignment data. The selected literature data is stored on the server.

[0791] Step 3:

[0792] The server passes the selected literature as input to the generative AI model. The generative AI model uses natural language processing techniques to generate conversational responses based on the literature. The generated responses are formatted in a way that is easy for the user to understand.

[0793] Step 4:

[0794] The server sends the generated interactive response as output to the terminal. The terminal displays this response to the user. A user-friendly interface is used to provide information in a visually clear and easy-to-understand manner.

[0795] Step 5:

[0796] The user continues learning based on the displayed information. They can also enter additional questions into their device as needed and receive responses from the server again. The server processes the input again, continuing to provide the information the user requests.

[0797] The above outlines the specific processing steps of the system program.

[0798] (Application Example 1)

[0799] 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".

[0800] In training for operating interconnected machinery in factories, there is a need for a safe and efficient way for users to learn how to operate the machines without relying on the actual equipment. Furthermore, a challenge lies in the difficulty of obtaining concrete feedback derived from on-site practice.

[0801] 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.

[0802] In this invention, the server includes means for receiving operation tasks in natural language format from a user, means for generating virtual operations of a collaborative machine based on the operation tasks, means for providing an environment in which the user can interactively experience the generated virtual operations, and means for analyzing the user's inquiries and generating appropriate dialogue responses. This enables the user to safely learn how to operate a machine in a virtual environment without relying on a real machine, and to learn efficiently and concretely.

[0803] A "user" is an entity that uses the system to learn operational tasks.

[0804] "Natural language forms" refer to the forms of language that humans use on a daily basis, including text as an example.

[0805] "Operational tasks" are assignments designed to teach the specific operating methods and procedures of the linked machines.

[0806] "Cooperative machinery" refers to industrial equipment and robots used in factories and work sites.

[0807] "Virtual operation" refers to a simulation environment that simulates actual machine operation, allowing learners to experience it firsthand.

[0808] An "interactive learning environment" refers to a virtual learning environment where users can interact with the system in a two-way manner while progressing through their learning.

[0809] A "question" refers to any statement made by a user to the system that includes questions or requests for confirmation.

[0810] "Appropriate dialogue response" refers to a contextually appropriate response generated by the system in response to a user's question.

[0811] To realize this application, the server first receives an operational task from the user in natural language format. This may include prompts such as, "Please tell me the steps to efficiently program a transport robot." After receiving the task, the server analyzes it and prepares data to generate the relevant virtual operation. The virtual operation is provided as a simulation environment that mimics Tanli's industrial robots, and users can access this environment via smartphones or head-mounted displays to conduct training without relying on actual equipment.

[0812] On the user side, the device provides an interface, enabling an interactive experience based on received virtual operation data. The generative AI model generates appropriate responses to user inquiries in real time, organizing and presenting relevant information in response to inputs called prompts to facilitate two-way communication. This allows users to gain efficient and deep learning.

[0813] As a concrete example, users can learn how to program transport robots using their smartphones. In this process, the generating AI will respond to specific questions provided by the user with relevant information and procedures as needed. Possible prompts include questions such as, "Please tell me the steps to efficiently program a transport robot."

[0814] The hardware used includes smartphones, head-mounted displays, and a computer system capable of running virtual operations, while the software utilizes machine learning libraries such as TensorFlow and PyTorch for data analysis. This enables a learning support system that integrates virtual operations and interactive responses.

[0815] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0816] Step 1:

[0817] The terminal receives an operational task from the user in the form of a prompt. This prompt is treated as input data for natural language processing.

[0818] Step 2:

[0819] The server analyzes the prompt text and extracts relevant information using a generative AI model. Specifically, it extracts keywords from the input data using natural language processing techniques and then uses these keywords to obtain relevant information from a literature database (e.g., an industrial robot operation manual). At this stage, it prepares the data necessary to generate a relevant virtual operation simulation.

[0820] Step 3:

[0821] The server generates a virtual operation based on the acquired information and constructs it as data for an interactive learning environment. Here, the simulation data necessary for the virtual operation is integrated and sent to the terminal as a single package. This package also includes dialogue response data from the generated AI model.

[0822] Step 4:

[0823] The terminal interactively displays and provides the user with the received virtual operation data. Through this, the user virtually experiences operating the robot. The terminal uses a head-mounted display or smartphone and reproduces the virtual environment using advanced graphics technology.

[0824] Step 5:

[0825] The user interacts with the AI ​​model through virtual operation and, as needed, sends additional prompt messages via the terminal. These additional prompt messages are entered by the user based on their understanding of the current situation and the steps they wish to learn more about.

[0826] Step 6:

[0827] The server generates a response to the received additional prompt using the AI ​​model and sends it back to the user in real time. At that time, it provides more specific information about operation methods and precautions based on the virtual operation status.

[0828] This process will enable users to learn how to operate the robot safely and effectively.

[0829] 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.

[0830] This invention provides an effective learning experience tailored to the user's emotions by combining an emotion engine with a learning support system. The system comprises a server, a terminal, a generative AI, and an emotion engine. Each component is described below.

[0831] server

[0832] The server is the central processing component that receives task data and input information from users. The server uses an analysis module to extract keywords and main themes from the task data and selects relevant literature from a literature database. Furthermore, it uses an emotion engine to analyze the user's emotional state and optimizes recommendation information and dialogue content based on this analysis. Another role of the server is to generate responses that facilitate interaction with the user using generative AI and send them to the terminal.

[0833] terminal

[0834] The terminal functions as an interface where users input tasks and questions, and data, including emotional triggers, is collected. The terminal sends the collected information to a server, and the information returned from the server (recommendations and conversation content) is displayed to the user. The terminal also monitors user interaction in real time through the UI and feeds back to the system using emotional changes as triggers.

[0835] User

[0836] Users begin the learning process by setting individual learning goals using this system and inputting assignment data into their terminal. The user's emotional state is also transmitted to the system as part of the input information, optimizing each individual learning experience. Specifically, when a user shows interest or is confused, the server automatically adjusts its conversational responses and provides information in a format that is easy for the user to understand.

[0837] Specific example

[0838] For example, if a user wishes to learn about "improving project management skills," they would input relevant assignments as initial input and begin learning. The user would ask questions about topics of interest, while the system simultaneously recognizes their emotions. The server uses an emotion engine to analyze the user's interests and understanding, and if, for example, the user appears confused, it would provide more specific and visual information or offer additional hints to clarify the conversation. In this way, the user can learn at an optimal pace and with the most relevant content.

[0839] The following describes the processing flow.

[0840] Step 1:

[0841] Users use the device's interface to input the topics they want to learn about or the problems they want to solve in text format.

[0842] Step 2:

[0843] The terminal sends the entered text data to the server, and at the same time, it also collects information necessary for emotion analysis, such as the user's facial expressions and voice data.

[0844] Step 3:

[0845] The server analyzes the received issue data using an analysis module and extracts key keywords and themes.

[0846] Step 4:

[0847] The server searches the literature database and selects highly relevant literature based on the extracted keywords.

[0848] Step 5:

[0849] The server utilizes an emotion engine to generate recommendation information that takes into account the individual emotional state of each user, based on the selected literature information.

[0850] Step 6:

[0851] The server sends the generated recommendation information to the terminal and suggests appropriate learning content to the user.

[0852] Step 7:

[0853] The terminal displays received recommendation information to the user and provides an interface to make it easier for the user to select literature.

[0854] Step 8:

[0855] Users select literature of interest from the recommended selections and provide additional input to prompt further questions or discussions.

[0856] Step 9:

[0857] The terminal then sends the user's additional input back to the server and requests the generation of the dialogue content.

[0858] Step 10:

[0859] The server uses generative AI to generate conversational responses based on selected literature and the user's emotional state, including visualizations and concrete examples of information as needed.

[0860] Step 11:

[0861] The server sends the generated dialogue response back to the terminal, providing information in a format that is easy for the user to understand.

[0862] Step 12:

[0863] Users utilize the presented information and, through interaction, progress through the learning process, sending emotional feedback to the system.

[0864] Step 13:

[0865] The server receives emotional feedback from users and makes adjustments to reflect this feedback in the conversation and future recommendations.

[0866] Step 14:

[0867] When a user provides their own expertise, the process begins by inputting the information using a terminal and generating it as an electronic publication.

[0868] Step 15:

[0869] The server analyzes the provided information, generates appropriate electronic publications that take emotional feedback into consideration, and presents the results to the user for confirmation.

[0870] (Example 2)

[0871] 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".

[0872] Conventional learning support systems have struggled to provide personalized learning experiences tailored to users' emotional states, often remaining limited to providing fixed information. Furthermore, they lacked the flexibility to appropriately respond to changes in user challenges and circumstances. This resulted in limited effectiveness and efficiency of learning.

[0873] 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.

[0874] In this invention, the server includes a device for receiving linguistic task information from a user, a device for analyzing semantic elements related to the task information, a device for selecting relevant documents and generating recommended information based on the analysis results, a generation device for facilitating dialogue between the user and information resources based on the generated recommended information, and a device for recognizing the user's emotional state and making adjustments to optimize the learning experience. This makes it possible to provide a flexible learning experience that is tailored to the individual state and needs of the user.

[0875] "User" refers to an individual or group of people who use the system to acquire, input, or engage in learning activities related to information.

[0876] "Language morphology challenge information" refers to natural language data, including text and audio, submitted by users to the system.

[0877] "Device" refers to hardware or software elements arranged or programmed to perform a specific function.

[0878] "Semantic elements" refer to important keywords and concepts contained in the information provided by the user.

[0879] "Analyzing" refers to the act of breaking down data or information and evaluating its constituent elements and interrelationships.

[0880] "Relevant documents" refer to literature and materials that are selected based on the user's problem information and are highly suitable and useful.

[0881] "Recommended information" refers to helpful advice and guidelines provided to users based on the analysis results.

[0882] A "generation device" refers to a component of a system designed to construct new content or responses based on specific data.

[0883] "Information resources" refer to digital content, including databases and knowledge bases, that are used to support users' learning and information gathering.

[0884] "Emotional state" refers to data or indicators that represent the user's current psychological or emotional condition.

[0885] "Making adjustments" refers to the process of modifying the system's output and operation according to the user's situation and needs.

[0886] A "flexible learning experience" refers to customized educational activities that adapt to the individual needs and circumstances of the users.

[0887] This invention is a system that utilizes information processing equipment and sentiment analysis technology to optimize the user's learning experience. The system comprises a server, a terminal, a generative AI, and a sentiment engine.

[0888] The server plays a central role in information processing. Using analysis modules, the server processes task data and questions provided by users. Specifically, it receives task information in linguistic form and extracts semantic elements such as keywords and main themes. Furthermore, the server selects relevant documents from a database and generates recommendation information. In this process, utilizing generative AI models makes it possible to provide effective interactive responses. Additionally, an emotion engine is used to analyze the user's emotional state and make adjustments to optimize the learning experience.

[0889] The terminal functions as an interface for users to input tasks and questions. Users begin the learning process by inputting tasks aligned with their learning goals. The terminal sends the input information to the server and displays the information returned from the server. The terminal also incorporates emotion recognition capabilities, using the camera and microphone to analyze the user's facial expressions and voice to determine their emotions, and then feeds that data back to the server.

[0890] Users set specific learning themes and communicate their interests and questions to the system along the way. For example, if a user enters a prompt such as "I want to learn about the latest project management techniques" into the terminal, the system will provide literature and visual materials related to that theme. Furthermore, if the server detects that the user is showing interest or is confused, it will adjust accordingly to provide more easily understandable information. This creates an environment where users can learn efficiently at their own pace.

[0891] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0892] Step 1:

[0893] The user enters assignment information about the content or topic they want to learn into the terminal. The entered text or audio data is acquired through the terminal's interface. For example, the user might enter the prompt "I want to learn about the latest project management techniques." The terminal then sends this information to the server as input data.

[0894] Step 2:

[0895] The server processes the issue information received from the terminal using an analysis module. First, the information is broken down into semantic elements, and keywords and main themes are extracted. This generates basic data for finding related content. Specifically, natural language processing technology is used to extract terms related to project management.

[0896] Step 3:

[0897] The server uses a generative AI model to select literature related to the extracted keywords from the database. It then generates information resources to present to the user as recommendations. This process efficiently scans a large database and filters out highly relevant materials. The output includes lists of visual materials and documents.

[0898] Step 4:

[0899] The server uses an emotion engine to analyze the user's emotional state. Emotional data is obtained based on information fed back from the device. This allows the server to measure the user's level of interest and confusion, and adjust the learning experience to be more personalized. For example, if the server determines that the user is confused, additional visual materials and detailed explanatory information will be generated.

[0900] Step 5:

[0901] The server sends the generated recommendations and adjusted content to the terminal. The terminal displays this information on its interface and presents it to the user. The user can learn based on the presented information, resolve questions at their own pace, and efficiently deepen their knowledge. The server continues to monitor the user's responses, and if new input is received, the process from step 2 is repeated.

[0902] (Application Example 2)

[0903] 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".

[0904] In modern manufacturing environments, improving work efficiency and managing worker health are crucial issues. However, current systems fail to provide adequate feedback that takes into account workers' emotional states and biometric data. As a result, it is difficult to obtain appropriate feedback that responds to workers' emotions, making it challenging to create an efficient work environment.

[0905] 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.

[0906] In this invention, the server includes a device for receiving task data in text format from a user; a device for selecting highly relevant materials based on the task data and generating recommendation information; a generation device for facilitating interaction between the user and the materials based on the recommendation information; a device for monitoring the user's biometric data and analyzing their emotional state; and a device for providing feedback to improve the user's work efficiency based on their emotional state. This enables efficient work support and health management in response to the analysis of the customer's emotional state based on their biometric data.

[0907] A "user" is a person who operates the system and provides information.

[0908] "Issue data" refers to information about problems or themes that users input into the system.

[0909] "Documents" refer to a collection of documents or data that contain information related to the assigned data.

[0910] "Recommended information" refers to highly relevant information selected and presented by the system based on the problem data provided by the user.

[0911] A "generation device" is a device that supports the interaction between users and materials based on recommendation information.

[0912] "Biometric data" refers to digital data collected from the user's body, such as heart rate and skin electrical activity.

[0913] "Emotional state" refers to the user's mental or emotional condition, as analyzed based on biometric data.

[0914] "Feedback" refers to advice or suggestions given to a user based on their emotional state.

[0915] This invention incorporates several functional components to realize a learning support system that provides feedback while taking into account the user's emotional state. Its main components and functions are described below.

[0916] The server receives text-based task data from the user and selects highly relevant materials from a literature database based on this data. Based on the selected materials, it generates recommendation information and uses an AI module to create responses that facilitate interaction between the user and the materials. Furthermore, the server uses a biometric data collection module to analyze the user's biometric data, such as heart rate and skin electrical activity, and uses an emotion engine to evaluate their emotional state. This provides a more effective learning experience by combining feedback based on the user's emotional state.

[0917] The terminal functions as an interface for users to input task data and send it to the server. The terminal also collects the user's biometric data in real time and monitors changes, providing a trigger for the system to provide appropriate feedback if the user is in an unfavorable state.

[0918] For example, if the user's heart rate, as received from the terminal, is higher than normal, the server will determine this to be a stressed state and provide feedback to the user such as, "We recommend you take a short break." In this way, it becomes possible to provide information tailored to each user's individual condition, thereby improving the user's work efficiency and mental health.

[0919] An example of a prompt message could be: "Please tell me the data points to consider when determining that a user is fatigued. Also, please suggest appropriate feedback for that situation." This is how one might instruct the generating AI.

[0920] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0921] Step 1:

[0922] The terminal receives task data in text format from the user as input. This data contains information about problems or themes that the user wants to solve. The terminal then sends the received task data to the server.

[0923] Step 2:

[0924] The server takes the received assignment data as input and selects highly relevant materials from the literature database. In this process, the analysis module extracts keywords and main themes, and then performs a material search based on them to output highly relevant materials.

[0925] Step 3:

[0926] The server generates recommendation information using selected materials. This recommendation information is the optimal collection of materials to provide knowledge to the user. The server uses a generative AI model to create responses that facilitate interaction between the materials and the user, and sends these responses to the terminal.

[0927] Step 4:

[0928] The terminal receives recommendation information and responses sent from the server and presents them to the user. The user uses this information to engage in learning activities and can input additional assignment data or questions as needed.

[0929] Step 5:

[0930] The device collects the user's biometric data in real time. Specifically, it acquires heart rate and skin electrical activity as input from devices such as smartwatches and smart bands, and sends this data to a server.

[0931] Step 6:

[0932] The server uses the received biometric data as input to analyze it with an emotion engine and evaluate the user's emotional state. For example, if the heart rate is higher than normal, it determines that the user is under stress. Based on this analysis, it generates optimal feedback for the user and sends it to the device.

[0933] Step 7:

[0934] The device receives feedback sent from the server and presents it to the user. This allows the user to receive advice and suggestions tailored to their emotional state, which can help improve their learning and work efficiency.

[0935] 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.

[0936] 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.

[0937] 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.

[0938] 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.

[0939] 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.

[0940] 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.

[0941] 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.

[0942] 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.

[0943] 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."

[0944] 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.

[0945] 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.

[0946] 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.

[0947] 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.

[0948] 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.

[0949] 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.

[0950] 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.

[0951] 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.

[0952] 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.

[0953] 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.

[0954] 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.

[0955] 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.

[0956] The following is further disclosed regarding the embodiments described above.

[0957] (Claim 1)

[0958] A means of receiving task data in text format from users,

[0959] A means for selecting highly relevant literature based on the aforementioned problem data and generating recommendation information,

[0960] Based on the aforementioned recommendation information, a generation means for facilitating dialogue between the user and the literature,

[0961] A learning support system that includes this.

[0962] (Claim 2)

[0963] The learning support system according to claim 1, further comprising means for receiving conditions from the user and generating simulation results corresponding to those conditions.

[0964] (Claim 3)

[0965] The learning support system according to claim 1, further comprising means for analyzing information provided by a user and generating an electronic publication based on the results of the analysis.

[0966] "Example 1"

[0967] (Claim 1)

[0968] A means of acquiring problem data through a device for inputting information from users,

[0969] A means for accessing literature sources based on the aforementioned problem data and selecting highly relevant information,

[0970] A means for creating a conversational response using a generative AI model based on the selected information,

[0971] A means for presenting the aforementioned response to the user,

[0972] A system that includes this.

[0973] (Claim 2)

[0974] The system according to claim 1, further comprising means for obtaining conditions from a user, performing a simulation that conforms to those conditions, and providing the results.

[0975] (Claim 3)

[0976] The system according to claim 1, further comprising means for analyzing data provided by users and creating digital publications based on the results of the analysis.

[0977] "Application Example 1"

[0978] (Claim 1)

[0979] A means for receiving operation tasks in natural language format from users,

[0980] A means for generating a virtual operation of a linked machine based on the aforementioned operational task,

[0981] A means of providing an environment in which users can interactively experience the generated virtual operations,

[0982] A generation means that analyzes the user's inquiry and generates an appropriate dialogue response,

[0983] A system that includes this.

[0984] (Claim 2)

[0985] The system according to claim 1, further comprising means for generating instructional information indicating how to operate a linked machine based on the simulation results provided by the generation means.

[0986] (Claim 3)

[0987] The system according to claim 1, further comprising means for analyzing operation information provided by a user and generating learning materials based on the results of the analysis.

[0988] "Example 2 of combining an emotion engine"

[0989] (Claim 1)

[0990] A device that receives language morphology challenge information from the user,

[0991] A device for analyzing semantic elements related to the aforementioned problem information,

[0992] A device that selects relevant documents based on the aforementioned analysis results and generates recommended information,

[0993] A generation device that facilitates interaction between users and information resources based on the generated recommendation information,

[0994] A device that recognizes the user's emotional state and makes adjustments to optimize the learning experience,

[0995] A system that includes this.

[0996] (Claim 2)

[0997] The system according to claim 1, further comprising a device that receives conditions from a user and generates simulation results corresponding to those conditions.

[0998] (Claim 3)

[0999] The system according to claim 1, further comprising a device that analyzes information provided by a user and generates an electronic publication based on the results of the analysis.

[1000] "Application example 2 when combining with an emotional engine"

[1001] (Claim 1)

[1002] A device that receives assignment data in text format from users,

[1003] A device that selects highly relevant materials based on the aforementioned problem data and generates recommendation information,

[1004] Based on the aforementioned recommendation information, a generation device that facilitates dialogue between the user and the materials,

[1005] A device that monitors users' biometric data and analyzes their emotional state,

[1006] A device that provides feedback to improve the user's work efficiency based on the aforementioned emotional state,

[1007] A system that includes this.

[1008] (Claim 2)

[1009] The system according to claim 1, further comprising a device that receives conditions from the user and generates simulation results corresponding to those conditions.

[1010] (Claim 3)

[1011] The system according to claim 1, further comprising a device that analyzes information provided by a user and generates an electronic publication based on the results of the analysis. [Explanation of Symbols]

[1012] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving task data in text format from users, A means for selecting highly relevant literature based on the aforementioned problem data and generating recommendation information, Based on the aforementioned recommendation information, a generation means for facilitating dialogue between the user and the literature, A learning support system that includes this.

2. The learning support system according to claim 1, further comprising means for receiving conditions from the user and generating simulation results corresponding to those conditions.

3. The learning support system according to claim 1, further comprising means for analyzing information provided by a user and generating an electronic publication based on the results of the analysis.

Images