system

Abstract

We provide the system. [Solution] A means of inputting specific vocabulary, Means having a generation engine for generating multiple vocabulary related to the input vocabulary, A means of visually arranging and displaying the generated vocabulary, Means for obtaining detailed information about visualized vocabulary, A system including means for presenting the aforementioned detailed information.

Description

Technical Field

[0005] ,

[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: 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 as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern environment of information overload, learners and information collectors are required to efficiently and visually organize relevant information and deeply understand its relevance. However, it has been difficult to grasp the overall picture of relevant information from conventional text-based search results, and means for easily referring to and exploring relevance have been underdeveloped, making it difficult to achieve rapid and efficient learning and information collection. The present invention aims to solve such problems.

Means for Solving the Problems

[0005] This invention provides means for inputting specific vocabulary and performs suggestions using a generation engine for generating multiple vocabulary related to the input vocabulary. Furthermore, it provides means for visually arranging and displaying the generated vocabulary, enabling the user to obtain detailed information about the visualized vocabulary. This makes information easy to understand and visualize, thereby enabling efficient and interactive learning and information gathering.

[0006] "Specific vocabulary" refers to the words and terms that users input as a starting point for information retrieval or learning.

[0007] A "generation engine" is a device or software that implements algorithms and techniques for generating vocabulary related to the input vocabulary.

[0008] A "node" is a component used to visually arrange related vocabulary and information, and is a basic unit that represents information structure.

[0009] "Means of visual arrangement and display" refers to methods and devices for arranging and displaying related vocabulary on a screen in an easily viewable manner, with the aim of making the content easier for the user to understand.

[0010] "Means for obtaining detailed information" refers to devices or software functions that allow users to obtain additional information or explanations about specific vocabulary. [Brief explanation of the drawing]

[0011] [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]

[0012] 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.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled 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.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface that includes a communication processor, an antenna, and the like. 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).

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] This invention is an educational support system that enables users to efficiently visually organize and deeply understand related information. The system aims to clarify the information structure by searching for information using specific vocabulary and visualizing related vocabulary.

[0033] The main components include a terminal for users to search for information, a server that generates and manages related information, and an interface that visually displays that information.

[0034] 1. Input via user interaction

[0035] The user enters the word to be investigated, such as "plant," into the input field of the interface on their device.

[0036] The terminal receives input and sends information about that word to the server as a request.

[0037] 2. Generation and provision of related vocabulary

[0038] The server receives a request and uses its internal database and generation engine to dynamically generate words related to the input vocabulary "plants." During this process, highly relevant vocabulary such as "photosynthesis," "seeds," and "cultivation" are selected based on past search data and language models.

[0039] 3. Visual arrangement of information

[0040] The server processes the generated list of related vocabulary words and sends the data to the terminal for visual display.

[0041] The terminal analyzes the received data and arranges related vocabulary as nodes in a visual memory tree on the user interface.

[0042] 4. Detailed explanation

[0043] When a user selects a specific node, such as "photosynthesis," a request is sent to the server asking for more information related to that node.

[0044] The server uses a generation engine to generate a detailed explanation, for example, sending to the terminal a statement such as, "Photosynthesis is the process by which plants use sunlight to produce chemical energy."

[0045] The device visually presents this explanation to the user.

[0046] This system allows users to expand on related information from words of interest and visually understand the interrelationships between pieces of information. Possible applications include supplementing educational materials in schools and using it as a tool for self-learners to organize and deepen their understanding of information.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The user enters a specific word into an input field displayed on the device's interface. For example, they might enter the word "plant" and request suggestions for related information.

[0050] Step 2:

[0051] The terminal sends the word entered by the user to the server as a request. This request includes relevant information such as the user ID, as well as data to associate it with past request history.

[0052] Step 3:

[0053] The server processes the received request and uses its database and generation engine to generate related vocabulary for the specified word "plant." This generates related words such as "photosynthesis," "seed," and "cultivation."

[0054] Step 4:

[0055] The server compiles the generated related vocabulary and sends a data packet containing it to the terminal. This packet also includes relevance scores and metadata for display purposes.

[0056] Step 5:

[0057] The terminal analyzes the data received from the server and visually displays related vocabulary as a memory tree on the user interface. "Plants" is placed as the central node, and suggested related words are arranged around it.

[0058] Step 6:

[0059] The user clicks on a node of interest in the memory tree, such as "photosynthesis," to request further information or explanation.

[0060] Step 7:

[0061] The terminal receives user input and sends a request to the server for a detailed explanation corresponding to the specified node.

[0062] Step 8:

[0063] The server uses a generation engine to generate detailed information and create an explanation about "photosynthesis." This information is generated using specialized databases and knowledge graphs within the server.

[0064] Step 9:

[0065] The server sends the generated explanatory information to the terminal.

[0066] Step 10:

[0067] The terminal receives explanatory information and displays the content above or below the corresponding node in the memory tree. This display allows the user to gain detailed knowledge about the selected node.

[0068] (Example 1)

[0069] 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."

[0070] The sheer volume of information can lead to user confusion and overload, and there is a growing need, particularly in the education sector, for students and learners to efficiently organize and deeply understand information. However, existing information retrieval systems and display methods often lack sufficient visual presentation of related information, making it difficult for users to easily understand the relationships between pieces of information.

[0071] 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.

[0072] In this invention, the server includes means for inputting a specific information unit, means for having an information processing device for generating a plurality of information units related to the input information unit, and means for visually arranging and displaying the generated information units. As a result, related information is visually presented based on the information unit selected by the user through the terminal, making it easy to understand the relationships between pieces of information and to deepen learning.

[0073] An "information unit" refers to a portion of the data that a user inputs and that is processed within the system, representing a specific vocabulary or concept.

[0074] An "information processing device" refers to a machine or program that has the function of generating and outputting information related to an input unit of information through calculation or retrieval.

[0075] "User interface" refers to the elements that provide screens and means of operation for users to interact with a system and receive information visually.

[0076] "Generative function" refers to the ability to automatically generate new related information based on information units input by the user, and includes generative AI models.

[0077] A "connection point" refers to a structural element that plays a role in linking information units together and visualizing the interrelationships between them.

[0078] "Learning function" refers to the ability of an information processing device to improve the relevance of information based on past data, and involves analysis and optimization.

[0079] This invention is a system for efficiently organizing information and presenting it visually to the user. The system generates related information based on words entered by the user and arranges it visually to facilitate information comprehension.

[0080] The server functions as an information processing device, receiving input information sent by the user from the terminal. The server then uses a generative AI model to generate new information related to the input information units. The generative AI model utilizes natural language processing techniques to select highly relevant vocabulary and calculates the necessary data based on the user's instructions.

[0081] The device visually presents information generated through the user interface. Specifically, it uses HTML5 and JavaScript (registered trademark) to arrange information units in a node format and visualizes the connections between pieces of information. This visualization allows users to easily understand the interrelationships between related information.

[0082] A concrete example of its use is a student in an educational setting who is interested in "energy conversion" and types the word "photosynthesis" into their device. In response, the server generates related vocabulary such as "carbon dioxide fixation" and "oxygen production," which the device then visualizes. As a result, the student can more easily understand the process of energy conversion in nature.

[0083] Examples of prompt statements include the following:

[0084] "Please explain photosynthesis and its related processes in detail."

[0085] "Please describe the important concepts in energy conversion and their relationships."

[0086] This embodiment of the invention makes it possible to achieve effective information provision and enhanced understanding by combining information generation and visualization.

[0087] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0088] Step 1:

[0089] The user inputs a unit of information into the terminal's user interface. For example, they might type the word "plant" into the input form. The terminal then retrieves the input data and prepares it as a request to the server.

[0090] Step 2:

[0091] The terminal sends a request to the server. This request contains units of information entered by the user. The terminal sends the data over the network using the HTTP protocol, and the server receives it.

[0092] Step 3:

[0093] The server activates a generative AI model based on the received request. Given the information unit "plant" as input data, the server generates related vocabulary. The generative AI model analyzes past data and language patterns to dynamically generate related words such as "photosynthesis," "seed," and "cultivation."

[0094] Step 4:

[0095] The server compiles the generated related vocabulary list and formats it for output to the terminal. This formatting process organizes the data into a hierarchical structure and adds metadata for visualization.

[0096] Step 5:

[0097] The server sends formatted data to the terminal. The terminal receives this data and begins internal analysis. The terminal then prepares to visually display the data on a user interface using HTML5 or JavaScript.

[0098] Step 6:

[0099] The terminal arranges related vocabulary on the screen in a node format. The user interface displays related information units as nodes on a memory tree, and each node is arranged in a selectable format.

[0100] Step 7:

[0101] When a user selects a specific node, the device sends another request to the server to retrieve more detailed information based on that node. For example, if the user selects "photosynthesis," a request will be generated asking for a detailed explanation related to it.

[0102] Step 8:

[0103] The server receives this request, uses the generation AI model again to generate detailed information, and sends it to the terminal. The generated information includes, for example, an explanation such as, "Photosynthesis is the process by which plants use sunlight to produce chemical energy."

[0104] Step 9:

[0105] The device presents the received explanatory data to the user. It visually constructs information and allows users to view detailed information associated with specific nodes. This can enrich the user's learning experience.

[0106] (Application Example 1)

[0107] 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."

[0108] Current learning support systems make it difficult for users to efficiently organize and understand information related to the vocabulary they input. In particular, the lack of visual information placement and presentation of related content to improve learning effectiveness makes it difficult for users to grasp the overall picture of the information.

[0109] 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.

[0110] In this invention, the server includes a mechanism for inputting a specific word, a generation device for generating multiple words related to the input word, and a mechanism for visually arranging and displaying the generated words. This allows the user to efficiently visually understand relevant information and easily obtain the content necessary for learning.

[0111] A "word" is the smallest meaningful component in natural language.

[0112] A "generation device" is a device in a system that has the function of generating relevant data based on input information.

[0113] "Visual arrangement" refers to organizing and displaying information visually, presenting data in a way that users can easily understand.

[0114] "Content" refers to information, learning materials, and media resources provided to users for learning.

[0115] A "node" refers to an individual element within a visual information structure, functioning as a point for displaying related information.

[0116] "Learning function" refers to a function that allows a system to improve its performance based on experience and data, aiming to increase the accuracy of relevant information.

[0117] This system provides support to help users effectively engage in learning activities. The following describes a specific embodiment of this system.

[0118] When a user inputs a specific word, the server generates several related words. This involves a process that uses a generative AI model to efficiently extract highly relevant words based on past data and learning outcomes. The generated words are visually organized and sent to the user's terminal.

[0119] On the device, a visually arranged tree of words is displayed. Through this tree, users can select words of interest and directly view detailed information and related content. This UI is built using an intuitive interface based on programming languages ​​such as JavaScript.

[0120] A concrete example is a student studying biology. When the student enters the word "photosynthesis," related words such as "carbon dioxide" and "oxygen" are displayed on the terminal. By selecting each word, related explanatory videos and text information are presented. This information is quickly processed and provided by the server using a generation engine.

[0121] Examples of prompts for a generative AI model are as follows:

[0122] "Generate code that generates vocabulary related to the word 'photosynthesis' entered by the user, and displays it in a tree-like visual interface."

[0123] With a system configured in this way, users can efficiently understand relevant information visually and easily acquire the content necessary for learning.

[0124] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0125] Step 1:

[0126] The user enters a specific word into the input field of the terminal. At this time, the entered word is sent to the server as a request. The input is the word from the user, and the output is the request data to the server. Specifically, for example, if the word "photosynthesis" is entered, a request is sent to the server.

[0127] Step 2:

[0128] The server generates several related words based on the words included in the received request. This process uses a generative AI model to select related words from historical data and language models related to the input words. The input is a list of words, and the output is a list of related words. The generated vocabulary includes words like "carbon dioxide" and "oxygen."

[0129] Step 3:

[0130] The server generates data for visually arranging the generated list of related words and sends it to the terminal. At this time, data that visually organizes the related words is created and provided in a format that the user can intuitively use. The input is a list of related words, and the output is data for visualization.

[0131] Step 4:

[0132] The terminal analyzes the visualization data received from the server and displays a tree of words visually arranged on the interface. This creates an environment where the user can freely make selections. The input is data for visualization, and the output is a tree of related words drawn on the user interface.

[0133] Step 5:

[0134] When a user selects a specific word on the interface, the terminal sends that selection data to the server as a request. This action initiates a process to retrieve detailed information related to the selected word. The input is the user selection data, and the output is the request to the server.

[0135] Step 6:

[0136] The server generates detailed information about the selected words and sends it to the terminal. At this stage, a generative AI model is used to create a detailed explanation of the selected content and deliver it to the terminal. The input is user-selected data, and the output is detailed information.

[0137] Step 7:

[0138] The terminal visually presents information to the user based on detailed information received from the server. This allows the user to gain a deeper understanding of the selected words. The input is detailed information, and the output is what is presented to the user.

[0139] 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.

[0140] This invention is a system for realizing a more personalized educational experience and information gathering by presenting information while taking user emotions into consideration. The aim of this system is to enable users to visually grasp relevant information, recognize the user's emotions in response to it, and provide optimized information.

[0141] System Configuration

[0142] 1. User terminal operation

[0143] The user uses the device's interface to input the vocabulary to be learned. For example, they might select the word "weather."

[0144] 2. Emotion recognition and generation of related vocabulary

[0145] The device is equipped with a camera and microphone, which analyze the user's emotions from their facial expressions and tone of voice. This allows the emotion engine to identify emotional states such as joy, confusion, or interest.

[0146] The server uses an advanced generative engine to generate relevant vocabulary based on the user's sentiment data and input vocabulary. Words such as "rain," "sunny," and "weather forecast" are generated, and their priority is set according to the user's sentiment.

[0147] 3. Visualization of Information

[0148] The server considers the user's emotions, calculates the optimal visual arrangement of the generated vocabulary as nodes, and sends it to the terminal.

[0149] The device uses the received data to construct a memory tree in a way that will interest the user, and displays it on the screen.

[0150] 4. Information presentation and content adjustment

[0151] When a user selects a node they are interested in (for example, "weather forecast"), a request for detailed information is sent from the terminal to the server.

[0152] The server uses the results of the emotion engine's analysis to generate and adjust appropriate information and content tailored to the user's emotional state, and sends the most suitable explanations to the device to ensure an enjoyable learning experience.

[0153] Through this system, users can enjoy information gathering and gain a deeper understanding by receiving information tailored to their emotions. This combination goes beyond simply displaying related information and enables personalized learning support that is tailored to each user.

[0154] The following describes the processing flow.

[0155] Step 1:

[0156] The user uses the input field on their device to enter the vocabulary they want to search for. For example, they might enter "weather".

[0157] Step 2:

[0158] The device captures the user's facial expressions with its camera and collects audio with its microphone to acquire emotional data. This data is then used by an emotion engine to analyze the user's current emotional state (joy, interest, fatigue, etc.).

[0159] Step 3:

[0160] The terminal sends the entered vocabulary word "weather" along with the acquired sentiment data to the server. The sentiment data is used as a parameter to improve the user's search experience.

[0161] Step 4:

[0162] The server uses a generation engine to generate relevant vocabulary based on the received "weather" and sentiment data. For example, it generates terms such as "rain," "sunny," and "weather forecast." If the sentiment data suggests a user's interest, the server assigns a higher priority to that relevant vocabulary.

[0163] Step 5:

[0164] The server arranges the generated vocabulary in a highly relevant order and calculates a visually effective layout. At this time, it also takes into account user emotions, considering factors such as readability and ease of interaction.

[0165] Step 6:

[0166] The server sends back related vocabulary and its placement information to the terminal.

[0167] Step 7:

[0168] The device receives this information and displays a memory tree on the user's screen. The size and color of the nodes are adjusted according to emotions, making it easier to engage the user.

[0169] Step 8:

[0170] Users can request detailed information by clicking on a node of interest from the displayed memory tree, such as "weather forecast."

[0171] Step 9:

[0172] The device detects the user's selection action, sends that information to the server, and requests detailed data.

[0173] Step 10:

[0174] The server then uses the emotion engine again to generate detailed information related to the selected node ("weather forecast"). At the same time, it also makes adjustments to present the information in a way that aligns with the emotion.

[0175] Step 11:

[0176] The server sends the generated detailed information to the terminal.

[0177] Step 12:

[0178] The device displays the received details on its screen and provides content related to the node selected by the user, thereby deepening their understanding. The displayed content is presented in an easy-to-understand format and at a suitable pace, taking into account the user's emotional state.

[0179] (Example 2)

[0180] 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".

[0181] In presenting information, there is a lack of personalized content that responds to users' emotions and interests, making it difficult to provide information efficiently and sustainably. Furthermore, there is room for improvement in methods of systematically visualizing related information.

[0182] 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.

[0183] In this invention, the server includes means for analyzing the user's emotional state and optimizing the content presented based on the analysis results, means for setting the priority of information presented according to the user's emotional state, and means having a learning function for strengthening the relationships between related data generated by the generation unit. This makes it possible to present information according to the user's emotions, enabling the efficient and attractive provision of information to individual users.

[0184] "Specific information" refers to data that users input into the system for learning or information gathering purposes.

[0185] "Generation unit" refers to a device or software that has the function of generating data related to the input information.

[0186] "Visual arrangement" refers to the method and result of displaying generated data in a way that is easy for users to understand.

[0187] "Emotional state" refers to the psychological and emotional state inferred from the user's facial expressions and tone of voice.

[0188] "Learning function" refers to a function that a system uses to improve the accuracy and usefulness of related data based on user feedback and interaction.

[0189] "Priority" refers to the criteria used to determine the display order based on the importance and level of interest of the information presented.

[0190] This invention is a system that comprehensively realizes everything from information input to data visualization and optimization of information provision through sentiment analysis. It primarily involves a server, terminals, and users, and in particular uses a generative AI model to generate relevant data based on user input.

[0191] The user inputs specific information into the terminal's interface. The terminal is equipped with a high-resolution camera and a high-sensitivity microphone to capture the user's facial expressions and tone of voice, and emotion analysis software is used to identify their emotional state. After receiving this emotional data, the server utilizes a generative AI model to generate data related to the input information. The generated data is then given priority according to the emotional state.

[0192] The generated data is then visualized on the server side using a visualization algorithm to determine the optimal layout, and then sent to the terminal. The terminal uses this data to display it on the user's screen. For example, if information about "weather" is entered, related data such as "rain," "sunny," and "weather forecast" will be displayed in an arrangement that suits the user's interests.

[0193] When a user selects an information node that interests them, a request is sent from the device to the server. The server then utilizes the emotion engine again to construct appropriate details, send them to the device, and present them to the user. This allows users to receive information that aligns with their emotions, making learning and information gathering more enjoyable.

[0194] As a concrete example, here is an example of a prompt message:

[0195] "How can I generate relevant weather-related information that a user is interested in and display it in a way that is optimized for the user's emotional state?"

[0196] This system allows users to receive personalized information experiences that respond to their emotions.

[0197] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0198] Step 1:

[0199] The user inputs specific information into the device. Specifically, the user inputs information such as "weather" in text format via the device's interface. This input data is stored in the device as basic information necessary for subsequent processing.

[0200] Step 2:

[0201] The device analyzes the user's emotional state. The device uses its camera to capture the user's facial expressions and its microphone to record their voice. Based on this data, emotion analysis software identifies the user's emotions (joy, interest, confusion, etc.) in real time. This emotion data is then sent to a server.

[0202] Step 3:

[0203] The server generates relevant data. Based on the received sentiment data and user input, the server inputs prompt messages into the generating AI model. In this process, to provide a dataset related to "weather," the generating AI model generates relevant data including "rain," "sunny," and "weather forecast." The generated results are then prioritized according to the sentiment.

[0204] Step 4:

[0205] The server calculates the visual arrangement of the generated data. Using a visualization algorithm, the server arranges the generated related data according to user sentiment priorities. This arrangement is then prepared for transmission to the device in a way that aligns with the user's interests.

[0206] Step 5:

[0207] The terminal displays the generated data. The terminal displays the visual data received from the server on the screen in a memory tree format. For example, if the user is interested in "weather forecasts," related information will be visually displayed around that. This display is arranged so that the user can easily explore the information.

[0208] Step 6:

[0209] The user requests more information. When the user selects an information node of interest (e.g., "weather forecast"), the request is sent from the terminal to the server. This selection is treated as a request for specific information retrieval.

[0210] Step 7:

[0211] The server generates detailed information. The server again utilizes the emotion engine to generate appropriate detailed information for the selected information node. The generated detailed information is written in a way that is most easily understood by the user, based on their emotions. This information is sent to the terminal and ultimately presented to the user.

[0212] Through this series of processes, users receive information that is appropriate to their emotions, and are provided with an information experience that is individually optimized for them.

[0213] (Application Example 2)

[0214] 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".

[0215] Current information delivery systems often provide uniform information without considering user emotions, and have the problem of failing to present optimal information tailored to the user's situation. As a result, users spend a lot of time obtaining the information they need, and the learning and information gathering experience cannot be personalized.

[0216] 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.

[0217] In this invention, the server includes means for inputting specific vocabulary, means for analyzing the user's emotions and optimizing relevant information based on the analysis results, and a device for presenting group information based on the user's state. This enables personalized information provision that responds to the user's emotions.

[0218] "Vocabulary" refers to a collection of words and technical terms used in a specific context.

[0219] A "generation device" is a device equipped with the function of creating relevant information based on input information.

[0220] "Visual arrangement" is a method of visually organizing and displaying information.

[0221] "Detailed information" refers to information that goes into more depth than the basic information provided.

[0222] "Emotion analysis" is a technology that reads and analyzes a user's emotions from their facial expressions and voice data.

[0223] A "device" is a rigid or flexible component that performs a specific function.

[0224] "Group information" refers to a collection of multiple related pieces of information.

[0225] The system for implementing this invention has the function of generating information based on user input and providing that information optimized to match the user's emotional state. The main components are an input device, an emotion analysis device, a generation device, a display device, and software that runs on a server.

[0226] The input device provides an interface for users to input specific vocabulary. This allows users to clearly indicate topics of interest.

[0227] The emotion analysis device uses cameras and microphones to collect data on the user's facial expressions and voice, and analyzes their emotions in real time using cloud computing services (e.g., Google® Cloud Vision API and Azure® Cognitive Services). The results of this analysis represent the user's emotional state as digital data.

[0228] The generator receives analyzed emotion data and generates relevant information according to the user's emotions. The generated information is used to change the priority of the information and personalize the user's personal experience.

[0229] The display device visually arranges the generated information and presents it in a format that is easily understandable to the user. This allows the user to intuitively grasp the relationships between the pieces of information.

[0230] The server manages these processes in an integrated manner, streamlining the processing of each piece of data. It is also designed to optimally combine relevant information using generative AI models, presenting valuable information to the user.

[0231] As a concrete example, when a user visiting a virtual store searches for a product, recommended products are presented based on their emotional state. In this case, the server sends a prompt message to the AI ​​model, such as "Generate relevant information to recommend when the user has an interested expression," and generates appropriate information.

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

[0233] Step 1:

[0234] The user inputs specific vocabulary using an input device. This input vocabulary forms the basis for information generation. This vocabulary is transmitted to the terminal and serves as the starting point for providing information tailored to the user's interests and needs.

[0235] Step 2:

[0236] The device uses its built-in camera and microphone to collect the user's facial expressions and voice in real time. This data is then sent to a server as input for emotion analysis.

[0237] Step 3:

[0238] The server uses the received facial and voice data to analyze the user's emotions using a cloud-based emotion analysis service (e.g., Google Cloud Vision API). The output obtained here is the user's emotional state expressed as numerical data.

[0239] Step 4:

[0240] The server uses a generative AI model to generate relevant information based on analyzed sentiment data and the user's input vocabulary. During this process, it prioritizes and optimizes the information according to the degree of emotion. The output is a set of information tailored to the emotion.

[0241] Step 5:

[0242] The terminal receives optimized information sent from the server and visually arranges the information on the display device. Here, the information is displayed as nodes, allowing the user to intuitively understand the relationships between them. The output is a display of the visually arranged information.

[0243] Step 6:

[0244] The user selects a node of interest from the presented information. The selected information request is then sent back from the terminal to the server.

[0245] Step 7:

[0246] The server generates additional detailed information related to the selected node and provides further information using prompts from the generating AI model (e.g., "Generate relevant information to recommend when the user makes an interested expression."). This output, consisting of additional details, is sent to the terminal.

[0247] Step 8:

[0248] The terminal receives additional information from the server, providing users with richer information and improving the quality of their learning experience and information gathering. The output is a display of detailed information tailored to the user.

[0249] 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.

[0250] Data generation model 58 is a type of 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.

[0251] 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.

[0252] [Second Embodiment]

[0253] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0254] 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.

[0255] 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).

[0256] 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.

[0257] 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.

[0258] 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).

[0259] 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.

[0260] 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.

[0261] 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.

[0262] 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.

[0263] 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.

[0264] 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".

[0265] This invention is an educational support system that enables users to efficiently visually organize and deeply understand related information. The system aims to clarify the information structure by searching for information using specific vocabulary and visualizing related vocabulary.

[0266] The main components include a terminal for users to search for information, a server that generates and manages related information, and an interface that visually displays that information.

[0267] 1. Input via user interaction

[0268] The user enters the word to be investigated, such as "plant," into the input field of the interface on their device.

[0269] The terminal receives input and sends information about that word to the server as a request.

[0270] 2. Generation and provision of related vocabulary

[0271] The server receives a request and uses its internal database and generation engine to dynamically generate words related to the input vocabulary "plants." During this process, highly relevant vocabulary such as "photosynthesis," "seeds," and "cultivation" are selected based on past search data and language models.

[0272] 3. Visual arrangement of information

[0273] The server processes the generated list of related vocabulary words and sends the data to the terminal for visual display.

[0274] The terminal analyzes the received data and arranges related vocabulary as nodes in a visual memory tree on the user interface.

[0275] 4. Detailed explanation

[0276] When a user selects a specific node, such as "photosynthesis," a request is sent to the server asking for more information related to that node.

[0277] The server uses a generation engine to generate a detailed explanation, for example, sending to the terminal a statement such as, "Photosynthesis is the process by which plants use sunlight to produce chemical energy."

[0278] The device visually presents this explanation to the user.

[0279] With the system configured in this way, users can expand relevant information from the words of interest and visually understand the interrelationships of information more easily. As an embodiment, it can be considered for use as a tool for supplementing teaching materials in the educational field or for users engaged in self-study to deepen the organization and understanding of information.

[0280] The following describes the processing flow.

[0281] Step 1:

[0282] The user enters a specific word in the input field displayed on the interface of the terminal. For example, enter the word "plant" and perform an operation to request suggestions for relevant information.

[0283] Step 2:

[0284] The terminal sends the word entered by the user to the server as a request. This request includes relevant information such as the user ID and also includes data for associating with the past request history.

[0285] Step 3:

[0286] The server processes the received request and uses a database and a generation engine to generate related vocabulary for the specified word "plant". As a result, related words such as "photosynthesis", "seed", and "cultivation" are generated.

[0287] Step 4:

[0288] The server summarizes the generated related vocabulary and sends a data packet containing this to the terminal. This packet also includes a relevance score and metadata for display.

[0289] ] Step 5:

[0290] The terminal analyzes the data received from the server and visually displays related vocabulary as a memory tree on the user interface. "Plants" is placed as the central node, and suggested related words are arranged around it.

[0291] Step 6:

[0292] The user clicks on a node of interest in the memory tree, such as "photosynthesis," to request further information or explanation.

[0293] Step 7:

[0294] The terminal receives user input and sends a request to the server for a detailed explanation corresponding to the specified node.

[0295] Step 8:

[0296] The server uses a generation engine to generate detailed information and create an explanation about "photosynthesis." This information is generated using specialized databases and knowledge graphs within the server.

[0297] Step 9:

[0298] The server sends the generated explanatory information to the terminal.

[0299] Step 10:

[0300] The terminal receives explanatory information and displays the content above or below the corresponding node in the memory tree. This display allows the user to gain detailed knowledge about the selected node.

[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] It is required to reduce the confusion and overload of users caused by the vast amount of information, especially in the field of education, where students and learners are required to efficiently organize and deeply understand information. However, existing information retrieval systems and display methods have the problem that the visual presentation of related information is insufficient, making it difficult for users to easily understand the relevance between information.

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

[0305] In this invention, the server includes means for inputting a specific information unit, means for having an information processing device for generating a plurality of information units related to the input information unit, and means for visually arranging and displaying the generated information units. Thereby, based on the information unit selected by the user through the terminal, related information is visually presented, so that the relevance between information can be easily understood and learning can proceed deeply.

[0306] "Information unit" refers to a part of the data input by the user and processed within the system, and represents a specific vocabulary or concept.

[0307] "Information processing device" refers to a mechanical device or program having a function of generating and outputting information related to the input information unit by calculation or search.

[0308] "User interface" refers to an element that provides a screen or operation means for the user to interact with the system and receive information visually.

[0309] "Generating function" refers to the ability to automatically generate new related information based on the information unit input by the user, and includes a generating AI model.

[0310] "Connection point" refers to a structural element that plays a role in connecting information units and visualizes the mutual relationship of information.

[0311] "Learning function" refers to the ability of an information processing device to improve the relevance of information based on past data, and involves analysis and optimization.

[0312] This invention is a system for efficiently organizing information and presenting it visually to the user. The system generates related information based on words entered by the user and arranges it visually to facilitate information comprehension.

[0313] The server functions as an information processing device, receiving input information sent by the user from the terminal. The server then uses a generative AI model to generate new information related to the input information units. The generative AI model utilizes natural language processing techniques to select highly relevant vocabulary and calculates the necessary data based on the user's instructions.

[0314] The device visually presents information generated through the user interface. Specifically, it uses HTML5 and JavaScript to arrange information units in a node format and visualizes the connections between pieces of information. This visualization allows users to easily understand the interrelationships between related information.

[0315] A concrete example of its use is a student in an educational setting who is interested in "energy conversion" and types the word "photosynthesis" into their device. In response, the server generates related vocabulary such as "carbon dioxide fixation" and "oxygen production," which the device then visualizes. As a result, the student can more easily understand the process of energy conversion in nature.

[0316] Examples of prompt statements include the following:

[0317] "Please explain photosynthesis and its related processes in detail."

[0318] "Please describe the important concepts in energy conversion and their relationships."

[0319] This embodiment of the invention makes it possible to achieve effective information provision and enhanced understanding by combining information generation and visualization.

[0320] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0321] Step 1:

[0322] The user inputs a unit of information into the terminal's user interface. For example, they might type the word "plant" into the input form. The terminal then retrieves the input data and prepares it as a request to the server.

[0323] Step 2:

[0324] The terminal sends a request to the server. This request contains units of information entered by the user. The terminal sends the data over the network using the HTTP protocol, and the server receives it.

[0325] Step 3:

[0326] The server activates a generative AI model based on the received request. Given the information unit "plant" as input data, the server generates related vocabulary. The generative AI model analyzes past data and language patterns to dynamically generate related words such as "photosynthesis," "seed," and "cultivation."

[0327] Step 4:

[0328] The server compiles the generated related vocabulary list and formats it for output to the terminal. This formatting process organizes the data into a hierarchical structure and adds metadata for visualization.

[0329] Step 5:

[0330] The server sends formatted data to the terminal. The terminal receives this data and begins internal analysis. The terminal then prepares to visually display the data on a user interface using HTML5 or JavaScript.

[0331] Step 6:

[0332] The terminal arranges related vocabulary on the screen in a node format. The user interface displays related information units as nodes on a memory tree, and each node is arranged in a selectable format.

[0333] Step 7:

[0334] When a user selects a specific node, the device sends another request to the server to retrieve more detailed information based on that node. For example, if the user selects "photosynthesis," a request will be generated asking for a detailed explanation related to it.

[0335] Step 8:

[0336] The server receives this request, uses the generation AI model again to generate detailed information, and sends it to the terminal. The generated information includes, for example, an explanation such as, "Photosynthesis is the process by which plants use sunlight to produce chemical energy."

[0337] Step 9:

[0338] The device presents the received explanatory data to the user. It visually constructs information and allows users to view detailed information associated with specific nodes. This can enrich the user's learning experience.

[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] Current learning support systems make it difficult for users to efficiently organize and understand information related to the vocabulary they input. In particular, the lack of visual information placement and presentation of related content to improve learning effectiveness makes it difficult for users to grasp the overall picture of the information.

[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 a mechanism for inputting a specific word, a generation device for generating multiple words related to the input word, and a mechanism for visually arranging and displaying the generated words. This allows the user to efficiently visually understand relevant information and easily obtain the content necessary for learning.

[0344] A "word" is the smallest meaningful component in natural language.

[0345] A "generation device" is a device in a system that has the function of generating relevant data based on input information.

[0346] "Visual arrangement" refers to organizing and displaying information visually, presenting data in a way that users can easily understand.

[0347] "Content" refers to information, learning materials, and media resources provided to users for learning.

[0348] A "node" refers to an individual element within a visual information structure, functioning as a point for displaying related information.

[0349] "Learning function" refers to a function that allows a system to improve its performance based on experience and data, aiming to increase the accuracy of relevant information.

[0350] This system provides support to help users effectively engage in learning activities. The following describes a specific embodiment of this system.

[0351] When a user inputs a specific word, the server generates several related words. This involves a process that uses a generative AI model to efficiently extract highly relevant words based on past data and learning outcomes. The generated words are visually organized and sent to the user's terminal.

[0352] On the device, a visually arranged tree of words is displayed. Through this tree, users can select words of interest and directly view detailed information and related content. This UI is built using an intuitive interface based on programming languages ​​such as JavaScript.

[0353] A concrete example is a student studying biology. When the student enters the word "photosynthesis," related words such as "carbon dioxide" and "oxygen" are displayed on the terminal. By selecting each word, related explanatory videos and text information are presented. This information is quickly processed and provided by the server using a generation engine.

[0354] Examples of prompts for a generative AI model are as follows:

[0355] "Generate code that generates vocabulary related to the word 'photosynthesis' entered by the user, and displays it in a tree-like visual interface."

[0356] With a system configured in this way, users can efficiently understand relevant information visually and easily acquire the content necessary for learning.

[0357] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0358] Step 1:

[0359] The user enters a specific word into the input field of the terminal. At this time, the entered word is sent to the server as a request. The input is the word from the user, and the output is the request data to the server. Specifically, for example, if the word "photosynthesis" is entered, a request is sent to the server.

[0360] Step 2:

[0361] The server generates several related words based on the words included in the received request. This process uses a generative AI model to select related words from historical data and language models related to the input words. The input is a list of words, and the output is a list of related words. The generated vocabulary includes words like "carbon dioxide" and "oxygen."

[0362] Step 3:

[0363] The server generates data for visually arranging the generated list of related words and sends it to the terminal. At this time, data that visually organizes the related words is created and provided in a format that the user can intuitively use. The input is a list of related words, and the output is data for visualization.

[0364] Step 4:

[0365] The terminal analyzes the visualization data received from the server and displays a tree of words visually arranged on the interface. This creates an environment where the user can freely make selections. The input is data for visualization, and the output is a tree of related words drawn on the user interface.

[0366] Step 5:

[0367] When a user selects a specific word on the interface, the terminal sends that selection data to the server as a request. This action initiates a process to retrieve detailed information related to the selected word. The input is the user selection data, and the output is the request to the server.

[0368] Step 6:

[0369] The server generates detailed information about the selected words and sends it to the terminal. At this stage, a generative AI model is used to create a detailed explanation of the selected content and deliver it to the terminal. The input is user-selected data, and the output is detailed information.

[0370] Step 7:

[0371] The terminal visually presents information to the user based on detailed information received from the server. This allows the user to gain a deeper understanding of the selected words. The input is detailed information, and the output is what is presented to the user.

[0372] 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.

[0373] This invention is a system for realizing a more personalized educational experience and information gathering by presenting information while taking user emotions into consideration. The aim of this system is to enable users to visually grasp relevant information, recognize the user's emotions in response to it, and provide optimized information.

[0374] System Configuration

[0375] 1. User terminal operation

[0376] The user uses the device's interface to input the vocabulary to be learned. For example, they might select the word "weather."

[0377] 2. Emotion recognition and generation of related vocabulary

[0378] The device is equipped with a camera and microphone, which analyze the user's emotions from their facial expressions and tone of voice. This allows the emotion engine to identify emotional states such as joy, confusion, or interest.

[0379] The server uses an advanced generative engine to generate relevant vocabulary based on the user's sentiment data and input vocabulary. Words such as "rain," "sunny," and "weather forecast" are generated, and their priority is set according to the user's sentiment.

[0380] 3. Visualization of Information

[0381] The server considers the user's emotions, calculates the optimal visual arrangement of the generated vocabulary as nodes, and sends it to the terminal.

[0382] The device uses the received data to construct a memory tree in a way that will interest the user, and displays it on the screen.

[0383] 4. Information presentation and content adjustment

[0384] When a user selects a node they are interested in (for example, "weather forecast"), a request for detailed information is sent from the terminal to the server.

[0385] The server uses the results of the emotion engine's analysis to generate and adjust appropriate information and content tailored to the user's emotional state, and sends the most suitable explanations to the device to ensure an enjoyable learning experience.

[0386] Through this system, users can enjoy information gathering and gain a deeper understanding by receiving information tailored to their emotions. This combination goes beyond simply displaying related information and enables personalized learning support that is tailored to each user.

[0387] The following describes the processing flow.

[0388] Step 1:

[0389] The user uses the input field on their device to enter the vocabulary they want to search for. For example, they might enter "weather".

[0390] Step 2:

[0391] The device captures the user's facial expressions with its camera and collects audio with its microphone to acquire emotional data. This data is then used by an emotion engine to analyze the user's current emotional state (joy, interest, fatigue, etc.).

[0392] Step 3:

[0393] The terminal sends the entered vocabulary word "weather" along with the acquired sentiment data to the server. The sentiment data is used as a parameter to improve the user's search experience.

[0394] Step 4:

[0395] The server uses a generation engine to generate relevant vocabulary based on the received "weather" and sentiment data. For example, it generates terms such as "rain," "sunny," and "weather forecast." If the sentiment data suggests a user's interest, the server assigns a higher priority to that relevant vocabulary.

[0396] Step 5:

[0397] The server arranges the generated vocabulary in a highly relevant order and calculates a visually effective layout. At this time, it also takes into account user emotions, considering factors such as readability and ease of interaction.

[0398] Step 6:

[0399] The server sends back related vocabulary and its placement information to the terminal.

[0400] Step 7:

[0401] The device receives this information and displays a memory tree on the user's screen. The size and color of the nodes are adjusted according to emotions, making it easier to engage the user.

[0402] Step 8:

[0403] Users can request detailed information by clicking on a node of interest from the displayed memory tree, such as "weather forecast."

[0404] Step 9:

[0405] The device detects the user's selection action, sends that information to the server, and requests detailed data.

[0406] Step 10:

[0407] The server then uses the emotion engine again to generate detailed information related to the selected node ("weather forecast"). At the same time, it also makes adjustments to present the information in a way that aligns with the emotion.

[0408] Step 11:

[0409] The server sends the generated detailed information to the terminal.

[0410] Step 12:

[0411] The device displays the received details on its screen and provides content related to the node selected by the user, thereby deepening their understanding. The displayed content is presented in an easy-to-understand format and at a suitable pace, taking into account the user's emotional state.

[0412] (Example 2)

[0413] 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".

[0414] In presenting information, there is a lack of personalized content that responds to users' emotions and interests, making it difficult to provide information efficiently and sustainably. Furthermore, there is room for improvement in methods of systematically visualizing related information.

[0415] 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.

[0416] In this invention, the server includes means for analyzing the user's emotional state and optimizing the content presented based on the analysis results, means for setting the priority of information presented according to the user's emotional state, and means having a learning function for strengthening the relationships between related data generated by the generation unit. This makes it possible to present information according to the user's emotions, enabling the efficient and attractive provision of information to individual users.

[0417] "Specific information" refers to data that users input into the system for learning or information gathering purposes.

[0418] "Generation unit" refers to a device or software that has the function of generating data related to the input information.

[0419] "Visual arrangement" refers to the method and result of displaying generated data in a way that is easy for users to understand.

[0420] "Emotional state" refers to the psychological and emotional state inferred from the user's facial expressions and tone of voice.

[0421] "Learning function" refers to a function that a system uses to improve the accuracy and usefulness of related data based on user feedback and interaction.

[0422] "Priority" refers to the criteria used to determine the display order based on the importance and level of interest of the information presented.

[0423] This invention is a system that comprehensively realizes everything from information input to data visualization and optimization of information provision through sentiment analysis. It primarily involves a server, terminals, and users, and in particular uses a generative AI model to generate relevant data based on user input.

[0424] The user inputs specific information into the terminal's interface. The terminal is equipped with a high-resolution camera and a high-sensitivity microphone to capture the user's facial expressions and tone of voice, and emotion analysis software is used to identify their emotional state. After receiving this emotional data, the server utilizes a generative AI model to generate data related to the input information. The generated data is then given priority according to the emotional state.

[0425] The generated data is then visualized on the server side using a visualization algorithm to determine the optimal layout, and then sent to the terminal. The terminal uses this data to display it on the user's screen. For example, if information about "weather" is entered, related data such as "rain," "sunny," and "weather forecast" will be displayed in an arrangement that suits the user's interests.

[0426] When a user selects an information node that interests them, a request is sent from the device to the server. The server then utilizes the emotion engine again to construct appropriate details, send them to the device, and present them to the user. This allows users to receive information that aligns with their emotions, making learning and information gathering more enjoyable.

[0427] As a concrete example, here is an example of a prompt message:

[0428] "How can I generate relevant weather-related information that a user is interested in and display it in a way that is optimized for the user's emotional state?"

[0429] This system allows users to receive personalized information experiences that respond to their emotions.

[0430] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0431] Step 1:

[0432] The user inputs specific information into the device. Specifically, the user inputs information such as "weather" in text format via the device's interface. This input data is stored in the device as basic information necessary for subsequent processing.

[0433] Step 2:

[0434] The device analyzes the user's emotional state. The device uses its camera to capture the user's facial expressions and its microphone to record their voice. Based on this data, emotion analysis software identifies the user's emotions (joy, interest, confusion, etc.) in real time. This emotion data is then sent to a server.

[0435] Step 3:

[0436] The server generates relevant data. Based on the received sentiment data and user input, the server inputs prompt messages into the generating AI model. In this process, to provide a dataset related to "weather," the generating AI model generates relevant data including "rain," "sunny," and "weather forecast." The generated results are then prioritized according to the sentiment.

[0437] Step 4:

[0438] The server calculates the visual arrangement of the generated data. Using a visualization algorithm, the server arranges the generated related data according to user sentiment priorities. This arrangement is then prepared for transmission to the device in a way that aligns with the user's interests.

[0439] Step 5:

[0440] The terminal displays the generated data. The terminal displays the visual data received from the server on the screen in a memory tree format. For example, if the user is interested in "weather forecasts," related information will be visually displayed around that. This display is arranged so that the user can easily explore the information.

[0441] Step 6:

[0442] The user requests more information. When the user selects an information node of interest (e.g., "weather forecast"), the request is sent from the terminal to the server. This selection is treated as a request for specific information retrieval.

[0443] Step 7:

[0444] The server generates detailed information. The server again utilizes the emotion engine to generate appropriate detailed information for the selected information node. The generated detailed information is written in a way that is most easily understood by the user, based on their emotions. This information is sent to the terminal and ultimately presented to the user.

[0445] Through this series of processes, users receive information that is appropriate to their emotions, and are provided with an information experience that is individually optimized for them.

[0446] (Application Example 2)

[0447] 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."

[0448] Current information delivery systems often provide uniform information without considering user emotions, and have the problem of failing to present optimal information tailored to the user's situation. As a result, users spend a lot of time obtaining the information they need, and the learning and information gathering experience cannot be personalized.

[0449] 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.

[0450] In this invention, the server includes means for inputting specific vocabulary, means for analyzing the user's emotions and optimizing relevant information based on the analysis results, and a device for presenting group information based on the user's state. This enables personalized information provision that responds to the user's emotions.

[0451] "Vocabulary" refers to a collection of words and technical terms used in a specific context.

[0452] A "generation device" is a device equipped with the function of creating relevant information based on input information.

[0453] "Visual arrangement" is a method of visually organizing and displaying information.

[0454] "Detailed information" refers to information that goes into more depth than the basic information provided.

[0455] "Emotion analysis" is a technology that reads and analyzes a user's emotions from their facial expressions and voice data.

[0456] A "device" is a rigid or flexible component that performs a specific function.

[0457] "Group information" refers to a collection of multiple related pieces of information.

[0458] The system for implementing this invention has the function of generating information based on user input and providing that information optimized to match the user's emotional state. The main components are an input device, an emotion analysis device, a generation device, a display device, and software that runs on a server.

[0459] The input device provides an interface for users to input specific vocabulary. This allows users to clearly indicate topics of interest.

[0460] The emotion analysis device uses cameras and microphones to collect data on the user's facial expressions and voice, and analyzes their emotions in real time using cloud computing services (e.g., Google Cloud Vision API or Azure Cognitive Services). The results of this analysis represent the user's emotional state as digital data.

[0461] The generator receives analyzed emotion data and generates relevant information according to the user's emotions. The generated information is used to change the priority of the information and personalize the user's personal experience.

[0462] The display device visually arranges the generated information and presents it in a format that is easily understandable to the user. This allows the user to intuitively grasp the relationships between the pieces of information.

[0463] The server manages these processes in an integrated manner, streamlining the processing of each piece of data. It is also designed to optimally combine relevant information using generative AI models, presenting valuable information to the user.

[0464] As a concrete example, when a user visiting a virtual store searches for a product, recommended products are presented based on their emotional state. In this case, the server sends a prompt message to the AI ​​model, such as "Generate relevant information to recommend when the user has an interested expression," and generates appropriate information.

[0465] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0466] Step 1:

[0467] The user inputs specific vocabulary using an input device. This input vocabulary forms the basis for information generation. This vocabulary is transmitted to the terminal and serves as the starting point for providing information tailored to the user's interests and needs.

[0468] Step 2:

[0469] The device uses its built-in camera and microphone to collect the user's facial expressions and voice in real time. This data is then sent to a server as input for emotion analysis.

[0470] Step 3:

[0471] The server uses the received facial and voice data to analyze the user's emotions using a cloud-based emotion analysis service (e.g., Google Cloud Vision API). The output obtained here is the user's emotional state expressed as numerical data.

[0472] Step 4:

[0473] The server uses a generative AI model to generate relevant information based on analyzed sentiment data and the user's input vocabulary. During this process, it prioritizes and optimizes the information according to the degree of emotion. The output is a set of information tailored to the emotion.

[0474] Step 5:

[0475] The terminal receives optimized information sent from the server and visually arranges the information on the display device. Here, the information is displayed as nodes, allowing the user to intuitively understand the relationships between them. The output is a display of the visually arranged information.

[0476] Step 6:

[0477] The user selects a node of interest from the presented information. The selected information request is then sent back from the terminal to the server.

[0478] Step 7:

[0479] The server generates additional detailed information related to the selected node and provides further information using prompts from the generating AI model (e.g., "Generate relevant information to recommend when the user makes an interested expression."). This output, consisting of additional details, is sent to the terminal.

[0480] Step 8:

[0481] The terminal receives additional information from the server, providing users with richer information and improving the quality of their learning experience and information gathering. The output is a display of detailed information tailored to the user.

[0482] 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.

[0483] 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.

[0484] 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.

[0485] [Third Embodiment]

[0486] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0487] 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.

[0488] 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).

[0489] 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.

[0490] 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.

[0491] 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).

[0492] 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.

[0493] 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.

[0494] 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.

[0495] 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.

[0496] 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.

[0497] 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".

[0498] This invention is an educational support system that enables users to efficiently visually organize and deeply understand related information. The system aims to clarify the information structure by searching for information using specific vocabulary and visualizing related vocabulary.

[0499] The main components include a terminal for users to search for information, a server that generates and manages related information, and an interface that visually displays that information.

[0500] 1. Input via user interaction

[0501] The user enters the word to be investigated, such as "plant," into the input field of the interface on their device.

[0502] The terminal receives input and sends information about that word to the server as a request.

[0503] 2. Generation and provision of related vocabulary

[0504] The server receives a request and uses its internal database and generation engine to dynamically generate words related to the input vocabulary "plants." During this process, highly relevant vocabulary such as "photosynthesis," "seeds," and "cultivation" are selected based on past search data and language models.

[0505] 3. Visual arrangement of information

[0506] The server processes the generated list of related vocabulary words and sends the data to the terminal for visual display.

[0507] The terminal analyzes the received data and arranges related vocabulary as nodes in a visual memory tree on the user interface.

[0508] 4. Detailed explanation

[0509] When a user selects a specific node, such as "photosynthesis," a request is sent to the server asking for more information related to that node.

[0510] The server uses a generation engine to generate a detailed explanation, for example, sending to the terminal a statement such as, "Photosynthesis is the process by which plants use sunlight to produce chemical energy."

[0511] The device visually presents this explanation to the user.

[0512] This system allows users to expand on related information from words of interest and visually understand the interrelationships between pieces of information. Possible applications include supplementing educational materials in schools and using it as a tool for self-learners to organize and deepen their understanding of information.

[0513] The following describes the processing flow.

[0514] Step 1:

[0515] The user enters a specific word into an input field displayed on the device's interface. For example, they might enter the word "plant" and request suggestions for related information.

[0516] Step 2:

[0517] The terminal sends the word entered by the user to the server as a request. This request includes relevant information such as the user ID, as well as data to associate it with past request history.

[0518] Step 3:

[0519] The server processes the received request and uses its database and generation engine to generate related vocabulary for the specified word "plant." This generates related words such as "photosynthesis," "seed," and "cultivation."

[0520] Step 4:

[0521] The server compiles the generated related vocabulary and sends a data packet containing it to the terminal. This packet also includes relevance scores and metadata for display purposes.

[0522] Step 5:

[0523] The terminal analyzes the data received from the server and visually displays related vocabulary as a memory tree on the user interface. "Plants" is placed as the central node, and suggested related words are arranged around it.

[0524] Step 6:

[0525] The user clicks on a node of interest in the memory tree, such as "photosynthesis," to request further information or explanation.

[0526] Step 7:

[0527] The terminal receives user input and sends a request to the server for a detailed explanation corresponding to the specified node.

[0528] Step 8:

[0529] The server uses a generation engine to generate detailed information and create an explanation about "photosynthesis." This information is generated using specialized databases and knowledge graphs within the server.

[0530] Step 9:

[0531] The server sends the generated explanatory information to the terminal.

[0532] Step 10:

[0533] The terminal receives explanatory information and displays the content above or below the corresponding node in the memory tree. This display allows the user to gain detailed knowledge about the selected node.

[0534] (Example 1)

[0535] 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."

[0536] The sheer volume of information can lead to user confusion and overload, and there is a growing need, particularly in the education sector, for students and learners to efficiently organize and deeply understand information. However, existing information retrieval systems and display methods often lack sufficient visual presentation of related information, making it difficult for users to easily understand the relationships between pieces of information.

[0537] 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.

[0538] In this invention, the server includes means for inputting a specific information unit, means for having an information processing device for generating a plurality of information units related to the input information unit, and means for visually arranging and displaying the generated information units. As a result, related information is visually presented based on the information unit selected by the user through the terminal, making it easy to understand the relationships between pieces of information and to deepen learning.

[0539] An "information unit" refers to a portion of the data that a user inputs and that is processed within the system, representing a specific vocabulary or concept.

[0540] An "information processing device" refers to a machine or program that has the function of generating and outputting information related to an input unit of information through calculation or retrieval.

[0541] "User interface" refers to the elements that provide screens and means of operation for users to interact with a system and receive information visually.

[0542] "Generative function" refers to the ability to automatically generate new related information based on information units input by the user, and includes generative AI models.

[0543] A "connection point" refers to a structural element that plays a role in linking information units together and visualizing the interrelationships between them.

[0544] "Learning function" refers to the ability of an information processing device to improve the relevance of information based on past data, and involves analysis and optimization.

[0545] This invention is a system for efficiently organizing information and presenting it visually to the user. The system generates related information based on words entered by the user and arranges it visually to facilitate information comprehension.

[0546] The server functions as an information processing device, receiving input information sent by the user from the terminal. The server then uses a generative AI model to generate new information related to the input information units. The generative AI model utilizes natural language processing techniques to select highly relevant vocabulary and calculates the necessary data based on the user's instructions.

[0547] The device visually presents information generated through the user interface. Specifically, it uses HTML5 and JavaScript to arrange information units in a node format and visualizes the connections between pieces of information. This visualization allows users to easily understand the interrelationships between related information.

[0548] A concrete example of its use is a student in an educational setting who is interested in "energy conversion" and types the word "photosynthesis" into their device. In response, the server generates related vocabulary such as "carbon dioxide fixation" and "oxygen production," which the device then visualizes. As a result, the student can more easily understand the process of energy conversion in nature.

[0549] Examples of prompt statements include the following:

[0550] "Please explain photosynthesis and its related processes in detail."

[0551] "Please describe the important concepts in energy conversion and their relationships."

[0552] This embodiment of the invention makes it possible to achieve effective information provision and enhanced understanding by combining information generation and visualization.

[0553] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0554] Step 1:

[0555] The user inputs a unit of information into the terminal's user interface. For example, they might type the word "plant" into the input form. The terminal then retrieves the input data and prepares it as a request to the server.

[0556] Step 2:

[0557] The terminal sends a request to the server. This request contains units of information entered by the user. The terminal sends the data over the network using the HTTP protocol, and the server receives it.

[0558] Step 3:

[0559] The server activates a generative AI model based on the received request. Given the information unit "plant" as input data, the server generates related vocabulary. The generative AI model analyzes past data and language patterns to dynamically generate related words such as "photosynthesis," "seed," and "cultivation."

[0560] Step 4:

[0561] The server compiles the generated related vocabulary list and formats it for output to the terminal. This formatting process organizes the data into a hierarchical structure and adds metadata for visualization.

[0562] Step 5:

[0563] The server sends formatted data to the terminal. The terminal receives this data and begins internal analysis. The terminal then prepares to visually display the data on a user interface using HTML5 or JavaScript.

[0564] Step 6:

[0565] The terminal arranges related vocabulary on the screen in a node format. The user interface displays related information units as nodes on a memory tree, and each node is arranged in a selectable format.

[0566] Step 7:

[0567] When a user selects a specific node, the device sends another request to the server to retrieve more detailed information based on that node. For example, if the user selects "photosynthesis," a request will be generated asking for a detailed explanation related to it.

[0568] Step 8:

[0569] The server receives this request, uses the generation AI model again to generate detailed information, and sends it to the terminal. The generated information includes, for example, an explanation such as, "Photosynthesis is the process by which plants use sunlight to produce chemical energy."

[0570] Step 9:

[0571] The device presents the received explanatory data to the user. It visually constructs information and allows users to view detailed information associated with specific nodes. This can enrich the user's learning experience.

[0572] (Application Example 1)

[0573] 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."

[0574] Current learning support systems make it difficult for users to efficiently organize and understand information related to the vocabulary they input. In particular, the lack of visual information placement and presentation of related content to improve learning effectiveness makes it difficult for users to grasp the overall picture of the information.

[0575] 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.

[0576] In this invention, the server includes a mechanism for inputting a specific word, a generation device for generating multiple words related to the input word, and a mechanism for visually arranging and displaying the generated words. This allows the user to efficiently visually understand relevant information and easily obtain the content necessary for learning.

[0577] A "word" is the smallest meaningful component in natural language.

[0578] A "generation device" is a device in a system that has the function of generating relevant data based on input information.

[0579] "Visual arrangement" refers to organizing and displaying information visually, presenting data in a way that users can easily understand.

[0580] "Content" refers to information, learning materials, and media resources provided to users for learning.

[0581] A "node" refers to an individual element within a visual information structure, functioning as a point for displaying related information.

[0582] "Learning function" refers to a function that allows a system to improve its performance based on experience and data, aiming to increase the accuracy of relevant information.

[0583] This system provides support to help users effectively engage in learning activities. The following describes a specific embodiment of this system.

[0584] When a user inputs a specific word, the server generates several related words. This involves a process that uses a generative AI model to efficiently extract highly relevant words based on past data and learning outcomes. The generated words are visually organized and sent to the user's terminal.

[0585] On the device, a visually arranged tree of words is displayed. Through this tree, users can select words of interest and directly view detailed information and related content. This UI is built using an intuitive interface based on programming languages ​​such as JavaScript.

[0586] A concrete example is a student studying biology. When the student enters the word "photosynthesis," related words such as "carbon dioxide" and "oxygen" are displayed on the terminal. By selecting each word, related explanatory videos and text information are presented. This information is quickly processed and provided by the server using a generation engine.

[0587] Examples of prompts for a generative AI model are as follows:

[0588] "Generate code that generates vocabulary related to the word 'photosynthesis' entered by the user, and displays it in a tree-like visual interface."

[0589] With a system configured in this way, users can efficiently understand relevant information visually and easily acquire the content necessary for learning.

[0590] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0591] Step 1:

[0592] The user enters a specific word into the input field of the terminal. At this time, the entered word is sent to the server as a request. The input is the word from the user, and the output is the request data to the server. Specifically, for example, if the word "photosynthesis" is entered, a request is sent to the server.

[0593] Step 2:

[0594] The server generates several related words based on the words included in the received request. This process uses a generative AI model to select related words from historical data and language models related to the input words. The input is a list of words, and the output is a list of related words. The generated vocabulary includes words like "carbon dioxide" and "oxygen."

[0595] Step 3:

[0596] The server generates data for visually arranging the generated list of related words and sends it to the terminal. At this time, data that visually organizes the related words is created and provided in a format that the user can intuitively use. The input is a list of related words, and the output is data for visualization.

[0597] Step 4:

[0598] The terminal analyzes the visualization data received from the server and displays a tree of words visually arranged on the interface. This creates an environment where the user can freely make selections. The input is data for visualization, and the output is a tree of related words drawn on the user interface.

[0599] Step 5:

[0600] When a user selects a specific word on the interface, the terminal sends that selection data to the server as a request. This action initiates a process to retrieve detailed information related to the selected word. The input is the user selection data, and the output is the request to the server.

[0601] Step 6:

[0602] The server generates detailed information about the selected words and sends it to the terminal. At this stage, a generative AI model is used to create a detailed explanation of the selected content and deliver it to the terminal. The input is user-selected data, and the output is detailed information.

[0603] Step 7:

[0604] The terminal visually presents information to the user based on detailed information received from the server. This allows the user to gain a deeper understanding of the selected words. The input is detailed information, and the output is what is presented to the user.

[0605] 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.

[0606] This invention is a system for realizing a more personalized educational experience and information gathering by presenting information while taking user emotions into consideration. The aim of this system is to enable users to visually grasp relevant information, recognize the user's emotions in response to it, and provide optimized information.

[0607] System Configuration

[0608] 1. User terminal operation

[0609] The user uses the device's interface to input the vocabulary to be learned. For example, they might select the word "weather."

[0610] 2. Emotion recognition and generation of related vocabulary

[0611] The device is equipped with a camera and microphone, which analyze the user's emotions from their facial expressions and tone of voice. This allows the emotion engine to identify emotional states such as joy, confusion, or interest.

[0612] The server uses an advanced generative engine to generate relevant vocabulary based on the user's sentiment data and input vocabulary. Words such as "rain," "sunny," and "weather forecast" are generated, and their priority is set according to the user's sentiment.

[0613] 3. Visualization of Information

[0614] The server considers the user's emotions, calculates the optimal visual arrangement of the generated vocabulary as nodes, and sends it to the terminal.

[0615] The device uses the received data to construct a memory tree in a way that will interest the user, and displays it on the screen.

[0616] 4. Information presentation and content adjustment

[0617] When a user selects a node they are interested in (for example, "weather forecast"), a request for detailed information is sent from the terminal to the server.

[0618] The server uses the results of the emotion engine's analysis to generate and adjust appropriate information and content tailored to the user's emotional state, and sends the most suitable explanations to the device to ensure an enjoyable learning experience.

[0619] Through this system, users can enjoy information gathering and gain a deeper understanding by receiving information tailored to their emotions. This combination goes beyond simply displaying related information and enables personalized learning support that is tailored to each user.

[0620] The following describes the processing flow.

[0621] Step 1:

[0622] The user uses the input field on their device to enter the vocabulary they want to search for. For example, they might enter "weather".

[0623] Step 2:

[0624] The device captures the user's facial expressions with its camera and collects audio with its microphone to acquire emotional data. This data is then used by an emotion engine to analyze the user's current emotional state (joy, interest, fatigue, etc.).

[0625] Step 3:

[0626] The terminal sends the entered vocabulary word "weather" along with the acquired sentiment data to the server. The sentiment data is used as a parameter to improve the user's search experience.

[0627] Step 4:

[0628] The server uses a generation engine to generate relevant vocabulary based on the received "weather" and sentiment data. For example, it generates terms such as "rain," "sunny," and "weather forecast." If the sentiment data suggests a user's interest, the server assigns a higher priority to that relevant vocabulary.

[0629] Step 5:

[0630] The server arranges the generated vocabulary in a highly relevant order and calculates a visually effective layout. At this time, it also takes into account user emotions, considering factors such as readability and ease of interaction.

[0631] Step 6:

[0632] The server sends back related vocabulary and its placement information to the terminal.

[0633] Step 7:

[0634] The device receives this information and displays a memory tree on the user's screen. The size and color of the nodes are adjusted according to emotions, making it easier to engage the user.

[0635] Step 8:

[0636] Users can request detailed information by clicking on a node of interest from the displayed memory tree, such as "weather forecast."

[0637] Step 9:

[0638] The device detects the user's selection action, sends that information to the server, and requests detailed data.

[0639] Step 10:

[0640] The server then uses the emotion engine again to generate detailed information related to the selected node ("weather forecast"). At the same time, it also makes adjustments to present the information in a way that aligns with the emotion.

[0641] Step 11:

[0642] The server sends the generated detailed information to the terminal.

[0643] Step 12:

[0644] The device displays the received details on its screen and provides content related to the node selected by the user, thereby deepening their understanding. The displayed content is presented in an easy-to-understand format and at a suitable pace, taking into account the user's emotional state.

[0645] (Example 2)

[0646] 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."

[0647] In presenting information, there is a lack of personalized content that responds to users' emotions and interests, making it difficult to provide information efficiently and sustainably. Furthermore, there is room for improvement in methods of systematically visualizing related information.

[0648] 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.

[0649] In this invention, the server includes means for analyzing the user's emotional state and optimizing the content presented based on the analysis results, means for setting the priority of information presented according to the user's emotional state, and means having a learning function for strengthening the relationships between related data generated by the generation unit. This makes it possible to present information according to the user's emotions, enabling the efficient and attractive provision of information to individual users.

[0650] "Specific information" refers to data that users input into the system for learning or information gathering purposes.

[0651] "Generation unit" refers to a device or software that has the function of generating data related to the input information.

[0652] "Visual arrangement" refers to the method and result of displaying generated data in a way that is easy for users to understand.

[0653] "Emotional state" refers to the psychological and emotional state inferred from the user's facial expressions and tone of voice.

[0654] "Learning function" refers to a function that a system uses to improve the accuracy and usefulness of related data based on user feedback and interaction.

[0655] "Priority" refers to the criteria used to determine the display order based on the importance and level of interest of the information presented.

[0656] This invention is a system that comprehensively realizes everything from information input to data visualization and optimization of information provision through sentiment analysis. It primarily involves a server, terminals, and users, and in particular uses a generative AI model to generate relevant data based on user input.

[0657] The user inputs specific information into the terminal's interface. The terminal is equipped with a high-resolution camera and a high-sensitivity microphone to capture the user's facial expressions and tone of voice, and emotion analysis software is used to identify their emotional state. After receiving this emotional data, the server utilizes a generative AI model to generate data related to the input information. The generated data is then given priority according to the emotional state.

[0658] The generated data is then visualized on the server side using a visualization algorithm to determine the optimal layout, and then sent to the terminal. The terminal uses this data to display it on the user's screen. For example, if information about "weather" is entered, related data such as "rain," "sunny," and "weather forecast" will be displayed in an arrangement that suits the user's interests.

[0659] When a user selects an information node that interests them, a request is sent from the device to the server. The server then utilizes the emotion engine again to construct appropriate details, send them to the device, and present them to the user. This allows users to receive information that aligns with their emotions, making learning and information gathering more enjoyable.

[0660] As a concrete example, here is an example of a prompt message:

[0661] "How can I generate relevant weather-related information that a user is interested in and display it in a way that is optimized for the user's emotional state?"

[0662] This system allows users to receive personalized information experiences that respond to their emotions.

[0663] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0664] Step 1:

[0665] The user inputs specific information into the device. Specifically, the user inputs information such as "weather" in text format via the device's interface. This input data is stored in the device as basic information necessary for subsequent processing.

[0666] Step 2:

[0667] The device analyzes the user's emotional state. The device uses its camera to capture the user's facial expressions and its microphone to record their voice. Based on this data, emotion analysis software identifies the user's emotions (joy, interest, confusion, etc.) in real time. This emotion data is then sent to a server.

[0668] Step 3:

[0669] The server generates relevant data. Based on the received sentiment data and user input, the server inputs prompt messages into the generating AI model. In this process, to provide a dataset related to "weather," the generating AI model generates relevant data including "rain," "sunny," and "weather forecast." The generated results are then prioritized according to the sentiment.

[0670] Step 4:

[0671] The server calculates the visual arrangement of the generated data. Using a visualization algorithm, the server arranges the generated related data according to user sentiment priorities. This arrangement is then prepared for transmission to the device in a way that aligns with the user's interests.

[0672] Step 5:

[0673] The terminal displays the generated data. The terminal displays the visual data received from the server on the screen in a memory tree format. For example, if the user is interested in "weather forecasts," related information will be visually displayed around that. This display is arranged so that the user can easily explore the information.

[0674] Step 6:

[0675] The user requests more information. When the user selects an information node of interest (e.g., "weather forecast"), the request is sent from the terminal to the server. This selection is treated as a request for specific information retrieval.

[0676] Step 7:

[0677] The server generates detailed information. The server again utilizes the emotion engine to generate appropriate detailed information for the selected information node. The generated detailed information is written in a way that is most easily understood by the user, based on their emotions. This information is sent to the terminal and ultimately presented to the user.

[0678] Through this series of processes, users receive information that is appropriate to their emotions, and are provided with an information experience that is individually optimized for them.

[0679] (Application Example 2)

[0680] 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."

[0681] Current information delivery systems often provide uniform information without considering user emotions, and have the problem of failing to present optimal information tailored to the user's situation. As a result, users spend a lot of time obtaining the information they need, and the learning and information gathering experience cannot be personalized.

[0682] 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.

[0683] In this invention, the server includes means for inputting specific vocabulary, means for analyzing the user's emotions and optimizing relevant information based on the analysis results, and a device for presenting group information based on the user's state. This enables personalized information provision that responds to the user's emotions.

[0684] "Vocabulary" refers to a collection of words and technical terms used in a specific context.

[0685] A "generation device" is a device equipped with the function of creating relevant information based on input information.

[0686] "Visual arrangement" is a method of visually organizing and displaying information.

[0687] "Detailed information" refers to information that goes into more depth than the basic information provided.

[0688] "Emotion analysis" is a technology that reads and analyzes a user's emotions from their facial expressions and voice data.

[0689] A "device" is a rigid or flexible component that performs a specific function.

[0690] "Group information" refers to a collection of multiple related pieces of information.

[0691] The system for implementing this invention has the function of generating information based on user input and providing that information optimized to match the user's emotional state. The main components are an input device, an emotion analysis device, a generation device, a display device, and software that runs on a server.

[0692] The input device provides an interface for users to input specific vocabulary. This allows users to clearly indicate topics of interest.

[0693] The emotion analysis device uses cameras and microphones to collect data on the user's facial expressions and voice, and analyzes their emotions in real time using cloud computing services (e.g., Google Cloud Vision API or Azure Cognitive Services). The results of this analysis represent the user's emotional state as digital data.

[0694] The generator receives analyzed emotion data and generates relevant information according to the user's emotions. The generated information is used to change the priority of the information and personalize the user's personal experience.

[0695] The display device visually arranges the generated information and presents it in a format that is easily understandable to the user. This allows the user to intuitively grasp the relationships between the pieces of information.

[0696] The server manages these processes in an integrated manner, streamlining the processing of each piece of data. It is also designed to optimally combine relevant information using generative AI models, presenting valuable information to the user.

[0697] As a concrete example, when a user visiting a virtual store searches for a product, recommended products are presented based on their emotional state. In this case, the server sends a prompt message to the AI ​​model, such as "Generate relevant information to recommend when the user has an interested expression," and generates appropriate information.

[0698] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0699] Step 1:

[0700] The user inputs specific vocabulary using an input device. This input vocabulary forms the basis for information generation. This vocabulary is transmitted to the terminal and serves as the starting point for providing information tailored to the user's interests and needs.

[0701] Step 2:

[0702] The device uses its built-in camera and microphone to collect the user's facial expressions and voice in real time. This data is then sent to a server as input for emotion analysis.

[0703] Step 3:

[0704] The server uses the received facial and voice data to analyze the user's emotions using a cloud-based emotion analysis service (e.g., Google Cloud Vision API). The output obtained here is the user's emotional state expressed as numerical data.

[0705] Step 4:

[0706] The server uses a generative AI model to generate relevant information based on analyzed sentiment data and the user's input vocabulary. During this process, it prioritizes and optimizes the information according to the degree of emotion. The output is a set of information tailored to the emotion.

[0707] Step 5:

[0708] The terminal receives optimized information sent from the server and visually arranges the information on the display device. Here, the information is displayed as nodes, allowing the user to intuitively understand the relationships between them. The output is a display of the visually arranged information.

[0709] Step 6:

[0710] The user selects a node of interest from the presented information. The selected information request is then sent back from the terminal to the server.

[0711] Step 7:

[0712] The server generates additional detailed information related to the selected node and provides further information using prompts from the generating AI model (e.g., "Generate relevant information to recommend when the user makes an interested expression."). This output, consisting of additional details, is sent to the terminal.

[0713] Step 8:

[0714] The terminal receives additional information from the server, providing users with richer information and improving the quality of their learning experience and information gathering. The output is a display of detailed information tailored to the user.

[0715] 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.

[0716] 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.

[0717] 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.

[0718] [Fourth Embodiment]

[0719] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0720] 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.

[0721] 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).

[0722] 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.

[0723] 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.

[0724] 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).

[0725] 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.

[0726] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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".

[0732] This invention is an educational support system that enables users to efficiently visually organize and deeply understand related information. The system aims to clarify the information structure by searching for information using specific vocabulary and visualizing related vocabulary.

[0733] The main components include a terminal for users to search for information, a server that generates and manages related information, and an interface that visually displays that information.

[0734] 1. Input via user interaction

[0735] The user enters the word to be investigated, such as "plant," into the input field of the interface on their device.

[0736] The terminal receives input and sends information about that word to the server as a request.

[0737] 2. Generation and provision of related vocabulary

[0738] The server receives a request and uses its internal database and generation engine to dynamically generate words related to the input vocabulary "plants." During this process, highly relevant vocabulary such as "photosynthesis," "seeds," and "cultivation" are selected based on past search data and language models.

[0739] 3. Visual arrangement of information

[0740] The server processes the generated list of related vocabulary words and sends the data to the terminal for visual display.

[0741] The terminal analyzes the received data and arranges related vocabulary as nodes in a visual memory tree on the user interface.

[0742] 4. Detailed explanation

[0743] When a user selects a specific node, such as "photosynthesis," a request is sent to the server asking for more information related to that node.

[0744] The server uses a generation engine to generate a detailed explanation, for example, sending to the terminal a statement such as, "Photosynthesis is the process by which plants use sunlight to produce chemical energy."

[0745] The device visually presents this explanation to the user.

[0746] This system allows users to expand on related information from words of interest and visually understand the interrelationships between pieces of information. Possible applications include supplementing educational materials in schools and using it as a tool for self-learners to organize and deepen their understanding of information.

[0747] The following describes the processing flow.

[0748] Step 1:

[0749] The user enters a specific word into an input field displayed on the device's interface. For example, they might enter the word "plant" and request suggestions for related information.

[0750] Step 2:

[0751] The terminal sends the word entered by the user to the server as a request. This request includes relevant information such as the user ID, as well as data to associate it with past request history.

[0752] Step 3:

[0753] The server processes the received request and uses its database and generation engine to generate related vocabulary for the specified word "plant." This generates related words such as "photosynthesis," "seed," and "cultivation."

[0754] Step 4:

[0755] The server compiles the generated related vocabulary and sends a data packet containing it to the terminal. This packet also includes relevance scores and metadata for display purposes.

[0756] Step 5:

[0757] The terminal analyzes the data received from the server and visually displays related vocabulary as a memory tree on the user interface. "Plants" is placed as the central node, and suggested related words are arranged around it.

[0758] Step 6:

[0759] The user clicks on a node of interest in the memory tree, such as "photosynthesis," to request further information or explanation.

[0760] Step 7:

[0761] The terminal receives user input and sends a request to the server for a detailed explanation corresponding to the specified node.

[0762] Step 8:

[0763] The server uses a generation engine to generate detailed information and create an explanation about "photosynthesis." This information is generated using specialized databases and knowledge graphs within the server.

[0764] Step 9:

[0765] The server sends the generated explanatory information to the terminal.

[0766] Step 10:

[0767] The terminal receives explanatory information and displays the content above or below the corresponding node in the memory tree. This display allows the user to gain detailed knowledge about the selected node.

[0768] (Example 1)

[0769] 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".

[0770] The sheer volume of information can lead to user confusion and overload, and there is a growing need, particularly in the education sector, for students and learners to efficiently organize and deeply understand information. However, existing information retrieval systems and display methods often lack sufficient visual presentation of related information, making it difficult for users to easily understand the relationships between pieces of information.

[0771] 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.

[0772] In this invention, the server includes means for inputting a specific information unit, means for having an information processing device for generating a plurality of information units related to the input information unit, and means for visually arranging and displaying the generated information units. As a result, related information is visually presented based on the information unit selected by the user through the terminal, making it easy to understand the relationships between pieces of information and to deepen learning.

[0773] An "information unit" refers to a portion of the data that a user inputs and that is processed within the system, representing a specific vocabulary or concept.

[0774] An "information processing device" refers to a machine or program that has the function of generating and outputting information related to an input unit of information through calculation or retrieval.

[0775] "User interface" refers to the elements that provide screens and means of operation for users to interact with a system and receive information visually.

[0776] "Generative function" refers to the ability to automatically generate new related information based on information units input by the user, and includes generative AI models.

[0777] A "connection point" refers to a structural element that plays a role in linking information units together and visualizing the interrelationships between them.

[0778] "Learning function" refers to the ability of an information processing device to improve the relevance of information based on past data, and involves analysis and optimization.

[0779] This invention is a system for efficiently organizing information and presenting it visually to the user. The system generates related information based on words entered by the user and arranges it visually to facilitate information comprehension.

[0780] The server functions as an information processing device, receiving input information sent by the user from the terminal. The server then uses a generative AI model to generate new information related to the input information units. The generative AI model utilizes natural language processing techniques to select highly relevant vocabulary and calculates the necessary data based on the user's instructions.

[0781] The device visually presents information generated through the user interface. Specifically, it uses HTML5 and JavaScript to arrange information units in a node format and visualizes the connections between pieces of information. This visualization allows users to easily understand the interrelationships between related information.

[0782] A concrete example of its use is a student in an educational setting who is interested in "energy conversion" and types the word "photosynthesis" into their device. In response, the server generates related vocabulary such as "carbon dioxide fixation" and "oxygen production," which the device then visualizes. As a result, the student can more easily understand the process of energy conversion in nature.

[0783] Examples of prompt statements include the following:

[0784] "Please explain photosynthesis and its related processes in detail."

[0785] "Please describe the important concepts in energy conversion and their relationships."

[0786] This embodiment of the invention makes it possible to achieve effective information provision and enhanced understanding by combining information generation and visualization.

[0787] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0788] Step 1:

[0789] The user inputs a unit of information into the terminal's user interface. For example, they might type the word "plant" into the input form. The terminal then retrieves the input data and prepares it as a request to the server.

[0790] Step 2:

[0791] The terminal sends a request to the server. This request contains units of information entered by the user. The terminal sends the data over the network using the HTTP protocol, and the server receives it.

[0792] Step 3:

[0793] The server activates a generative AI model based on the received request. Given the information unit "plant" as input data, the server generates related vocabulary. The generative AI model analyzes past data and language patterns to dynamically generate related words such as "photosynthesis," "seed," and "cultivation."

[0794] Step 4:

[0795] The server compiles the generated related vocabulary list and formats it for output to the terminal. This formatting process organizes the data into a hierarchical structure and adds metadata for visualization.

[0796] Step 5:

[0797] The server sends formatted data to the terminal. The terminal receives this data and begins internal analysis. The terminal then prepares to visually display the data on a user interface using HTML5 or JavaScript.

[0798] Step 6:

[0799] The terminal arranges related vocabulary on the screen in a node format. The user interface displays related information units as nodes on a memory tree, and each node is arranged in a selectable format.

[0800] Step 7:

[0801] When a user selects a specific node, the device sends another request to the server to retrieve more detailed information based on that node. For example, if the user selects "photosynthesis," a request will be generated asking for a detailed explanation related to it.

[0802] Step 8:

[0803] The server receives this request, uses the generation AI model again to generate detailed information, and sends it to the terminal. The generated information includes, for example, an explanation such as, "Photosynthesis is the process by which plants use sunlight to produce chemical energy."

[0804] Step 9:

[0805] The device presents the received explanatory data to the user. It visually constructs information and allows users to view detailed information associated with specific nodes. This can enrich the user's learning experience.

[0806] (Application Example 1)

[0807] 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".

[0808] Current learning support systems make it difficult for users to efficiently organize and understand information related to the vocabulary they input. In particular, the lack of visual information placement and presentation of related content to improve learning effectiveness makes it difficult for users to grasp the overall picture of the information.

[0809] 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.

[0810] In this invention, the server includes a mechanism for inputting a specific word, a generation device for generating multiple words related to the input word, and a mechanism for visually arranging and displaying the generated words. This allows the user to efficiently visually understand relevant information and easily obtain the content necessary for learning.

[0811] A "word" is the smallest meaningful component in natural language.

[0812] A "generation device" is a device in a system that has the function of generating relevant data based on input information.

[0813] "Visual arrangement" refers to organizing and displaying information visually, presenting data in a way that users can easily understand.

[0814] "Content" refers to information, learning materials, and media resources provided to users for learning.

[0815] A "node" refers to an individual element within a visual information structure, functioning as a point for displaying related information.

[0816] "Learning function" refers to a function that allows a system to improve its performance based on experience and data, aiming to increase the accuracy of relevant information.

[0817] This system provides support to help users effectively engage in learning activities. The following describes a specific embodiment of this system.

[0818] When a user inputs a specific word, the server generates several related words. This involves a process that uses a generative AI model to efficiently extract highly relevant words based on past data and learning outcomes. The generated words are visually organized and sent to the user's terminal.

[0819] On the device, a visually arranged tree of words is displayed. Through this tree, users can select words of interest and directly view detailed information and related content. This UI is built using an intuitive interface based on programming languages ​​such as JavaScript.

[0820] A concrete example is a student studying biology. When the student enters the word "photosynthesis," related words such as "carbon dioxide" and "oxygen" are displayed on the terminal. By selecting each word, related explanatory videos and text information are presented. This information is quickly processed and provided by the server using a generation engine.

[0821] Examples of prompts for a generative AI model are as follows:

[0822] "Generate code that generates vocabulary related to the word 'photosynthesis' entered by the user, and displays it in a tree-like visual interface."

[0823] With a system configured in this way, users can efficiently understand relevant information visually and easily acquire the content necessary for learning.

[0824] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0825] Step 1:

[0826] The user enters a specific word into the input field of the terminal. At this time, the entered word is sent to the server as a request. The input is the word from the user, and the output is the request data to the server. Specifically, for example, if the word "photosynthesis" is entered, a request is sent to the server.

[0827] Step 2:

[0828] The server generates several related words based on the words included in the received request. This process uses a generative AI model to select related words from historical data and language models related to the input words. The input is a list of words, and the output is a list of related words. The generated vocabulary includes words like "carbon dioxide" and "oxygen."

[0829] Step 3:

[0830] The server generates data for visually arranging the generated list of related words and sends it to the terminal. At this time, data that visually organizes the related words is created and provided in a format that the user can intuitively use. The input is a list of related words, and the output is data for visualization.

[0831] Step 4:

[0832] The terminal analyzes the visualization data received from the server and displays a tree of words visually arranged on the interface. This creates an environment where the user can freely make selections. The input is data for visualization, and the output is a tree of related words drawn on the user interface.

[0833] Step 5:

[0834] When a user selects a specific word on the interface, the terminal sends that selection data to the server as a request. This action initiates a process to retrieve detailed information related to the selected word. The input is the user selection data, and the output is the request to the server.

[0835] Step 6:

[0836] The server generates detailed information about the selected words and sends it to the terminal. At this stage, a generative AI model is used to create a detailed explanation of the selected content and deliver it to the terminal. The input is user-selected data, and the output is detailed information.

[0837] Step 7:

[0838] The terminal visually presents information to the user based on detailed information received from the server. This allows the user to gain a deeper understanding of the selected words. The input is detailed information, and the output is what is presented to the user.

[0839] 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.

[0840] This invention is a system for realizing a more personalized educational experience and information gathering by presenting information while taking user emotions into consideration. The aim of this system is to enable users to visually grasp relevant information, recognize the user's emotions in response to it, and provide optimized information.

[0841] System Configuration

[0842] 1. User terminal operation

[0843] The user uses the device's interface to input the vocabulary to be learned. For example, they might select the word "weather."

[0844] 2. Emotion recognition and generation of related vocabulary

[0845] The device is equipped with a camera and microphone, which analyze the user's emotions from their facial expressions and tone of voice. This allows the emotion engine to identify emotional states such as joy, confusion, or interest.

[0846] The server uses an advanced generative engine to generate relevant vocabulary based on the user's sentiment data and input vocabulary. Words such as "rain," "sunny," and "weather forecast" are generated, and their priority is set according to the user's sentiment.

[0847] 3. Visualization of Information

[0848] The server considers the user's emotions, calculates the optimal visual arrangement of the generated vocabulary as nodes, and sends it to the terminal.

[0849] The device uses the received data to construct a memory tree in a way that will interest the user, and displays it on the screen.

[0850] 4. Information presentation and content adjustment

[0851] When a user selects a node they are interested in (for example, "weather forecast"), a request for detailed information is sent from the terminal to the server.

[0852] The server uses the results of the emotion engine's analysis to generate and adjust appropriate information and content tailored to the user's emotional state, and sends the most suitable explanations to the device to ensure an enjoyable learning experience.

[0853] Through this system, users can enjoy information gathering and gain a deeper understanding by receiving information tailored to their emotions. This combination goes beyond simply displaying related information and enables personalized learning support that is tailored to each user.

[0854] The following describes the processing flow.

[0855] Step 1:

[0856] The user uses the input field on their device to enter the vocabulary they want to search for. For example, they might enter "weather".

[0857] Step 2:

[0858] The device captures the user's facial expressions with its camera and collects audio with its microphone to acquire emotional data. This data is then used by an emotion engine to analyze the user's current emotional state (joy, interest, fatigue, etc.).

[0859] Step 3:

[0860] The terminal sends the entered vocabulary word "weather" along with the acquired sentiment data to the server. The sentiment data is used as a parameter to improve the user's search experience.

[0861] Step 4:

[0862] The server uses a generation engine to generate relevant vocabulary based on the received "weather" and sentiment data. For example, it generates terms such as "rain," "sunny," and "weather forecast." If the sentiment data suggests a user's interest, the server assigns a higher priority to that relevant vocabulary.

[0863] Step 5:

[0864] The server arranges the generated vocabulary in a highly relevant order and calculates a visually effective layout. At this time, it also takes into account user emotions, considering factors such as readability and ease of interaction.

[0865] Step 6:

[0866] The server sends back related vocabulary and its placement information to the terminal.

[0867] Step 7:

[0868] The device receives this information and displays a memory tree on the user's screen. The size and color of the nodes are adjusted according to emotions, making it easier to engage the user.

[0869] Step 8:

[0870] Users can request detailed information by clicking on a node of interest from the displayed memory tree, such as "weather forecast."

[0871] Step 9:

[0872] The device detects the user's selection action, sends that information to the server, and requests detailed data.

[0873] Step 10:

[0874] The server then uses the emotion engine again to generate detailed information related to the selected node ("weather forecast"). At the same time, it also makes adjustments to present the information in a way that aligns with the emotion.

[0875] Step 11:

[0876] The server sends the generated detailed information to the terminal.

[0877] Step 12:

[0878] The device displays the received details on its screen and provides content related to the node selected by the user, thereby deepening their understanding. The displayed content is presented in an easy-to-understand format and at a suitable pace, taking into account the user's emotional state.

[0879] (Example 2)

[0880] 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".

[0881] In presenting information, there is a lack of personalized content that responds to users' emotions and interests, making it difficult to provide information efficiently and sustainably. Furthermore, there is room for improvement in methods of systematically visualizing related information.

[0882] 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.

[0883] In this invention, the server includes means for analyzing the user's emotional state and optimizing the content presented based on the analysis results, means for setting the priority of information presented according to the user's emotional state, and means having a learning function for strengthening the relationships between related data generated by the generation unit. This makes it possible to present information according to the user's emotions, enabling the efficient and attractive provision of information to individual users.

[0884] "Specific information" refers to data that users input into the system for learning or information gathering purposes.

[0885] "Generation unit" refers to a device or software that has the function of generating data related to the input information.

[0886] "Visual arrangement" refers to the method and result of displaying generated data in a way that is easy for users to understand.

[0887] "Emotional state" refers to the psychological and emotional state inferred from the user's facial expressions and tone of voice.

[0888] "Learning function" refers to a function that a system uses to improve the accuracy and usefulness of related data based on user feedback and interaction.

[0889] "Priority" refers to the criteria used to determine the display order based on the importance and level of interest of the information presented.

[0890] This invention is a system that comprehensively realizes everything from information input to data visualization and optimization of information provision through sentiment analysis. It primarily involves a server, terminals, and users, and in particular uses a generative AI model to generate relevant data based on user input.

[0891] The user inputs specific information into the terminal's interface. The terminal is equipped with a high-resolution camera and a high-sensitivity microphone to capture the user's facial expressions and tone of voice, and emotion analysis software is used to identify their emotional state. After receiving this emotional data, the server utilizes a generative AI model to generate data related to the input information. The generated data is then given priority according to the emotional state.

[0892] The generated data is then visualized on the server side using a visualization algorithm to determine the optimal layout, and then sent to the terminal. The terminal uses this data to display it on the user's screen. For example, if information about "weather" is entered, related data such as "rain," "sunny," and "weather forecast" will be displayed in an arrangement that suits the user's interests.

[0893] When a user selects an information node that interests them, a request is sent from the device to the server. The server then utilizes the emotion engine again to construct appropriate details, send them to the device, and present them to the user. This allows users to receive information that aligns with their emotions, making learning and information gathering more enjoyable.

[0894] As a concrete example, here is an example of a prompt message:

[0895] "How can I generate relevant weather-related information that a user is interested in and display it in a way that is optimized for the user's emotional state?"

[0896] This system allows users to receive personalized information experiences that respond to their emotions.

[0897] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0898] Step 1:

[0899] The user inputs specific information into the device. Specifically, the user inputs information such as "weather" in text format via the device's interface. This input data is stored in the device as basic information necessary for subsequent processing.

[0900] Step 2:

[0901] The device analyzes the user's emotional state. The device uses its camera to capture the user's facial expressions and its microphone to record their voice. Based on this data, emotion analysis software identifies the user's emotions (joy, interest, confusion, etc.) in real time. This emotion data is then sent to a server.

[0902] Step 3:

[0903] The server generates relevant data. Based on the received sentiment data and user input, the server inputs prompt messages into the generating AI model. In this process, to provide a dataset related to "weather," the generating AI model generates relevant data including "rain," "sunny," and "weather forecast." The generated results are then prioritized according to the sentiment.

[0904] Step 4:

[0905] The server calculates the visual arrangement of the generated data. Using a visualization algorithm, the server arranges the generated related data according to user sentiment priorities. This arrangement is then prepared for transmission to the device in a way that aligns with the user's interests.

[0906] Step 5:

[0907] The terminal displays the generated data. The terminal displays the visual data received from the server on the screen in a memory tree format. For example, if the user is interested in "weather forecasts," related information will be visually displayed around that. This display is arranged so that the user can easily explore the information.

[0908] Step 6:

[0909] The user requests more information. When the user selects an information node of interest (e.g., "weather forecast"), the request is sent from the terminal to the server. This selection is treated as a request for specific information retrieval.

[0910] Step 7:

[0911] The server generates detailed information. The server again utilizes the emotion engine to generate appropriate detailed information for the selected information node. The generated detailed information is written in a way that is most easily understood by the user, based on their emotions. This information is sent to the terminal and ultimately presented to the user.

[0912] Through this series of processes, users receive information that is appropriate to their emotions, and are provided with an information experience that is individually optimized for them.

[0913] (Application Example 2)

[0914] 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".

[0915] Current information delivery systems often provide uniform information without considering user emotions, and have the problem of failing to present optimal information tailored to the user's situation. As a result, users spend a lot of time obtaining the information they need, and the learning and information gathering experience cannot be personalized.

[0916] 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.

[0917] In this invention, the server includes means for inputting specific vocabulary, means for analyzing the user's emotions and optimizing relevant information based on the analysis results, and a device for presenting group information based on the user's state. This enables personalized information provision that responds to the user's emotions.

[0918] "Vocabulary" refers to a collection of words and technical terms used in a specific context.

[0919] A "generation device" is a device equipped with the function of creating relevant information based on input information.

[0920] "Visual arrangement" is a method of visually organizing and displaying information.

[0921] "Detailed information" refers to information that goes into more depth than the basic information provided.

[0922] "Emotion analysis" is a technology that reads and analyzes a user's emotions from their facial expressions and voice data.

[0923] A "device" is a rigid or flexible component that performs a specific function.

[0924] "Group information" refers to a collection of multiple related pieces of information.

[0925] The system for implementing this invention has the function of generating information based on user input and providing that information optimized to match the user's emotional state. The main components are an input device, an emotion analysis device, a generation device, a display device, and software that runs on a server.

[0926] The input device provides an interface for users to input specific vocabulary. This allows users to clearly indicate topics of interest.

[0927] The emotion analysis device uses cameras and microphones to collect data on the user's facial expressions and voice, and analyzes their emotions in real time using cloud computing services (e.g., Google Cloud Vision API or Azure Cognitive Services). The results of this analysis represent the user's emotional state as digital data.

[0928] The generator receives analyzed emotion data and generates relevant information according to the user's emotions. The generated information is used to change the priority of the information and personalize the user's personal experience.

[0929] The display device visually arranges the generated information and presents it in a format that is easily understandable to the user. This allows the user to intuitively grasp the relationships between the pieces of information.

[0930] The server manages these processes in an integrated manner, streamlining the processing of each piece of data. It is also designed to optimally combine relevant information using generative AI models, presenting valuable information to the user.

[0931] As a concrete example, when a user visiting a virtual store searches for a product, recommended products are presented based on their emotional state. In this case, the server sends a prompt message to the AI ​​model, such as "Generate relevant information to recommend when the user has an interested expression," and generates appropriate information.

[0932] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0933] Step 1:

[0934] The user inputs specific vocabulary using an input device. This input vocabulary forms the basis for information generation. This vocabulary is transmitted to the terminal and serves as the starting point for providing information tailored to the user's interests and needs.

[0935] Step 2:

[0936] The device uses its built-in camera and microphone to collect the user's facial expressions and voice in real time. This data is then sent to a server as input for emotion analysis.

[0937] Step 3:

[0938] The server uses the received facial and voice data to analyze the user's emotions using a cloud-based emotion analysis service (e.g., Google Cloud Vision API). The output obtained here is the user's emotional state expressed as numerical data.

[0939] Step 4:

[0940] The server uses a generative AI model to generate relevant information based on analyzed sentiment data and the user's input vocabulary. During this process, it prioritizes and optimizes the information according to the degree of emotion. The output is a set of information tailored to the emotion.

[0941] Step 5:

[0942] The terminal receives optimized information sent from the server and visually arranges the information on the display device. Here, the information is displayed as nodes, allowing the user to intuitively understand the relationships between them. The output is a display of the visually arranged information.

[0943] Step 6:

[0944] The user selects a node of interest from the presented information. The selected information request is then sent back from the terminal to the server.

[0945] Step 7:

[0946] The server generates additional detailed information related to the selected node and provides further information using prompts from the generating AI model (e.g., "Generate relevant information to recommend when the user makes an interested expression."). This output, consisting of additional details, is sent to the terminal.

[0947] Step 8:

[0948] The terminal receives additional information from the server, providing users with richer information and improving the quality of their learning experience and information gathering. The output is a display of detailed information tailored to the user.

[0949] 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.

[0950] 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.

[0951] 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.

[0952] 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.

[0953] 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.

[0954] 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.

[0955] 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.

[0956] 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.

[0957] 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."

[0958] 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.

[0959] 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.

[0960] 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.

[0961] 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.

[0962] 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.

[0963] 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.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] 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.

[0968] 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.

[0969] 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.

[0970] The following is further disclosed regarding the embodiments described above.

[0971] (Claim 1)

[0972] A means of inputting specific vocabulary,

[0973] Means having a generation engine for generating multiple vocabulary related to the input vocabulary,

[0974] A means of visually arranging and displaying the generated vocabulary,

[0975] Means for obtaining detailed information about visualized vocabulary,

[0976] A system that includes means of presenting that detailed information.

[0977] (Claim 2)

[0978] The system according to claim 1, comprising means for arranging related vocabulary as nodes, with a vocabulary selected by the user as the central vocabulary.

[0979] (Claim 3)

[0980] The system according to claim 1, wherein the generation engine has means for having a learning function to enhance the relevance of the generated related vocabulary.

[0981] "Example 1"

[0982] (Claim 1)

[0983] A means of inputting a specific unit of information,

[0984] Means having an information processing device for generating multiple information units related to an input information unit,

[0985] A means for visually arranging and displaying the generated information units,

[0986] Means for obtaining detailed information about visualized information units,

[0987] The means of presenting that detailed information,

[0988] A means by which a user selects an information unit through a terminal, and a server provides a detailed explanation using an information processing device,

[0989] Means including having a function that allows the server to generate further information based on the selected information unit,

[0990] A system that includes means for visually presenting the interrelationships of information on a user interface based on the generated information.

[0991] (Claim 2)

[0992] The system according to claim 1, comprising means for arranging related information units as connection points, with an information unit selected by the user as the center.

[0993] (Claim 3)

[0994] The system according to claim 1, wherein the information processing device is equipped with means for having a learning function for strengthening the relationships between the generated related information units.

[0995] "Application Example 1"

[0996] (Claim 1)

[0997] A mechanism for inputting specific words,

[0998] A generator for generating multiple words related to an input word,

[0999] A mechanism for visually arranging and displaying the generated words,

[1000] A mechanism for obtaining detailed information about visualized words,

[1001] A mechanism for presenting that detailed information,

[1002] A mechanism for displaying content related to learning support,

[1003] A mechanism for presenting relevant content based on user selections.

[1004] A system that includes this.

[1005] (Claim 2)

[1006] The system according to claim 1, comprising a device for arranging related words as nodes, centered around a word selected by the user.

[1007] (Claim 3)

[1008] The system according to claim 1, characterized in that the generating device has a learning function for reinforcing the relationships between the generated related words.

[1009] "Example 2 of combining an emotion engine"

[1010] (Claim 1)

[1011] A means of inputting specific information,

[1012] Means having a generation unit for generating multiple data related to input information,

[1013] A means of visually arranging and displaying the generated data,

[1014] Means for obtaining detailed information about visualized data,

[1015] The means of presenting that detailed information,

[1016] A system that includes means for analyzing the emotional state of a user and optimizing the content presented based on the analysis results.

[1017] (Claim 2)

[1018] The system according to claim 1, comprising means for arranging related data as visual elements, centered on information selected by the user.

[1019] (Claim 3)

[1020] The system according to claim 1, comprising means having a learning function for strengthening the relationships between related data generated by the generation unit, and means for setting the priority of information presented according to the user's emotional state.

[1021] "Application example 2 when combining with an emotional engine"

[1022] (Claim 1)

[1023] A means of inputting specific vocabulary,

[1024] Means having a generation device for generating multiple vocabulary related to the input vocabulary,

[1025] A means of visually arranging and displaying the generated vocabulary,

[1026] Means for obtaining detailed information about visualized vocabulary,

[1027] The means of presenting that detailed information,

[1028] A means for analyzing user emotions and optimizing relevant information based on the analysis results,

[1029] A system including a device for presenting group information based on the user's status.

[1030] (Claim 2)

[1031] A means of arranging related vocabulary as nodes, centered around vocabulary selected by the user,

[1032] The system according to claim 1, comprising means for adjusting information recommendations according to the user's emotions.

[1033] (Claim 3)

[1034] The generating device has means for having a learning function to strengthen the relationships of the generated related vocabulary,

[1035] The system according to claim 1, comprising means for prioritizing information based on captured sentiment data. [Explanation of Symbols]

[1036] 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 inputting specific vocabulary, Means having a generation engine for generating multiple vocabulary related to the input vocabulary, A means of visually arranging and displaying the generated vocabulary, Means for obtaining detailed information about visualized vocabulary, A system including means for presenting the aforementioned detailed information.

2. The system according to claim 1, comprising means for arranging related vocabulary as nodes, with a vocabulary selected by the user as the central vocabulary.

3. The system according to claim 1, wherein the generation engine is equipped with means for having a learning function to enhance the relevance of the generated related vocabulary.

Images