system

Abstract

We provide the system. [Solution] Means of collecting digital data from information sources, A means of converting collected digital data into text format, A method for extracting important terms from text data using natural language processing, A means for automatically generating definitions for extracted terms, A means of storing the generated terms and definitions and providing them as a dictionary, A means of translating dictionaries into multiple languages ​​and making them available for use in multiple languages, A system that includes this.

Description

【Technical Field】 , 【0001】 The technology of the present disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 <00​​​​​​​​​​​​This invention solves the above problems by providing a system that collects digital data from information sources, converts it into text format, and processes it. Specifically, it provides means for applying natural language processing to the collected text data and extracting important terms. Then, it automatically generates definitions for the extracted terms and stores this information as a glossary. Furthermore, the generated terms and definitions are translated into multiple languages, enabling the use of the glossary across multiple languages. This allows the glossary to be customized based on user attribute information, facilitating the understanding of specialized terminology within an organization, and also enables the provision of the latest information by updating the glossary in real time. These means make it possible to streamline communication between organizations and promote the sharing and transfer of knowledge. 【0006】 "Information source" refers to the media or platform that provides digital data, and specifically includes social media, email, voice calls, meeting minutes, etc. 【0007】 "Digital data" refers to information recorded electronically, and can take the form of text, audio, images, and other media. 【0008】 "Converting to text format" refers to the process of converting non-text data, such as audio or images, into a string of characters that is easier to analyze and process. 【0009】 "Natural language processing" refers to the technologies and methods used for computers to understand and process human language, and is a technology used in data analysis and information extraction. 【0010】 "Important terminology" refers to terms that are frequently used in a particular context or domain and whose understanding is necessary for communication and the performance of tasks. 【0011】 A "glossary" refers to a reference material or database that lists terms and their definitions used in a specific field or for a particular purpose. 【0012】 "Translating into multiple languages" refers to the process of converting information written in one language into several other different languages, while maintaining the equivalence of the content and making it communicable. 【0013】 "User attribute information" refers to information about a user, and typically includes information related to their usage patterns, department, nationality, language, and other characteristics. 【0014】 "Customization" refers to adjusting and optimizing products and services to meet the needs and requirements of individual users or specific groups. 【0015】 "Real-time updates" means instantly supplementing or correcting information and data to keep it always up-to-date. [Brief explanation of the drawing] 【0016】 [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] Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined. 【Mode for Carrying Out the Invention】 【0017】 Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the attached drawings. 【0018】 First, the terms used in the following description will be described. 【0019】 In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of 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. 【0020】 In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0021】 In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes. 【0022】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0023】 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." 【0024】 [First Embodiment] 【0025】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0026】 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. 【0027】 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). 【0028】 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. 【0029】 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. 【0030】 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. 【0031】 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. 【0032】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0033】 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. 【0034】 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. 【0035】 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. 【0036】 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". 【0037】 In this embodiment of the present invention, the AI ​​glossary automatic generation system is implemented as follows. First, the server collects digital data from information sources such as social media, email, voice calls, and meeting minutes. In this process, data is acquired in real time using a dedicated API or scraping technology. The collected voice data is transcribed using speech recognition technology and converted into text data. 【0038】 Subsequently, the server uses natural language processing techniques to extract important terms from the text data. This stage involves sentence structure analysis, term frequency analysis, and contextual analysis. The extracted terms may include new technologies, abbreviations, and industry-specific expressions. 【0039】 Next, the server automatically generates appropriate definitions for the extracted terms. The generated definitions refer to the context of different information sources and are written in natural language using an AI model. This allows even users without specialized knowledge to immediately understand the meaning of the terms. 【0040】 Once a definition is generated, the server builds it into a glossary. This glossary includes registered terms and their definitions, and supports international environments through its multilingual translation function. Furthermore, based on the user's attribute information, the glossary is personalized to meet individual needs. 【0041】 Subsequently, the device provides the generated dictionary in real time in response to user requests. Users can search for terms of interest through the application interface and quickly view their definitions and usage examples. In addition, the device analyzes the user's search trends and suggests related terms to facilitate deeper learning. 【0042】 As a concrete example, suppose a new project team is formed in a multinational corporation, and a new employee joins the team. When this employee encounters technical terms such as "ROI" or "KPI" during a meeting, they can instantly search for the terms on their device and confirm their meaning and background information. This allows them to efficiently bridge knowledge gaps and contribute to the project quickly. In this way, the present invention provides a form that supports communication within an organization and promotes knowledge sharing. 【0043】 The following describes the processing flow. 【0044】 Step 1: 【0045】 The server uses APIs and scraping techniques to collect digital data from various sources, such as social media, email, voice calls, and meeting minutes. The collected data is stored in a database. 【0046】 Step 2: 【0047】 The server transcribes the collected audio data using speech recognition software and converts all the data into text format. This process makes the audio data analyzable in the same way as other text data. 【0048】 Step 3: 【0049】 The server analyzes text data using natural language processing techniques and extracts important terms. Specifically, it breaks down sentences using morphological analysis to identify noun phrases and technical terms. Furthermore, it evaluates the importance of each term based on its frequency and contextual information. 【0050】 Step 4: 【0051】 The server automatically generates appropriate definitions for the extracted key terms using an AI model. In doing so, it considers the context in which the terms are used and generates definitions in natural language. 【0052】 Step 5: 【0053】 The server stores the generated terms and their definitions in a database as a glossary, and its multilingual translation function enables use in multiple languages. This ensures consistent terminology understanding even within international organizations. 【0054】 Step 6: 【0055】 The device displays a glossary upon user request. Users can search for specific terms through the application and quickly view their definitions and usage examples. If a term needs translation, it will be displayed in the appropriate language according to the user's settings. 【0056】 Step 7: 【0057】 The server customizes the glossary individually based on user attribute information and search history, recommending highly relevant terms. This feature allows users to deepen their understanding of their field of expertise. 【0058】 Step 8: 【0059】 The server periodically performs a collection process, updating new terminology and definition changes in real time. This continuous updating ensures that the most up-to-date information is always available within the organization. 【0060】 (Example 1) 【0061】 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." 【0062】 In recent years, with the information explosion, it has become increasingly difficult for users to understand the technical terminology they need and to keep up with the latest information. In particular, there is a growing need to quickly understand and utilize information on specialized terminology and new technologies. To achieve this, it is necessary to provide reliable, real-time definitions of terms and their background information. Furthermore, it is crucial to customize information to meet diverse user needs and provide it in multiple languages. 【0063】 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. 【0064】 In this invention, the server includes means for collecting digital data from information sources, means for converting the collected digital data into text format, means for analyzing important terms from the text data using natural language processing and extracting them through term frequency analysis and context analysis, means for automatically generating definitions for the extracted terms using a generative AI model, means for storing the generated terms and definitions and providing them as an indexed dictionary for efficient searching and browsing, and means for automatically translating the dictionary into multiple languages ​​to enable multilingual use. As a result, users can intuitively deepen their understanding of specialized terminology, track the latest information in real time, and acquire knowledge adapted to diverse cultural and linguistic backgrounds. 【0065】 "Information sources" refer to any medium or platform used to acquire digital data. Specifically, this includes social media, websites, email, voice calls, and meeting minutes. 【0066】 "Digital data" refers to information that is generated and stored electronically and can be processed by a computer. It can take many forms, including text, audio, images, and video. 【0067】 "Converting to text format" refers to the process of representing audio data or other forms of digital data as string data. Transcription using speech recognition technology is one example. 【0068】 "Natural language processing" refers to the technology of processing and understanding human language using computers. Methods such as morphological analysis and contextual analysis are employed. 【0069】 A "generative AI model" refers to an artificial intelligence model that can learn from large amounts of data and generate and understand natural language. It is used in applications such as automatic text generation and translation. 【0070】 "Indexing" refers to the process of creating an index on data based on specific rules in order to efficiently search and manage that data. 【0071】 "Multilingual translation" refers to the process of converting information expressed in one language into another language. Using machine translation technology, it is possible to automatically handle multiple languages. 【0072】 "Specialized terminology" refers to unique words and expressions used in a particular field or industry. Generally, it is often difficult to understand unless you have specialized knowledge in that field. 【0073】 "Latest information" refers to the most up-to-date information available at the present time, including constantly changing data and news reports. 【0074】 The AI ​​glossary automatic generation system in this invention is implemented as follows. 【0075】 First, the server collects digital data from various sources, including social media, email, voice calls, and meeting minutes. Specifically, the server uses dedicated APIs and web scraping techniques to capture data in real time. The audio data collected during this process is then converted into text format using speech recognition software. 【0076】 Next, the server analyzes the collected text data using natural language processing techniques. This analysis includes morphological analysis and contextual analysis to extract important terms. For example, technical terms and abbreviations that appear frequently in the text are targeted. 【0077】 Subsequently, the server automatically generates definitions for the extracted terms using a generative AI model. Specifically, it utilizes a large-scale language model to generate definition sentences based on the context of the terms. At this time, the AI ​​is given prompts to combine the contexts of different information sources, such as, "List the latest AI terms in alphabetical order and create a clear definition of each term in five lines or less." 【0078】 The generated definitions are incorporated into the glossary by the server. The dictionary is indexed to enable efficient searching and browsing, and features multilingual translation capabilities to accommodate international users. Since the dictionary is available in multiple languages, users can understand the terminology in the language that suits them best. 【0079】 Finally, the terminal provides this dictionary in real time upon user request. Users can search for terms through the application interface and quickly find their definitions and usage examples. For example, an employee joining a new project in a multinational corporation can search for the meaning of the technical term "KPI" and instantly obtain background information. This system facilitates the sharing of expertise within the organization and supports users' rapid learning. 【0080】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0081】 Step 1: 【0082】 The server collects digital data from information sources. Inputs include social networking service (SNS) APIs, website URLs, and voice call recordings. Data collection is performed using API calls and web scraping, and the output is text or audio files as digital data. For example, the server might use an API to retrieve the latest posts from a social networking service and save them to a database. 【0083】 Step 2: 【0084】 The server converts collected digital data into text format. Inputs include audio files and non-text digital data. Speech recognition software converts audio files into text data and outputs it as text. Specifically, audio data is sent to a speech recognition engine, and the result is obtained as a human-readable string of characters. 【0085】 Step 3: 【0086】 The server extracts important terms from text data using natural language processing techniques. The input consists of digital data in text format. Morphological analysis and contextual analysis are performed to identify frequently occurring words and important phrases, which are then output as a list. For example, morphological analysis is used to extract nouns and verbs, and then calculations are performed to evaluate them based on the context in which they appear. 【0087】 Step 4: 【0088】 The server uses a generative AI model to automatically generate definitions for extracted terms. The input consists of extracted terms and their associated contextual data. A prompt is input to the AI ​​language model, which then outputs a detailed definition of the corresponding term. For example, the term "ROI" is given to the generative AI, and it is instructed to "describe the meaning of this term and provide examples of its actual use" to obtain a definition. 【0089】 Step 5: 【0090】 The server stores the generated terms and definitions and prepares them for provision as a dictionary. The input consists of the generated terms and their definitions. This is registered in a database and indexed for efficient searching and multilingual translation. The result is an output in the form of a user-searchable digital dictionary. Specific examples include the operation of saving terms and definitions as key-value pairs in the database. 【0091】 (Application Example 1) 【0092】 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." 【0093】 In modern society, electronic payments are becoming increasingly widespread, and their terminology is constantly evolving. In this environment, users are required to acquire and understand the latest knowledge in a timely manner. However, existing systems lack sufficient multilingual support and individual needs, resulting in time-consuming information acquisition processes. Therefore, a system is needed that provides electronic payment terminology quickly and in multiple languages, and delivers information tailored to the characteristics of each individual user. 【0094】 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. 【0095】 In this invention, the server includes means for collecting information from information sources, means for converting the collected information into a standard format, and means for selecting important vocabulary from the data using language processing techniques. This enables the rapid provision of the latest vocabulary related to electronic payments in multiple languages ​​and the provision of personalized information according to user characteristics. 【0096】 "Information sources" refer to the media or locations where the digital data to be collected exists, including social media, email, voice calls, and meeting minutes. 【0097】 "Information" refers to digital and text data collected for specific purposes. 【0098】 A "standard format" refers to a specific format established to improve data consistency and processing efficiency. 【0099】 "Vocabulary" is a concept that refers to a collection of terms and words considered important in a particular field or situation. 【0100】 "Language processing technology" refers to the techniques for analyzing, understanding, and generating natural language. 【0101】 "Explanation" refers to automatically generated text intended to clarify the meaning and background of specific vocabulary. 【0102】 "Reference materials" refers to a collection of data that allows users to search for and utilize information, i.e., a dictionary or encyclopedia. 【0103】 "Multilingualism" is a concept that refers to a system that enables the provision of information and communication in multiple different languages. 【0104】 "User" refers to anyone who uses this system to search for or learn information. 【0105】 "Rapid" refers to a situation where the required information or processing is completed in a very short period of time. 【0106】 "Characteristics" refer to the unique attributes and profile information that each individual user possesses. 【0107】 This invention is a system that enables the immediate understanding of specialized vocabulary related to electronic payments. The system mainly consists of a server and a terminal. The server collects necessary information from information sources and converts it into a standard format. The software used in this process includes Python and Flask / Django for collection and format conversion, and libraries such as NLTK and spaCy for natural language processing. Important vocabulary is identified from the collected data through language processing techniques. Explanations are automatically generated for that vocabulary using a generative AI model. The generated explanations are stored on the server as reference material and are also translated into different languages. 【0108】 The terminal quickly retrieves and presents information from the server in response to user requests. An AI application is installed on devices such as smartphones, providing an interface that allows users to easily search for terms related to electronic payments. This interface also provides personalized information tailored to the user's characteristics. For example, if a user searches for "What is PSD2?", the meaning and related information are immediately presented. Through prompts such as "What is PSD2? Please explain its impact on electronic payments in detail," users can obtain the specific information they are looking for. 【0109】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0110】 Step 1: 【0111】 The server retrieves information from its sources. It uses digital data such as social media, emails, voice calls, and meeting minutes as input. It acquires data in real time using dedicated APIs and scraping techniques, and begins processing for information gathering. The collected digital data is obtained as output. 【0112】 Step 2: 【0113】 The server converts collected digital data into a standard format. It uses digital audio and text as input. Audio data is converted to text using speech recognition technology. A Python library is used to convert this to text data, and the result is output as standard format text data. 【0114】 Step 3: 【0115】 The server extracts important vocabulary from standard-format text data. It uses formatted text data as input. Utilizing natural language processing techniques, it performs word frequency analysis and contextual analysis, and uses an AI model to select meaningful vocabulary. The output is a list of important vocabulary words. 【0116】 Step 4: 【0117】 The server automatically generates explanations for extracted vocabulary. It uses a list of important vocabulary words as input. A generative AI model is employed to generate text explaining the background and meaning of each vocabulary word in natural language. The output consists of the vocabulary word and its explanation. 【0118】 Step 5: 【0119】 The server stores the generated vocabulary and explanations and provides them as reference material. It takes a newly generated set of explanations as input. The information is stored in a database and organized for later searching. As output, a database of reference materials is formed. 【0120】 Step 6: 【0121】 The terminal accesses the server and retrieves information based on a request from the user. It uses the user's searched prompt as input. The program processes the request, searches for the definition of the relevant vocabulary, and outputs the result. 【0122】 Step 7: 【0123】 The device provides personalized information based on the user's search results. It considers user characteristics and past search history as input. It suggests relevant vocabulary and explanations to facilitate deeper learning. The output provides information optimized for the user. 【0124】 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. 【0125】 In this embodiment of the present invention, a more personalized information delivery is achieved by integrating an emotion engine into the AI ​​glossary automatic generation system. The system in this embodiment is configured as follows. 【0126】 First, the server collects data from various digital sources and converts all data into text format by applying speech recognition technology to audio data. Next, it analyzes the text data using natural language processing and extracts important terms. At this stage, contextual information of the terms is also analyzed simultaneously, and appropriate definitions for the terms are automatically generated by an AI model. 【0127】 The generated definitions are stored in a database as a glossary and applied to multiple languages ​​using multilingual translation technology. This ensures consistent terminology use for international users. Furthermore, the glossary is individually customized based on user attribute information, prioritizing the presentation of highly relevant information. 【0128】 With the addition of an emotion engine, the server analyzes the user's emotional state. The emotion engine infers the user's current emotions based on the user's voice tone and input data. Using this emotional information, the system suggests the most appropriate terminology definitions and related information to the user in real time. For example, if the system detects that the user is confused, it can respond by presenting more detailed and descriptive definitions. 【0129】 Furthermore, the server updates the glossary in real time based on this information and can flexibly respond to changes in the user's emotions. For example, if the system detects that a new employee on a project team is confused by the technical term "ROI," it will provide additional information explaining its meaning in an easy-to-understand way, as well as explanations of related terms. This accelerates the new employee's knowledge acquisition and allows them to contribute to the project more quickly. 【0130】 This invention not only deepens the understanding of technical terminology but also enhances the efficiency of communication within organizations and improves overall productivity by providing flexible support in response to changes in the user's emotions. 【0131】 The following describes the processing flow. 【0132】 Step 1: 【0133】 The server uses APIs and scraping techniques to collect digital data from various sources such as social media, email, voice calls, and meeting minutes. The collected data is automatically stored in a database. 【0134】 Step 2: 【0135】 The server converts the collected audio data into text data using speech recognition technology. All digital data is then in text format and ready for analysis. 【0136】 Step 3: 【0137】 The server uses natural language processing techniques to analyze the text data and extract important terms. At this stage, morphological analysis is performed to identify particularly frequent nouns and technical terms. 【0138】 Step 4: 【0139】 The server automatically generates definitions for the extracted terms using an AI model. It analyzes the context in which each term is used and generates clear and understandable meanings. 【0140】 Step 5: 【0141】 The server constructs the generated term definitions as a glossary and stores them in a database. Furthermore, it uses a multilingual translation function to make these definitions available in multiple languages, ensuring they can be used by international users. 【0142】 Step 6: 【0143】 The server uses an emotion engine to analyze the user's emotions. By analyzing the tone of voice and input text data, it infers the user's emotional state. Based on this information, it adjusts the system's output. 【0144】 Step 7: 【0145】 When a user searches for a term, the device considers the sentiment engine's analysis results and adjusts the level of detail in the definition as needed. For example, if it determines that the user is confused, it will provide a more detailed explanation of the term. 【0146】 Step 8: 【0147】 The server updates its glossary in real time to accommodate various emotional states, ensuring that the information remains up-to-date. This allows the server to consistently provide users with appropriate and current information. 【0148】 (Example 2) 【0149】 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". 【0150】 In today's world, with the rapid increase in information and increasing globalization, there is a need for systems that can quickly and accurately understand specialized terminology and knowledge, and effectively share information in a multilingual environment. However, conventional systems have challenges such as difficulty in providing information that fully considers the user's emotional state and attribute information, and insufficient understanding of specialized terminology. 【0151】 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. 【0152】 In this invention, the server includes means for collecting data from information sources, means for analyzing the user's emotional state and suggesting information appropriate to that state, and means for updating the collected digital data in real time to maintain the latest information and to flexibly respond to changes in the user's emotions. As a result, users can easily understand specialized terminology and related information according to their own emotional state and attributes, and can obtain internationally standardized information. 【0153】 "Information sources" refer to the starting point or location from which data or information can be obtained, and these can range from news articles and technical papers to forum posts. 【0154】 "Data" refers to information and can exist in various forms, such as text, audio, images, and numbers. 【0155】 "Text format" refers to a format that can be read and written as text, and is a state in which digital information has been converted into a form that is easy to use. 【0156】 "Natural language technology" refers to technologies that enable machines to understand and process human language, and is used for analyzing text data and extracting information. 【0157】 An "item" refers to a unit of information that is considered particularly important, such as a term or piece of content, and is the object of definition in dictionaries and other reference materials. 【0158】 "Automatically generating" refers to a process in which a program or system operates and outputs results without human intervention. 【0159】 "Aggregated information" refers to a structured collection of data that is organized in a way that makes it easy to access and use. 【0160】 "Multilingual use" refers to a state where users who speak different languages ​​can understand and use information in their respective native languages. 【0161】 "User emotional state" refers to the emotions and moods a user exhibits when entering data, and this influences the system's suggested content. 【0162】 "To propose" refers to the act of presenting options or information to the user, thereby supporting the user's actions and decision-making. 【0163】 "Responding flexibly" refers to the process of responding quickly and appropriately to changing circumstances and demands, and selecting the most appropriate course of action as needed. 【0164】 This invention describes the details necessary to implement an AI-powered glossary automatic generation system. The basic configuration of the system is realized through the processes of data collection, analysis, generation, translation, customization, and sentiment analysis. 【0165】 First, the server collects data from various sources. Platforms used for this include databases accessible via APIs and publicly available information on the internet. If the collected data is in audio format, it is typically converted to text using speech recognition software. Cloud-based services can be utilized for speech recognition technology. 【0166】 Next, the server analyzes the text information from the data and extracts important items using a natural language processing library. Python or similar open-source programming languages ​​are suitable for this task. The items obtained from the text analysis are then automatically defined using a generative AI model, such as a widely used AI model. 【0167】 After generating the definition, the server stores the generated information in a database and, if necessary, translates it using multilingual translation software. This translation process is crucial for providing information in a format easily understood by international users, and an online translation API assists in this process. 【0168】 When a user accesses the dictionary through their device, the server customizes the content based on their profile information. This ensures that information relevant to the user's area of ​​expertise and interests is presented preferentially. Furthermore, the server estimates the user's emotional state by analyzing their voice and input, and adjusts the information as needed. A general sentiment analysis API can be used for this sentiment analysis technology. 【0169】 For example, if a user enters a prompt into the system stating, "I would like a customized dictionary to be created to help me understand the technical terms used in this project, and to provide additional explanations based on the user's emotional state," the server will respond by collecting, translating, and displaying appropriate terms and their definitions. Furthermore, based on this information, the server will provide detailed information in real time about terms that the user is deemed unfamiliar with, ensuring that the user is always presented with the most up-to-date and optimized information. 【0170】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0171】 Step 1: 【0172】 The server searches for information sources from the internet and dedicated databases and collects data. In doing so, it may utilize APIs from various platforms, specifically targeting text data such as news feeds and academic papers. Input is raw data obtained from the information sources, and output is in a formatted text data format. 【0173】 Step 2: 【0174】 The server uses speech recognition technology to convert audio data, if present, into text. For example, it uses speech recognition software for audio input and outputs it as text data. The input is raw audio data, and the output is digital text data. 【0175】 Step 3: 【0176】 The server uses natural language processing libraries to analyze the collected text. Specific operations include text tokenization, part-of-speech tagging, and dependency analysis. The input is the collected text data, and the output is a dataset containing extracted important items. 【0177】 Step 4: 【0178】 The server uses a generative AI model to generate definitions for items extracted from text data. The prompt is a request to the model such as, "Please provide the definition of the technical term 'Machine Learning'." The input consists of important items and related text data, and the output is the defined text information. 【0179】 Step 5: 【0180】 The server stores the generated definitions in a database and translates them into the required languages ​​using multilingual translation software. This process is performed using a translation API, and the definitions are stored in a categorized format for each language. The input is the generated definitions, and the output is a set of translated definitions. 【0181】 Step 6: 【0182】 When a user accesses the dictionary through their device, the server displays customized content based on the user's profile information. It analyzes the user's expertise and interests and selects relevant information accordingly. The input is the user's profile information, and the output is a customized information display. 【0183】 Step 7: 【0184】 The server receives voice and text input from the user and analyzes their emotional state. It evaluates the user's current mood and emotions through an emotion analysis API and provides appropriate information based on that evaluation. Input is voice or text data from the user, and output is information based on their emotional state. 【0185】 Step 8: 【0186】 The server uses the information obtained at each processing step to suggest relevant information to the user in real time, maintaining a constantly up-to-date data set. This enables the rapid provision of appropriate and current information. The input is the overall process data, and the output is optimized information suggestions for the user. 【0187】 (Application Example 2) 【0188】 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". 【0189】 When users try to understand technical terms and information in their daily lives, their emotions can sometimes hinder that understanding. This invention aims to facilitate the understanding of terminology and enable more personalized support by providing information that takes the user's emotional state into account. 【0190】 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. 【0191】 In this invention, the server includes means for acquiring digital information from an information source, means for converting the acquired digital information into text format, and means for extracting important terms from the text information using natural language processing. This makes it possible to provide appropriate information according to the user's emotional state. 【0192】 An "information source" is the source of the data from which digital information is acquired. 【0193】 "Digital information" refers to all data in a format that can be processed by a computer. 【0194】 "Text formatting" refers to a format that represents data as textual information. 【0195】 "Natural language processing" is the technology of analyzing and interpreting human language using computers. 【0196】 "Terminology" refers to specialized or important words or expressions used in a particular field or context. 【0197】 A "definition" is an explanatory statement that clarifies the meaning and content of a term. 【0198】 A "dictionary" is a database that compiles terms and their definitions into a referenceable format. 【0199】 "Multilingualism" refers to the use or correspondence of multiple languages. 【0200】 A "user" is someone who uses a system or service. 【0201】 An "emotion engine" is a technology or system used to analyze a user's emotional state. 【0202】 "Information provision" refers to the act or means of transmitting information to users. 【0203】 This invention relates to a system that integrates an emotion engine into an AI-powered glossary automatic generation system. This system analyzes the user's emotional state and provides personalized information based on that analysis, and is applicable to consumer robot applications. The following outlines the processing overview of this system. 【0204】 The server collects data from various digital sources and uses a speech recognition system to convert the audio data into text data. Software such as "Google® Speech-to-Text" is used for this purpose. Next, the server analyzes the text data using a natural language processing (NLP) library, such as "spaCy," and extracts terms. Then, a generative AI model, such as "GPT-3®," automatically generates definitions for the extracted terms. This creates a dictionary that can be used in multiple languages. 【0205】 Furthermore, the terminal uses an emotion engine, such as "IBM Watson® Tone Analyzer," to analyze the user's emotions. Based on the emotion information inferred from the user's voice tone and input, the server can present the user with the most appropriate definitions and relevant information. For example, if the terminal detects that the user is confused about "how to use saffron," it will provide a detailed explanation. 【0206】 As a concrete example, consider a scenario where a resident has a question about how to use saffron when cooking. In this case, the robot assistant would detect the user's confusion from voice input and provide specific explanations such as, "Saffron is added at the very end to add flavor, so please use it carefully." An example of this prompt might be, "If I want to know more about how to use saffron, please briefly explain it from the first step for beginners." 【0207】 In summary, robot assistants can enrich users' lives and provide a new form of terminology understanding support that is more empathetic to their emotions. 【0208】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0209】 Step 1: 【0210】 The server collects audio and text data from information sources. Audio data is acquired via microphones and sensors. The input is a real-time audio stream, and the output is the audio data. 【0211】 Step 2: 【0212】 The server converts the collected audio data into text format using a speech recognition system. Tools such as "Google Speech-to-Text" are used for this process. The input is audio data, and the output is converted text data. In this step, data conversion is performed to recognize speech as text information. 【0213】 Step 3: 【0214】 The server performs natural language processing on the converted text data to extract important terms. Natural language processing libraries such as "spaCy" are used here. The input is text data, and the output is a list of extracted terms. The process involves identifying specific keywords and phrases through text analysis. 【0215】 Step 4: 【0216】 The server automatically generates definitions for the extracted terms using a generative AI model. An AI model such as "GPT-3" is applied in this process. The input is a list of terms, and the output is a definition sentence. In this procedure, the AI ​​model generates comprehensible text that conveys the meaning of the terms. 【0217】 Step 5: 【0218】 The generated terms and definitions are stored in a dictionary database by the server. This process creates a glossary of terms that can be referenced in the future. The input is the terms and their definitions, and the output is the stored database entries. 【0219】 Step 6: 【0220】 The server uses an emotion engine to process user input data and infer their emotional state. This role is handled by applications such as "IBM Watson Tone Analyzer." Input is either user voice or text, and output is the inferred emotional state. Prompt messages are set to something like, "If the user is feeling anxious, please provide a more detailed definition." 【0221】 Step 7: 【0222】 The device provides appropriate definitions and relevant information in real time, based on the user's emotional state. This operation is performed through the device's display and speaker. The input is the inferred emotion and definition of the term, and the output is the information presented to the user. Specifically, detailed explanations tailored to the emotional state and additional relevant information are presented. 【0223】 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. 【0224】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0225】 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. 【0226】 [Second Embodiment] 【0227】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0228】 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. 【0229】 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). 【0230】 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. 【0231】 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. 【0232】 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). 【0233】 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. 【0234】 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. 【0235】 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. 【0236】 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. 【0237】 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. 【0238】 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". 【0239】 In this embodiment of the present invention, the AI ​​glossary automatic generation system is implemented as follows. First, the server collects digital data from information sources such as social media, email, voice calls, and meeting minutes. In this process, data is acquired in real time using a dedicated API or scraping technology. The collected voice data is transcribed using speech recognition technology and converted into text data. 【0240】 Subsequently, the server uses natural language processing techniques to extract important terms from the text data. This stage involves sentence structure analysis, term frequency analysis, and contextual analysis. The extracted terms may include new technologies, abbreviations, and industry-specific expressions. 【0241】 Next, the server automatically generates appropriate definitions for the extracted terms. The generated definitions refer to the context of different information sources and are written in natural language using an AI model. This allows even users without specialized knowledge to immediately understand the meaning of the terms. 【0242】 Once a definition is generated, the server builds it into a glossary. This glossary includes registered terms and their definitions, and supports international environments through its multilingual translation function. Furthermore, based on the user's attribute information, the glossary is personalized to meet individual needs. 【0243】 Subsequently, the device provides the generated dictionary in real time in response to user requests. Users can search for terms of interest through the application interface and quickly view their definitions and usage examples. In addition, the device analyzes the user's search trends and suggests related terms to facilitate deeper learning. 【0244】 As a concrete example, suppose a new project team is formed in a multinational corporation, and a new employee joins the team. When this employee encounters technical terms such as "ROI" or "KPI" during a meeting, they can instantly search for the terms on their device and confirm their meaning and background information. This allows them to efficiently bridge knowledge gaps and contribute to the project quickly. In this way, the present invention provides a form that supports communication within an organization and promotes knowledge sharing. 【0245】 The following describes the processing flow. 【0246】 Step 1: 【0247】 The server uses APIs and scraping techniques to collect digital data from various sources, such as social media, email, voice calls, and meeting minutes. The collected data is stored in a database. 【0248】 Step 2: 【0249】 The server transcribes the collected audio data using speech recognition software and converts all the data into text format. This process makes the audio data analyzable in the same way as other text data. 【0250】 Step 3: 【0251】 The server analyzes text data using natural language processing techniques and extracts important terms. Specifically, it breaks down sentences using morphological analysis to identify noun phrases and technical terms. Furthermore, it evaluates the importance of each term based on its frequency and contextual information. 【0252】 Step 4: 【0253】 The server automatically generates appropriate definitions for the extracted key terms using an AI model. In doing so, it considers the context in which the terms are used and generates definitions in natural language. 【0254】 Step 5: 【0255】 The server stores the generated terms and their definitions in a database as a glossary, and its multilingual translation function enables use in multiple languages. This ensures consistent terminology understanding even within international organizations. 【0256】 Step 6: 【0257】 The device displays a glossary upon user request. Users can search for specific terms through the application and quickly view their definitions and usage examples. If a term needs translation, it will be displayed in the appropriate language according to the user's settings. 【0258】 Step 7: 【0259】 The server customizes the glossary individually based on user attribute information and search history, recommending highly relevant terms. This feature allows users to deepen their understanding of their field of expertise. 【0260】 Step 8: 【0261】 The server periodically performs a collection process, updating new terminology and definition changes in real time. This continuous updating ensures that the most up-to-date information is always available within the organization. 【0262】 (Example 1) 【0263】 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." 【0264】 In recent years, with the information explosion, it has become increasingly difficult for users to understand the technical terminology they need and to keep up with the latest information. In particular, there is a growing need to quickly understand and utilize information on specialized terminology and new technologies. To achieve this, it is necessary to provide reliable, real-time definitions of terms and their background information. Furthermore, it is crucial to customize information to meet diverse user needs and provide it in multiple languages. 【0265】 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. 【0266】 In this invention, the server includes means for collecting digital data from information sources, means for converting the collected digital data into text format, means for analyzing important terms from the text data using natural language processing and extracting them through term frequency analysis and context analysis, means for automatically generating definitions for the extracted terms using a generative AI model, means for storing the generated terms and definitions and providing them as an indexed dictionary for efficient searching and browsing, and means for automatically translating the dictionary into multiple languages ​​to enable multilingual use. As a result, users can intuitively deepen their understanding of specialized terminology, track the latest information in real time, and acquire knowledge adapted to diverse cultural and linguistic backgrounds. 【0267】 "Information sources" refer to any medium or platform used to acquire digital data. Specifically, this includes social media, websites, email, voice calls, and meeting minutes. 【0268】 "Digital data" refers to information that is generated and stored electronically and can be processed by a computer. It can take many forms, including text, audio, images, and video. 【0269】 "Converting to text format" refers to the process of representing audio data or other forms of digital data as string data. Transcription using speech recognition technology is one example. 【0270】 "Natural language processing" refers to the technology of processing and understanding human language using computers. Methods such as morphological analysis and contextual analysis are employed. 【0271】 A "generative AI model" refers to an artificial intelligence model that can learn from large amounts of data and generate and understand natural language. It is used in applications such as automatic text generation and translation. 【0272】 "Indexing" refers to the process of creating an index on data based on specific rules in order to efficiently search and manage that data. 【0273】 "Multilingual translation" refers to the process of converting information expressed in one language into another language. Using machine translation technology, it is possible to automatically handle multiple languages. 【0274】 "Specialized terminology" refers to unique words and expressions used in a particular field or industry. Generally, it is often difficult to understand unless you have specialized knowledge in that field. 【0275】 "Latest information" refers to the most up-to-date information available at the present time, including constantly changing data and news reports. 【0276】 The AI ​​glossary automatic generation system in this invention is implemented as follows. 【0277】 First, the server collects digital data from various sources, including social media, email, voice calls, and meeting minutes. Specifically, the server uses dedicated APIs and web scraping techniques to capture data in real time. The audio data collected during this process is then converted into text format using speech recognition software. 【0278】 Next, the server analyzes the collected text data using natural language processing techniques. This analysis includes morphological analysis and contextual analysis to extract important terms. For example, technical terms and abbreviations that appear frequently in the text are targeted. 【0279】 Subsequently, the server automatically generates definitions for the extracted terms using a generative AI model. Specifically, it utilizes a large-scale language model to generate definition sentences based on the context of the terms. At this time, the AI ​​is given prompts to combine the contexts of different information sources, such as, "List the latest AI terms in alphabetical order and create a clear definition of each term in five lines or less." 【0280】 The generated definitions are incorporated into the glossary by the server. The glossary is indexed to enable efficient search and browsing, and with a multilingual translation function, it can also accommodate international users. Since the glossary is provided in multiple languages, users can understand the terms in a language suitable for them. 【0281】 Finally, the terminal provides this glossary in real time in response to requests from users. Users can search for terms via the application interface and quickly check their definitions and usage examples. For example, an employee participating in a new project in a multinational company can search for the meaning of the technical term "KPI" and immediately obtain background information. This system promotes the sharing of specialized knowledge within the organization and enables the support of users' rapid learning. 【0282】 The flow of the specific process in Example 1 will be described using FIG. 11. 【0283】 Step 1: 【0284】 The server collects digital data from information sources. The inputs include the API of SNS, the URL of the website, the recording file of the voice call, etc. API calls and scraping are used for data collection, and text and voice files are output as digital data. For example, the server uses the API to obtain the latest posts from SNS and performs the operation of saving them in the database. 【0285】 Step 2: 【0286】 The server converts the collected digital data into text format. The inputs are voice files and non-text digital data. The voice recognition software converts the voice file into character data and outputs it as text format data. Specifically, the voice data is sent to the voice recognition engine, and the result is obtained as a string that can be read by humans. 【0287】 Step 3: 【0288】 The server extracts important terms from text data using natural language processing techniques. The input consists of digital data in text format. Morphological analysis and contextual analysis are performed to identify frequently occurring words and important phrases, which are then output as a list. For example, morphological analysis is used to extract nouns and verbs, and then calculations are performed to evaluate them based on the context in which they appear. 【0289】 Step 4: 【0290】 The server uses a generative AI model to automatically generate definitions for extracted terms. The input consists of extracted terms and their associated contextual data. A prompt is input to the AI ​​language model, which then outputs a detailed definition of the corresponding term. For example, the term "ROI" is given to the generative AI, and it is instructed to "describe the meaning of this term and provide examples of its actual use" to obtain a definition. 【0291】 Step 5: 【0292】 The server stores the generated terms and definitions and prepares them for provision as a dictionary. The input consists of the generated terms and their definitions. This is registered in a database and indexed for efficient searching and multilingual translation. The result is an output in the form of a user-searchable digital dictionary. Specific examples include the operation of saving terms and definitions as key-value pairs in the database. 【0293】 (Application Example 1) 【0294】 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." 【0295】 In modern society, electronic payments are becoming increasingly widespread, and their terminology is constantly evolving. In this environment, users are required to acquire and understand the latest knowledge in a timely manner. However, existing systems lack sufficient multilingual support and individual needs, resulting in time-consuming information acquisition processes. Therefore, a system is needed that provides electronic payment terminology quickly and in multiple languages, and delivers information tailored to the characteristics of each individual user. 【0296】 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. 【0297】 In this invention, the server includes means for collecting information from information sources, means for converting the collected information into a standard format, and means for selecting important vocabulary from the data using language processing techniques. This enables the rapid provision of the latest vocabulary related to electronic payments in multiple languages ​​and the provision of personalized information according to user characteristics. 【0298】 "Information sources" refer to the media or locations where the digital data to be collected exists, including social media, email, voice calls, and meeting minutes. 【0299】 "Information" refers to digital and text data collected for specific purposes. 【0300】 A "standard format" refers to a specific format established to improve data consistency and processing efficiency. 【0301】 "Vocabulary" is a concept that refers to a collection of terms and words considered important in a particular field or situation. 【0302】 "Language processing technology" refers to the techniques for analyzing, understanding, and generating natural language. 【0303】 "Explanation" refers to automatically generated text intended to clarify the meaning and background of specific vocabulary. 【0304】 "Reference materials" refers to a collection of data that enables users to search for and utilize information, that is, a dictionary or encyclopedia. 【0305】 "Multilingual" refers to a concept that enables information provision and communication in multiple different languages. 【0306】 "User" refers to a person who uses this system to search for and learn information. 【0307】 "Quick" indicates that the required information or processing is completed in a very short period of time. 【0308】 "Characteristic" refers to the unique attributes or profile information of individual users. 【0309】 This invention is a system that enables immediate understanding of specialized vocabulary related to electronic payment. The system mainly consists of a server and a terminal. The server collects the necessary information from the information source and converts it into a standard format. In the software used in this process, Python and Flask / Django are used for collection and format conversion, and libraries such as NLTK and spaCy are used for natural language processing. The important vocabulary is identified from the collected data through language processing technology. Regarding that vocabulary, an explanation is automatically generated using a generative AI model. The generated explanation is stored in the server as reference materials and is also translated into different languages. 【0310】 The terminal quickly retrieves and presents information from the server in response to user requests. An AI application is installed on devices such as smartphones, providing an interface that allows users to easily search for terms related to electronic payments. This interface also provides personalized information tailored to the user's characteristics. For example, if a user searches for "What is PSD2?", the meaning and related information are immediately presented. Through prompts such as "What is PSD2? Please explain its impact on electronic payments in detail," users can obtain the specific information they are looking for. 【0311】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0312】 Step 1: 【0313】 The server retrieves information from its sources. It uses digital data such as social media, emails, voice calls, and meeting minutes as input. It acquires data in real time using dedicated APIs and scraping techniques, and begins processing for information gathering. The collected digital data is obtained as output. 【0314】 Step 2: 【0315】 The server converts collected digital data into a standard format. It uses digital audio and text as input. Audio data is converted to text using speech recognition technology. A Python library is used to convert this to text data, and the result is output as standard format text data. 【0316】 Step 3: 【0317】 The server extracts important vocabulary from standard-format text data. It uses formatted text data as input. Utilizing natural language processing techniques, it performs word frequency analysis and contextual analysis, and uses an AI model to select meaningful vocabulary. The output is a list of important vocabulary words. 【0318】 Step 4: 【0319】 The server automatically generates explanations for extracted vocabulary. It uses a list of important vocabulary words as input. A generative AI model is employed to generate text explaining the background and meaning of each vocabulary word in natural language. The output consists of the vocabulary word and its explanation. 【0320】 Step 5: 【0321】 The server stores the generated vocabulary and explanations and provides them as reference material. It takes a newly generated set of explanations as input. The information is stored in a database and organized for later searching. As output, a database of reference materials is formed. 【0322】 Step 6: 【0323】 The terminal accesses the server and retrieves information based on a request from the user. It uses the user's searched prompt as input. The program processes the request, searches for the definition of the relevant vocabulary, and outputs the result. 【0324】 Step 7: 【0325】 The device provides personalized information based on the user's search results. It considers user characteristics and past search history as input. It suggests relevant vocabulary and explanations to facilitate deeper learning. The output provides information optimized for the user. 【0326】 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. 【0327】 In this embodiment of the present invention, a more personalized information delivery is achieved by integrating an emotion engine into the AI ​​glossary automatic generation system. The system in this embodiment is configured as follows. 【0328】 First, the server collects data from various digital sources and converts all data into text format by applying speech recognition technology to audio data. Next, it analyzes the text data using natural language processing and extracts important terms. At this stage, contextual information of the terms is also analyzed simultaneously, and appropriate definitions for the terms are automatically generated by an AI model. 【0329】 The generated definitions are stored in a database as a glossary and applied to multiple languages ​​using multilingual translation technology. This ensures consistent terminology use for international users. Furthermore, the glossary is individually customized based on user attribute information, prioritizing the presentation of highly relevant information. 【0330】 With the addition of an emotion engine, the server analyzes the user's emotional state. The emotion engine infers the user's current emotions based on the user's voice tone and input data. Using this emotional information, the system suggests the most appropriate terminology definitions and related information to the user in real time. For example, if the system detects that the user is confused, it can respond by presenting more detailed and descriptive definitions. 【0331】 Furthermore, the server updates the glossary in real time based on this information and can flexibly respond to changes in the user's emotions. For example, if the system detects that a new employee on a project team is confused by the technical term "ROI," it will provide additional information explaining its meaning in an easy-to-understand way, as well as explanations of related terms. This accelerates the new employee's knowledge acquisition and allows them to contribute to the project more quickly. 【0332】 This invention not only deepens the understanding of technical terminology but also enhances the efficiency of communication within organizations and improves overall productivity by providing flexible support in response to changes in the user's emotions. 【0333】 The following describes the processing flow. 【0334】 Step 1: 【0335】 The server uses APIs and scraping techniques to collect digital data from various sources such as social media, email, voice calls, and meeting minutes. The collected data is automatically stored in a database. 【0336】 Step 2: 【0337】 The server converts the collected audio data into text data using speech recognition technology. All digital data is then in text format and ready for analysis. 【0338】 Step 3: 【0339】 The server uses natural language processing techniques to analyze the text data and extract important terms. At this stage, morphological analysis is performed to identify particularly frequent nouns and technical terms. 【0340】 Step 4: 【0341】 The server automatically generates definitions for the extracted terms using an AI model. It analyzes the context in which each term is used and generates clear and understandable meanings. 【0342】 Step 5: 【0343】 The server constructs the generated term definitions as a glossary and stores them in a database. Furthermore, it uses a multilingual translation function to make these definitions available in multiple languages, ensuring they can be used by international users. 【0344】 Step 6: 【0345】 The server uses an emotion engine to analyze the user's emotions. By analyzing the tone of voice and input text data, it infers the user's emotional state. Based on this information, it adjusts the system's output. 【0346】 Step 7: 【0347】 When a user searches for a term, the device considers the sentiment engine's analysis results and adjusts the level of detail in the definition as needed. For example, if it determines that the user is confused, it will provide a more detailed explanation of the term. 【0348】 Step 8: 【0349】 The server updates its glossary in real time to accommodate various emotional states, ensuring that the information remains up-to-date. This allows the server to consistently provide users with appropriate and current information. 【0350】 (Example 2) 【0351】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0352】 In today's world, with the rapid increase in information and increasing globalization, there is a need for systems that can quickly and accurately understand specialized terminology and knowledge, and effectively share information in a multilingual environment. However, conventional systems have challenges such as difficulty in providing information that fully considers the user's emotional state and attribute information, and insufficient understanding of specialized terminology. 【0353】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0354】 In this invention, the server includes means for collecting data from information sources, means for analyzing the user's emotional state and suggesting information appropriate to that state, and means for updating the collected digital data in real time to maintain the latest information and to flexibly respond to changes in the user's emotions. As a result, users can easily understand specialized terminology and related information according to their own emotional state and attributes, and can obtain internationally standardized information. 【0355】 "Information sources" refer to the starting point or location from which data or information can be obtained, and these can range from news articles and technical papers to forum posts. 【0356】 "Data" refers to information and can exist in various forms, such as text, audio, images, and numbers. 【0357】 "Text format" refers to a format that can be read and written as text, and is a state in which digital information has been converted into a form that is easy to use. 【0358】 "Natural language technology" refers to technologies that enable machines to understand and process human language, and is used for analyzing text data and extracting information. 【0359】 An "item" refers to a unit of information that is considered particularly important, such as a term or piece of content, and is the object of definition in dictionaries and other reference materials. 【0360】 "Automatically generating" refers to a process in which a program or system operates and outputs results without human intervention. 【0361】 "Aggregated information" refers to a structured collection of data that is organized in a way that makes it easy to access and use. 【0362】 "Multilingual use" refers to a state where users who speak different languages ​​can understand and use information in their respective native languages. 【0363】 "User emotional state" refers to the emotions and moods a user exhibits when entering data, and this influences the system's suggested content. 【0364】 "To propose" refers to the act of presenting options or information to the user, thereby supporting the user's actions and decision-making. 【0365】 "Responding flexibly" refers to the process of responding quickly and appropriately to changing circumstances and demands, and selecting the most appropriate course of action as needed. 【0366】 This invention describes the details necessary to implement an AI-powered glossary automatic generation system. The basic configuration of the system is realized through the processes of data collection, analysis, generation, translation, customization, and sentiment analysis. 【0367】 First, the server collects data from various sources. Platforms used for this include databases accessible via APIs and publicly available information on the internet. If the collected data is in audio format, it is typically converted to text using speech recognition software. Cloud-based services can be utilized for speech recognition technology. 【0368】 Next, the server analyzes the text information from the data and extracts important items using a natural language processing library. Python or similar open-source programming languages ​​are suitable for this task. The items obtained from the text analysis are then automatically defined using a generative AI model, such as a widely used AI model. 【0369】 After generating the definition, the server stores the generated information in a database and, if necessary, translates it using multilingual translation software. This translation process is crucial for providing information in a format easily understood by international users, and an online translation API assists in this process. 【0370】 When a user accesses the dictionary through their device, the server customizes the content based on their profile information. This ensures that information relevant to the user's area of ​​expertise and interests is presented preferentially. Furthermore, the server estimates the user's emotional state by analyzing their voice and input, and adjusts the information as needed. A general sentiment analysis API can be used for this sentiment analysis technology. 【0371】 For example, if a user enters a prompt into the system stating, "I would like a customized dictionary to be created to help me understand the technical terms used in this project, and to provide additional explanations based on the user's emotional state," the server will respond by collecting, translating, and displaying appropriate terms and their definitions. Furthermore, based on this information, the server will provide detailed information in real time about terms that the user is deemed unfamiliar with, ensuring that the user is always presented with the most up-to-date and optimized information. 【0372】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0373】 Step 1: 【0374】 The server searches for information sources from the internet and dedicated databases and collects data. In doing so, it may utilize APIs from various platforms, specifically targeting text data such as news feeds and academic papers. Input is raw data obtained from the information sources, and output is in a formatted text data format. 【0375】 Step 2: 【0376】 The server uses speech recognition technology to convert audio data, if present, into text. For example, it uses speech recognition software for audio input and outputs it as text data. The input is raw audio data, and the output is digital text data. 【0377】 Step 3: 【0378】 The server uses natural language processing libraries to analyze the collected text. Specific operations include text tokenization, part-of-speech tagging, and dependency analysis. The input is the collected text data, and the output is a dataset containing extracted important items. 【0379】 Step 4: 【0380】 The server uses a generative AI model to generate definitions for items extracted from text data. The prompt is a request to the model such as, "Please provide the definition of the technical term 'Machine Learning'." The input consists of important items and related text data, and the output is the defined text information. 【0381】 Step 5: 【0382】 The server stores the generated definitions in a database and translates them into the required languages ​​using multilingual translation software. This process is performed using a translation API, and the definitions are stored in a categorized format for each language. The input is the generated definitions, and the output is a set of translated definitions. 【0383】 Step 6: 【0384】 When a user accesses the dictionary through their device, the server displays customized content based on the user's profile information. It analyzes the user's expertise and interests and selects relevant information accordingly. The input is the user's profile information, and the output is a customized information display. 【0385】 Step 7: 【0386】 The server receives voice and text input from the user and analyzes their emotional state. It evaluates the user's current mood and emotions through an emotion analysis API and provides appropriate information based on that evaluation. Input is voice or text data from the user, and output is information based on their emotional state. 【0387】 Step 8: 【0388】 The server uses the information obtained at each processing step to suggest relevant information to the user in real time, maintaining a constantly up-to-date data set. This enables the rapid provision of appropriate and current information. The input is the overall process data, and the output is optimized information suggestions for the user. 【0389】 (Application Example 2) 【0390】 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." 【0391】 When users try to understand technical terms and information in their daily lives, their emotions can sometimes hinder that understanding. This invention aims to facilitate the understanding of terminology and enable more personalized support by providing information that takes the user's emotional state into account. 【0392】 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. 【0393】 In this invention, the server includes means for acquiring digital information from an information source, means for converting the acquired digital information into text format, and means for extracting important terms from the text information using natural language processing. This makes it possible to provide appropriate information according to the user's emotional state. 【0394】 An "information source" is the source of the data from which digital information is acquired. 【0395】 "Digital information" refers to all data in a format that can be processed by a computer. 【0396】 "Text formatting" refers to a format that represents data as textual information. 【0397】 "Natural language processing" is the technology of analyzing and interpreting human language using computers. 【0398】 "Terminology" refers to specialized or important words or expressions used in a particular field or context. 【0399】 A "definition" is an explanatory statement that clarifies the meaning and content of a term. 【0400】 A "dictionary" is a database that compiles terms and their definitions into a referenceable format. 【0401】 "Multilingualism" refers to the use or correspondence of multiple languages. 【0402】 A "user" is someone who uses a system or service. 【0403】 An "emotion engine" is a technology or system used to analyze a user's emotional state. 【0404】 "Information provision" refers to the act or means of transmitting information to users. 【0405】 This invention relates to a system that integrates an emotion engine into an AI-powered glossary automatic generation system. This system analyzes the user's emotional state and provides personalized information based on that analysis, and is applicable to consumer robot applications. The following outlines the processing overview of this system. 【0406】 The server collects data from various digital sources and uses a speech recognition system to convert the audio data into text data. Software such as "Google Speech-to-Text" is used for this purpose. Next, the server analyzes the text data using a natural language processing (NLP) library, such as "spaCy," and extracts terms. Then, a generative AI model, such as "GPT-3," automatically generates definitions for the extracted terms. This creates a dictionary that can be used in multiple languages. 【0407】 Furthermore, the terminal uses an emotion engine, such as "IBM Watson Tone Analyzer," to analyze the user's emotions. Based on the emotion information inferred from the user's voice tone and input, the server can present the user with the most appropriate definitions and relevant information. For example, if the terminal detects that the user is confused about "how to use saffron," it will provide a detailed explanation. 【0408】 As a concrete example, consider a scenario where a resident has a question about how to use saffron when cooking. In this case, the robot assistant would detect the user's confusion from voice input and provide specific explanations such as, "Saffron is added at the very end to add flavor, so please use it carefully." An example of this prompt might be, "If I want to know more about how to use saffron, please briefly explain it from the first step for beginners." 【0409】 In summary, robot assistants can enrich users' lives and provide a new form of terminology understanding support that is more empathetic to their emotions. 【0410】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0411】 Step 1: 【0412】 The server collects audio and text data from information sources. Audio data is acquired via microphones and sensors. The input is a real-time audio stream, and the output is the audio data. 【0413】 Step 2: 【0414】 The server converts the collected audio data into text format using a speech recognition system. Tools such as "Google Speech-to-Text" are used for this process. The input is audio data, and the output is converted text data. In this step, data conversion is performed to recognize speech as text information. 【0415】 Step 3: 【0416】 The server performs natural language processing on the converted text data to extract important terms. Natural language processing libraries such as "spaCy" are used here. The input is text data, and the output is a list of extracted terms. The process involves identifying specific keywords and phrases through text analysis. 【0417】 Step 4: 【0418】 The server automatically generates definitions for the extracted terms using a generative AI model. An AI model such as "GPT-3" is applied in this process. The input is a list of terms, and the output is a definition sentence. In this procedure, the AI ​​model generates comprehensible text that conveys the meaning of the terms. 【0419】 Step 5: 【0420】 The generated terms and definitions are stored in a dictionary database by the server. This process creates a glossary of terms that can be referenced in the future. The input is the terms and their definitions, and the output is the stored database entries. 【0421】 Step 6: 【0422】 The server uses an emotion engine to process user input data and infer their emotional state. This role is handled by applications such as "IBM Watson Tone Analyzer." Input is either user voice or text, and output is the inferred emotional state. Prompt messages are set to something like, "If the user is feeling anxious, please provide a more detailed definition." 【0423】 Step 7: 【0424】 The device provides appropriate definitions and relevant information in real time, based on the user's emotional state. This operation is performed through the device's display and speaker. The input is the inferred emotion and definition of the term, and the output is the information presented to the user. Specifically, detailed explanations tailored to the emotional state and additional relevant information are presented. 【0425】 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. 【0426】 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. 【0427】 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. 【0428】 [Third Embodiment] 【0429】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0430】 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. 【0431】 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). 【0432】 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. 【0433】 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. 【0434】 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). 【0435】 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. 【0436】 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. 【0437】 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. 【0438】 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. 【0439】 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. 【0440】 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". 【0441】 In this embodiment of the present invention, the AI ​​glossary automatic generation system is implemented as follows. First, the server collects digital data from information sources such as social media, email, voice calls, and meeting minutes. In this process, data is acquired in real time using a dedicated API or scraping technology. The collected voice data is transcribed using speech recognition technology and converted into text data. 【0442】 Subsequently, the server uses natural language processing techniques to extract important terms from the text data. This stage involves sentence structure analysis, term frequency analysis, and contextual analysis. The extracted terms may include new technologies, abbreviations, and industry-specific expressions. 【0443】 Next, the server automatically generates appropriate definitions for the extracted terms. The generated definitions refer to the context of different information sources and are written in natural language using an AI model. This allows even users without specialized knowledge to immediately understand the meaning of the terms. 【0444】 Once a definition is generated, the server builds it into a glossary. This glossary includes registered terms and their definitions, and supports international environments through its multilingual translation function. Furthermore, based on the user's attribute information, the glossary is personalized to meet individual needs. 【0445】 Subsequently, the device provides the generated dictionary in real time in response to user requests. Users can search for terms of interest through the application interface and quickly view their definitions and usage examples. In addition, the device analyzes the user's search trends and suggests related terms to facilitate deeper learning. 【0446】 As a concrete example, suppose a new project team is formed in a multinational corporation, and a new employee joins the team. When this employee encounters technical terms such as "ROI" or "KPI" during a meeting, they can instantly search for the terms on their device and confirm their meaning and background information. This allows them to efficiently bridge knowledge gaps and contribute to the project quickly. In this way, the present invention provides a form that supports communication within an organization and promotes knowledge sharing. 【0447】 The following describes the processing flow. 【0448】 Step 1: 【0449】 The server uses APIs and scraping techniques to collect digital data from various sources, such as social media, email, voice calls, and meeting minutes. The collected data is stored in a database. 【0450】 Step 2: 【0451】 The server transcribes the collected audio data using speech recognition software and converts all the data into text format. This process makes the audio data analyzable in the same way as other text data. 【0452】 Step 3: 【0453】 The server analyzes text data using natural language processing techniques and extracts important terms. Specifically, it breaks down sentences using morphological analysis to identify noun phrases and technical terms. Furthermore, it evaluates the importance of each term based on its frequency and contextual information. 【0454】 Step 4: 【0455】 The server automatically generates appropriate definitions for the extracted key terms using an AI model. In doing so, it considers the context in which the terms are used and generates definitions in natural language. 【0456】 Step 5: 【0457】 The server stores the generated terms and their definitions in a database as a glossary, and its multilingual translation function enables use in multiple languages. This ensures consistent terminology understanding even within international organizations. 【0458】 Step 6: 【0459】 The device displays a glossary upon user request. Users can search for specific terms through the application and quickly view their definitions and usage examples. If a term needs translation, it will be displayed in the appropriate language according to the user's settings. 【0460】 Step 7: 【0461】 The server customizes the glossary individually based on user attribute information and search history, recommending highly relevant terms. This feature allows users to deepen their understanding of their field of expertise. 【0462】 Step 8: 【0463】 The server periodically performs a collection process, updating new terminology and definition changes in real time. This continuous updating ensures that the most up-to-date information is always available within the organization. 【0464】 (Example 1) 【0465】 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." 【0466】 In recent years, with the information explosion, it has become increasingly difficult for users to understand the technical terminology they need and to keep up with the latest information. In particular, there is a growing need to quickly understand and utilize information on specialized terminology and new technologies. To achieve this, it is necessary to provide reliable, real-time definitions of terms and their background information. Furthermore, it is crucial to customize information to meet diverse user needs and provide it in multiple languages. 【0467】 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. 【0468】 In this invention, the server includes means for collecting digital data from information sources, means for converting the collected digital data into text format, means for analyzing important terms from the text data using natural language processing and extracting them through term frequency analysis and context analysis, means for automatically generating definitions for the extracted terms using a generative AI model, means for storing the generated terms and definitions and providing them as an indexed dictionary for efficient searching and browsing, and means for automatically translating the dictionary into multiple languages ​​to enable multilingual use. As a result, users can intuitively deepen their understanding of specialized terminology, track the latest information in real time, and acquire knowledge adapted to diverse cultural and linguistic backgrounds. 【0469】 "Information sources" refer to any medium or platform used to acquire digital data. Specifically, this includes social media, websites, email, voice calls, and meeting minutes. 【0470】 "Digital data" refers to information that is generated and stored electronically and can be processed by a computer. It can take many forms, including text, audio, images, and video. 【0471】 "Converting to text format" refers to the process of representing audio data or other forms of digital data as string data. Transcription using speech recognition technology is one example. 【0472】 "Natural language processing" refers to the technology of processing and understanding human language using computers. Methods such as morphological analysis and contextual analysis are employed. 【0473】 A "generative AI model" refers to an artificial intelligence model that can learn from large amounts of data and generate and understand natural language. It is used in applications such as automatic text generation and translation. 【0474】 "Indexing" refers to the process of creating an index on data based on specific rules in order to efficiently search and manage that data. 【0475】 "Multilingual translation" refers to the process of converting information expressed in one language into another language. Using machine translation technology, it is possible to automatically handle multiple languages. 【0476】 "Specialized terminology" refers to unique words and expressions used in a particular field or industry. Generally, it is often difficult to understand unless you have specialized knowledge in that field. 【0477】 "Latest information" refers to the most up-to-date information available at the present time, including constantly changing data and news reports. 【0478】 The AI ​​glossary automatic generation system in this invention is implemented as follows. 【0479】 First, the server collects digital data from various sources, including social media, email, voice calls, and meeting minutes. Specifically, the server uses dedicated APIs and web scraping techniques to capture data in real time. The audio data collected during this process is then converted into text format using speech recognition software. 【0480】 Next, the server analyzes the collected text data using natural language processing techniques. This analysis includes morphological analysis and contextual analysis to extract important terms. For example, technical terms and abbreviations that appear frequently in the text are targeted. 【0481】 Subsequently, the server automatically generates definitions for the extracted terms using a generative AI model. Specifically, it utilizes a large-scale language model to generate definition sentences based on the context of the terms. At this time, the AI ​​is given prompts to combine the contexts of different information sources, such as, "List the latest AI terms in alphabetical order and create a clear definition of each term in five lines or less." 【0482】 The generated definitions are incorporated into the glossary by the server. The dictionary is indexed to enable efficient searching and browsing, and features multilingual translation capabilities to accommodate international users. Since the dictionary is available in multiple languages, users can understand the terminology in the language that suits them best. 【0483】 Finally, the terminal provides this dictionary in real time upon user request. Users can search for terms through the application interface and quickly find their definitions and usage examples. For example, an employee joining a new project in a multinational corporation can search for the meaning of the technical term "KPI" and instantly obtain background information. This system facilitates the sharing of expertise within the organization and supports users' rapid learning. 【0484】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0485】 Step 1: 【0486】 The server collects digital data from information sources. Inputs include social networking service (SNS) APIs, website URLs, and voice call recordings. Data collection is performed using API calls and web scraping, and the output is text or audio files as digital data. For example, the server might use an API to retrieve the latest posts from a social networking service and save them to a database. 【0487】 Step 2: 【0488】 The server converts collected digital data into text format. Inputs include audio files and non-text digital data. Speech recognition software converts audio files into text data and outputs it as text. Specifically, audio data is sent to a speech recognition engine, and the result is obtained as a human-readable string of characters. 【0489】 Step 3: 【0490】 The server extracts important terms from text data using natural language processing techniques. The input consists of digital data in text format. Morphological analysis and contextual analysis are performed to identify frequently occurring words and important phrases, which are then output as a list. For example, morphological analysis is used to extract nouns and verbs, and then calculations are performed to evaluate them based on the context in which they appear. 【0491】 Step 4: 【0492】 The server uses a generative AI model to automatically generate definitions for extracted terms. The input consists of extracted terms and their associated contextual data. A prompt is input to the AI ​​language model, which then outputs a detailed definition of the corresponding term. For example, the term "ROI" is given to the generative AI, and it is instructed to "describe the meaning of this term and provide examples of its actual use" to obtain a definition. 【0493】 Step 5: 【0494】 The server stores the generated terms and definitions and prepares them for provision as a dictionary. The input consists of the generated terms and their definitions. This is registered in a database and indexed for efficient searching and multilingual translation. The result is an output in the form of a user-searchable digital dictionary. Specific examples include the operation of saving terms and definitions as key-value pairs in the database. 【0495】 (Application Example 1) 【0496】 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." 【0497】 In modern society, electronic payments are becoming increasingly widespread, and their terminology is constantly evolving. In this environment, users are required to acquire and understand the latest knowledge in a timely manner. However, existing systems lack sufficient multilingual support and individual needs, resulting in time-consuming information acquisition processes. Therefore, a system is needed that provides electronic payment terminology quickly and in multiple languages, and delivers information tailored to the characteristics of each individual user. 【0498】 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. 【0499】 In this invention, the server includes means for collecting information from information sources, means for converting the collected information into a standard format, and means for selecting important vocabulary from the data using language processing techniques. This enables the rapid provision of the latest vocabulary related to electronic payments in multiple languages ​​and the provision of personalized information according to user characteristics. 【0500】 "Information sources" refer to the media or locations where the digital data to be collected exists, including social media, email, voice calls, and meeting minutes. 【0501】 "Information" refers to digital and text data collected for specific purposes. 【0502】 A "standard format" refers to a specific format established to improve data consistency and processing efficiency. 【0503】 "Vocabulary" is a concept that refers to a collection of terms and words considered important in a particular field or situation. 【0504】 "Language processing technology" refers to the techniques for analyzing, understanding, and generating natural language. 【0505】 "Explanation" refers to automatically generated text intended to clarify the meaning and background of specific vocabulary. 【0506】 "Reference materials" refers to a collection of data that allows users to search for and utilize information, i.e., a dictionary or encyclopedia. 【0507】 "Multilingualism" is a concept that refers to a system that enables the provision of information and communication in multiple different languages. 【0508】 "User" refers to anyone who uses this system to search for or learn information. 【0509】 "Rapid" refers to a situation where the required information or processing is completed in a very short period of time. 【0510】 "Characteristics" refer to the unique attributes and profile information that each individual user possesses. 【0511】 This invention is a system that enables the immediate understanding of specialized vocabulary related to electronic payments. The system mainly consists of a server and a terminal. The server collects necessary information from information sources and converts it into a standard format. The software used in this process includes Python and Flask / Django for collection and format conversion, and libraries such as NLTK and spaCy for natural language processing. Important vocabulary is identified from the collected data through language processing techniques. Explanations are automatically generated for that vocabulary using a generative AI model. The generated explanations are stored on the server as reference material and are also translated into different languages. 【0512】 The terminal quickly retrieves and presents information from the server in response to user requests. An AI application is installed on devices such as smartphones, providing an interface that allows users to easily search for terms related to electronic payments. This interface also provides personalized information tailored to the user's characteristics. For example, if a user searches for "What is PSD2?", the meaning and related information are immediately presented. Through prompts such as "What is PSD2? Please explain its impact on electronic payments in detail," users can obtain the specific information they are looking for. 【0513】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0514】 Step 1: 【0515】 The server retrieves information from its sources. It uses digital data such as social media, emails, voice calls, and meeting minutes as input. It acquires data in real time using dedicated APIs and scraping techniques, and begins processing for information gathering. The collected digital data is obtained as output. 【0516】 Step 2: 【0517】 The server converts collected digital data into a standard format. It uses digital audio and text as input. Audio data is converted to text using speech recognition technology. A Python library is used to convert this to text data, and the result is output as standard format text data. 【0518】 Step 3: 【0519】 The server extracts important vocabulary from standard-format text data. It uses formatted text data as input. Utilizing natural language processing techniques, it performs word frequency analysis and contextual analysis, and uses an AI model to select meaningful vocabulary. The output is a list of important vocabulary words. 【0520】 Step 4: 【0521】 The server automatically generates explanations for extracted vocabulary. It uses a list of important vocabulary words as input. A generative AI model is employed to generate text explaining the background and meaning of each vocabulary word in natural language. The output consists of the vocabulary word and its explanation. 【0522】 Step 5: 【0523】 The server stores the generated vocabulary and explanations and provides them as reference material. It takes a newly generated set of explanations as input. The information is stored in a database and organized for later searching. As output, a database of reference materials is formed. 【0524】 Step 6: 【0525】 The terminal accesses the server and retrieves information based on a request from the user. It uses the user's searched prompt as input. The program processes the request, searches for the definition of the relevant vocabulary, and outputs the result. 【0526】 Step 7: 【0527】 The device provides personalized information based on the user's search results. It considers user characteristics and past search history as input. It suggests relevant vocabulary and explanations to facilitate deeper learning. The output provides information optimized for the user. 【0528】 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. 【0529】 In this embodiment of the present invention, a more personalized information delivery is achieved by integrating an emotion engine into the AI ​​glossary automatic generation system. The system in this embodiment is configured as follows. 【0530】 First, the server collects data from various digital sources and converts all data into text format by applying speech recognition technology to audio data. Next, it analyzes the text data using natural language processing and extracts important terms. At this stage, contextual information of the terms is also analyzed simultaneously, and appropriate definitions for the terms are automatically generated by an AI model. 【0531】 The generated definitions are stored in a database as a glossary and applied to multiple languages ​​using multilingual translation technology. This ensures consistent terminology use for international users. Furthermore, the glossary is individually customized based on user attribute information, prioritizing the presentation of highly relevant information. 【0532】 With the addition of an emotion engine, the server analyzes the user's emotional state. The emotion engine infers the user's current emotions based on the user's voice tone and input data. Using this emotional information, the system suggests the most appropriate terminology definitions and related information to the user in real time. For example, if the system detects that the user is confused, it can respond by presenting more detailed and descriptive definitions. 【0533】 Furthermore, the server updates the glossary in real time based on this information and can flexibly respond to changes in the user's emotions. For example, if the system detects that a new employee on a project team is confused by the technical term "ROI," it will provide additional information explaining its meaning in an easy-to-understand way, as well as explanations of related terms. This accelerates the new employee's knowledge acquisition and allows them to contribute to the project more quickly. 【0534】 This invention not only deepens the understanding of technical terminology but also enhances the efficiency of communication within organizations and improves overall productivity by providing flexible support in response to changes in the user's emotions. 【0535】 The following describes the processing flow. 【0536】 Step 1: 【0537】 The server uses APIs and scraping techniques to collect digital data from various sources such as social media, email, voice calls, and meeting minutes. The collected data is automatically stored in a database. 【0538】 Step 2: 【0539】 The server converts the collected audio data into text data using speech recognition technology. All digital data is then in text format and ready for analysis. 【0540】 Step 3: 【0541】 The server uses natural language processing techniques to analyze the text data and extract important terms. At this stage, morphological analysis is performed to identify particularly frequent nouns and technical terms. 【0542】 Step 4: 【0543】 The server automatically generates definitions for the extracted terms using an AI model. It analyzes the context in which each term is used and generates clear and understandable meanings. 【0544】 Step 5: 【0545】 The server constructs the generated term definitions as a glossary and stores them in a database. Furthermore, it uses a multilingual translation function to make these definitions available in multiple languages, ensuring they can be used by international users. 【0546】 Step 6: 【0547】 The server uses an emotion engine to analyze the user's emotions. By analyzing the tone of voice and input text data, it infers the user's emotional state. Based on this information, it adjusts the system's output. 【0548】 Step 7: 【0549】 When a user searches for a term, the device considers the sentiment engine's analysis results and adjusts the level of detail in the definition as needed. For example, if it determines that the user is confused, it will provide a more detailed explanation of the term. 【0550】 Step 8: 【0551】 The server updates its glossary in real time to accommodate various emotional states, ensuring that the information remains up-to-date. This allows the server to consistently provide users with appropriate and current information. 【0552】 (Example 2) 【0553】 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." 【0554】 In today's world, with the rapid increase in information and increasing globalization, there is a need for systems that can quickly and accurately understand specialized terminology and knowledge, and effectively share information in a multilingual environment. However, conventional systems have challenges such as difficulty in providing information that fully considers the user's emotional state and attribute information, and insufficient understanding of specialized terminology. 【0555】 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. 【0556】 In this invention, the server includes means for collecting data from information sources, means for analyzing the user's emotional state and suggesting information appropriate to that state, and means for updating the collected digital data in real time to maintain the latest information and to flexibly respond to changes in the user's emotions. As a result, users can easily understand specialized terminology and related information according to their own emotional state and attributes, and can obtain internationally standardized information. 【0557】 "Information sources" refer to the starting point or location from which data or information can be obtained, and these can range from news articles and technical papers to forum posts. 【0558】 "Data" refers to information and can exist in various forms, such as text, audio, images, and numbers. 【0559】 "Text format" refers to a format that can be read and written as text, and is a state in which digital information has been converted into a form that is easy to use. 【0560】 "Natural language technology" refers to technologies that enable machines to understand and process human language, and is used for analyzing text data and extracting information. 【0561】 An "item" refers to a unit of information that is considered particularly important, such as a term or piece of content, and is the object of definition in dictionaries and other reference materials. 【0562】 "Automatically generating" refers to a process in which a program or system operates and outputs results without human intervention. 【0563】 "Aggregated information" refers to a structured collection of data that is organized in a way that makes it easy to access and use. 【0564】 "Multilingual use" refers to a state where users who speak different languages ​​can understand and use information in their respective native languages. 【0565】 "User emotional state" refers to the emotions and moods a user exhibits when entering data, and this influences the system's suggested content. 【0566】 "To propose" refers to the act of presenting options or information to the user, thereby supporting the user's actions and decision-making. 【0567】 "Responding flexibly" refers to the process of responding quickly and appropriately to changing circumstances and demands, and selecting the most appropriate course of action as needed. 【0568】 This invention describes the details necessary to implement an AI-powered glossary automatic generation system. The basic configuration of the system is realized through the processes of data collection, analysis, generation, translation, customization, and sentiment analysis. 【0569】 First, the server collects data from various sources. Platforms used for this include databases accessible via APIs and publicly available information on the internet. If the collected data is in audio format, it is typically converted to text using speech recognition software. Cloud-based services can be utilized for speech recognition technology. 【0570】 Next, the server analyzes the text information from the data and extracts important items using a natural language processing library. Python or similar open-source programming languages ​​are suitable for this task. The items obtained from the text analysis are then automatically defined using a generative AI model, such as a widely used AI model. 【0571】 After generating the definition, the server stores the generated information in a database and, if necessary, translates it using multilingual translation software. This translation process is crucial for providing information in a format easily understood by international users, and an online translation API assists in this process. 【0572】 When a user accesses the dictionary through their device, the server customizes the content based on their profile information. This ensures that information relevant to the user's area of ​​expertise and interests is presented preferentially. Furthermore, the server estimates the user's emotional state by analyzing their voice and input, and adjusts the information as needed. A general sentiment analysis API can be used for this sentiment analysis technology. 【0573】 For example, if a user enters a prompt into the system stating, "I would like a customized dictionary to be created to help me understand the technical terms used in this project, and to provide additional explanations based on the user's emotional state," the server will respond by collecting, translating, and displaying appropriate terms and their definitions. Furthermore, based on this information, the server will provide detailed information in real time about terms that the user is deemed unfamiliar with, ensuring that the user is always presented with the most up-to-date and optimized information. 【0574】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0575】 Step 1: 【0576】 The server searches for information sources from the internet and dedicated databases and collects data. In doing so, it may utilize APIs from various platforms, specifically targeting text data such as news feeds and academic papers. Input is raw data obtained from the information sources, and output is in a formatted text data format. 【0577】 Step 2: 【0578】 The server uses speech recognition technology to convert audio data, if present, into text. For example, it uses speech recognition software for audio input and outputs it as text data. The input is raw audio data, and the output is digital text data. 【0579】 Step 3: 【0580】 The server uses natural language processing libraries to analyze the collected text. Specific operations include text tokenization, part-of-speech tagging, and dependency analysis. The input is the collected text data, and the output is a dataset containing extracted important items. 【0581】 Step 4: 【0582】 The server uses a generative AI model to generate definitions for items extracted from text data. The prompt is a request to the model such as, "Please provide the definition of the technical term 'Machine Learning'." The input consists of important items and related text data, and the output is the defined text information. 【0583】 Step 5: 【0584】 The server stores the generated definitions in a database and translates them into the required languages ​​using multilingual translation software. This process is performed using a translation API, and the definitions are stored in a categorized format for each language. The input is the generated definitions, and the output is a set of translated definitions. 【0585】 Step 6: 【0586】 When a user accesses the dictionary through their device, the server displays customized content based on the user's profile information. It analyzes the user's expertise and interests and selects relevant information accordingly. The input is the user's profile information, and the output is a customized information display. 【0587】 Step 7: 【0588】 The server receives voice and text input from the user and analyzes their emotional state. It evaluates the user's current mood and emotions through an emotion analysis API and provides appropriate information based on that evaluation. Input is voice or text data from the user, and output is information based on their emotional state. 【0589】 Step 8: 【0590】 The server uses the information obtained at each processing step to suggest relevant information to the user in real time, maintaining a constantly up-to-date data set. This enables the rapid provision of appropriate and current information. The input is the overall process data, and the output is optimized information suggestions for the user. 【0591】 (Application Example 2) 【0592】 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." 【0593】 When users try to understand technical terms and information in their daily lives, their emotions can sometimes hinder that understanding. This invention aims to facilitate the understanding of terminology and enable more personalized support by providing information that takes the user's emotional state into account. 【0594】 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. 【0595】 In this invention, the server includes means for acquiring digital information from an information source, means for converting the acquired digital information into text format, and means for extracting important terms from the text information using natural language processing. This makes it possible to provide appropriate information according to the user's emotional state. 【0596】 An "information source" is the source of the data from which digital information is acquired. 【0597】 "Digital information" refers to all data in a format that can be processed by a computer. 【0598】 "Text formatting" refers to a format that represents data as textual information. 【0599】 "Natural language processing" is the technology of analyzing and interpreting human language using computers. 【0600】 "Terminology" refers to specialized or important words or expressions used in a particular field or context. 【0601】 A "definition" is an explanatory statement that clarifies the meaning and content of a term. 【0602】 A "dictionary" is a database that compiles terms and their definitions into a referenceable format. 【0603】 "Multilingualism" refers to the use or correspondence of multiple languages. 【0604】 A "user" is someone who uses a system or service. 【0605】 An "emotion engine" is a technology or system used to analyze a user's emotional state. 【0606】 "Information provision" refers to the act or means of transmitting information to users. 【0607】 This invention relates to a system that integrates an emotion engine into an AI-powered glossary automatic generation system. This system analyzes the user's emotional state and provides personalized information based on that analysis, and is applicable to consumer robot applications. The following outlines the processing overview of this system. 【0608】 The server collects data from various digital sources and uses a speech recognition system to convert the audio data into text data. Software such as "Google Speech-to-Text" is used for this purpose. Next, the server analyzes the text data using a natural language processing (NLP) library, such as "spaCy," and extracts terms. Then, a generative AI model, such as "GPT-3," automatically generates definitions for the extracted terms. This creates a dictionary that can be used in multiple languages. 【0609】 Furthermore, the terminal uses an emotion engine, such as "IBM Watson Tone Analyzer," to analyze the user's emotions. Based on the emotion information inferred from the user's voice tone and input, the server can present the user with the most appropriate definitions and relevant information. For example, if the terminal detects that the user is confused about "how to use saffron," it will provide a detailed explanation. 【0610】 As a concrete example, consider a scenario where a resident has a question about how to use saffron when cooking. In this case, the robot assistant would detect the user's confusion from voice input and provide specific explanations such as, "Saffron is added at the very end to add flavor, so please use it carefully." An example of this prompt might be, "If I want to know more about how to use saffron, please briefly explain it from the first step for beginners." 【0611】 In summary, robot assistants can enrich users' lives and provide a new form of terminology understanding support that is more empathetic to their emotions. 【0612】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0613】 Step 1: 【0614】 The server collects audio and text data from information sources. Audio data is acquired via microphones and sensors. The input is a real-time audio stream, and the output is the audio data. 【0615】 Step 2: 【0616】 The server converts the collected audio data into text format using a speech recognition system. Tools such as "Google Speech-to-Text" are used for this process. The input is audio data, and the output is converted text data. In this step, data conversion is performed to recognize speech as text information. 【0617】 Step 3: 【0618】 The server performs natural language processing on the converted text data to extract important terms. Natural language processing libraries such as "spaCy" are used here. The input is text data, and the output is a list of extracted terms. The process involves identifying specific keywords and phrases through text analysis. 【0619】 Step 4: 【0620】 The server automatically generates definitions for the extracted terms using a generative AI model. An AI model such as "GPT-3" is applied in this process. The input is a list of terms, and the output is a definition sentence. In this procedure, the AI ​​model generates comprehensible text that conveys the meaning of the terms. 【0621】 Step 5: 【0622】 The generated terms and definitions are stored in a dictionary database by the server. This process creates a glossary of terms that can be referenced in the future. The input is the terms and their definitions, and the output is the stored database entries. 【0623】 Step 6: 【0624】 The server uses an emotion engine to process user input data and infer their emotional state. This role is handled by applications such as "IBM Watson Tone Analyzer." Input is either user voice or text, and output is the inferred emotional state. Prompt messages are set to something like, "If the user is feeling anxious, please provide a more detailed definition." 【0625】 Step 7: 【0626】 The device provides appropriate definitions and relevant information in real time, based on the user's emotional state. This operation is performed through the device's display and speaker. The input is the inferred emotion and definition of the term, and the output is the information presented to the user. Specifically, detailed explanations tailored to the emotional state and additional relevant information are presented. 【0627】 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. 【0628】 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. 【0629】 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. 【0630】 [Fourth Embodiment] 【0631】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0632】 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. 【0633】 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). 【0634】 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. 【0635】 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. 【0636】 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). 【0637】 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. 【0638】 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. 【0639】 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. 【0640】 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. 【0641】 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. 【0642】 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. 【0643】 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". 【0644】 In this embodiment of the present invention, the AI ​​glossary automatic generation system is implemented as follows. First, the server collects digital data from information sources such as social media, email, voice calls, and meeting minutes. In this process, data is acquired in real time using a dedicated API or scraping technology. The collected voice data is transcribed using speech recognition technology and converted into text data. 【0645】 Subsequently, the server uses natural language processing techniques to extract important terms from the text data. This stage involves sentence structure analysis, term frequency analysis, and contextual analysis. The extracted terms may include new technologies, abbreviations, and industry-specific expressions. 【0646】 Next, the server automatically generates appropriate definitions for the extracted terms. The generated definitions refer to the context of different information sources and are written in natural language using an AI model. This allows even users without specialized knowledge to immediately understand the meaning of the terms. 【0647】 Once a definition is generated, the server builds it into a glossary. This glossary includes registered terms and their definitions, and supports international environments through its multilingual translation function. Furthermore, based on the user's attribute information, the glossary is personalized to meet individual needs. 【0648】 Subsequently, the device provides the generated dictionary in real time in response to user requests. Users can search for terms of interest through the application interface and quickly view their definitions and usage examples. In addition, the device analyzes the user's search trends and suggests related terms to facilitate deeper learning. 【0649】 As a concrete example, suppose a new project team is formed in a multinational corporation, and a new employee joins the team. When this employee encounters technical terms such as "ROI" or "KPI" during a meeting, they can instantly search for the terms on their device and confirm their meaning and background information. This allows them to efficiently bridge knowledge gaps and contribute to the project quickly. In this way, the present invention provides a form that supports communication within an organization and promotes knowledge sharing. 【0650】 The following describes the processing flow. 【0651】 Step 1: 【0652】 The server uses APIs and scraping techniques to collect digital data from various sources, such as social media, email, voice calls, and meeting minutes. The collected data is stored in a database. 【0653】 Step 2: 【0654】 The server transcribes the collected audio data using speech recognition software and converts all the data into text format. This process makes the audio data analyzable in the same way as other text data. 【0655】 Step 3: 【0656】 The server analyzes text data using natural language processing techniques and extracts important terms. Specifically, it breaks down sentences using morphological analysis to identify noun phrases and technical terms. Furthermore, it evaluates the importance of each term based on its frequency and contextual information. 【0657】 Step 4: 【0658】 The server automatically generates appropriate definitions for the extracted key terms using an AI model. In doing so, it considers the context in which the terms are used and generates definitions in natural language. 【0659】 Step 5: 【0660】 The server stores the generated terms and their definitions in a database as a glossary, and its multilingual translation function enables use in multiple languages. This ensures consistent terminology understanding even within international organizations. 【0661】 Step 6: 【0662】 The device displays a glossary upon user request. Users can search for specific terms through the application and quickly view their definitions and usage examples. If a term needs translation, it will be displayed in the appropriate language according to the user's settings. 【0663】 Step 7: 【0664】 The server customizes the glossary individually based on user attribute information and search history, recommending highly relevant terms. This feature allows users to deepen their understanding of their field of expertise. 【0665】 Step 8: 【0666】 The server periodically performs a collection process, updating new terminology and definition changes in real time. This continuous updating ensures that the most up-to-date information is always available within the organization. 【0667】 (Example 1) 【0668】 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". 【0669】 In recent years, with the information explosion, it has become increasingly difficult for users to understand the technical terminology they need and to keep up with the latest information. In particular, there is a growing need to quickly understand and utilize information on specialized terminology and new technologies. To achieve this, it is necessary to provide reliable, real-time definitions of terms and their background information. Furthermore, it is crucial to customize information to meet diverse user needs and provide it in multiple languages. 【0670】 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. 【0671】 In this invention, the server includes means for collecting digital data from information sources, means for converting the collected digital data into text format, means for analyzing important terms from the text data using natural language processing and extracting them through term frequency analysis and context analysis, means for automatically generating definitions for the extracted terms using a generative AI model, means for storing the generated terms and definitions and providing them as an indexed dictionary for efficient searching and browsing, and means for automatically translating the dictionary into multiple languages ​​to enable multilingual use. As a result, users can intuitively deepen their understanding of specialized terminology, track the latest information in real time, and acquire knowledge adapted to diverse cultural and linguistic backgrounds. 【0672】 "Information sources" refer to any medium or platform used to acquire digital data. Specifically, this includes social media, websites, email, voice calls, and meeting minutes. 【0673】 "Digital data" refers to information that is generated and stored electronically and can be processed by a computer. It can take many forms, including text, audio, images, and video. 【0674】 "Converting to text format" refers to the process of representing audio data or other forms of digital data as string data. Transcription using speech recognition technology is one example. 【0675】 "Natural language processing" refers to the technology of processing and understanding human language using computers. Methods such as morphological analysis and contextual analysis are employed. 【0676】 A "generative AI model" refers to an artificial intelligence model that can learn from large amounts of data and generate and understand natural language. It is used in applications such as automatic text generation and translation. 【0677】 "Indexing" refers to the process of creating an index on data based on specific rules in order to efficiently search and manage that data. 【0678】 "Multilingual translation" refers to the process of converting information expressed in one language into another language. Using machine translation technology, it is possible to automatically handle multiple languages. 【0679】 "Specialized terminology" refers to unique words and expressions used in a particular field or industry. Generally, it is often difficult to understand unless you have specialized knowledge in that field. 【0680】 "Latest information" refers to the most up-to-date information available at the present time, including constantly changing data and news reports. 【0681】 The AI ​​glossary automatic generation system in this invention is implemented as follows. 【0682】 First, the server collects digital data from various sources, including social media, email, voice calls, and meeting minutes. Specifically, the server uses dedicated APIs and web scraping techniques to capture data in real time. The audio data collected during this process is then converted into text format using speech recognition software. 【0683】 Next, the server analyzes the collected text data using natural language processing techniques. This analysis includes morphological analysis and contextual analysis to extract important terms. For example, technical terms and abbreviations that appear frequently in the text are targeted. 【0684】 Subsequently, the server automatically generates definitions for the extracted terms using a generative AI model. Specifically, it utilizes a large-scale language model to generate definition sentences based on the context of the terms. At this time, the AI ​​is given prompts to combine the contexts of different information sources, such as, "List the latest AI terms in alphabetical order and create a clear definition of each term in five lines or less." 【0685】 The generated definitions are incorporated into the glossary by the server. The dictionary is indexed to enable efficient searching and browsing, and features multilingual translation capabilities to accommodate international users. Since the dictionary is available in multiple languages, users can understand the terminology in the language that suits them best. 【0686】 Finally, the terminal provides this dictionary in real time upon user request. Users can search for terms through the application interface and quickly find their definitions and usage examples. For example, an employee joining a new project in a multinational corporation can search for the meaning of the technical term "KPI" and instantly obtain background information. This system facilitates the sharing of expertise within the organization and supports users' rapid learning. 【0687】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0688】 Step 1: 【0689】 The server collects digital data from information sources. Inputs include social networking service (SNS) APIs, website URLs, and voice call recordings. Data collection is performed using API calls and web scraping, and the output is text or audio files as digital data. For example, the server might use an API to retrieve the latest posts from a social networking service and save them to a database. 【0690】 Step 2: 【0691】 The server converts collected digital data into text format. Inputs include audio files and non-text digital data. Speech recognition software converts audio files into text data and outputs it as text. Specifically, audio data is sent to a speech recognition engine, and the result is obtained as a human-readable string of characters. 【0692】 Step 3: 【0693】 The server extracts important terms from text data using natural language processing techniques. The input consists of digital data in text format. Morphological analysis and contextual analysis are performed to identify frequently occurring words and important phrases, which are then output as a list. For example, morphological analysis is used to extract nouns and verbs, and then calculations are performed to evaluate them based on the context in which they appear. 【0694】 Step 4: 【0695】 The server uses a generative AI model to automatically generate definitions for extracted terms. The input consists of extracted terms and their associated contextual data. A prompt is input to the AI ​​language model, which then outputs a detailed definition of the corresponding term. For example, the term "ROI" is given to the generative AI, and it is instructed to "describe the meaning of this term and provide examples of its actual use" to obtain a definition. 【0696】 Step 5: 【0697】 The server stores the generated terms and definitions and prepares them for provision as a dictionary. The input consists of the generated terms and their definitions. This is registered in a database and indexed for efficient searching and multilingual translation. The result is an output in the form of a user-searchable digital dictionary. Specific examples include the operation of saving terms and definitions as key-value pairs in the database. 【0698】 (Application Example 1) 【0699】 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". 【0700】 In modern society, electronic payments are becoming increasingly widespread, and their terminology is constantly evolving. In this environment, users are required to acquire and understand the latest knowledge in a timely manner. However, existing systems lack sufficient multilingual support and individual needs, resulting in time-consuming information acquisition processes. Therefore, a system is needed that provides electronic payment terminology quickly and in multiple languages, and delivers information tailored to the characteristics of each individual user. 【0701】 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. 【0702】 In this invention, the server includes means for collecting information from information sources, means for converting the collected information into a standard format, and means for selecting important vocabulary from the data using language processing techniques. This enables the rapid provision of the latest vocabulary related to electronic payments in multiple languages ​​and the provision of personalized information according to user characteristics. 【0703】 "Information sources" refer to the media or locations where the digital data to be collected exists, including social media, email, voice calls, and meeting minutes. 【0704】 "Information" refers to digital and text data collected for specific purposes. 【0705】 A "standard format" refers to a specific format established to improve data consistency and processing efficiency. 【0706】 "Vocabulary" is a concept that refers to a collection of terms and words considered important in a particular field or situation. 【0707】 "Language processing technology" refers to the techniques for analyzing, understanding, and generating natural language. 【0708】 "Explanation" refers to automatically generated text intended to clarify the meaning and background of specific vocabulary. 【0709】 "Reference materials" refers to a collection of data that allows users to search for and utilize information, i.e., a dictionary or encyclopedia. 【0710】 "Multilingualism" is a concept that refers to a system that enables the provision of information and communication in multiple different languages. 【0711】 "User" refers to anyone who uses this system to search for or learn information. 【0712】 "Rapid" refers to a situation where the required information or processing is completed in a very short period of time. 【0713】 "Characteristics" refer to the unique attributes and profile information that each individual user possesses. 【0714】 This invention is a system that enables the immediate understanding of specialized vocabulary related to electronic payments. The system mainly consists of a server and a terminal. The server collects necessary information from information sources and converts it into a standard format. The software used in this process includes Python and Flask / Django for collection and format conversion, and libraries such as NLTK and spaCy for natural language processing. Important vocabulary is identified from the collected data through language processing techniques. Explanations are automatically generated for that vocabulary using a generative AI model. The generated explanations are stored on the server as reference material and are also translated into different languages. 【0715】 The terminal quickly retrieves and presents information from the server in response to user requests. An AI application is installed on devices such as smartphones, providing an interface that allows users to easily search for terms related to electronic payments. This interface also provides personalized information tailored to the user's characteristics. For example, if a user searches for "What is PSD2?", the meaning and related information are immediately presented. Through prompts such as "What is PSD2? Please explain its impact on electronic payments in detail," users can obtain the specific information they are looking for. 【0716】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0717】 Step 1: 【0718】 The server retrieves information from its sources. It uses digital data such as social media, emails, voice calls, and meeting minutes as input. It acquires data in real time using dedicated APIs and scraping techniques, and begins processing for information gathering. The collected digital data is obtained as output. 【0719】 Step 2: 【0720】 The server converts collected digital data into a standard format. It uses digital audio and text as input. Audio data is converted to text using speech recognition technology. A Python library is used to convert this to text data, and the result is output as standard format text data. 【0721】 Step 3: 【0722】 The server extracts important vocabulary from standard-format text data. It uses formatted text data as input. Utilizing natural language processing techniques, it performs word frequency analysis and contextual analysis, and uses an AI model to select meaningful vocabulary. The output is a list of important vocabulary words. 【0723】 Step 4: 【0724】 The server automatically generates explanations for extracted vocabulary. It uses a list of important vocabulary words as input. A generative AI model is employed to generate text explaining the background and meaning of each vocabulary word in natural language. The output consists of the vocabulary word and its explanation. 【0725】 Step 5: 【0726】 The server stores the generated vocabulary and explanations and provides them as reference material. It takes a newly generated set of explanations as input. The information is stored in a database and organized for later searching. As output, a database of reference materials is formed. 【0727】 Step 6: 【0728】 The terminal accesses the server and retrieves information based on a request from the user. It uses the user's searched prompt as input. The program processes the request, searches for the definition of the relevant vocabulary, and outputs the result. 【0729】 Step 7: 【0730】 The device provides personalized information based on the user's search results. It considers user characteristics and past search history as input. It suggests relevant vocabulary and explanations to facilitate deeper learning. The output provides information optimized for the user. 【0731】 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. 【0732】 In this embodiment of the present invention, a more personalized information delivery is achieved by integrating an emotion engine into the AI ​​glossary automatic generation system. The system in this embodiment is configured as follows. 【0733】 First, the server collects data from various digital sources and converts all data into text format by applying speech recognition technology to audio data. Next, it analyzes the text data using natural language processing and extracts important terms. At this stage, contextual information of the terms is also analyzed simultaneously, and appropriate definitions for the terms are automatically generated by an AI model. 【0734】 The generated definitions are stored in a database as a glossary and applied to multiple languages ​​using multilingual translation technology. This ensures consistent terminology use for international users. Furthermore, the glossary is individually customized based on user attribute information, prioritizing the presentation of highly relevant information. 【0735】 With the addition of an emotion engine, the server analyzes the user's emotional state. The emotion engine infers the user's current emotions based on the user's voice tone and input data. Using this emotional information, the system suggests the most appropriate terminology definitions and related information to the user in real time. For example, if the system detects that the user is confused, it can respond by presenting more detailed and descriptive definitions. 【0736】 Furthermore, the server updates the glossary in real time based on this information and can flexibly respond to changes in the user's emotions. For example, if the system detects that a new employee on a project team is confused by the technical term "ROI," it will provide additional information explaining its meaning in an easy-to-understand way, as well as explanations of related terms. This accelerates the new employee's knowledge acquisition and allows them to contribute to the project more quickly. 【0737】 This invention not only deepens the understanding of technical terminology but also enhances the efficiency of communication within organizations and improves overall productivity by providing flexible support in response to changes in the user's emotions. 【0738】 The following describes the processing flow. 【0739】 Step 1: 【0740】 The server uses APIs and scraping techniques to collect digital data from various sources such as social media, email, voice calls, and meeting minutes. The collected data is automatically stored in a database. 【0741】 Step 2: 【0742】 The server converts the collected audio data into text data using speech recognition technology. All digital data is then in text format and ready for analysis. 【0743】 Step 3: 【0744】 The server uses natural language processing techniques to analyze the text data and extract important terms. At this stage, morphological analysis is performed to identify particularly frequent nouns and technical terms. 【0745】 Step 4: 【0746】 The server automatically generates definitions for the extracted terms using an AI model. It analyzes the context in which each term is used and generates clear and understandable meanings. 【0747】 Step 5: 【0748】 The server constructs the generated term definitions as a glossary and stores them in a database. Furthermore, it uses a multilingual translation function to make these definitions available in multiple languages, ensuring they can be used by international users. 【0749】 Step 6: 【0750】 The server uses an emotion engine to analyze the user's emotions. By analyzing the tone of voice and input text data, it infers the user's emotional state. Based on this information, it adjusts the system's output. 【0751】 Step 7: 【0752】 When a user searches for a term, the device considers the sentiment engine's analysis results and adjusts the level of detail in the definition as needed. For example, if it determines that the user is confused, it will provide a more detailed explanation of the term. 【0753】 Step 8: 【0754】 The server updates its glossary in real time to accommodate various emotional states, ensuring that the information remains up-to-date. This allows the server to consistently provide users with appropriate and current information. 【0755】 (Example 2) 【0756】 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". 【0757】 In today's world, with the rapid increase in information and increasing globalization, there is a need for systems that can quickly and accurately understand specialized terminology and knowledge, and effectively share information in a multilingual environment. However, conventional systems have challenges such as difficulty in providing information that fully considers the user's emotional state and attribute information, and insufficient understanding of specialized terminology. 【0758】 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. 【0759】 In this invention, the server includes means for collecting data from information sources, means for analyzing the user's emotional state and suggesting information appropriate to that state, and means for updating the collected digital data in real time to maintain the latest information and to flexibly respond to changes in the user's emotions. As a result, users can easily understand specialized terminology and related information according to their own emotional state and attributes, and can obtain internationally standardized information. 【0760】 "Information sources" refer to the starting point or location from which data or information can be obtained, and these can range from news articles and technical papers to forum posts. 【0761】 "Data" refers to information and can exist in various forms, such as text, audio, images, and numbers. 【0762】 "Text format" refers to a format that can be read and written as text, and is a state in which digital information has been converted into a form that is easy to use. 【0763】 "Natural language technology" refers to technologies that enable machines to understand and process human language, and is used for analyzing text data and extracting information. 【0764】 An "item" refers to a unit of information that is considered particularly important, such as a term or piece of content, and is the object of definition in dictionaries and other reference materials. 【0765】 "Automatically generating" refers to a process in which a program or system operates and outputs results without human intervention. 【0766】 "Aggregated information" refers to a structured collection of data that is organized in a way that makes it easy to access and use. 【0767】 "Multilingual use" refers to a state where users who speak different languages ​​can understand and use information in their respective native languages. 【0768】 "User emotional state" refers to the emotions and moods a user exhibits when entering data, and this influences the system's suggested content. 【0769】 "To propose" refers to the act of presenting options or information to the user, thereby supporting the user's actions and decision-making. 【0770】 "Responding flexibly" refers to the process of responding quickly and appropriately to changing circumstances and demands, and selecting the most appropriate course of action as needed. 【0771】 This invention describes the details necessary to implement an AI-powered glossary automatic generation system. The basic configuration of the system is realized through the processes of data collection, analysis, generation, translation, customization, and sentiment analysis. 【0772】 First, the server collects data from various sources. Platforms used for this include databases accessible via APIs and publicly available information on the internet. If the collected data is in audio format, it is typically converted to text using speech recognition software. Cloud-based services can be utilized for speech recognition technology. 【0773】 Next, the server analyzes the text information from the data and extracts important items using a natural language processing library. Python or similar open-source programming languages ​​are suitable for this task. The items obtained from the text analysis are then automatically defined using a generative AI model, such as a widely used AI model. 【0774】 After generating the definition, the server stores the generated information in a database and, if necessary, translates it using multilingual translation software. This translation process is crucial for providing information in a format easily understood by international users, and an online translation API assists in this process. 【0775】 When a user accesses the dictionary through their device, the server customizes the content based on their profile information. This ensures that information relevant to the user's area of ​​expertise and interests is presented preferentially. Furthermore, the server estimates the user's emotional state by analyzing their voice and input, and adjusts the information as needed. A general sentiment analysis API can be used for this sentiment analysis technology. 【0776】 For example, if a user enters a prompt into the system stating, "I would like a customized dictionary to be created to help me understand the technical terms used in this project, and to provide additional explanations based on the user's emotional state," the server will respond by collecting, translating, and displaying appropriate terms and their definitions. Furthermore, based on this information, the server will provide detailed information in real time about terms that the user is deemed unfamiliar with, ensuring that the user is always presented with the most up-to-date and optimized information. 【0777】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0778】 Step 1: 【0779】 The server searches for information sources from the internet and dedicated databases and collects data. In doing so, it may utilize APIs from various platforms, specifically targeting text data such as news feeds and academic papers. Input is raw data obtained from the information sources, and output is in a formatted text data format. 【0780】 Step 2: 【0781】 The server uses speech recognition technology to convert audio data, if present, into text. For example, it uses speech recognition software for audio input and outputs it as text data. The input is raw audio data, and the output is digital text data. 【0782】 Step 3: 【0783】 The server uses natural language processing libraries to analyze the collected text. Specific operations include text tokenization, part-of-speech tagging, and dependency analysis. The input is the collected text data, and the output is a dataset containing extracted important items. 【0784】 Step 4: 【0785】 The server uses a generative AI model to generate definitions for items extracted from text data. The prompt is a request to the model such as, "Please provide the definition of the technical term 'Machine Learning'." The input consists of important items and related text data, and the output is the defined text information. 【0786】 Step 5: 【0787】 The server stores the generated definitions in a database and translates them into the required languages ​​using multilingual translation software. This process is performed using a translation API, and the definitions are stored in a categorized format for each language. The input is the generated definitions, and the output is a set of translated definitions. 【0788】 Step 6: 【0789】 When a user accesses the dictionary through their device, the server displays customized content based on the user's profile information. It analyzes the user's expertise and interests and selects relevant information accordingly. The input is the user's profile information, and the output is a customized information display. 【0790】 Step 7: 【0791】 The server receives voice and text input from the user and analyzes their emotional state. It evaluates the user's current mood and emotions through an emotion analysis API and provides appropriate information based on that evaluation. Input is voice or text data from the user, and output is information based on their emotional state. 【0792】 Step 8: 【0793】 The server uses the information obtained at each processing step to suggest relevant information to the user in real time, maintaining a constantly up-to-date data set. This enables the rapid provision of appropriate and current information. The input is the overall process data, and the output is optimized information suggestions for the user. 【0794】 (Application Example 2) 【0795】 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". 【0796】 When users try to understand technical terms and information in their daily lives, their emotions can sometimes hinder that understanding. This invention aims to facilitate the understanding of terminology and enable more personalized support by providing information that takes the user's emotional state into account. 【0797】 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. 【0798】 In this invention, the server includes means for acquiring digital information from an information source, means for converting the acquired digital information into text format, and means for extracting important terms from the text information using natural language processing. This makes it possible to provide appropriate information according to the user's emotional state. 【0799】 An "information source" is the source of the data from which digital information is acquired. 【0800】 "Digital information" refers to all data in a format that can be processed by a computer. 【0801】 "Text formatting" refers to a format that represents data as textual information. 【0802】 "Natural language processing" is the technology of analyzing and interpreting human language using computers. 【0803】 "Terminology" refers to specialized or important words or expressions used in a particular field or context. 【0804】 A "definition" is an explanatory statement that clarifies the meaning and content of a term. 【0805】 A "dictionary" is a database that compiles terms and their definitions into a referenceable format. 【0806】 "Multilingualism" refers to the use or correspondence of multiple languages. 【0807】 A "user" is someone who uses a system or service. 【0808】 An "emotion engine" is a technology or system used to analyze a user's emotional state. 【0809】 "Information provision" refers to the act or means of transmitting information to users. 【0810】 This invention relates to a system that integrates an emotion engine into an AI-powered glossary automatic generation system. This system analyzes the user's emotional state and provides personalized information based on that analysis, and is applicable to consumer robot applications. The following outlines the processing overview of this system. 【0811】 The server collects data from various digital sources and uses a speech recognition system to convert the audio data into text data. Software such as "Google Speech-to-Text" is used for this purpose. Next, the server analyzes the text data using a natural language processing (NLP) library, such as "spaCy," and extracts terms. Then, a generative AI model, such as "GPT-3," automatically generates definitions for the extracted terms. This creates a dictionary that can be used in multiple languages. 【0812】 Furthermore, the terminal uses an emotion engine, such as "IBM Watson Tone Analyzer," to analyze the user's emotions. Based on the emotion information inferred from the user's voice tone and input, the server can present the user with the most appropriate definitions and relevant information. For example, if the terminal detects that the user is confused about "how to use saffron," it will provide a detailed explanation. 【0813】 As a concrete example, consider a scenario where a resident has a question about how to use saffron when cooking. In this case, the robot assistant would detect the user's confusion from voice input and provide specific explanations such as, "Saffron is added at the very end to add flavor, so please use it carefully." An example of this prompt might be, "If I want to know more about how to use saffron, please briefly explain it from the first step for beginners." 【0814】 In summary, robot assistants can enrich users' lives and provide a new form of terminology understanding support that is more empathetic to their emotions. 【0815】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0816】 Step 1: 【0817】 The server collects audio and text data from information sources. Audio data is acquired via microphones and sensors. The input is a real-time audio stream, and the output is the audio data. 【0818】 Step 2: 【0819】 The server converts the collected audio data into text format using a speech recognition system. Tools such as "Google Speech-to-Text" are used for this process. The input is audio data, and the output is converted text data. In this step, data conversion is performed to recognize speech as text information. 【0820】 Step 3: 【0821】 The server performs natural language processing on the converted text data to extract important terms. Natural language processing libraries such as "spaCy" are used here. The input is text data, and the output is a list of extracted terms. The process involves identifying specific keywords and phrases through text analysis. 【0822】 Step 4: 【0823】 The server automatically generates definitions for the extracted terms using a generative AI model. An AI model such as "GPT-3" is applied in this process. The input is a list of terms, and the output is a definition sentence. In this procedure, the AI ​​model generates comprehensible text that conveys the meaning of the terms. 【0824】 Step 5: 【0825】 The generated terms and definitions are stored in a dictionary database by the server. This process creates a glossary of terms that can be referenced in the future. The input is the terms and their definitions, and the output is the stored database entries. 【0826】 Step 6: 【0827】 The server uses an emotion engine to process user input data and infer their emotional state. This role is handled by applications such as "IBM Watson Tone Analyzer." Input is either user voice or text, and output is the inferred emotional state. Prompt messages are set to something like, "If the user is feeling anxious, please provide a more detailed definition." 【0828】 Step 7: 【0829】 The device provides appropriate definitions and relevant information in real time, based on the user's emotional state. This operation is performed through the device's display and speaker. The input is the inferred emotion and definition of the term, and the output is the information presented to the user. Specifically, detailed explanations tailored to the emotional state and additional relevant information are presented. 【0830】 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. 【0831】 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. 【0832】 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. 【0833】 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. 【0834】 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. 【0835】 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. 【0836】 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. 【0837】 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. 【0838】 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." 【0839】 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. 【0840】 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. 【0841】 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. 【0842】 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. 【0843】 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. 【0844】 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. 【0845】 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. 【0846】 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. 【0847】 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. 【0848】 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. 【0849】 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. 【0850】 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. 【0851】 The following is further disclosed regarding the embodiments described above. 【0852】 (Claim 1) 【0853】 Means of collecting digital data from information sources, 【0854】 A means of converting collected digital data into text format, 【0855】 A method for extracting important terms from text data using natural language processing, 【0856】 A means for automatically generating definitions for extracted terms, 【0857】 A means of storing the generated terms and definitions and providing them as a dictionary, 【0858】 A means of translating dictionaries into multiple languages ​​and making them available for use in multiple languages, 【0859】 A system that includes this. 【0860】 (Claim 2) 【0861】 The system according to claim 1, which customizes a glossary of terms individually based on user attribute information. 【0862】 (Claim 3) 【0863】 The system according to claim 1, which updates collected digital data in real time and maintains the latest information. 【0864】 "Example 1" 【0865】 (Claim 1) 【0866】 Means of collecting digital data from information sources, 【0867】 A means of converting collected digital data into text format, 【0868】 A means for analyzing important terms from text data using natural language processing, and extracting them through term frequency analysis and context analysis, 【0869】 A means of automatically generating definitions for extracted terms using a generative AI model, 【0870】 A means of storing generated terms and definitions and providing them as an indexed dictionary for efficient searching and browsing, 【0871】 A means to automatically translate dictionaries into multiple languages ​​and enable multilingual use, 【0872】 A system that includes this. 【0873】 (Claim 2) 【0874】 The system according to claim 1, which enhances user learning by individually customizing a glossary and suggesting relevant terms based on the user's attribute information and search history. 【0875】 (Claim 3) 【0876】 The system according to claim 1, which updates collected digital data in real time and regenerates definitions while maintaining the latest information. 【0877】 "Application Example 1" 【0878】 (Claim 1) 【0879】 Means of gathering information from sources, 【0880】 A means of converting the collected information into a standard format, 【0881】 A means of selecting important vocabulary from data using language processing techniques, 【0882】 A means for automatically generating explanations for selected vocabulary, 【0883】 A means of accumulating generated vocabulary and explanations and providing them as reference material, 【0884】 A means of translating reference materials into different languages ​​and making them available in multiple languages, 【0885】 A means of specifically identifying and providing vocabulary related to electronic payments, 【0886】 A system that includes this. 【0887】 (Claim 2) 【0888】 The system according to claim 1, which individually adjusts reference materials based on user characteristic information. 【0889】 (Claim 3) 【0890】 The system according to claim 1, which rapidly updates collected information and maintains the latest information. 【0891】 "Example 2 of combining an emotion engine" 【0892】 (Claim 1) 【0893】 Means of collecting data from information sources, 【0894】 A means of converting the collected data into text format, 【0895】 A method for extracting important items from text data using natural language processing technology, 【0896】 A means for automatically generating definitions for the extracted items, 【0897】 A means for storing the generated items and definitions and providing them as aggregated information, 【0898】 A means of translating aggregated information into multiple languages ​​and enabling its use in multiple languages, 【0899】 A means of analyzing the user's emotional state and suggesting information appropriate to that state, 【0900】 A system that includes this. 【0901】 (Claim 2) 【0902】 The system according to claim 1, which individually customizes aggregated information based on user attribute information and sentiment analysis. 【0903】 (Claim 3) 【0904】 The system according to claim 1, which updates collected digital data in real time to maintain the latest information and flexibly responds to changes in the user's emotions. 【0905】 "Application example 2 when combining with an emotional engine" 【0906】 (Claim 1) 【0907】 Means of obtaining digital information from information sources, 【0908】 A means of converting acquired digital information into text format, 【0909】 A method for extracting important terms from text information using natural language processing, 【0910】 A means of automatically creating definitions for extracted terms, 【0911】 A means of saving the created terms and definitions and providing them as a dictionary, 【0912】 A means of translating dictionaries into multiple languages ​​and making them usable in multiple languages, 【0913】 By using an emotion engine that analyzes the user's emotional state, a means of providing information in accordance with their emotions is provided. 【0914】 A system that includes this. 【0915】 (Claim 2) 【0916】 The system according to claim 1, which converts a glossary of terms individually based on user attribute information. 【0917】 (Claim 3) 【0918】 The system according to claim 1, which updates collected digital information in real time and maintains the latest information. [Explanation of symbols] 【0919】 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

[Claim 1] Means of collecting digital data from information sources, A means of converting collected digital data into text format, A method for extracting important terms from text data using natural language processing, A means for automatically generating definitions for extracted terms, A means of storing the generated terms and definitions and providing them as a dictionary, A means of translating dictionaries into multiple languages ​​and making them available for use in multiple languages, A system that includes this. [Claim 2] The system according to claim 1, which individually customizes a glossary based on user attribute information. [Claim 3] The system according to claim 1, which updates collected digital data in real time and maintains the latest information.

Images