system

Abstract

We provide the system. [Solution] Means for collecting diverse natural language information, A means of analyzing collected natural language information and extracting language-specific meanings and grammatical rules, A means for identifying and classifying similarities between different natural languages ​​based on extracted meanings and grammatical rules, A means of constructing the vocabulary and grammar of an integrated language based on identified similarities, A means of evaluating the usefulness and comprehension of the integrated language and improving it based on feedback, Means for distributing and supporting the unified language in order to promote its widespread use, 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 persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] To eliminate communication losses and misunderstandings caused by differences in meaning and nuance among diverse natural languages with different cultures and historical backgrounds. In particular, it is necessary to overcome ambiguous expressions that cannot be accurately conveyed by existing translation systems and barriers due to grammar structures peculiar to each language.

Means for Solving the Problems

[0005] This invention collects diverse natural language information and analyzes it using a generative AI model to extract language-specific meanings and grammatical rules. It then identifies similarities between different natural languages ​​and constructs an integrated, unified vocabulary and grammar to generate a new common language. Furthermore, it can evaluate the practicality and comprehensibility of this language and continuously improve the language system based on user feedback. This interconnected process enables accurate and effective international communication.

[0006] "Natural language information" refers to information provided as text, audio, or video written in the language that humans use on a daily basis.

[0007] A "generative AI model" is a type of artificial intelligence technology that analyzes natural language based on large datasets and learns patterns and rules.

[0008] "Meaning" refers to the concept or interpretation that a particular word or phrase possesses in language.

[0009] "Grammar rules" are systematic rules for accurately constructing sentences and phrases in a particular language.

[0010] "Similarity" refers to the characteristics or properties that are common to different languages.

[0011] A "unified language" is a language that combines elements from various languages ​​to create a common vocabulary and grammar.

[0012] "Feedback" refers to opinions and impressions provided by users, which are useful information for improving a new language. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2]It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It 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 Example 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 Example 2 when an 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 an emotion engine is combined.

Mode for Carrying Out the Invention

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

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

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

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The system of this invention consists of three main elements: a server, a terminal, and a user. These elements work together to efficiently build a new integrated language.

[0035] First, the server collects diverse natural language information in text, audio, and video formats through the internet and existing databases. This results in a wealth of data from various cultural backgrounds.

[0036] Next, the data collected by the server is input into a generating AI model, which then analyzes the linguistic data. In this analysis process, the unique meanings and grammatical rules of each language are identified and organized into a database. At this point, the AI ​​technology processes a large amount of information and identifies similarities between different languages.

[0037] Subsequently, the server constructs a new unified language based on the identified similarities. A unified vocabulary and grammar are generated based on the identified commonalities. Linguists' expertise is also utilized here, and the new language is designed with practicality in mind.

[0038] The device functions as an interface to the user. It provides users with content and learning materials using an integrated language and tests their understanding. It also includes a function to check the user experience and any problems with the new language through user feedback.

[0039] Specifically, when a user attempts to communicate in the new language, the device displays a guide explaining the vocabulary and grammar of the new language, allowing the user to learn at their own pace. This feedback is then sent to the server and used as data to improve the language.

[0040] In general, through repeated testing and improvement, with servers, terminals, and users each fulfilling their respective roles, a new language can be effectively built to enable accurate communication. This system aims to become internationally widespread and used by many people.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects diverse natural language data from the internet and existing databases. The data is collected in text, audio, and video formats. The server automatically aggregates the data using web crawlers and APIs and stores it in a database.

[0044] Step 2:

[0045] The server cleanses the collected data and removes noise. Specifically, this includes formatting text, deleting unnecessary data, transcribing audio data, and extracting audio and text data from video. This prepares the data for analysis.

[0046] Step 3:

[0047] The server feeds the cleansed data into an AI model, which automatically analyzes its meaning and grammatical rules. The AI ​​utilizes existing large-scale language models to analyze common meanings, grammatical patterns, and vocabulary frequencies across various languages.

[0048] Step 4:

[0049] The server identifies similarities between different natural languages ​​based on the analyzed data. This process uses clustering algorithms to identify common vocabulary and grammar by forming clusters of similar words.

[0050] Step 5:

[0051] Based on the similarities identified by the server, a new unified language vocabulary and grammatical rules are created. Linguistic insights are also applied in this process to construct more natural and practical expressions.

[0052] Step 6:

[0053] The device provides users with educational content and dialogue systems based on the new language. Through this tool, users can experience and learn the new language firsthand. The device records user actions and usage and provides feedback to the server.

[0054] Step 7:

[0055] When users attempt to communicate using the new language, the server modifies and improves the language based on feedback received through their devices. Based on the analysis of this feedback, vocabulary is added and grammatical rules are adjusted to improve the language's applicability.

[0056] Step 8:

[0057] The server will begin efforts to promote the improved new language. It will provide a platform for educational institutions and businesses, offering online courses and materials, aiming for widespread adoption.

[0058] (Example 1)

[0059] 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."

[0060] In modern society, the existence of diverse natural languages, each with its own distinct grammatical rules and vocabulary, presents numerous challenges in communication between different languages. Furthermore, translation and understanding between multiple languages ​​require considerable time and resources, hindering efficient international exchange. There is a need to solve these problems and build a new, unified language to facilitate smooth communication and reduce language barriers.

[0061] 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.

[0062] In this invention, the server includes means for collecting diverse natural language data, means for analyzing the collected natural language data and extracting language-specific meanings and grammatical structures, and means for constructing a new integrated language form based on the identified commonalities. This makes it possible to effectively analyze commonalities between different languages, construct a new integrated language, and promote international communication.

[0063] "Diverse natural language data" refers to information such as text, audio, and video that consists of multiple languages ​​rooted in different cultures and regions.

[0064] "Analysis" refers to the process of understanding the meaning and grammatical structure from collected data, breaking down the information, and deriving valuable insights.

[0065] "Language-specific meanings and grammatical structures" refer to the meanings of vocabulary and the structure that indicates the rules for sentence formation that are unique to a particular language.

[0066] "Identifying and classifying commonalities" refers to the process of finding similarities between different languages, organizing them, and categorizing them.

[0067] A "integrated linguistic form" refers to a new language consisting of common vocabulary and grammatical rules, created based on the commonalities of different languages.

[0068] "Evaluating practicality and comprehension" refers to activities that measure how effective the constructed integrated language is in actual communication and how well users can understand it.

[0069] "Collecting user feedback and making improvements" refers to the process of continuously improving a language based on the opinions and experiences of users of an integrated language format.

[0070] "Providing and supporting resources to promote widespread adoption" refers to activities that provide necessary educational materials and technical support to make the developed language widely known.

[0071] This invention is configured as a system for achieving smooth communication between diverse natural languages. Its form is described below.

[0072] The server utilizes the internet and existing information management systems to collect diverse natural language data from around the world. This data includes various formats such as text, audio, and video. The server aggregates this data into a storage system and then analyzes it using generative AI models. Specifically, it employs technologies such as NLTK and spaCy as natural language processing libraries to extract language-specific meanings and grammatical structures from the data. This identifies commonalities between different languages ​​and lays the foundation for building an integrated language.

[0073] The terminal functions as an interface to the user, providing learning materials and content using the unified language. It displays interactive lessons and presents comprehension questions to help users learn the new language. It also directly receives user feedback and sends this information to the server to improve the unified language.

[0074] Users learn a new language using learning materials provided through their device. Guides are displayed as needed, facilitating smooth vocabulary and grammar acquisition. Feedback includes information on what was understood and what was difficult, contributing to an assessment of the language's practical usability.

[0075] One concrete example is a process where a server collects greetings from different languages, such as "hello," "hola," and "konnichiwa," and integrates their meanings. This process aims to identify similarities between languages ​​and construct new, concise, and easy-to-pronounce greetings.

[0076] An example of a prompt for a generative AI model is: "Generate basic greetings for a new unified language based on the following text dataset."

[0077] This system will evolve through collaboration between users, servers, and terminals, continuously improving its unified language to become a valuable tool for everyday communication.

[0078] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0079] Step 1:

[0080] The server collects diverse natural language data via the internet and existing information management systems. Inputs include web pages, audio files, and video content. The server utilizes web crawlers and API interfaces to efficiently retrieve this data. The data is stored in a storage system, serving as a foundation for subsequent processing.

[0081] Step 2:

[0082] The server inputs the collected natural language data into a generative AI model. The input data consists of text, audio, and video information collected in the previous stage. The server uses natural language processing libraries (such as NLTK and spaCy) to tokenize the text data, tag parts of speech, and perform syntactic analysis. The output of this process is information about the grammatical structure and vocabulary specific to each language, which is stored in a database.

[0083] Step 3:

[0084] The server identifies commonalities between different languages ​​based on the analysis results and constructs a new unified language. The input includes grammatical structure and vocabulary information obtained in the previous stage. Using this information, the server employs generative AI models and statistical algorithms to generate a common vocabulary list and grammatical rules. The output obtained in this process is the basic vocabulary and grammatical rules of the new language.

[0085] Step 4:

[0086] The terminal provides users with learning materials and content using the integrated language. The input here is the vocabulary and grammar information of the integrated language built by the server. Based on this, the terminal creates interactive lessons and question-and-answer formatted materials, presenting them in a way that is easy for the user to understand. The output of this process is the user's improved proficiency in the new language.

[0087] Step 5:

[0088] Users access learning materials through their devices and progress through the learning process. User input consists of answers and feedback entered into the device during learning. The device collects this data and sends the correctness of the answers to the server. Output is data representing the user's level of understanding, which is transmitted to the server as feedback and used to improve language skills.

[0089] In this way, the development and widespread adoption of a new unified programming language is achieved through the cooperation of servers, terminals, and users in processing programs.

[0090] (Application Example 1)

[0091] 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."

[0092] There are problems that make it difficult for users with diverse cultural and linguistic backgrounds to communicate in a unified manner. In particular, there is a growing need for accurate and efficient information exchange between groups with different language systems. This invention aims to provide a new integrated language system that overcomes such language barriers and enables smooth communication between multiple languages.

[0093] 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.

[0094] In this invention, the server includes means for collecting diverse natural language information, means for analyzing the collected natural language information and extracting language-specific meanings and grammatical rules, and means for identifying and classifying similarities between different natural languages ​​based on the extracted meanings and grammatical rules. This makes it possible to communicate between different languages ​​using a unified vocabulary and grammar.

[0095] "Diverse natural language information" refers to a collection of languages ​​used in various cultures and regions, including in forms such as text, audio, and video.

[0096] "Language-specific meanings and grammatical rules" refer to the rules that shape the meanings of words and sentence structures that are unique to each natural language.

[0097] "Similarities between different natural languages" refers to elements and patterns that are common to different languages.

[0098] An "integrated language" is a means of communication that has a newly constructed vocabulary and grammar based on the similarities between different natural languages.

[0099] "User learning history" refers to a record of the learning activities a user has undertaken to date, including progress and achievements.

[0100] "Teaching materials" refer to instructional materials and content used by learners to acquire certain knowledge or skills.

[0101] "Feedback" refers to opinions and results regarding user experience and areas for improvement that a system receives from users.

[0102] "Testing understanding of the integrated language through interaction" means that users perform operations and communicate using the integrated language, and the results are evaluated.

[0103] To implement this invention, a system is needed in which three elements—a server, a terminal, and a user—work in conjunction with each other. The server collects diverse natural language information via the internet and inputs this information into a generative AI model. The generative AI model extracts language-specific meanings and grammatical rules from the collected data and identifies similarities between different natural languages. The software used in this process is a platform with AI model analysis capabilities.

[0104] Next, based on the extracted similarities, the server constructs the vocabulary and grammar of the unified language. During this process, a database management system is used to organize and store the constructed unified language. The server also collects user feedback and functions to evaluate the language's usefulness and comprehensibility.

[0105] The device serves as a user interface, providing users with integrated language learning materials. Applications on the device record learning history and provide personalized learning support. This enables users to leverage the integrated language and communicate effectively with people from diverse linguistic backgrounds.

[0106] As a concrete example, consider a user using the integrated language at an international exchange event. Before the event, the user learns the basics of the new integrated language using an application on their device, participates in the event, and puts that knowledge into practice. The application can use prompts such as: "Please tell me some simple phrases I can use at recent events," "I want to see more examples of this grammar rule," and "Please tell me some example sentences using this vocabulary." Through such concrete support, the user can deepen their understanding of the integrated language and communicate smoothly in international settings.

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The server collects diverse natural language information via the internet in text, audio, and video formats. This allows for the accumulation of culturally and regionally specific language data in the database. The input information then serves as foundational data for processing in the next step.

[0110] Step 2:

[0111] The server inputs collected natural language information into a generative AI model, which extracts language-specific meanings and grammatical rules. This process involves data analysis, and the extracted meanings and grammar are stored in a database. The output is a dataset representing the unique characteristics of the language.

[0112] Step 3:

[0113] The server uses the data extracted in the previous step to identify similarities between different natural languages. It analyzes the dataset stored in the database to classify similar patterns and rules, and obtains information indicating the commonalities between languages ​​as output.

[0114] Step 4:

[0115] The server constructs the vocabulary and grammar of the unified language based on the obtained similarity information. It generates new vocabulary and grammar that reflect the identified commonalities and registers them in the database. The output is the basic structure of the unified language.

[0116] Step 5:

[0117] The terminal provides the user with learning materials using an integrated language retrieved from the server. In this step, explanations of vocabulary and grammar are displayed as learning content, and interactions are provided to enhance the user's understanding. As output, the user's learning history is updated in real time.

[0118] Step 6:

[0119] Users learn the integrated language through their devices and provide feedback. This feedback, including user experience and problems, is sent back to the server. User opinions are collected as input, and information useful for improving the language is obtained as output.

[0120] Step 7:

[0121] The server dynamically improves the integrated language based on user feedback. New data is re-inputted into the AI ​​model, and the language structure is adapted and improved. As output, the optimized integrated language data becomes available and is redistributed through the terminal.

[0122] 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.

[0123] This invention combines a system that collects diverse natural language information and generates a new integrated language with an emotion engine that recognizes and analyzes user emotions in real time. This system consists of a server, a terminal, and a user, and each element works in coordination.

[0124] First, the server collects diverse natural language information. The collected data is obtained from various cultural regions in text, audio, and video formats. Then, AI technology is used to analyze this language data and extract the meanings and grammatical rules specific to each language.

[0125] Next, the server identifies similarities between different natural languages ​​based on these analysis results and constructs the vocabulary and grammar of the unified language based on these similarities. By adding an emotion engine to this process, the expressions in the unified language can be adapted to the user's emotions using the analyzed emotion data.

[0126] The device provides an interface for users to experience the new unified language. When users use the new language, the device incorporates an emotion engine that recognizes the user's emotional state from text, audio, and video data. For example, when a user writes text, the appropriate emotion for the context is identified and displayed. The unified language is fine-tuned to ensure users receive positive feedback.

[0127] For example, when a user creates a message in the new unified language, the device analyzes the message's content and tone, and if it determines that the user is enjoying it, it offers encouraging messages and additional hints. At this point, the emotion engine monitors changes in emotion and can provide appropriate advice and modifications to improve the user's learning experience.

[0128] By integrating these elements, the system enables more natural and smooth international communication while being mindful of user emotions. Furthermore, through continuous language improvement based on feedback, it provides a user-friendly and effective language learning environment.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The server collects diverse natural language information from the internet and existing databases. The information is systematically stored in the database in text, audio, and video formats. This allows for the collection of a wide range of data from different cultural backgrounds.

[0132] Step 2:

[0133] The server collects natural language information, which is then input into a generating AI model for analysis. Through this analysis, meanings and grammatical rules specific to each language are automatically extracted and organized as visualized data.

[0134] Step 3:

[0135] The server identifies similarities between different natural languages ​​based on the analysis results and clusters those with similar linguistic features. This identifies common vocabulary and expressions.

[0136] Step 4:

[0137] The server initiates the process of building the vocabulary and grammar of the unified language. Based on identified similarities, a concise and clear vocabulary and unified grammatical rules are created.

[0138] Step 5:

[0139] An emotion engine built into the device recognizes the user's emotional state from text, voice, and video data. In particular, it analyzes the user's reactions as they use the system in real time and collects emotional information.

[0140] Step 6:

[0141] The device generates feedback when using the integrated language based on the user's emotions. For example, when a user is trying to understand a difficult expression, it displays an encouraging message to support their learning.

[0142] Step 7:

[0143] Users will communicate using a new unified language via their devices. By receiving emotion-based feedback, users will be able to more easily understand their own progress and challenges.

[0144] Step 8:

[0145] The server collects user feedback and improves the integrated language along with sentiment analysis results. This process continuously optimizes the integrated language, improving users' communication capabilities.

[0146] (Example 2)

[0147] 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".

[0148] Barriers to international communication include differences between diverse languages ​​and the inability to obtain appropriate feedback that takes user emotions into consideration. In such situations, smooth intercultural communication is difficult, and the effectiveness of language learning is limited. Therefore, there is a need for a system that integrates diverse linguistic characteristics and provides a new language experience that takes user emotions into account.

[0149] 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.

[0150] In this invention, the server includes means for collecting diverse language data, means for analyzing the collected language data using analysis techniques to identify grammatical elements and vocabulary, and means for identifying and aggregating commonalities between different languages ​​based on the identified grammatical elements and vocabulary. This enables more effective and natural international communication by integrating the characteristics of different languages ​​while considering the user's emotions.

[0151] "Diverse language data" refers to data in written, audio, and video formats collected from different regions and cultural areas.

[0152] "Analysis techniques" refer to techniques used to identify grammatical elements and vocabulary from collected data, and include machine learning and natural language processing methods.

[0153] "Grammar elements and vocabulary" refer to the structure and meaning of words that are unique to each language, and are the elements that constitute the foundation of language.

[0154] "Common ground" refers to similar grammatical and vocabulary features between different languages, which serve as the basis for constructing a new language.

[0155] "Emotion recognition technology" is a technology used to detect and analyze a user's emotional state, and is used to analyze emotional information in linguistic data.

[0156] A "feedback mechanism" is a system that analyzes user responses and uses them to improve language, playing a role in dynamically adjusting the language.

[0157] In an embodiment of this invention, the system consists of a server, a terminal, and a user. The server collects diverse linguistic data and analyzes it using analytical techniques. Here, machine learning models such as BERT and GPT are often used as representative natural language processing techniques. Through this, the server identifies grammatical elements and vocabulary of each language and, based on this, identifies commonalities between different languages. A new language is formed through these identified commonalities.

[0158] Emotion recognition technology is also integrated into the server, enabling analysis of user emotional information. This allows for appropriate language fine-tuning, resulting in a more natural user experience of the new language. Specifically, the server is equipped with a high-performance GPU, and the software utilizes deep learning frameworks such as TENSORFLOW® and PyTorch.

[0159] The terminal is a device that provides users with a new language interface. When a user inputs text or voice, the terminal uses its built-in emotion engine to analyze the emotion in real time and sends the results to a server. The terminal is envisioned to be a multi-functional computer or smartphone, and the aforementioned analysis function will be provided as a dedicated application.

[0160] As a concrete example, when a user begins learning a new language, the device captures the user's initial responses, which are then analyzed by a server. To improve the user's experience, emotion-based feedback is provided, and language expressions are adjusted as needed. This process is carried out in the form of prompts using a generative AI model. For example, the user might input a prompt such as, "Please tell me how to create a self-introduction using the new language while maintaining a positive tone." Through this process, the user can efficiently learn the language and acquire new ways of expression.

[0161] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0162] Step 1:

[0163] The server collects diverse linguistic data. It receives text, audio, and video data from multiple cultural regions as input. To analyze this data, the server runs machine learning algorithms to extract language-specific grammatical elements and vocabulary. This process outputs the elements necessary for the initial construction of a language model.

[0164] Step 2:

[0165] The server identifies commonalities between different languages ​​from language data extracted using analytical techniques. It uses a list of grammatical elements and vocabulary generated in step 1 as input. The server executes a clustering algorithm to group similar elements. The output of this operation is aggregated information on commonalities between languages.

[0166] Step 3:

[0167] The server forms a new language structure based on commonalities. The information aggregated in Step 2 is input, and AI technology is used to design the grammar and vocabulary of the unified language. Natural language generation models are utilized for this. As output, an initial model of the new unified language is generated.

[0168] Step 4:

[0169] The device provides an interface that allows users to experience a new unified language. It receives data from the user in text or voice as input and analyzes it in real time using an emotion engine. Based on this analysis, it provides appropriate feedback to the user to facilitate learning. As output, the device displays feedback and advice tailored to the user's emotions.

[0170] Step 5:

[0171] Emotion recognition technology is used to continuously collect user feedback and improve the language. User emotion data and feedback are sent to the server as input. The server analyzes this data and adjusts the integrated language as needed. The output is the improved language model, which is used to enhance the user's communication experience.

[0172] (Application Example 2)

[0173] 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".

[0174] To integrate languages ​​from different cultural backgrounds and enable more natural and smooth international communication, it is necessary to appropriately analyze and integrate diverse information, as well as improve individual user experiences through content suggestions based on the user's emotional state. Furthermore, optimizing the viewing experience using real-time emotional analysis is a challenge that has not been adequately addressed with conventional technologies.

[0175] 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.

[0176] In this invention, the server includes means for collecting diverse natural language information, means for analyzing the collected natural language information and extracting language-specific meanings and grammatical rules, and means for identifying and classifying similarities between different natural languages ​​based on the extracted meanings and grammatical rules. This enables appropriate integration between each language and the suggestion of optimal content according to the user's emotional state.

[0177] "Diverse natural language information" refers to language data composed of text, audio, video, and other formats collected from different cultural spheres and regions.

[0178] "Meaning and grammatical rules" refer to the word definitions, sentence structures, and grammatical rules specific to each natural language.

[0179] "Similarities between different natural languages" is a concept that refers to common elements and characteristics found between different languages.

[0180] An "integrated language" is a language system newly constructed based on elements extracted from diverse natural languages.

[0181] "Emotion recognition technology" is a technology that analyzes a user's facial expressions, tone of voice, and actions to identify their emotional state.

[0182] "Real-time analysis" is a process that performs immediate processing and analysis of data as it is collected.

[0183] "Content suggestion" is the act of selecting the next piece of information or entertainment that should be provided based on the user's interests and emotions.

[0184] The system that realizes this invention has the function of recognizing the emotional state of the user in real time in response to the content they are watching and optimizing the viewing experience.

[0185] The server collects diverse natural language information via the internet and other means, and analyzes the collected data. The analysis uses a natural language processing engine to extract meanings and grammatical rules specific to each language. Next, it identifies similarities between different languages ​​and uses this to construct the vocabulary and grammar of an integrated language. This data is then compiled into an integrated language and provided to the user's terminal.

[0186] The device displays integrated language information and analyzes the user's emotional state in real time using emotion recognition technology. Specifically, it uses devices such as cameras and microphones to detect and analyze emotions from the user's facial expressions and voice. In this process, the emotion recognition technology utilizes a recognition engine (for example, general computer vision or speech analysis software).

[0187] While a user is watching a particular video content, the system constantly monitors their emotional state and suggests the next content to watch based on the analysis results. For example, if a user cries during a moving scene, the system can use that emotion to recommend another work that evokes similar emotions. This process can be initiated with the prompt message, "Please recommend a new movie based on the emotions the user has perceived."

[0188] This allows users' viewing experiences to be optimized according to their individual emotional states, enabling a more personalized content experience.

[0189] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0190] Step 1:

[0191] The server collects diverse natural language information from the internet. Inputs include text, audio, and video data, which are stored in a database. The output is a language dataset ready for analysis.

[0192] Step 2:

[0193] The server analyzes the collected language data using a natural language processing engine. The input is language data in a database, and the AI ​​model extracts language-specific meanings and grammatical rules. The output is the extracted grammatical structure and word-semantic data. In this process, the generative AI model identifies grammatical patterns.

[0194] Step 3:

[0195] The server identifies similarities between different natural languages ​​from the analyzed data. The input consists of grammatical structure and semantic data, and statistical methods are used to determine similarity. The output is a list of similar language pairs. Here, a generative AI model calculates similarity scores.

[0196] Step 4:

[0197] The server constructs the vocabulary and grammar of an integrated language based on the obtained similarity data. The input is information on similar language pairs, and the output is a prototype of the integrated language. Structural analysis and construction techniques are used for data processing.

[0198] Step 5:

[0199] The device uses a camera and microphone to perform real-time analysis to recognize the user's emotional state. Input consists of the user's facial expressions and voice data, while output is an emotional state evaluation score. A software-based emotion recognition engine is used, and its evaluation is formalized through prompt messages.

[0200] Step 6:

[0201] Based on the user's emotional state towards the content they are currently viewing, the device suggests the next content to watch. The input consists of an emotional evaluation score and data on the currently viewed content, while the output is a list of recommended content. A selection algorithm is used for data processing, and a generative AI model is applied.

[0202] This series of steps makes it possible to provide users with a content experience that is individually optimized for them.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] [Second Embodiment]

[0207] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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".

[0219] The system of this invention consists of three main elements: a server, a terminal, and a user. These elements work together to efficiently build a new integrated language.

[0220] First, the server collects diverse natural language information in text, audio, and video formats through the internet and existing databases. This results in a wealth of data from various cultural backgrounds.

[0221] Next, the data collected by the server is input into a generating AI model, which then analyzes the linguistic data. In this analysis process, the unique meanings and grammatical rules of each language are identified and organized into a database. At this point, the AI ​​technology processes a large amount of information and identifies similarities between different languages.

[0222] Subsequently, the server constructs a new unified language based on the identified similarities. A unified vocabulary and grammar are generated based on the identified commonalities. Linguists' expertise is also utilized here, and the new language is designed with practicality in mind.

[0223] The device functions as an interface to the user. It provides users with content and learning materials using an integrated language and tests their understanding. It also includes a function to check the user experience and any problems with the new language through user feedback.

[0224] Specifically, when a user attempts to communicate in the new language, the device displays a guide explaining the vocabulary and grammar of the new language, allowing the user to learn at their own pace. This feedback is then sent to the server and used as data to improve the language.

[0225] In general, through repeated testing and improvement, with servers, terminals, and users each fulfilling their respective roles, a new language can be effectively built to enable accurate communication. This system aims to become internationally widespread and used by many people.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The server collects diverse natural language data from the internet and existing databases. The data is collected in text, audio, and video formats. The server automatically aggregates the data using web crawlers and APIs and stores it in a database.

[0229] Step 2:

[0230] The server cleanses the collected data and removes noise. Specifically, this includes formatting text, deleting unnecessary data, transcribing audio data, and extracting audio and text data from video. This prepares the data for analysis.

[0231] Step 3:

[0232] The server feeds the cleansed data into an AI model, which automatically analyzes its meaning and grammatical rules. The AI ​​utilizes existing large-scale language models to analyze common meanings, grammatical patterns, and vocabulary frequencies across various languages.

[0233] Step 4:

[0234] The server identifies similarities between different natural languages ​​based on the analyzed data. This process uses clustering algorithms to identify common vocabulary and grammar by forming clusters of similar words.

[0235] Step 5:

[0236] Based on the similarities identified by the server, a new unified language vocabulary and grammatical rules are created. Linguistic insights are also applied in this process to construct more natural and practical expressions.

[0237] Step 6:

[0238] The device provides users with educational content and dialogue systems based on the new language. Through this tool, users can experience and learn the new language firsthand. The device records user actions and usage and provides feedback to the server.

[0239] Step 7:

[0240] When users attempt to communicate using the new language, the server modifies and improves the language based on feedback received through their devices. Based on the analysis of this feedback, vocabulary is added and grammatical rules are adjusted to improve the language's applicability.

[0241] Step 8:

[0242] The server will begin efforts to promote the improved new language. It will provide a platform for educational institutions and businesses, offering online courses and materials, aiming for widespread adoption.

[0243] (Example 1)

[0244] 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."

[0245] In modern society, the existence of diverse natural languages, each with its own distinct grammatical rules and vocabulary, presents numerous challenges in communication between different languages. Furthermore, translation and understanding between multiple languages ​​require considerable time and resources, hindering efficient international exchange. There is a need to solve these problems and build a new, unified language to facilitate smooth communication and reduce language barriers.

[0246] 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.

[0247] In this invention, the server includes means for collecting diverse natural language data, means for analyzing the collected natural language data and extracting language-specific meanings and grammatical structures, and means for constructing a new integrated language form based on the identified commonalities. This makes it possible to effectively analyze commonalities between different languages, construct a new integrated language, and promote international communication.

[0248] "Diverse natural language data" refers to information such as text, audio, and video that consists of multiple languages ​​rooted in different cultures and regions.

[0249] "Analysis" refers to the process of understanding the meaning and grammatical structure from collected data, breaking down the information, and deriving valuable insights.

[0250] "Language-specific meanings and grammatical structures" refer to the meanings of vocabulary and the structure that indicates the rules for sentence formation that are unique to a particular language.

[0251] "Identifying and classifying commonalities" refers to the process of finding similarities between different languages, organizing them, and categorizing them.

[0252] A "integrated linguistic form" refers to a new language consisting of common vocabulary and grammatical rules, created based on the commonalities of different languages.

[0253] "Evaluating practicality and comprehension" refers to activities that measure how effective the constructed integrated language is in actual communication and how well users can understand it.

[0254] "Collecting user feedback and making improvements" refers to the process of continuously improving a language based on the opinions and experiences of users of an integrated language format.

[0255] "Providing and supporting resources to promote widespread adoption" refers to activities that provide necessary educational materials and technical support to make the developed language widely known.

[0256] This invention is configured as a system for achieving smooth communication between diverse natural languages. Its form is described below.

[0257] The server utilizes the internet and existing information management systems to collect diverse natural language data from around the world. This data includes various formats such as text, audio, and video. The server aggregates this data into a storage system and then analyzes it using generative AI models. Specifically, it employs technologies such as NLTK and spaCy as natural language processing libraries to extract language-specific meanings and grammatical structures from the data. This identifies commonalities between different languages ​​and lays the foundation for building an integrated language.

[0258] The terminal functions as an interface to the user, providing learning materials and content using the unified language. It displays interactive lessons and presents comprehension questions to help users learn the new language. It also directly receives user feedback and sends this information to the server to improve the unified language.

[0259] Users learn a new language using learning materials provided through their device. Guides are displayed as needed, facilitating smooth vocabulary and grammar acquisition. Feedback includes information on what was understood and what was difficult, contributing to an assessment of the language's practical usability.

[0260] One concrete example is a process where a server collects greetings from different languages, such as "hello," "hola," and "konnichiwa," and integrates their meanings. This process aims to identify similarities between languages ​​and construct new, concise, and easy-to-pronounce greetings.

[0261] An example of a prompt for a generative AI model is: "Generate basic greetings for a new unified language based on the following text dataset."

[0262] This system will evolve through collaboration between users, servers, and terminals, continuously improving its unified language to become a valuable tool for everyday communication.

[0263] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0264] Step 1:

[0265] The server collects diverse natural language data via the internet and existing information management systems. Inputs include web pages, audio files, and video content. The server utilizes web crawlers and API interfaces to efficiently retrieve this data. The data is stored in a storage system, serving as a foundation for subsequent processing.

[0266] Step 2:

[0267] The server inputs the collected natural language data into a generative AI model. The input data consists of text, audio, and video information collected in the previous stage. The server uses natural language processing libraries (such as NLTK and spaCy) to tokenize the text data, tag parts of speech, and perform syntactic analysis. The output of this process is information about the grammatical structure and vocabulary specific to each language, which is stored in a database.

[0268] Step 3:

[0269] The server identifies commonalities between different languages ​​based on the analysis results and constructs a new unified language. The input includes grammatical structure and vocabulary information obtained in the previous stage. Using this information, the server employs generative AI models and statistical algorithms to generate a common vocabulary list and grammatical rules. The output obtained in this process is the basic vocabulary and grammatical rules of the new language.

[0270] Step 4:

[0271] The terminal provides users with learning materials and content using the integrated language. The input here is the vocabulary and grammar information of the integrated language built by the server. Based on this, the terminal creates interactive lessons and question-and-answer formatted materials, presenting them in a way that is easy for the user to understand. The output of this process is the user's improved proficiency in the new language.

[0272] Step 5:

[0273] Users access learning materials through their devices and progress through the learning process. User input consists of answers and feedback entered into the device during learning. The device collects this data and sends the correctness of the answers to the server. Output is data representing the user's level of understanding, which is transmitted to the server as feedback and used to improve language skills.

[0274] In this way, the development and widespread adoption of a new unified programming language is achieved through the cooperation of servers, terminals, and users in processing programs.

[0275] (Application Example 1)

[0276] 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."

[0277] There are problems that make it difficult for users with diverse cultural and linguistic backgrounds to communicate in a unified manner. In particular, there is a growing need for accurate and efficient information exchange between groups with different language systems. This invention aims to provide a new integrated language system that overcomes such language barriers and enables smooth communication between multiple languages.

[0278] 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.

[0279] In this invention, the server includes means for collecting various natural language information, means for analyzing the collected natural language information and extracting language-specific meanings and grammar rules, and means for identifying and classifying similarities between different natural languages based on the extracted meanings and grammar rules. As a result, it becomes possible to communicate between different languages using a unified vocabulary and grammar.

[0280] "Various natural language information" refers to a collection of languages used in various cultures and regions, including forms such as text, voice, and video.

[0281] "Language-specific meanings and grammar rules" refer to the meanings of words and the rules for forming sentence structures that are specific to each natural language.

[0282] "Similarities between different natural languages" refer to elements and patterns that are common between different languages.

[0283] "Integrated language" is a communication means with a vocabulary and grammar newly constructed based on the similarities of different natural languages.

[0284] "User's learning history" refers to a record of the learning activities that the user has carried out so far, including progress and achievement status.

[0285] "Teaching materials" refer to the guiding materials and contents used by learners to acquire certain knowledge and skills.

[0286] "Feedback" refers to the opinions and results regarding the user experience and improvement points obtained by the system from the user.

[0287] "Testing the understanding degree of the integrated language through interaction" means that the user performs operations and communications using the integrated language and evaluates the results.

[0288] To implement this invention, a system is needed in which three elements—a server, a terminal, and a user—work in conjunction with each other. The server collects diverse natural language information via the internet and inputs this information into a generative AI model. The generative AI model extracts language-specific meanings and grammatical rules from the collected data and identifies similarities between different natural languages. The software used in this process is a platform with AI model analysis capabilities.

[0289] Next, based on the extracted similarities, the server constructs the vocabulary and grammar of the unified language. During this process, a database management system is used to organize and store the constructed unified language. The server also collects user feedback and functions to evaluate the language's usefulness and comprehensibility.

[0290] The device serves as a user interface, providing users with integrated language learning materials. Applications on the device record learning history and provide personalized learning support. This enables users to leverage the integrated language and communicate effectively with people from diverse linguistic backgrounds.

[0291] As a concrete example, consider a user using the integrated language at an international exchange event. Before the event, the user learns the basics of the new integrated language using an application on their device, participates in the event, and puts that knowledge into practice. The application can use prompts such as: "Please tell me some simple phrases I can use at recent events," "I want to see more examples of this grammar rule," and "Please tell me some example sentences using this vocabulary." Through such concrete support, the user can deepen their understanding of the integrated language and communicate smoothly in international settings.

[0292] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0293] Step 1:

[0294] The server collects diverse natural language information via the internet in text, audio, and video formats. This allows for the accumulation of culturally and regionally specific language data in the database. The input information then serves as foundational data for processing in the next step.

[0295] Step 2:

[0296] The server inputs collected natural language information into a generative AI model, which extracts language-specific meanings and grammatical rules. This process involves data analysis, and the extracted meanings and grammar are stored in a database. The output is a dataset representing the unique characteristics of the language.

[0297] Step 3:

[0298] The server uses the data extracted in the previous step to identify similarities between different natural languages. It analyzes the dataset stored in the database to classify similar patterns and rules, and obtains information indicating the commonalities between languages ​​as output.

[0299] Step 4:

[0300] The server constructs the vocabulary and grammar of the unified language based on the obtained similarity information. It generates new vocabulary and grammar that reflect the identified commonalities and registers them in the database. The output is the basic structure of the unified language.

[0301] Step 5:

[0302] The terminal provides the user with learning materials using an integrated language retrieved from the server. In this step, explanations of vocabulary and grammar are displayed as learning content, and interactions are provided to enhance the user's understanding. As output, the user's learning history is updated in real time.

[0303] Step 6:

[0304] The user learns the integrated language through the terminal and provides feedback. The feedback from the user includes the usage experience and problems, and is sent back to the server again. The opinions of the user are collected as input, and information useful for improving the language is obtained as output.

[0305] Step 7:

[0306] Based on the feedback from the user, the server dynamically improves the integrated language. The new data is input into the generative AI model again to adapt and improve the language structure. As output, optimized integrated language data becomes available and is redistributed through the terminal.

[0307] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0308] The present invention combines an emotion engine that recognizes and analyzes the user's emotion in real time with a system that collects various natural language information and generates a new integrated language. This system is composed of a server, a terminal, and a user, and each element operates in cooperation.

[0309] First, the server collects various natural language information. The collected data is obtained from various cultural regions in text, audio, and video formats. Then, these language data are analyzed using AI technology to extract the meanings and grammar rules specific to each language.

[0310] Subsequently, based on these analysis results, the server identifies the similarities between different natural languages and constructs the vocabulary and grammar of the integrated language based on that. By adding the emotion engine to this process, the expression of the integrated language can be adapted to the user's emotion using the analyzed emotion data.

[0311] The device provides an interface for users to experience the new unified language. When users use the new language, the device incorporates an emotion engine that recognizes the user's emotional state from text, audio, and video data. For example, when a user writes text, the appropriate emotion for the context is identified and displayed. The unified language is fine-tuned to ensure users receive positive feedback.

[0312] For example, when a user creates a message in the new unified language, the device analyzes the message's content and tone, and if it determines that the user is enjoying it, it offers encouraging messages and additional hints. At this point, the emotion engine monitors changes in emotion and can provide appropriate advice and modifications to improve the user's learning experience.

[0313] By integrating these elements, the system enables more natural and smooth international communication while being mindful of user emotions. Furthermore, through continuous language improvement based on feedback, it provides a user-friendly and effective language learning environment.

[0314] The following describes the processing flow.

[0315] Step 1:

[0316] The server collects diverse natural language information from the internet and existing databases. The information is systematically stored in the database in text, audio, and video formats. This allows for the collection of a wide range of data from different cultural backgrounds.

[0317] Step 2:

[0318] The server collects natural language information, which is then input into a generating AI model for analysis. Through this analysis, meanings and grammatical rules specific to each language are automatically extracted and organized as visualized data.

[0319] Step 3:

[0320] The server identifies similarities between different natural languages ​​based on the analysis results and clusters those with similar linguistic features. This identifies common vocabulary and expressions.

[0321] Step 4:

[0322] The server initiates the process of building the vocabulary and grammar of the unified language. Based on identified similarities, a concise and clear vocabulary and unified grammatical rules are created.

[0323] Step 5:

[0324] An emotion engine built into the device recognizes the user's emotional state from text, voice, and video data. In particular, it analyzes the user's reactions as they use the system in real time and collects emotional information.

[0325] Step 6:

[0326] The device generates feedback when using the integrated language based on the user's emotions. For example, when a user is trying to understand a difficult expression, it displays an encouraging message to support their learning.

[0327] Step 7:

[0328] Users will communicate using a new unified language via their devices. By receiving emotion-based feedback, users will be able to more easily understand their own progress and challenges.

[0329] Step 8:

[0330] The server collects user feedback and improves the integrated language along with sentiment analysis results. This process continuously optimizes the integrated language, improving users' communication capabilities.

[0331] (Example 2)

[0332] 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".

[0333] Barriers to international communication include differences between diverse languages ​​and the inability to obtain appropriate feedback that takes user emotions into consideration. In such situations, smooth intercultural communication is difficult, and the effectiveness of language learning is limited. Therefore, there is a need for a system that integrates diverse linguistic characteristics and provides a new language experience that takes user emotions into account.

[0334] 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.

[0335] In this invention, the server includes means for collecting diverse language data, means for analyzing the collected language data using analysis techniques to identify grammatical elements and vocabulary, and means for identifying and aggregating commonalities between different languages ​​based on the identified grammatical elements and vocabulary. This enables more effective and natural international communication by integrating the characteristics of different languages ​​while considering the user's emotions.

[0336] "Diverse language data" refers to data in written, audio, and video formats collected from different regions and cultural areas.

[0337] "Analysis techniques" refer to techniques used to identify grammatical elements and vocabulary from collected data, and include machine learning and natural language processing methods.

[0338] "Grammar elements and vocabulary" refer to the structure and meaning of words that are unique to each language, and are the elements that constitute the foundation of language.

[0339] "Common ground" refers to similar grammatical and vocabulary features between different languages, which serve as the basis for constructing a new language.

[0340] "Emotion recognition technology" is a technology used to detect and analyze a user's emotional state, and is used to analyze emotional information in linguistic data.

[0341] A "feedback mechanism" is a system that analyzes user responses and uses them to improve language, playing a role in dynamically adjusting the language.

[0342] In an embodiment of this invention, the system consists of a server, a terminal, and a user. The server collects diverse linguistic data and analyzes it using analytical techniques. Here, machine learning models such as BERT and GPT are often used as representative natural language processing techniques. Through this, the server identifies grammatical elements and vocabulary of each language and, based on this, identifies commonalities between different languages. A new language is formed through these identified commonalities.

[0343] Emotion recognition technology is also integrated into the server, enabling analysis of user emotion information. This allows for appropriate language fine-tuning, resulting in a more natural user experience of the new language. Specifically, the server is equipped with high-performance GPUs, and the software utilizes deep learning frameworks such as TensorFlow and PyTorch.

[0344] The terminal is a device that provides users with a new language interface. When a user inputs text or voice, the terminal uses its built-in emotion engine to analyze the emotion in real time and sends the results to a server. The terminal is envisioned to be a multi-functional computer or smartphone, and the aforementioned analysis function will be provided as a dedicated application.

[0345] As a concrete example, when a user begins learning a new language, the device captures the user's initial responses, which are then analyzed by a server. To improve the user's experience, emotion-based feedback is provided, and language expressions are adjusted as needed. This process is carried out in the form of prompts using a generative AI model. For example, the user might input a prompt such as, "Please tell me how to create a self-introduction using the new language while maintaining a positive tone." Through this process, the user can efficiently learn the language and acquire new ways of expression.

[0346] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0347] Step 1:

[0348] The server collects diverse linguistic data. It receives text, audio, and video data from multiple cultural regions as input. To analyze this data, the server runs machine learning algorithms to extract language-specific grammatical elements and vocabulary. This process outputs the elements necessary for the initial construction of a language model.

[0349] Step 2:

[0350] The server identifies commonalities between different languages ​​from language data extracted using analytical techniques. It uses a list of grammatical elements and vocabulary generated in step 1 as input. The server executes a clustering algorithm to group similar elements. The output of this operation is aggregated information on commonalities between languages.

[0351] Step 3:

[0352] The server forms a new language structure based on commonalities. The information aggregated in Step 2 is input, and AI technology is used to design the grammar and vocabulary of the unified language. Natural language generation models are utilized for this. As output, an initial model of the new unified language is generated.

[0353] Step 4:

[0354] The device provides an interface that allows users to experience a new unified language. It receives data from the user in text or voice as input and analyzes it in real time using an emotion engine. Based on this analysis, it provides appropriate feedback to the user to facilitate learning. As output, the device displays feedback and advice tailored to the user's emotions.

[0355] Step 5:

[0356] Emotion recognition technology is used to continuously collect user feedback and improve the language. User emotion data and feedback are sent to the server as input. The server analyzes this data and adjusts the integrated language as needed. The output is the improved language model, which is used to enhance the user's communication experience.

[0357] (Application Example 2)

[0358] 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."

[0359] To integrate languages ​​from different cultural backgrounds and enable more natural and smooth international communication, it is necessary to appropriately analyze and integrate diverse information, as well as improve individual user experiences through content suggestions based on the user's emotional state. Furthermore, optimizing the viewing experience using real-time emotional analysis is a challenge that has not been adequately addressed with conventional technologies.

[0360] 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.

[0361] In this invention, the server includes means for collecting diverse natural language information, means for analyzing the collected natural language information and extracting language-specific meanings and grammatical rules, and means for identifying and classifying similarities between different natural languages ​​based on the extracted meanings and grammatical rules. This enables appropriate integration between each language and the suggestion of optimal content according to the user's emotional state.

[0362] "Diverse natural language information" refers to language data composed of text, audio, video, and other formats collected from different cultural spheres and regions.

[0363] "Meaning and grammatical rules" refer to the word definitions, sentence structures, and grammatical rules specific to each natural language.

[0364] "Similarities between different natural languages" is a concept that refers to common elements and characteristics found between different languages.

[0365] An "integrated language" is a language system newly constructed based on elements extracted from diverse natural languages.

[0366] "Emotion recognition technology" is a technology that analyzes a user's facial expressions, tone of voice, and actions to identify their emotional state.

[0367] "Real-time analysis" is a process that performs immediate processing and analysis of data as it is collected.

[0368] "Content suggestion" is the act of selecting the next piece of information or entertainment that should be provided based on the user's interests and emotions.

[0369] The system that realizes this invention has the function of recognizing the emotional state of the user in real time in response to the content they are watching and optimizing the viewing experience.

[0370] The server collects diverse natural language information via the internet and other means, and analyzes the collected data. The analysis uses a natural language processing engine to extract meanings and grammatical rules specific to each language. Next, it identifies similarities between different languages ​​and uses this to construct the vocabulary and grammar of an integrated language. This data is then compiled into an integrated language and provided to the user's terminal.

[0371] The device displays integrated language information and analyzes the user's emotional state in real time using emotion recognition technology. Specifically, it uses devices such as cameras and microphones to detect and analyze emotions from the user's facial expressions and voice. In this process, the emotion recognition technology utilizes a recognition engine (for example, general computer vision or speech analysis software).

[0372] While a user is watching a particular video content, the system constantly monitors their emotional state and suggests the next content to watch based on the analysis results. For example, if a user cries during a moving scene, the system can use that emotion to recommend another work that evokes similar emotions. This process can be initiated with the prompt message, "Please recommend a new movie based on the emotions the user has perceived."

[0373] This allows users' viewing experiences to be optimized according to their individual emotional states, enabling a more personalized content experience.

[0374] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0375] Step 1:

[0376] The server collects diverse natural language information from the internet. Inputs include text, audio, and video data, which are stored in a database. The output is a language dataset ready for analysis.

[0377] Step 2:

[0378] The server analyzes the collected language data using a natural language processing engine. The input is language data in a database, and the AI ​​model extracts language-specific meanings and grammatical rules. The output is the extracted grammatical structure and word-semantic data. In this process, the generative AI model identifies grammatical patterns.

[0379] Step 3:

[0380] The server identifies similarities between different natural languages ​​from the analyzed data. The input consists of grammatical structure and semantic data, and statistical methods are used to determine similarity. The output is a list of similar language pairs. Here, a generative AI model calculates similarity scores.

[0381] Step 4:

[0382] The server constructs the vocabulary and grammar of an integrated language based on the obtained similarity data. The input is information on similar language pairs, and the output is a prototype of the integrated language. Structural analysis and construction techniques are used for data processing.

[0383] Step 5:

[0384] The device uses a camera and microphone to perform real-time analysis to recognize the user's emotional state. Input consists of the user's facial expressions and voice data, while output is an emotional state evaluation score. A software-based emotion recognition engine is used, and its evaluation is formalized through prompt messages.

[0385] Step 6:

[0386] Based on the user's emotional state towards the content they are currently viewing, the device suggests the next content to watch. The input consists of an emotional evaluation score and data on the currently viewed content, while the output is a list of recommended content. A selection algorithm is used for data processing, and a generative AI model is applied.

[0387] This series of steps makes it possible to provide users with a content experience that is individually optimized for them.

[0388] 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.

[0389] 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.

[0390] 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.

[0391] [Third Embodiment]

[0392] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0393] 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.

[0394] 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).

[0395] 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.

[0396] 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.

[0397] 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).

[0398] 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.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] 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.

[0403] 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".

[0404] The system of this invention consists of three main elements: a server, a terminal, and a user. These elements work together to efficiently build a new integrated language.

[0405] First, the server collects diverse natural language information in text, audio, and video formats through the internet and existing databases. This results in a wealth of data from various cultural backgrounds.

[0406] Next, the data collected by the server is input into a generating AI model, which then analyzes the linguistic data. In this analysis process, the unique meanings and grammatical rules of each language are identified and organized into a database. At this point, the AI ​​technology processes a large amount of information and identifies similarities between different languages.

[0407] Subsequently, the server constructs a new unified language based on the identified similarities. A unified vocabulary and grammar are generated based on the identified commonalities. Linguists' expertise is also utilized here, and the new language is designed with practicality in mind.

[0408] The device functions as an interface to the user. It provides users with content and learning materials using an integrated language and tests their understanding. It also includes a function to check the user experience and any problems with the new language through user feedback.

[0409] Specifically, when a user attempts to communicate in the new language, the device displays a guide explaining the vocabulary and grammar of the new language, allowing the user to learn at their own pace. This feedback is then sent to the server and used as data to improve the language.

[0410] In general, through repeated testing and improvement, with servers, terminals, and users each fulfilling their respective roles, a new language can be effectively built to enable accurate communication. This system aims to become internationally widespread and used by many people.

[0411] The following describes the processing flow.

[0412] Step 1:

[0413] The server collects diverse natural language data from the internet and existing databases. The data is collected in text, audio, and video formats. The server automatically aggregates the data using web crawlers and APIs and stores it in a database.

[0414] Step 2:

[0415] The server cleanses the collected data and removes noise. Specifically, this includes formatting text, deleting unnecessary data, transcribing audio data, and extracting audio and text data from video. This prepares the data for analysis.

[0416] Step 3:

[0417] The server feeds the cleansed data into an AI model, which automatically analyzes its meaning and grammatical rules. The AI ​​utilizes existing large-scale language models to analyze common meanings, grammatical patterns, and vocabulary frequencies across various languages.

[0418] Step 4:

[0419] The server identifies similarities between different natural languages ​​based on the analyzed data. This process uses clustering algorithms to identify common vocabulary and grammar by forming clusters of similar words.

[0420] Step 5:

[0421] Based on the similarities identified by the server, a new unified language vocabulary and grammatical rules are created. Linguistic insights are also applied in this process to construct more natural and practical expressions.

[0422] Step 6:

[0423] The device provides users with educational content and dialogue systems based on the new language. Through this tool, users can experience and learn the new language firsthand. The device records user actions and usage and provides feedback to the server.

[0424] Step 7:

[0425] When users attempt to communicate using the new language, the server modifies and improves the language based on feedback received through their devices. Based on the analysis of this feedback, vocabulary is added and grammatical rules are adjusted to improve the language's applicability.

[0426] Step 8:

[0427] The server will begin efforts to promote the improved new language. It will provide a platform for educational institutions and businesses, offering online courses and materials, aiming for widespread adoption.

[0428] (Example 1)

[0429] 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."

[0430] In modern society, the existence of diverse natural languages, each with its own distinct grammatical rules and vocabulary, presents numerous challenges in communication between different languages. Furthermore, translation and understanding between multiple languages ​​require considerable time and resources, hindering efficient international exchange. There is a need to solve these problems and build a new, unified language to facilitate smooth communication and reduce language barriers.

[0431] 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.

[0432] In this invention, the server includes means for collecting diverse natural language data, means for analyzing the collected natural language data and extracting language-specific meanings and grammatical structures, and means for constructing a new integrated language form based on the identified commonalities. This makes it possible to effectively analyze commonalities between different languages, construct a new integrated language, and promote international communication.

[0433] "Diverse natural language data" refers to information such as text, audio, and video that consists of multiple languages ​​rooted in different cultures and regions.

[0434] "Analysis" refers to the process of understanding the meaning and grammatical structure from collected data, breaking down the information, and deriving valuable insights.

[0435] "Language-specific meanings and grammatical structures" refer to the meanings of vocabulary and the structure that indicates the rules for sentence formation that are unique to a particular language.

[0436] "Identifying and classifying commonalities" refers to the process of finding similarities between different languages, organizing them, and categorizing them.

[0437] A "integrated linguistic form" refers to a new language consisting of common vocabulary and grammatical rules, created based on the commonalities of different languages.

[0438] "Evaluating practicality and comprehension" refers to activities that measure how effective the constructed integrated language is in actual communication and how well users can understand it.

[0439] "Collecting user feedback and making improvements" refers to the process of continuously improving a language based on the opinions and experiences of users of an integrated language format.

[0440] "Providing and supporting resources to promote widespread adoption" refers to activities that provide necessary educational materials and technical support to make the developed language widely known.

[0441] This invention is configured as a system for achieving smooth communication between diverse natural languages. Its form is described below.

[0442] The server utilizes the internet and existing information management systems to collect diverse natural language data from around the world. This data includes various formats such as text, audio, and video. The server aggregates this data into a storage system and then analyzes it using generative AI models. Specifically, it employs technologies such as NLTK and spaCy as natural language processing libraries to extract language-specific meanings and grammatical structures from the data. This identifies commonalities between different languages ​​and lays the foundation for building an integrated language.

[0443] The terminal functions as an interface to the user, providing learning materials and content using the unified language. It displays interactive lessons and presents comprehension questions to help users learn the new language. It also directly receives user feedback and sends this information to the server to improve the unified language.

[0444] Users learn a new language using learning materials provided through their device. Guides are displayed as needed, facilitating smooth vocabulary and grammar acquisition. Feedback includes information on what was understood and what was difficult, contributing to an assessment of the language's practical usability.

[0445] One concrete example is a process where a server collects greetings from different languages, such as "hello," "hola," and "konnichiwa," and integrates their meanings. This process aims to identify similarities between languages ​​and construct new, concise, and easy-to-pronounce greetings.

[0446] An example of a prompt for a generative AI model is: "Generate basic greetings for a new unified language based on the following text dataset."

[0447] This system will evolve through collaboration between users, servers, and terminals, continuously improving its unified language to become a valuable tool for everyday communication.

[0448] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0449] Step 1:

[0450] The server collects diverse natural language data via the internet and existing information management systems. Inputs include web pages, audio files, and video content. The server utilizes web crawlers and API interfaces to efficiently retrieve this data. The data is stored in a storage system, serving as a foundation for subsequent processing.

[0451] Step 2:

[0452] The server inputs the collected natural language data into a generative AI model. The input data consists of text, audio, and video information collected in the previous stage. The server uses natural language processing libraries (such as NLTK and spaCy) to tokenize the text data, tag parts of speech, and perform syntactic analysis. The output of this process is information about the grammatical structure and vocabulary specific to each language, which is stored in a database.

[0453] Step 3:

[0454] The server identifies commonalities between different languages ​​based on the analysis results and constructs a new unified language. The input includes grammatical structure and vocabulary information obtained in the previous stage. Using this information, the server employs generative AI models and statistical algorithms to generate a common vocabulary list and grammatical rules. The output obtained in this process is the basic vocabulary and grammatical rules of the new language.

[0455] Step 4:

[0456] The terminal provides users with learning materials and content using the integrated language. The input here is the vocabulary and grammar information of the integrated language built by the server. Based on this, the terminal creates interactive lessons and question-and-answer formatted materials, presenting them in a way that is easy for the user to understand. The output of this process is the user's improved proficiency in the new language.

[0457] Step 5:

[0458] Users access learning materials through their devices and progress through the learning process. User input consists of answers and feedback entered into the device during learning. The device collects this data and sends the correctness of the answers to the server. Output is data representing the user's level of understanding, which is transmitted to the server as feedback and used to improve language skills.

[0459] In this way, the development and widespread adoption of a new unified programming language is achieved through the cooperation of servers, terminals, and users in processing programs.

[0460] (Application Example 1)

[0461] 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."

[0462] There are problems that make it difficult for users with diverse cultural and linguistic backgrounds to communicate in a unified manner. In particular, there is a growing need for accurate and efficient information exchange between groups with different language systems. This invention aims to provide a new integrated language system that overcomes such language barriers and enables smooth communication between multiple languages.

[0463] 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.

[0464] In this invention, the server includes means for collecting diverse natural language information, means for analyzing the collected natural language information and extracting language-specific meanings and grammatical rules, and means for identifying and classifying similarities between different natural languages ​​based on the extracted meanings and grammatical rules. This makes it possible to communicate between different languages ​​using a unified vocabulary and grammar.

[0465] "Diverse natural language information" refers to a collection of languages ​​used in various cultures and regions, including in forms such as text, audio, and video.

[0466] "Language-specific meanings and grammatical rules" refer to the rules that shape the meanings of words and sentence structures that are unique to each natural language.

[0467] "Similarities between different natural languages" refers to elements and patterns that are common to different languages.

[0468] An "integrated language" is a means of communication that has a newly constructed vocabulary and grammar based on the similarities between different natural languages.

[0469] "User learning history" refers to a record of the learning activities a user has undertaken to date, including progress and achievements.

[0470] "Teaching materials" refer to instructional materials and content used by learners to acquire certain knowledge or skills.

[0471] "Feedback" refers to opinions and results regarding user experience and areas for improvement that a system receives from users.

[0472] "Testing understanding of the integrated language through interaction" means that users perform operations and communicate using the integrated language, and the results are evaluated.

[0473] To implement this invention, a system is needed in which three elements—a server, a terminal, and a user—work in conjunction with each other. The server collects diverse natural language information via the internet and inputs this information into a generative AI model. The generative AI model extracts language-specific meanings and grammatical rules from the collected data and identifies similarities between different natural languages. The software used in this process is a platform with AI model analysis capabilities.

[0474] Next, based on the extracted similarities, the server constructs the vocabulary and grammar of the unified language. During this process, a database management system is used to organize and store the constructed unified language. The server also collects user feedback and functions to evaluate the language's usefulness and comprehensibility.

[0475] The device serves as a user interface, providing users with integrated language learning materials. Applications on the device record learning history and provide personalized learning support. This enables users to leverage the integrated language and communicate effectively with people from diverse linguistic backgrounds.

[0476] As a concrete example, consider a user using the integrated language at an international exchange event. Before the event, the user learns the basics of the new integrated language using an application on their device, participates in the event, and puts that knowledge into practice. The application can use prompts such as: "Please tell me some simple phrases I can use at recent events," "I want to see more examples of this grammar rule," and "Please tell me some example sentences using this vocabulary." Through such concrete support, the user can deepen their understanding of the integrated language and communicate smoothly in international settings.

[0477] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0478] Step 1:

[0479] The server collects diverse natural language information via the internet in text, audio, and video formats. This allows for the accumulation of culturally and regionally specific language data in the database. The input information then serves as foundational data for processing in the next step.

[0480] Step 2:

[0481] The server inputs collected natural language information into a generative AI model, which extracts language-specific meanings and grammatical rules. This process involves data analysis, and the extracted meanings and grammar are stored in a database. The output is a dataset representing the unique characteristics of the language.

[0482] Step 3:

[0483] The server uses the data extracted in the previous step to identify similarities between different natural languages. It analyzes the dataset stored in the database to classify similar patterns and rules, and obtains information indicating the commonalities between languages ​​as output.

[0484] Step 4:

[0485] The server constructs the vocabulary and grammar of the unified language based on the obtained similarity information. It generates new vocabulary and grammar that reflect the identified commonalities and registers them in the database. The output is the basic structure of the unified language.

[0486] Step 5:

[0487] The terminal provides the user with learning materials using an integrated language retrieved from the server. In this step, explanations of vocabulary and grammar are displayed as learning content, and interactions are provided to enhance the user's understanding. As output, the user's learning history is updated in real time.

[0488] Step 6:

[0489] Users learn the integrated language through their devices and provide feedback. This feedback, including user experience and problems, is sent back to the server. User opinions are collected as input, and information useful for improving the language is obtained as output.

[0490] Step 7:

[0491] The server dynamically improves the integrated language based on user feedback. New data is re-inputted into the AI ​​model, and the language structure is adapted and improved. As output, the optimized integrated language data becomes available and is redistributed through the terminal.

[0492] 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.

[0493] This invention combines a system that collects diverse natural language information and generates a new integrated language with an emotion engine that recognizes and analyzes user emotions in real time. This system consists of a server, a terminal, and a user, and each element works in coordination.

[0494] First, the server collects diverse natural language information. The collected data is obtained from various cultural regions in text, audio, and video formats. Then, AI technology is used to analyze this language data and extract the meanings and grammatical rules specific to each language.

[0495] Next, the server identifies similarities between different natural languages ​​based on these analysis results and constructs the vocabulary and grammar of the unified language based on these similarities. By adding an emotion engine to this process, the expressions in the unified language can be adapted to the user's emotions using the analyzed emotion data.

[0496] The device provides an interface for users to experience the new unified language. When users use the new language, the device incorporates an emotion engine that recognizes the user's emotional state from text, audio, and video data. For example, when a user writes text, the appropriate emotion for the context is identified and displayed. The unified language is fine-tuned to ensure users receive positive feedback.

[0497] For example, when a user creates a message in the new unified language, the device analyzes the message's content and tone, and if it determines that the user is enjoying it, it offers encouraging messages and additional hints. At this point, the emotion engine monitors changes in emotion and can provide appropriate advice and modifications to improve the user's learning experience.

[0498] By integrating these elements, the system enables more natural and smooth international communication while being mindful of user emotions. Furthermore, through continuous language improvement based on feedback, it provides a user-friendly and effective language learning environment.

[0499] The following describes the processing flow.

[0500] Step 1:

[0501] The server collects diverse natural language information from the internet and existing databases. The information is systematically stored in the database in text, audio, and video formats. This allows for the collection of a wide range of data from different cultural backgrounds.

[0502] Step 2:

[0503] The server collects natural language information, which is then input into a generating AI model for analysis. Through this analysis, meanings and grammatical rules specific to each language are automatically extracted and organized as visualized data.

[0504] Step 3:

[0505] The server identifies similarities between different natural languages ​​based on the analysis results and clusters those with similar linguistic features. This identifies common vocabulary and expressions.

[0506] Step 4:

[0507] The server initiates the process of building the vocabulary and grammar of the unified language. Based on identified similarities, a concise and clear vocabulary and unified grammatical rules are created.

[0508] Step 5:

[0509] An emotion engine built into the device recognizes the user's emotional state from text, voice, and video data. In particular, it analyzes the user's reactions as they use the system in real time and collects emotional information.

[0510] Step 6:

[0511] The device generates feedback when using the integrated language based on the user's emotions. For example, when a user is trying to understand a difficult expression, it displays an encouraging message to support their learning.

[0512] Step 7:

[0513] Users will communicate using a new unified language via their devices. By receiving emotion-based feedback, users will be able to more easily understand their own progress and challenges.

[0514] Step 8:

[0515] The server collects user feedback and improves the integrated language along with sentiment analysis results. This process continuously optimizes the integrated language, improving users' communication capabilities.

[0516] (Example 2)

[0517] 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."

[0518] Barriers to international communication include differences between diverse languages ​​and the inability to obtain appropriate feedback that takes user emotions into consideration. In such situations, smooth intercultural communication is difficult, and the effectiveness of language learning is limited. Therefore, there is a need for a system that integrates diverse linguistic characteristics and provides a new language experience that takes user emotions into account.

[0519] 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.

[0520] In this invention, the server includes means for collecting diverse language data, means for analyzing the collected language data using analysis techniques to identify grammatical elements and vocabulary, and means for identifying and aggregating commonalities between different languages ​​based on the identified grammatical elements and vocabulary. This enables more effective and natural international communication by integrating the characteristics of different languages ​​while considering the user's emotions.

[0521] "Diverse language data" refers to data in written, audio, and video formats collected from different regions and cultural areas.

[0522] "Analysis techniques" refer to techniques used to identify grammatical elements and vocabulary from collected data, and include machine learning and natural language processing methods.

[0523] "Grammar elements and vocabulary" refer to the structure and meaning of words that are unique to each language, and are the elements that constitute the foundation of language.

[0524] "Common ground" refers to similar grammatical and vocabulary features between different languages, which serve as the basis for constructing a new language.

[0525] "Emotion recognition technology" is a technology used to detect and analyze a user's emotional state, and is used to analyze emotional information in linguistic data.

[0526] A "feedback mechanism" is a system that analyzes user responses and uses them to improve language, playing a role in dynamically adjusting the language.

[0527] In an embodiment of this invention, the system consists of a server, a terminal, and a user. The server collects diverse linguistic data and analyzes it using analytical techniques. Here, machine learning models such as BERT and GPT are often used as representative natural language processing techniques. Through this, the server identifies grammatical elements and vocabulary of each language and, based on this, identifies commonalities between different languages. A new language is formed through these identified commonalities.

[0528] Emotion recognition technology is also integrated into the server, enabling analysis of user emotion information. This allows for appropriate language fine-tuning, resulting in a more natural user experience of the new language. Specifically, the server is equipped with high-performance GPUs, and the software utilizes deep learning frameworks such as TensorFlow and PyTorch.

[0529] The terminal is a device that provides users with a new language interface. When a user inputs text or voice, the terminal uses its built-in emotion engine to analyze the emotion in real time and sends the results to a server. The terminal is envisioned to be a multi-functional computer or smartphone, and the aforementioned analysis function will be provided as a dedicated application.

[0530] As a concrete example, when a user begins learning a new language, the device captures the user's initial responses, which are then analyzed by a server. To improve the user's experience, emotion-based feedback is provided, and language expressions are adjusted as needed. This process is carried out in the form of prompts using a generative AI model. For example, the user might input a prompt such as, "Please tell me how to create a self-introduction using the new language while maintaining a positive tone." Through this process, the user can efficiently learn the language and acquire new ways of expression.

[0531] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0532] Step 1:

[0533] The server collects diverse linguistic data. It receives text, audio, and video data from multiple cultural regions as input. To analyze this data, the server runs machine learning algorithms to extract language-specific grammatical elements and vocabulary. This process outputs the elements necessary for the initial construction of a language model.

[0534] Step 2:

[0535] The server identifies commonalities between different languages ​​from language data extracted using analytical techniques. It uses a list of grammatical elements and vocabulary generated in step 1 as input. The server executes a clustering algorithm to group similar elements. The output of this operation is aggregated information on commonalities between languages.

[0536] Step 3:

[0537] The server forms a new language structure based on commonalities. The information aggregated in Step 2 is input, and AI technology is used to design the grammar and vocabulary of the unified language. Natural language generation models are utilized for this. As output, an initial model of the new unified language is generated.

[0538] Step 4:

[0539] The device provides an interface that allows users to experience a new unified language. It receives data from the user in text or voice as input and analyzes it in real time using an emotion engine. Based on this analysis, it provides appropriate feedback to the user to facilitate learning. As output, the device displays feedback and advice tailored to the user's emotions.

[0540] Step 5:

[0541] Emotion recognition technology is used to continuously collect user feedback and improve the language. User emotion data and feedback are sent to the server as input. The server analyzes this data and adjusts the integrated language as needed. The output is the improved language model, which is used to enhance the user's communication experience.

[0542] (Application Example 2)

[0543] 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."

[0544] To integrate languages ​​from different cultural backgrounds and enable more natural and smooth international communication, it is necessary to appropriately analyze and integrate diverse information, as well as improve individual user experiences through content suggestions based on the user's emotional state. Furthermore, optimizing the viewing experience using real-time emotional analysis is a challenge that has not been adequately addressed with conventional technologies.

[0545] 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.

[0546] In this invention, the server includes means for collecting diverse natural language information, means for analyzing the collected natural language information and extracting language-specific meanings and grammatical rules, and means for identifying and classifying similarities between different natural languages ​​based on the extracted meanings and grammatical rules. This enables appropriate integration between each language and the suggestion of optimal content according to the user's emotional state.

[0547] "Diverse natural language information" refers to language data composed of text, audio, video, and other formats collected from different cultural spheres and regions.

[0548] "Meaning and grammatical rules" refer to the word definitions, sentence structures, and grammatical rules specific to each natural language.

[0549] "Similarities between different natural languages" is a concept that refers to common elements and characteristics found between different languages.

[0550] An "integrated language" is a language system newly constructed based on elements extracted from diverse natural languages.

[0551] "Emotion recognition technology" is a technology that analyzes a user's facial expressions, tone of voice, and actions to identify their emotional state.

[0552] "Real-time analysis" is a process that performs immediate processing and analysis of data as it is collected.

[0553] "Content suggestion" is the act of selecting the next piece of information or entertainment that should be provided based on the user's interests and emotions.

[0554] The system that realizes this invention has the function of recognizing the emotional state of the user in real time in response to the content they are watching and optimizing the viewing experience.

[0555] The server collects diverse natural language information via the internet and other means, and analyzes the collected data. The analysis uses a natural language processing engine to extract meanings and grammatical rules specific to each language. Next, it identifies similarities between different languages ​​and uses this to construct the vocabulary and grammar of an integrated language. This data is then compiled into an integrated language and provided to the user's terminal.

[0556] The device displays integrated language information and analyzes the user's emotional state in real time using emotion recognition technology. Specifically, it uses devices such as cameras and microphones to detect and analyze emotions from the user's facial expressions and voice. In this process, the emotion recognition technology utilizes a recognition engine (for example, general computer vision or speech analysis software).

[0557] While a user is watching a particular video content, the system constantly monitors their emotional state and suggests the next content to watch based on the analysis results. For example, if a user cries during a moving scene, the system can use that emotion to recommend another work that evokes similar emotions. This process can be initiated with the prompt message, "Please recommend a new movie based on the emotions the user has perceived."

[0558] This allows users' viewing experiences to be optimized according to their individual emotional states, enabling a more personalized content experience.

[0559] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0560] Step 1:

[0561] The server collects diverse natural language information from the internet. Inputs include text, audio, and video data, which are stored in a database. The output is a language dataset ready for analysis.

[0562] Step 2:

[0563] The server analyzes the collected language data using a natural language processing engine. The input is language data in a database, and the AI ​​model extracts language-specific meanings and grammatical rules. The output is the extracted grammatical structure and word-semantic data. In this process, the generative AI model identifies grammatical patterns.

[0564] Step 3:

[0565] The server identifies similarities between different natural languages ​​from the analyzed data. The input consists of grammatical structure and semantic data, and statistical methods are used to determine similarity. The output is a list of similar language pairs. Here, a generative AI model calculates similarity scores.

[0566] Step 4:

[0567] The server constructs the vocabulary and grammar of an integrated language based on the obtained similarity data. The input is information on similar language pairs, and the output is a prototype of the integrated language. Structural analysis and construction techniques are used for data processing.

[0568] Step 5:

[0569] The device uses a camera and microphone to perform real-time analysis to recognize the user's emotional state. Input consists of the user's facial expressions and voice data, while output is an emotional state evaluation score. A software-based emotion recognition engine is used, and its evaluation is formalized through prompt messages.

[0570] Step 6:

[0571] Based on the user's emotional state towards the content they are currently viewing, the device suggests the next content to watch. The input consists of an emotional evaluation score and data on the currently viewed content, while the output is a list of recommended content. A selection algorithm is used for data processing, and a generative AI model is applied.

[0572] This series of steps makes it possible to provide users with a content experience that is individually optimized for them.

[0573] 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.

[0574] 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.

[0575] 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.

[0576] [Fourth Embodiment]

[0577] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0578] 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.

[0579] 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).

[0580] 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.

[0581] 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.

[0582] 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).

[0583] 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.

[0584] 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.

[0585] 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.

[0586] 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.

[0587] 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.

[0588] 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.

[0589] 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".

[0590] The system of this invention consists of three main elements: a server, a terminal, and a user. These elements work together to efficiently build a new integrated language.

[0591] First, the server collects diverse natural language information in text, audio, and video formats through the internet and existing databases. This results in a wealth of data from various cultural backgrounds.

[0592] Next, the data collected by the server is input into a generating AI model, which then analyzes the linguistic data. In this analysis process, the unique meanings and grammatical rules of each language are identified and organized into a database. At this point, the AI ​​technology processes a large amount of information and identifies similarities between different languages.

[0593] Subsequently, the server constructs a new unified language based on the identified similarities. A unified vocabulary and grammar are generated based on the identified commonalities. Linguists' expertise is also utilized here, and the new language is designed with practicality in mind.

[0594] The device functions as an interface to the user. It provides users with content and learning materials using an integrated language and tests their understanding. It also includes a function to check the user experience and any problems with the new language through user feedback.

[0595] Specifically, when a user attempts to communicate in the new language, the device displays a guide explaining the vocabulary and grammar of the new language, allowing the user to learn at their own pace. This feedback is then sent to the server and used as data to improve the language.

[0596] In general, through repeated testing and improvement, with servers, terminals, and users each fulfilling their respective roles, a new language can be effectively built to enable accurate communication. This system aims to become internationally widespread and used by many people.

[0597] The following describes the processing flow.

[0598] Step 1:

[0599] The server collects diverse natural language data from the internet and existing databases. The data is collected in text, audio, and video formats. The server automatically aggregates the data using web crawlers and APIs and stores it in a database.

[0600] Step 2:

[0601] The server cleanses the collected data and removes noise. Specifically, this includes formatting text, deleting unnecessary data, transcribing audio data, and extracting audio and text data from video. This prepares the data for analysis.

[0602] Step 3:

[0603] The server feeds the cleansed data into an AI model, which automatically analyzes its meaning and grammatical rules. The AI ​​utilizes existing large-scale language models to analyze common meanings, grammatical patterns, and vocabulary frequencies across various languages.

[0604] Step 4:

[0605] The server identifies similarities between different natural languages ​​based on the analyzed data. This process uses clustering algorithms to identify common vocabulary and grammar by forming clusters of similar words.

[0606] Step 5:

[0607] Based on the similarities identified by the server, a new unified language vocabulary and grammatical rules are created. Linguistic insights are also applied in this process to construct more natural and practical expressions.

[0608] Step 6:

[0609] The device provides users with educational content and dialogue systems based on the new language. Through this tool, users can experience and learn the new language firsthand. The device records user actions and usage and provides feedback to the server.

[0610] Step 7:

[0611] When users attempt to communicate using the new language, the server modifies and improves the language based on feedback received through their devices. Based on the analysis of this feedback, vocabulary is added and grammatical rules are adjusted to improve the language's applicability.

[0612] Step 8:

[0613] The server will begin efforts to promote the improved new language. It will provide a platform for educational institutions and businesses, offering online courses and materials, aiming for widespread adoption.

[0614] (Example 1)

[0615] 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".

[0616] In modern society, the existence of diverse natural languages, each with its own distinct grammatical rules and vocabulary, presents numerous challenges in communication between different languages. Furthermore, translation and understanding between multiple languages ​​require considerable time and resources, hindering efficient international exchange. There is a need to solve these problems and build a new, unified language to facilitate smooth communication and reduce language barriers.

[0617] 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.

[0618] In this invention, the server includes means for collecting diverse natural language data, means for analyzing the collected natural language data and extracting language-specific meanings and grammatical structures, and means for constructing a new integrated language form based on the identified commonalities. This makes it possible to effectively analyze commonalities between different languages, construct a new integrated language, and promote international communication.

[0619] "Diverse natural language data" refers to information such as text, audio, and video that consists of multiple languages ​​rooted in different cultures and regions.

[0620] "Analysis" refers to the process of understanding the meaning and grammatical structure from collected data, breaking down the information, and deriving valuable insights.

[0621] "Language-specific meanings and grammatical structures" refer to the meanings of vocabulary and the structure that indicates the rules for sentence formation that are unique to a particular language.

[0622] "Identifying and classifying commonalities" refers to the process of finding similarities between different languages, organizing them, and categorizing them.

[0623] A "integrated linguistic form" refers to a new language consisting of common vocabulary and grammatical rules, created based on the commonalities of different languages.

[0624] "Evaluating practicality and comprehension" refers to activities that measure how effective the constructed integrated language is in actual communication and how well users can understand it.

[0625] "Collecting user feedback and making improvements" refers to the process of continuously improving a language based on the opinions and experiences of users of an integrated language format.

[0626] "Providing and supporting resources to promote widespread adoption" refers to activities that provide necessary educational materials and technical support to make the developed language widely known.

[0627] This invention is configured as a system for achieving smooth communication between diverse natural languages. Its form is described below.

[0628] The server utilizes the internet and existing information management systems to collect diverse natural language data from around the world. This data includes various formats such as text, audio, and video. The server aggregates this data into a storage system and then analyzes it using generative AI models. Specifically, it employs technologies such as NLTK and spaCy as natural language processing libraries to extract language-specific meanings and grammatical structures from the data. This identifies commonalities between different languages ​​and lays the foundation for building an integrated language.

[0629] The terminal functions as an interface to the user, providing learning materials and content using the unified language. It displays interactive lessons and presents comprehension questions to help users learn the new language. It also directly receives user feedback and sends this information to the server to improve the unified language.

[0630] Users learn a new language using learning materials provided through their device. Guides are displayed as needed, facilitating smooth vocabulary and grammar acquisition. Feedback includes information on what was understood and what was difficult, contributing to an assessment of the language's practical usability.

[0631] One concrete example is a process where a server collects greetings from different languages, such as "hello," "hola," and "konnichiwa," and integrates their meanings. This process aims to identify similarities between languages ​​and construct new, concise, and easy-to-pronounce greetings.

[0632] An example of a prompt for a generative AI model is: "Generate basic greetings for a new unified language based on the following text dataset."

[0633] This system will evolve through collaboration between users, servers, and terminals, continuously improving its unified language to become a valuable tool for everyday communication.

[0634] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0635] Step 1:

[0636] The server collects diverse natural language data via the internet and existing information management systems. Inputs include web pages, audio files, and video content. The server utilizes web crawlers and API interfaces to efficiently retrieve this data. The data is stored in a storage system, serving as a foundation for subsequent processing.

[0637] Step 2:

[0638] The server inputs the collected natural language data into a generative AI model. The input data consists of text, audio, and video information collected in the previous stage. The server uses natural language processing libraries (such as NLTK and spaCy) to tokenize the text data, tag parts of speech, and perform syntactic analysis. The output of this process is information about the grammatical structure and vocabulary specific to each language, which is stored in a database.

[0639] Step 3:

[0640] The server identifies commonalities between different languages ​​based on the analysis results and constructs a new unified language. The input includes grammatical structure and vocabulary information obtained in the previous stage. Using this information, the server employs generative AI models and statistical algorithms to generate a common vocabulary list and grammatical rules. The output obtained in this process is the basic vocabulary and grammatical rules of the new language.

[0641] Step 4:

[0642] The terminal provides users with learning materials and content using the integrated language. The input here is the vocabulary and grammar information of the integrated language built by the server. Based on this, the terminal creates interactive lessons and question-and-answer formatted materials, presenting them in a way that is easy for the user to understand. The output of this process is the user's improved proficiency in the new language.

[0643] Step 5:

[0644] Users access learning materials through their devices and progress through the learning process. User input consists of answers and feedback entered into the device during learning. The device collects this data and sends the correctness of the answers to the server. Output is data representing the user's level of understanding, which is transmitted to the server as feedback and used to improve language skills.

[0645] In this way, the development and widespread adoption of a new unified programming language is achieved through the cooperation of servers, terminals, and users in processing programs.

[0646] (Application Example 1)

[0647] 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".

[0648] There are problems that make it difficult for users with diverse cultural and linguistic backgrounds to communicate in a unified manner. In particular, there is a growing need for accurate and efficient information exchange between groups with different language systems. This invention aims to provide a new integrated language system that overcomes such language barriers and enables smooth communication between multiple languages.

[0649] 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.

[0650] In this invention, the server includes means for collecting diverse natural language information, means for analyzing the collected natural language information and extracting language-specific meanings and grammatical rules, and means for identifying and classifying similarities between different natural languages ​​based on the extracted meanings and grammatical rules. This makes it possible to communicate between different languages ​​using a unified vocabulary and grammar.

[0651] "Diverse natural language information" refers to a collection of languages ​​used in various cultures and regions, including in forms such as text, audio, and video.

[0652] "Language-specific meanings and grammatical rules" refer to the rules that shape the meanings of words and sentence structures that are unique to each natural language.

[0653] "Similarities between different natural languages" refers to elements and patterns that are common to different languages.

[0654] An "integrated language" is a means of communication that has a newly constructed vocabulary and grammar based on the similarities between different natural languages.

[0655] "User learning history" refers to a record of the learning activities a user has undertaken to date, including progress and achievements.

[0656] "Teaching materials" refer to instructional materials and content used by learners to acquire certain knowledge or skills.

[0657] "Feedback" refers to opinions and results regarding user experience and areas for improvement that a system receives from users.

[0658] "Testing understanding of the integrated language through interaction" means that users perform operations and communicate using the integrated language, and the results are evaluated.

[0659] To implement this invention, a system is needed in which three elements—a server, a terminal, and a user—work in conjunction with each other. The server collects diverse natural language information via the internet and inputs this information into a generative AI model. The generative AI model extracts language-specific meanings and grammatical rules from the collected data and identifies similarities between different natural languages. The software used in this process is a platform with AI model analysis capabilities.

[0660] Next, based on the extracted similarities, the server constructs the vocabulary and grammar of the unified language. During this process, a database management system is used to organize and store the constructed unified language. The server also collects user feedback and functions to evaluate the language's usefulness and comprehensibility.

[0661] The device serves as a user interface, providing users with integrated language learning materials. Applications on the device record learning history and provide personalized learning support. This enables users to leverage the integrated language and communicate effectively with people from diverse linguistic backgrounds.

[0662] As a concrete example, consider a user using the integrated language at an international exchange event. Before the event, the user learns the basics of the new integrated language using an application on their device, participates in the event, and puts that knowledge into practice. The application can use prompts such as: "Please tell me some simple phrases I can use at recent events," "I want to see more examples of this grammar rule," and "Please tell me some example sentences using this vocabulary." Through such concrete support, the user can deepen their understanding of the integrated language and communicate smoothly in international settings.

[0663] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0664] Step 1:

[0665] The server collects diverse natural language information via the internet in text, audio, and video formats. This allows for the accumulation of culturally and regionally specific language data in the database. The input information then serves as foundational data for processing in the next step.

[0666] Step 2:

[0667] The server inputs collected natural language information into a generative AI model, which extracts language-specific meanings and grammatical rules. This process involves data analysis, and the extracted meanings and grammar are stored in a database. The output is a dataset representing the unique characteristics of the language.

[0668] Step 3:

[0669] The server uses the data extracted in the previous step to identify similarities between different natural languages. It analyzes the dataset stored in the database to classify similar patterns and rules, and obtains information indicating the commonalities between languages ​​as output.

[0670] Step 4:

[0671] The server constructs the vocabulary and grammar of the unified language based on the obtained similarity information. It generates new vocabulary and grammar that reflect the identified commonalities and registers them in the database. The output is the basic structure of the unified language.

[0672] Step 5:

[0673] The terminal provides the user with learning materials using an integrated language retrieved from the server. In this step, explanations of vocabulary and grammar are displayed as learning content, and interactions are provided to enhance the user's understanding. As output, the user's learning history is updated in real time.

[0674] Step 6:

[0675] Users learn the integrated language through their devices and provide feedback. This feedback, including user experience and problems, is sent back to the server. User opinions are collected as input, and information useful for improving the language is obtained as output.

[0676] Step 7:

[0677] The server dynamically improves the integrated language based on user feedback. New data is re-inputted into the AI ​​model, and the language structure is adapted and improved. As output, the optimized integrated language data becomes available and is redistributed through the terminal.

[0678] 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.

[0679] This invention combines a system that collects diverse natural language information and generates a new integrated language with an emotion engine that recognizes and analyzes user emotions in real time. This system consists of a server, a terminal, and a user, and each element works in coordination.

[0680] First, the server collects diverse natural language information. The collected data is obtained from various cultural regions in text, audio, and video formats. Then, AI technology is used to analyze this language data and extract the meanings and grammatical rules specific to each language.

[0681] Next, the server identifies similarities between different natural languages ​​based on these analysis results and constructs the vocabulary and grammar of the unified language based on these similarities. By adding an emotion engine to this process, the expressions in the unified language can be adapted to the user's emotions using the analyzed emotion data.

[0682] The device provides an interface for users to experience the new unified language. When users use the new language, the device incorporates an emotion engine that recognizes the user's emotional state from text, audio, and video data. For example, when a user writes text, the appropriate emotion for the context is identified and displayed. The unified language is fine-tuned to ensure users receive positive feedback.

[0683] For example, when a user creates a message in the new unified language, the device analyzes the message's content and tone, and if it determines that the user is enjoying it, it offers encouraging messages and additional hints. At this point, the emotion engine monitors changes in emotion and can provide appropriate advice and modifications to improve the user's learning experience.

[0684] By integrating these elements, the system enables more natural and smooth international communication while being mindful of user emotions. Furthermore, through continuous language improvement based on feedback, it provides a user-friendly and effective language learning environment.

[0685] The following describes the processing flow.

[0686] Step 1:

[0687] The server collects diverse natural language information from the internet and existing databases. The information is systematically stored in the database in text, audio, and video formats. This allows for the collection of a wide range of data from different cultural backgrounds.

[0688] Step 2:

[0689] The server collects natural language information, which is then input into a generating AI model for analysis. Through this analysis, meanings and grammatical rules specific to each language are automatically extracted and organized as visualized data.

[0690] Step 3:

[0691] The server identifies similarities between different natural languages ​​based on the analysis results and clusters those with similar linguistic features. This identifies common vocabulary and expressions.

[0692] Step 4:

[0693] The server initiates the process of building the vocabulary and grammar of the unified language. Based on identified similarities, a concise and clear vocabulary and unified grammatical rules are created.

[0694] Step 5:

[0695] An emotion engine built into the device recognizes the user's emotional state from text, voice, and video data. In particular, it analyzes the user's reactions as they use the system in real time and collects emotional information.

[0696] Step 6:

[0697] The device generates feedback when using the integrated language based on the user's emotions. For example, when a user is trying to understand a difficult expression, it displays an encouraging message to support their learning.

[0698] Step 7:

[0699] Users will communicate using a new unified language via their devices. By receiving emotion-based feedback, users will be able to more easily understand their own progress and challenges.

[0700] Step 8:

[0701] The server collects user feedback and improves the integrated language along with sentiment analysis results. This process continuously optimizes the integrated language, improving users' communication capabilities.

[0702] (Example 2)

[0703] 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".

[0704] Barriers to international communication include differences between diverse languages ​​and the inability to obtain appropriate feedback that takes user emotions into consideration. In such situations, smooth intercultural communication is difficult, and the effectiveness of language learning is limited. Therefore, there is a need for a system that integrates diverse linguistic characteristics and provides a new language experience that takes user emotions into account.

[0705] 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.

[0706] In this invention, the server includes means for collecting diverse language data, means for analyzing the collected language data using analysis techniques to identify grammatical elements and vocabulary, and means for identifying and aggregating commonalities between different languages ​​based on the identified grammatical elements and vocabulary. This enables more effective and natural international communication by integrating the characteristics of different languages ​​while considering the user's emotions.

[0707] "Diverse language data" refers to data in written, audio, and video formats collected from different regions and cultural areas.

[0708] "Analysis techniques" refer to techniques used to identify grammatical elements and vocabulary from collected data, and include machine learning and natural language processing methods.

[0709] "Grammar elements and vocabulary" refer to the structure and meaning of words that are unique to each language, and are the elements that constitute the foundation of language.

[0710] "Common ground" refers to similar grammatical and vocabulary features between different languages, which serve as the basis for constructing a new language.

[0711] "Emotion recognition technology" is a technology used to detect and analyze a user's emotional state, and is used to analyze emotional information in linguistic data.

[0712] A "feedback mechanism" is a system that analyzes user responses and uses them to improve language, playing a role in dynamically adjusting the language.

[0713] In an embodiment of this invention, the system consists of a server, a terminal, and a user. The server collects diverse linguistic data and analyzes it using analytical techniques. Here, machine learning models such as BERT and GPT are often used as representative natural language processing techniques. Through this, the server identifies grammatical elements and vocabulary of each language and, based on this, identifies commonalities between different languages. A new language is formed through these identified commonalities.

[0714] Emotion recognition technology is also integrated into the server, enabling analysis of user emotion information. This allows for appropriate language fine-tuning, resulting in a more natural user experience of the new language. Specifically, the server is equipped with high-performance GPUs, and the software utilizes deep learning frameworks such as TensorFlow and PyTorch.

[0715] The terminal is a device that provides users with a new language interface. When a user inputs text or voice, the terminal uses its built-in emotion engine to analyze the emotion in real time and sends the results to a server. The terminal is envisioned to be a multi-functional computer or smartphone, and the aforementioned analysis function will be provided as a dedicated application.

[0716] As a concrete example, when a user begins learning a new language, the device captures the user's initial responses, which are then analyzed by a server. To improve the user's experience, emotion-based feedback is provided, and language expressions are adjusted as needed. This process is carried out in the form of prompts using a generative AI model. For example, the user might input a prompt such as, "Please tell me how to create a self-introduction using the new language while maintaining a positive tone." Through this process, the user can efficiently learn the language and acquire new ways of expression.

[0717] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0718] Step 1:

[0719] The server collects diverse linguistic data. It receives text, audio, and video data from multiple cultural regions as input. To analyze this data, the server runs machine learning algorithms to extract language-specific grammatical elements and vocabulary. This process outputs the elements necessary for the initial construction of a language model.

[0720] Step 2:

[0721] The server identifies commonalities between different languages ​​from language data extracted using analytical techniques. It uses a list of grammatical elements and vocabulary generated in step 1 as input. The server executes a clustering algorithm to group similar elements. The output of this operation is aggregated information on commonalities between languages.

[0722] Step 3:

[0723] The server forms a new language structure based on commonalities. The information aggregated in Step 2 is input, and AI technology is used to design the grammar and vocabulary of the unified language. Natural language generation models are utilized for this. As output, an initial model of the new unified language is generated.

[0724] Step 4:

[0725] The device provides an interface that allows users to experience a new unified language. It receives data from the user in text or voice as input and analyzes it in real time using an emotion engine. Based on this analysis, it provides appropriate feedback to the user to facilitate learning. As output, the device displays feedback and advice tailored to the user's emotions.

[0726] Step 5:

[0727] Emotion recognition technology is used to continuously collect user feedback and improve the language. User emotion data and feedback are sent to the server as input. The server analyzes this data and adjusts the integrated language as needed. The output is the improved language model, which is used to enhance the user's communication experience.

[0728] (Application Example 2)

[0729] 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".

[0730] To integrate languages ​​from different cultural backgrounds and enable more natural and smooth international communication, it is necessary to appropriately analyze and integrate diverse information, as well as improve individual user experiences through content suggestions based on the user's emotional state. Furthermore, optimizing the viewing experience using real-time emotional analysis is a challenge that has not been adequately addressed with conventional technologies.

[0731] 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.

[0732] In this invention, the server includes means for collecting diverse natural language information, means for analyzing the collected natural language information and extracting language-specific meanings and grammatical rules, and means for identifying and classifying similarities between different natural languages ​​based on the extracted meanings and grammatical rules. This enables appropriate integration between each language and the suggestion of optimal content according to the user's emotional state.

[0733] "Diverse natural language information" refers to language data composed of text, audio, video, and other formats collected from different cultural spheres and regions.

[0734] "Meaning and grammatical rules" refer to the word definitions, sentence structures, and grammatical rules specific to each natural language.

[0735] "Similarities between different natural languages" is a concept that refers to common elements and characteristics found between different languages.

[0736] An "integrated language" is a language system newly constructed based on elements extracted from diverse natural languages.

[0737] "Emotion recognition technology" is a technology that analyzes a user's facial expressions, tone of voice, and actions to identify their emotional state.

[0738] "Real-time analysis" is a process that performs immediate processing and analysis of data as it is collected.

[0739] "Content suggestion" is the act of selecting the next piece of information or entertainment that should be provided based on the user's interests and emotions.

[0740] The system that realizes this invention has the function of recognizing the emotional state of the user in real time in response to the content they are watching and optimizing the viewing experience.

[0741] The server collects diverse natural language information via the internet and other means, and analyzes the collected data. The analysis uses a natural language processing engine to extract meanings and grammatical rules specific to each language. Next, it identifies similarities between different languages ​​and uses this to construct the vocabulary and grammar of an integrated language. This data is then compiled into an integrated language and provided to the user's terminal.

[0742] The device displays integrated language information and analyzes the user's emotional state in real time using emotion recognition technology. Specifically, it uses devices such as cameras and microphones to detect and analyze emotions from the user's facial expressions and voice. In this process, the emotion recognition technology utilizes a recognition engine (for example, general computer vision or speech analysis software).

[0743] While a user is watching a particular video content, the system constantly monitors their emotional state and suggests the next content to watch based on the analysis results. For example, if a user cries during a moving scene, the system can use that emotion to recommend another work that evokes similar emotions. This process can be initiated with the prompt message, "Please recommend a new movie based on the emotions the user has perceived."

[0744] This allows users' viewing experiences to be optimized according to their individual emotional states, enabling a more personalized content experience.

[0745] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0746] Step 1:

[0747] The server collects diverse natural language information from the internet. Inputs include text, audio, and video data, which are stored in a database. The output is a language dataset ready for analysis.

[0748] Step 2:

[0749] The server analyzes the collected language data using a natural language processing engine. The input is language data in a database, and the AI ​​model extracts language-specific meanings and grammatical rules. The output is the extracted grammatical structure and word-semantic data. In this process, the generative AI model identifies grammatical patterns.

[0750] Step 3:

[0751] The server identifies similarities between different natural languages ​​from the analyzed data. The input consists of grammatical structure and semantic data, and statistical methods are used to determine similarity. The output is a list of similar language pairs. Here, a generative AI model calculates similarity scores.

[0752] Step 4:

[0753] The server constructs the vocabulary and grammar of an integrated language based on the obtained similarity data. The input is information on similar language pairs, and the output is a prototype of the integrated language. Structural analysis and construction techniques are used for data processing.

[0754] Step 5:

[0755] The device uses a camera and microphone to perform real-time analysis to recognize the user's emotional state. Input consists of the user's facial expressions and voice data, while output is an emotional state evaluation score. A software-based emotion recognition engine is used, and its evaluation is formalized through prompt messages.

[0756] Step 6:

[0757] Based on the user's emotional state towards the content they are currently viewing, the device suggests the next content to watch. The input consists of an emotional evaluation score and data on the currently viewed content, while the output is a list of recommended content. A selection algorithm is used for data processing, and a generative AI model is applied.

[0758] This series of steps makes it possible to provide users with a content experience that is individually optimized for them.

[0759] 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.

[0760] 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.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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."

[0768] 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.

[0769] 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.

[0770] 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.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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 as being incorporated by reference.

[0780] The following is further disclosed regarding the embodiments described above.

[0781] (Claim 1)

[0782] Means for collecting diverse natural language information,

[0783] A means of analyzing collected natural language information and extracting language-specific meanings and grammatical rules,

[0784] A means for identifying and classifying similarities between different natural languages ​​based on extracted meanings and grammatical rules,

[0785] A means of constructing the vocabulary and grammar of an integrated language based on identified similarities,

[0786] A means of evaluating the usefulness and comprehension of the integrated language and improving it based on feedback,

[0787] Means for distributing and supporting the unified language in order to promote its widespread use,

[0788] A system that includes this.

[0789] (Claim 2)

[0790] The system according to claim 1, wherein the collected natural language information includes text, audio, and video formats.

[0791] (Claim 3)

[0792] The system according to claim 1, which dynamically improves the construction of natural language based on the aforementioned feedback and has a series of processes including user interaction.

[0793] "Example 1"

[0794] (Claim 1)

[0795] A means of collecting diverse natural language data,

[0796] A means of analyzing collected natural language data and extracting language-specific meanings and grammatical structures,

[0797] A means of identifying and classifying commonalities between different natural languages ​​based on extracted meanings and grammatical structures,

[0798] A means of constructing a new integrated linguistic form based on identified commonalities,

[0799] A means of evaluating the practicality and comprehensibility of integrated language formats, collecting user feedback, and making improvements.

[0800] Means for providing and supporting the dissemination of integrated language formats,

[0801] An information processing system that includes this.

[0802] (Claim 2)

[0803] The information processing system according to claim 1, wherein the collected natural language data includes symbols, sound, and image data.

[0804] (Claim 3)

[0805] The information processing system according to claim 1, which dynamically improves the construction of an integrated language format based on the aforementioned feedback and has a processing process that includes user interaction.

[0806] "Application Example 1"

[0807] (Claim 1)

[0808] Means for collecting diverse natural language information,

[0809] A means of analyzing collected natural language information and extracting language-specific meanings and grammatical rules,

[0810] A means for identifying and classifying similarities between different natural languages ​​based on extracted meanings and grammatical rules,

[0811] A means of constructing the vocabulary and grammar of an integrated language based on identified similarities,

[0812] A means of evaluating the usefulness and comprehension of the integrated language and improving it based on feedback,

[0813] Means for distributing and supporting the unified language in order to promote its widespread use,

[0814] A means of providing learning materials that analyze the user's learning history and support their learning,

[0815] A means to dynamically improve the language structure based on user feedback,

[0816] A system that includes this.

[0817] (Claim 2)

[0818] The system according to claim 1, wherein the collected natural language information includes text, audio, and video formats.

[0819] (Claim 3)

[0820] The system according to claim 1, comprising a process for testing the level of understanding of the integrated language through user interaction and providing feedback based on the results.

[0821] "Example 2 of combining an emotion engine"

[0822] (Claim 1)

[0823] Means for collecting diverse linguistic data,

[0824] A means of analyzing language data collected using analytical techniques to identify grammatical elements and vocabulary,

[0825] A means of identifying and aggregating commonalities between different languages ​​based on identified grammatical elements and vocabulary,

[0826] A means of forming a new language structure based on commonalities,

[0827] A means of acquiring user emotional information using emotion recognition technology and reflecting it in a new language,

[0828] A means having a feedback mechanism that analyzes user responses and improves language,

[0829] Means to promote and support the use of new languages,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] The system according to claim 1, wherein the collected language data includes text, audio, and video formats.

[0833] (Claim 3)

[0834] The system according to claim 1, which dynamically improves the language structure based on the aforementioned feedback and has a process that includes user interaction accompanied by emotion recognition.

[0835] "Application example 2 when combining with an emotional engine"

[0836] (Claim 1)

[0837] Means for collecting diverse natural language information,

[0838] A means of analyzing collected natural language information and extracting language-specific meanings and grammatical rules,

[0839] A means for identifying and classifying similarities between different natural languages ​​based on extracted meanings and grammatical rules,

[0840] A means of constructing the vocabulary and grammar of an integrated language based on identified similarities,

[0841] A means of evaluating the usefulness and comprehension of the integrated language and improving it based on feedback,

[0842] Means for distributing and supporting the unified language in order to promote its widespread use,

[0843] A means of analyzing a user's emotional state in real time based on emotion recognition technology and suggesting content accordingly,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, wherein the collected natural language information includes text, audio, and video formats, and has a function to analyze emotional data such as the user's facial expressions.

[0847] (Claim 3)

[0848] The system according to claim 1, which is a process for dynamically improving the construction of natural language based on the aforementioned feedback, and comprises a series of processes including user interaction and emotional analysis. [Explanation of symbols]

[0849] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting diverse natural language information, A means of analyzing collected natural language information and extracting language-specific meanings and grammatical rules, A means for identifying and classifying similarities between different natural languages ​​based on extracted meanings and grammatical rules, A means of constructing the vocabulary and grammar of an integrated language based on identified similarities, A means of evaluating the usefulness and comprehension of the integrated language and improving it based on feedback, Means for distributing and supporting the unified language in order to promote its widespread use, A system that includes this.

2. The system according to claim 1, wherein the collected natural language information includes text, audio, and video formats.

3. The system according to claim 1, which dynamically improves the construction of natural language based on the aforementioned feedback and has a series of processes including user interaction.

Images