System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting global language data; means for generating a natural language processing model for analyzing the collected language data; means for grouping words or phrases having a common meaning or nuance from the analyzed data; means for creating a new language grammar and vocabulary based on the analysis result and the grouped information; means for providing the newly created language to a user and collecting feedback; and means for improving the new language based on the collected feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Currently, conveying accurate meanings and nuances between different languages ​​is difficult. Nuances are often lost when translating unique expressions rooted in cultural and historical backgrounds and customs. This can also lead to misunderstandings and communication loss. This problem is serious in international communication and business, and a solution is needed. This invention aims to solve these issues by developing a new language whose meanings and nuances can be shared and understood worldwide. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes: means for collecting language data from around the world; means for generating a natural language processing model for analyzing the collected language data; means for grouping words and phrases with common meanings and nuances from the analyzed data; means for creating a grammar and vocabulary for a new language based on the analysis results and the grouped information; means for providing the newly created language to users and collecting feedback; and means for improving the new language based on the collected feedback. Specifically, all processes of collecting, analyzing, and grouping language data, creating the grammar and vocabulary, and collecting and improving the feedback are automated. Furthermore, expert feedback is incorporated during the grammar and vocabulary creation stage to take into account specific cultural backgrounds and differences in nuance. This enables the development of a new language that can be commonly understood around the world.

[0006] "Linguistic Data" refers to words, phrases, grammar, and text information collected from different languages ​​around the world.

[0007] A "natural language processing model" refers to an algorithm that uses machine learning technology to analyze and understand sentences and words and extract meaning and nuance.

[0008] "Analysis" refers to the process of examining collected linguistic data in detail to identify and classify meanings, usage, grammatical structures, and nuances.

[0009] "Grouping" refers to classifying words or phrases with common meanings or nuances from analyzed data into a single category.

[0010] "Grammar" refers to the system that defines the structure and rules of a language and the conjugation of words based on them.

[0011] "Vocabulary" refers to the set of words and phrases used in a particular language.

[0012] "Feedback" refers to information and opinions from users about their experience with the product and areas for improvement.

[0013] "Refinement" refers to the process of making adjustments and improvements to a system or language based on collected feedback. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, 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), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a 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.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0028] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] This invention is a system for generating a new language with common meanings and nuances by collecting and analyzing language data from around the world. The system is primarily composed of a server, terminals, and users. The program processing of the system is explained in detail below.

[0036] Program processing

[0037] The server first collects language data from around the world via the internet and existing databases, such as Wikipedia articles, Google® Books, and academic paper databases, and then integrates it into a single large dataset, including text, grammar information, and translation materials.

[0038] The collected data is then analyzed by a server using a generative AI model, such as machine learning techniques like BERT or GPT-4 (registered trademark). The generative AI model performs detailed analysis of the meaning, usage, grammar, and nuances of words in each language. The results of this analysis are stored in a database for use in later processes.

[0039] Next, the generative AI model uses the analysis results to group words and phrases that share common meanings and nuances. In this step, they are classified into categories such as "greetings," "thanks," and "honorifics." The server then performs these groupings and stores the related information in a database.

[0040] The user (a linguistics expert) then reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. This additional information is sent to the server, which updates the database. For example, a user might note that the Japanese greeting "konnichiwa" (hello) is widely used and not limited to a specific time of day.

[0041] Based on the grouped information, the user (linguist) designs the grammar and vocabulary of the new language, taking into account definitions of parts of speech, sentence structure, verb conjugation rules, etc. The user documents the grammar rules and uploads them to the server.

[0042] The generated grammar and vocabulary are then implemented by the server. For example, a common greeting, "Helkona," is created for the new language. Based on this, dictionaries and learning manuals for the new language are created by users (linguistic experts) and uploaded digitally to the server.

[0043] This new language is provided to users via their devices. Users attempt to communicate in the new language, and the results and feedback are collected via the devices. The collected feedback is analyzed by the server, and generative AI models are used to improve the system and the language.

[0044] Specific examples

[0045] Consider the following scenario as a concrete example. The server collects and analyzes the English and Japanese versions of "Thank you," identifying differences in cultural background and subtle nuances in the expressions of gratitude. For example, the Japanese version of "Thank you" is used regardless of the formality, while the English version is best suited to informal situations. Taking this difference into account, the analysis results are stored in a database, and a new word, such as "Gratalo," is generated as a common vocabulary. Users then attempt to converse using this new word via their devices, and the server uses the resulting feedback to improve the system.

[0046] This system will enable the development of new languages ​​that take into account the nuances and cultural backgrounds of different languages, in order to achieve accurate communication worldwide.

[0047] The processing flow will be explained below.

[0048] Step 1:

[0049] The server collects language data from around the world by crawling and collecting text data from internet text corpora, translation materials, linguistic research papers, etc. Specifically, it integrates data from Wikipedia articles, academic paper databases, online dictionaries, etc., and compiles it into a single large dataset.

[0050] Step 2:

[0051] The server inputs the collected language data into a natural language processing model, which uses generative AI models such as BERT and GPT-4 to analyze the meaning, usage, grammar, and nuances of each word in each language. This analysis process yields detailed information about each word and phrase.

[0052] Step 3:

[0053] The server stores the analysis results in a database that contains detailed analysis information about the meaning, usage, grammar, and nuance of words and phrases in each language.

[0054] Step 4:

[0055] The server uses a generative AI model to group words and phrases that share a common meaning or nuance, for example, into categories such as greetings, thanks, and honorifics. The results of this grouping are also stored in a database.

[0056] Step 5:

[0057] The user (a linguistics expert) retrieves the analysis results from the server and adds annotations about specific cultural backgrounds and nuances, such as noting that "hello" is used widely and not limited to a specific time of day, resulting in more precise data.

[0058] Step 6:

[0059] The information added by the user is sent again to the server, and the server stores the updated analysis results in the database.

[0060] Step 7:

[0061] The server uses a generative AI model to summarize the analysis results and provide information about grouped words and phrases, which are then stored in a database for further processing.

[0062] Step 8:

[0063] The user (linguist) designs the grammar and vocabulary of the new language based on the summarization results. At this stage, definitions of parts of speech, sentence structure, verb conjugation rules, etc. are designed.

[0064] Step 9:

[0065] A user (a linguist) documents grammar rules and uploads them to a server.

[0066] Step 10:

[0067] The server uses a generative AI model to create the vocabulary needed for the new language. For example, a common greeting, "Helkona," is generated for the new language. This vocabulary list is also stored in a database.

[0068] Step 11:

[0069] A user (a linguistics expert) creates a dictionary or study manual based on the grammar and vocabulary of a new language, including basic words, phrases, and grammar rules of the new language.

[0070] Step 12:

[0071] A user uploads a dictionary or manual created by the user to a server in digital format.

[0072] Step 13:

[0073] The server will develop an app or platform to provide new languages ​​to users, which will help them learn the new language and allow them to actually use the new language.

[0074] Step 14:

[0075] The device will present phrases and words in the new language to the user through the app, allowing the user to try communicating using the new language.

[0076] Step 15:

[0077] Users can input their results and feedback on their communication using the new language through their devices, such as whether the greeting "Helkona" was useful or if there are areas for improvement.

[0078] Step 16:

[0079] The server collects the user feedback and stores it in a database.

[0080] Step 17:

[0081] The server considers improvements to the system and language based on the feedback collected, and uses generative AI models to propose new expressions and update the entire system.

[0082] This concretely implements a series of processes from collection to analysis, development of a new language, testing, gathering feedback, and improvement.

[0083] Example 1

[0084] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0085] Communication between existing languages ​​is problematic due to the many differences in cultural background and nuances that make accurate communication difficult. To solve this problem, there is a need for a method to analyze language data from around the world, generate new languages ​​with common meanings and nuances, and make them easy for users to understand and use.

[0086] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0087] In this invention, the server includes a means for collecting language data from around the world, a means for using a generative AI model to analyze the collected language data, and a means for grouping words and phrases with common meanings and nuances from the analyzed data, thereby creating a grammar and vocabulary for a new language, providing it to users, and collecting feedback to refine it.

[0088] "Global language data" refers to data such as texts, grammar information, and translation materials written in different languages ​​around the world.

[0089] "Generative AI models" refers to machine learning techniques, such as BERT and GPT-4, used to analyze collected language data.

[0090] "Means of collection" refers to methods for acquiring and integrating language data from around the world from the Internet and existing databases.

[0091] "Means of analysis" refers to the use of generative AI models to analyze collected language data and elucidate the meaning, usage, grammar, and nuances of words in each language.

[0092] "Grouping methods" refers to methods for categorizing words and phrases with common meanings and nuances based on the analysis results.

[0093] "Method for creating a grammar and vocabulary for a new language" refers to a method for designing and documenting the grammar rules and vocabulary for a new language based on the analysis results and grouped information.

[0094] "Feedback gathering methods" refers to methods for providing the newly created language to users and gathering their thoughts and suggestions for improvement based on their usage and experiences.

[0095] "Means of improvement" refers to how generative AI models are used to improve the grammar and vocabulary of a new language based on collected feedback.

[0096] This invention is a system for generating new languages ​​with common meanings and nuances by collecting and analyzing language data from around the world. This system is mainly composed of a server, terminals, and users.

[0097] The server collects language data from around the world through the internet and existing databases, such as Wikipedia articles, Google Books, and academic paper databases, and retrieves text, grammar information, and translation materials. This data is then integrated into a single large dataset.

[0098] The collected data is then analyzed by a server. Generative AI models, specifically advanced machine learning techniques such as BERT and GPT-4, are used for the analysis. Generative AI models perform detailed analysis of the meaning, usage, grammar, and nuances of words in each language, and the analysis results are stored in a database. For example, the BERT model is used to analyze the relationships between words in a sentence.

[0099] Next, the server uses a generative AI model to group words and phrases with common meanings and nuances based on the analysis results. At this stage, they are classified into categories such as "greetings," "thanks," and "honorifics." The classified information is stored in a database. For example, "arigato" (thank you) and "thank you" are classified into the "gratitude" category.

[0100] The user (a linguistics expert) reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. For example, the Japanese word "arigatou" (thank you) is widely used, while the English word "thank you" is used mainly in casual settings. This difference is added as a note. This additional information is sent to the server, and the database is updated.

[0101] The user (linguist) designs the grammar and vocabulary of a new language based on the grouped information, taking into account definitions of parts of speech, sentence structure, verb conjugation rules, etc. The user documents the grammar rules and uploads them to the server.

[0102] The generated grammar and vocabulary are implemented by the server. For example, a common greeting word, "Helkona," is created for the new language. The dictionary and learning manual for the new language are created by users (linguistic experts) and uploaded digitally to the server.

[0103] This new language is provided to users via their devices. Users attempt to communicate using it, and the results and feedback are collected via the device. The collected feedback is analyzed by the server, and generative AI models are used to improve the system and language.

[0104] Specific examples

[0105] For example, the system collects the English and Japanese expressions of gratitude, "arigatou" (thank you) and "thank you," and analyzes their cultural backgrounds and differences in meaning. The server categorizes these into groups, and users (linguistic experts) add annotations pointing out the differences. "Gratalo" is generated as a new common vocabulary, which users can use via their terminals. The system is improved based on user feedback.

[0106] Examples of prompt statements

[0107] "Generate words for a new language based on the following dataset: The dataset contains sentences about expressions of gratitude in Japanese and English. Analyze each sentence, taking into account differences in vocabulary and nuance."

[0108] This will enable the development of new languages ​​that take into account the nuances and cultural backgrounds of different languages ​​in order to achieve accurate communication worldwide.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1:

[0111] Data collection

[0112] The server collects language data from around the world from the Internet and existing databases.

[0113] Specifically, it retrieves text, grammar information, and translation materials from Wikipedia, academic paper databases, digital book repositories, etc.

[0114] Input: URL and access parameters of the target online database.

[0115] Output: A large dataset that integrates retrieved text, grammar information, and translation materials.

[0116] Step 2:

[0117] Data analysis

[0118] The server analyzes the collected data using a generative AI model (e.g., BERT or GPT-4).

[0119] At this stage, the meaning, usage, grammar, and nuances of words in each language are analyzed, and the results are stored in a database.

[0120] Specifically, it uses the BERT model to analyze the relationships between words in a sentence.

[0121] Input: A large collected dataset.

[0122] Output: Analysis results on word meaning, usage, grammar, and nuance.

[0123] Step 3:

[0124] Grouping of meanings and nuances

[0125] Based on the analysis results, the server groups words and phrases that share a common meaning or nuance.

[0126] At this stage, expressions are classified into "greetings," "thanks," "honorifics," etc.

[0127] As a specific action, "arigatou" and "thank you" are classified into the category of "gratitude."

[0128] Input: Analysis results.

[0129] Output: Words and phrases grouped by category.

[0130] Step 4:

[0131] Expertly reviewed and annotated

[0132] The user (a linguistics expert) reviews the analysis results and adds annotations regarding specific cultural backgrounds and nuances.

[0133] As a specific action, for example, notes are added about the use of "thank you" at specific times and in specific situations.

[0134] Input: Grouped words or phrases.

[0135] Output: Information annotated with cultural context and nuances.

[0136] Step 5:

[0137] Designing grammars and vocabularies for new languages

[0138] The user (a linguist) designs the grammar and vocabulary of a new language based on the grouped information.

[0139] The specific operation is designed taking into consideration definitions of parts of speech, sentence structure, and verb conjugation rules.

[0140] Input: The annotated information.

[0141] Output: Grammar rules and vocabulary of the new language.

[0142] Step 6:

[0143] The realization of a new language

[0144] The server instantiates a new language based on the generated grammar and vocabulary.

[0145] Specific actions include creating a common greeting for the new language called "Helkona" and creating a dictionary and learning manual for the new language in digital format.

[0146] Input: grammar rules and vocabulary of the new language.

[0147] Output: A dictionary and learning manual for the new language.

[0148] Step 7:

[0149] Gathering feedback and improving

[0150] The new language is provided to users via their devices, and their communication results and feedback are collected.

[0151] Specifically, users attempt to communicate in a new language and collect the results and feedback from their devices.

[0152] Input: User feedback.

[0153] Output: The grammar and vocabulary of the new language, improved based on feedback.

[0154] (Application example 1)

[0155] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0156] In today's increasingly globalized world, there are more and more situations where multilingual support is required. Communication between sales staff and customers who speak a variety of languages ​​is a particular challenge in brick-and-mortar stores. Conventional translation applications struggle to provide accurate translations that fully take into account cultural backgrounds and nuances. This leads to lower customer satisfaction and lost sales opportunities. To solve these problems, there is a need for a more accurate multilingual translation system that takes cultural backgrounds and nuances into account.

[0157] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0158] In this invention, the server includes means for collecting language data from around the world, means for generating a natural language processing model for analyzing the collected language data, means for grouping words and phrases with common meanings and nuances from the analyzed data, means for creating a grammar and vocabulary for a new language based on the analysis results and the grouped information, means for providing the newly created language to users and performing real-time multilingual translation between sales staff and customers in physical stores, means for collecting feedback on communication in physical stores, and means for improving the new language based on the collected feedback, thereby enabling advanced multilingual translation and smooth customer service in physical stores.

[0159] "Global Language Data" is a dataset that includes text data, grammar information, translation materials, and more in all languages ​​collected from many sources on the Internet.

[0160] A "collection means" is a system component that collects language data from the Internet or existing databases.

[0161] A "natural language processing model for analysis" is a generative AI model (e.g., BERT or GPT-4) used to analyze collected language data and understand word meaning, usage, grammar, nuances, etc.

[0162] A "grouping means" is a system component that categorizes words and phrases that share a common meaning or nuance from the analyzed data.

[0163] The "means for creating new language grammars and vocabularies" is a system component that designs and generates new grammar rules and vocabularies based on collected and analyzed data.

[0164] The "means to provide to users" refers to the system components that allow users to actually use the new language created.

[0165] The "means for real-time multilingual translation" is a system component that supports real-time multilingual translation between sales staff and customers in a physical store.

[0166] A "feedback gathering means" is a system component that gathers results and user comments on using the new language.

[0167] "Means for improvement" are system components that allow improvements to be made to the system or new languages ​​based on collected feedback.

[0168] This invention is a system that collects and analyzes language data from around the world to generate new languages ​​with common meanings and nuances, enabling real-time multilingual translation between sales staff and customers in physical stores. The system is primarily composed of a server, terminals, and users.

[0169] Server Functions and Processing

[0170] The server performs the following process:

[0171] 1. Collecting global language data:

[0172] The server collects language data from many sources on the Internet, including resources such as Wikipedia, Google Books, and academic paper databases.

[0173] 2. Linguistic Data Analysis:

[0174] The server uses natural language processing models (such as BERT or GPT-4) to analyze the collected data. This generative AI model performs detailed analysis of the meaning, usage, grammar, and nuance of words in each language.

[0175] 3. Grouping words and phrases that share a common meaning or nuance:

[0176] Based on the analysis results, the server groups words and phrases into categories such as "greetings," "thanks," and "honorifics."

[0177] 4. Creating a new language:

[0178] The grammar and vocabulary of the new language are created based on feedback from linguists, and this information is stored on a server for later use.

[0179] Terminal functions and processing

[0180] The following process is implemented on the terminal used by the salesperson:

[0181] 1. New language offerings:

[0182] An application will be installed that will allow salespeople and customers to communicate in real time through the new language created.

[0183] 2. Multilingual Translation:

[0184] Interactions between salespeople and customers will be translated in real time through a new common language, which requires the device to have high-performance computing power and an internet connection.

[0185] User Roles

[0186] The user (linguistics expert) plays the following roles:

[0187] 1. Review the analysis results:

[0188] The server then scrutinizes the data and adds annotations for specific cultural backgrounds and nuances.

[0189] 2. Gather feedback and improve:

[0190] Usage results and feedback from physical stores are collected through the terminals, and based on this, the server uses a generative AI model to improve the new language.

[0191] Hardware and software used

[0192] Generative AI models: Use advanced natural language processing techniques such as BERT and GPT-4.

[0193] Server: Use a server with high-performance data processing capabilities.

[0194] Device: A smartphone or tablet is used.

[0195] Specific examples

[0196] For example, consider an interaction between a Japanese salesperson and an English-speaking customer in a clothing store. When the salesperson says, "Welcome, what are you looking for?", the application translates this into the new common language and displays, "Helkona, what are you looking for?". When the customer says, "Tell me more about this item, please," the translation is displayed to the salesperson as, "Tell me more about this item, please."

[0197] Prompt Sentence Examples

[0198] Here are some examples of prompts:

[0199] Input: Welcome, what are you looking for?

[0200] Prompt: Translate the following sentence into the new common language. Consider cultural context and grammar rules: "Welcome, what are you looking for?"

[0201] Expected output: Helkona, what are you looking for?

[0202]

[0203] Input: Tell me more about this product.

[0204] Prompt: Translate the following sentence into a new common language. Consider cultural context and grammar rules: "Tell me more about this product."

[0205] Expected output: Tell me more about this item, please.

[0206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0207] Step 1:

[0208] The server collects language data from around the world, including text, grammar information, and translation materials from online sources such as Wikipedia, Google Books, and academic paper databases, and builds a large-scale dataset.

[0209] Input: URL of the website or database to be collected

[0210] Output: A large dataset of collected language data

[0211] Step 2:

[0212] The server analyzes the collected data using natural language processing models (such as BERT and GPT-4), which analyzes the meaning, usage, grammar, and nuance of words in each language in detail.

[0213] Input: A large dataset of collected language data

[0214] Output: Parsed linguistic data (detailed information about word meanings, usage, grammar, and nuances)

[0215] Step 3:

[0216] The server uses a generative AI model to analyze data and group words and phrases with common meanings and nuances into categories such as "greetings," "thanks," and "honorifics."

[0217] Input: Parsed language data

[0218] Output: Words and phrases grouped by category

[0219] Step 4:

[0220] Users (linguistic experts) can review the results analyzed and grouped by the server and add annotations about specific cultural backgrounds and nuances, resulting in more accurate information being stored in the database.

[0221] Input: Grouped words or phrases

[0222] Output: Annotated language data

[0223] Step 5:

[0224] The server creates the grammar and vocabulary of the new language based on feedback from users (linguistic experts), designing definitions of parts of speech, sentence structure, verb conjugation rules, and so on.

[0225] Input: Annotated language data

[0226] Output: Grammar and vocabulary of the new language

[0227] Step 6:

[0228] The server generates specific translation dictionaries and study manuals based on the grammar and vocabulary of the new language, and this information is stored on the system and provided to the terminal.

[0229] Input: Grammar and vocabulary of a new language

[0230] Output: Translation dictionary, learning manual

[0231] Step 7:

[0232] The device (smartphone or tablet) will be provided to the salesperson, and will perform real-time multilingual translation using the newly created language. The salesperson will use this translation function when interacting with customers.

[0233] Input: Text entered by the salesperson

[0234] Output: Translation results in the new language

[0235] Step 8:

[0236] Users (customers and salespeople) use the language generated through interactions in physical stores and send the results and feedback to the system via their terminals.

[0237] Input: Details of the interaction in the physical store

[0238] Output: Feedback from customers and salespeople

[0239] Step 9:

[0240] The server uses the collected feedback to refine the new language using a generative AI model, thereby improving the quality of the system and the language.

[0241] Input: Feedback data from customers and salespeople

[0242] Output: New and improved language

[0243] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0244] This invention is a system that collects and analyzes language data from around the world to generate new languages ​​with common meanings and nuances, and further combines it with an emotion engine that recognizes the user's emotions to improve the user experience. The program processing of this system is explained in detail below.

[0245] Program processing

[0246] The server first collects language data from around the world via the internet and existing databases, such as Wikipedia articles, Google Books, and academic paper databases, and then integrates it into a large dataset that includes text, grammar information, and translation materials.

[0247] The collected data is then analyzed by a server using a generative AI model, such as the latest natural language processing technology like BERT or GPT-4. The generative AI model analyzes the meaning, usage, grammar, and nuance of words in each language. The analysis results are stored in a database and used in subsequent processes.

[0248] Next, the generative AI model uses the analysis results to group words and phrases that share common meanings and nuances. In this step, they are classified into categories such as "greetings," "thanks," and "honorifics." The server then performs these groupings and stores the related information in a database.

[0249] The user (a linguistics expert) then reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. This additional information is sent to the server, which updates the database. For example, a user might note that the Japanese greeting "konnichiwa" (hello) is widely used and not limited to a specific time of day.

[0250] Next, the user (a linguist) designs the grammar and vocabulary of the new language. This stage takes into account definitions of parts of speech, sentence structure, verb conjugation rules, etc. The grammar rules are documented and uploaded to the server.

[0251] The generated grammar and vocabulary are then implemented by the server. For example, a common greeting, "Helkona," is generated for the new language. Based on this, a dictionary and learning manual for the new language can be created by the user (a linguistics expert) and uploaded digitally to the server.

[0252] The new language is provided to users via their devices. Users attempt to communicate in the new language, and the results and feedback are collected via the devices. The collected feedback is analyzed by the server, and the system and language are improved using a generative AI model.

[0253] Adding an Emotion Engine

[0254] A distinctive feature of this invention is that by combining it with an emotion engine, it is possible to provide language that takes the user's emotions into consideration. The device uses the emotion engine to analyze emotions from the user's voice and text. For example, using voice recognition technology and text emotion analysis algorithms, the device can identify the user's emotions, such as "happy," "sad," or "angry."

[0255] The identified emotions are then sent to a server and stored in a database, which uses this emotional information to adapt the grammar and vocabulary of the new language accordingly, for example by providing phrases containing more comforting expressions when negative emotions are recognized.

[0256] Specific examples

[0257] Consider the following scenario: The server collects and analyzes the English and Japanese versions of "Thank you," identifying differences in cultural background and subtle nuances in the expression of gratitude. For example, the Japanese version of "Thank you" is used regardless of formality, while the English version of "Thank you" is best suited to informal situations. Taking this difference into account, the analysis results are stored in a database, and a new common vocabulary word, such as "Gratalo," is generated.

[0258] Meanwhile, the device has emotion recognition capabilities and analyzes the emotions users feel when using Gratalo. If the user is expressing positive emotions, the emotion engine will suggest additional expressions that match that emotion. Conversely, if the user is expressing negative emotions, the engine will adjust to provide more comforting phrases.

[0259] Through this process, the system will collect, analyze, develop a new language, adjust based on emotions, test, collect feedback, and refine, developing a new language that is universally understandable and flexible enough to respond to emotions.

[0260] The processing flow will be explained below.

[0261] Step 1:

[0262] The server collects language data from around the world, including internet text corpora, translations, and linguistic research papers. For example, it crawls language data from Wikipedia articles, Google Books, and academic paper databases, and combines them into one large dataset.

[0263] Step 2:

[0264] The server inputs the collected language data into a natural language processing model. Here, generative AI models such as BERT and GPT-4 are used to analyze the meaning, usage, grammar, and nuance of words in each language. Specifically, detailed information about each word is extracted based on context, frequency, analogy, and other factors.

[0265] Step 3:

[0266] The server stores the analysis results in a database that contains detailed analysis information about the meaning, usage, grammar, and nuance of words and phrases in each language.

[0267] Step 4:

[0268] The server uses a generative AI model to group words and phrases with common meanings and nuances based on the analysis results, for example, into categories such as "greetings," "thanks," and "honorifics," and stores the related information in a database.

[0269] Step 5:

[0270] Users (linguistic experts) can take the analysis results and add annotations about specific cultural backgrounds and nuances, such as noting that "hello" is used widely and not limited to a specific time of day, resulting in more precise data.

[0271] Step 6:

[0272] The information added by the user is sent again to the server, and the server stores the updated analysis results in the database.

[0273] Step 7:

[0274] The server uses a generative AI model to summarize the analysis results and provide information about grouped words and phrases, which are then stored in a database for further processing.

[0275] Step 8:

[0276] The user (linguist) designs the grammar and vocabulary of the new language based on the summarization results. At this stage, definitions of parts of speech, sentence structure, verb conjugation rules, etc. are taken into account. The grammar rules are documented and uploaded to the server.

[0277] Step 9:

[0278] The server uses a generative AI model to create the vocabulary needed for the new language. For example, a common greeting, "Helkona," is generated for the new language. This vocabulary list is also stored in a database.

[0279] Step 10:

[0280] A user (a linguistics expert) creates a dictionary or study manual based on the grammar and vocabulary of a new language, including basic words, phrases, and grammar rules of the new language.

[0281] Step 11:

[0282] A user uploads a dictionary or manual created by the user to a server in digital format.

[0283] Step 12:

[0284] The server will develop an app or platform to provide new languages ​​to users, which will help them learn the new language and allow them to actually use the new language.

[0285] Step 13:

[0286] The device will present phrases and words in the new language to the user through the app, allowing the user to try communicating using the new language.

[0287] Step 14:

[0288] The device uses an emotion engine to analyze emotions from the user's voice and text. For example, it uses voice recognition technology and text emotion analysis algorithms to identify emotions such as "happy," "sad," or "angry."

[0289] Step 15:

[0290] The device sends the identified emotions to a server, which stores the information in a database.

[0291] Step 16:

[0292] The server uses the emotional information to adjust the grammar and vocabulary of the new language depending on the user's emotions, for example by providing phrases that contain more comforting expressions if negative emotions are recognized.

[0293] Step 17:

[0294] Users can input their results and feedback on their communication using the new language through their devices, such as whether the greeting "Helkona" was useful or if there are areas for improvement.

[0295] Step 18:

[0296] The server collects the user feedback and stores it in a database.

[0297] Step 19:

[0298] The server considers improvements to the system and language based on the feedback collected, and uses generative AI models to propose new expressions and update the entire system.

[0299] Through these steps, a series of processes are concretely carried out, from collection and analysis, to new language development, adjustment based on emotions, testing, and feedback collection and refinement. This system will develop a new language that is universally understandable, flexible, and responds to emotions.

[0300] Example 2

[0301] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0302] In modern society, there are many different languages, and communication between different languages ​​is often a barrier. Differences in emotional expression also lead to misunderstandings between different cultures. While efforts have been made to develop a common language that is not dependent on a specific language or culture, it is often insufficient in addressing the nuances of language and emotional expression. To solve these issues, there is a need to develop a new language that can be understood universally and is flexible enough to respond to emotions.

[0303] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0304] In this invention, the server includes: means for collecting language data from around the world; means for using a generative AI model to analyze the collected language data; means for grouping words and phrases with common meanings and nuances from the analyzed data; means for creating the grammar and vocabulary of a new language based on the analysis results and the grouped information; means for providing the newly created language to users and collecting feedback; means for improving the new language based on the collected feedback; means for using an emotion engine to analyze user emotions; and means for adjusting the grammar and vocabulary of the new language based on the user emotions. This enables the development of a new language that is universally understandable and flexible enough to respond to emotions.

[0305] "Global language data" refers to text data, grammar information, translation materials, etc. in various languages ​​collected from the Internet and existing databases.

[0306] A "generative AI model" is an artificial intelligence model based on the latest natural language processing techniques such as BERT and GPT-4, and is used to analyze language data.

[0307] "Grouping" refers to the process of categorizing words and phrases with common meanings and nuances from analyzed data.

[0308] A "new language" refers to a language with a newly created grammar and vocabulary that has been analyzed and grouped based on linguistic data from around the world.

[0309] "User" refers to the person or group who uses this new language and provides feedback.

[0310] "Feedback" is information such as users' experiences and opinions when using a new language, and this information is collected to help improve the language.

[0311] An "emotion engine" refers to algorithms and technologies that analyze a user's voice and text data to identify emotions.

[0312] "Grammar and vocabulary adjustment" refers to the process of appropriately modifying and optimizing the grammar and vocabulary of the new language based on the identified emotional information.

[0313] "Universally understandable and emotionally responsive" refers to a language that can be commonly understood by people who speak any language, and has flexible language characteristics that can adapt to the user's emotions.

[0314] This invention is a system that collects language data from around the world, analyzes and groups the data using a generative AI model, and generates a new common language. By combining this system with an emotion engine, the system aims to provide a flexible language that also responds to the user's emotions. Detailed embodiments of this system are described below.

[0315] The server first collects language data from around the world from the Internet and existing databases. Specific sources used include Wikipedia, Google Books, and academic paper databases. The collected data includes text data, grammar information, and translation materials. The server collects this data and builds a large dataset. The data is collected using crawling techniques and APIs.

[0316] The collected language data is then analyzed by the server. Generative AI models, such as BERT and GPT-4, are used for the analysis. These models use deep learning to analyze the meaning, usage, grammar, and nuances of words in each language. The analysis results are stored in a database and used in later processes. Furthermore, based on the analysis results, words and phrases with common meanings and nuances are grouped into categories. Clustering algorithms and other techniques are used here.

[0317] Next, the user (a linguistics expert) reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. This additional information is also sent to the server, and the database is updated. For example, a note is added about the difference between the usage of "arigatou" in Japanese and the English "thank you."

[0318] Next, the user (a linguist) designs the grammar and vocabulary of the new language. At this stage, definitions of parts of speech, sentence structure, verb conjugation rules, etc. are considered in detail. The designed grammar rules are then uploaded to the server.

[0319] Based on the generated grammar and vocabulary, the server will create a new language. For example, a new common greeting called "Helkona" will be generated. The dictionary and learning manual for this new language will be created by linguistic experts and uploaded digitally to the server.

[0320] The new language is provided to users via their devices. Users attempt to communicate using this new language, and the results and feedback are collected via the devices. The feedback information is analyzed by the server, and the system and language are improved using a generative AI model.

[0321] Furthermore, an emotion engine is built into the system. The device uses voice recognition technology and text emotion analysis algorithms to analyze the user's emotions. For example, emotions such as "happy," "sad," and "angry" are identified. This emotion information is sent to the server and stored in a database. Based on this information, the server adjusts the grammar and vocabulary of the new language. For example, if a negative emotion is recognized, adjustments are made to provide more comforting expressions.

[0322] As a concrete example, the server collects and analyzes the English and Japanese versions of "Thank you," revealing differences in cultural background and subtle nuances in the expression of gratitude. For example, the Japanese version of "Thank you" is commonly used, while the English version is limited to specific situations. Taking this difference into account, the word "Gratalo" is generated as a new common vocabulary.

[0323] An example prompt is, "Use GPT-4 to analyze the subtle differences in nuance between the Japanese and English versions of 'thank you' and generate a new common vocabulary." In this way, a new language that is universally understandable and flexible enough to accommodate emotions will be developed.

[0324] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0325] Step 1:

[0326] The server collects language data from around the world from the internet and existing databases. This process uses crawling techniques and APIs to obtain text data, grammar information, translation materials, and more from various sources (e.g., Wikipedia, Google Books, academic paper databases).

[0327] Input: A list of URLs from which language data can be sourced

[0328] Output: A set of collected language data

[0329] Specific operation: The server runs the crawling script to obtain data from the URL list, and then stores the obtained data in storage.

[0330] Step 2:

[0331] The server analyzes the collected language data using generative AI models (e.g., BERT and GPT-4), which extracts the meanings, usage, grammar, and nuances of words in each language.

[0332] Input: Collected language data

[0333] Output: Parsed language data

[0334] How it works: The server runs a Python script to invoke the generative AI model, which then analyzes the language data as input. The analysis results are then stored in a database.

[0335] Step 3:

[0336] The server groups words and phrases with common meanings and nuances based on the analysis results, and then categorizes them using a clustering algorithm.

[0337] Input: Parsed language data

[0338] Output: Words and phrases grouped by category

[0339] How it works: Based on the output of the generative AI model, the server applies a clustering algorithm to group words and phrases and stores the classification results in a database.

[0340] Step 4:

[0341] The user (a linguistics expert) reviews the results and adds annotations about specific cultural backgrounds and nuances, and this additional information is sent back to the server.

[0342] Input: Grouped words or phrases

[0343] Output: Data annotated with cultural context and nuances

[0344] What it does: Linguists access the data through a dedicated interface, add any necessary annotations, and then send the data to the server, which updates the database.

[0345] Step 5:

[0346] A user (linguist) designs the grammar and vocabulary of a new language, carefully examining the definitions of parts of speech, sentence structure, verb conjugation rules, etc., and uploads the designed grammar rules to the server.

[0347] Input: Annotated analysis results

[0348] Output: Draft grammar and vocabulary of the new language

[0349] What it does: Linguists use specialized editing software to design the grammar and vocabulary of a new language, then upload the data to a server.

[0350] Step 6:

[0351] The server then creates the new language based on the generated grammar and vocabulary. At this stage, a dictionary and learning manual for the new language are created and uploaded digitally.

[0352] Input: A draft grammar and vocabulary for the new language

[0353] Output: Dictionary and learning manual for the new language

[0354] Specific operation: The server generates a digital dictionary and learning manual for the new language based on the grammar and vocabulary and stores it in a database.

[0355] Step 7:

[0356] The device provides the new language to the user and collects communication results and feedback from the user.

[0357] Input: Dictionary and learning manual for a new language

[0358] Output: User feedback

[0359] Specific operation: A dedicated application installed on the device provides the new language, collects user usage logs and feedback, and sends them to a server.

[0360] Step 8:

[0361] The device uses an emotion engine to analyze the user's emotions, using voice recognition technology and text emotion analysis algorithms.

[0362] Input: User voice or text data

[0363] Output: Emotion data

[0364] Specific operation: Using the device's voice recognition software and natural language processing library, the system analyzes the user's emotions in real time and sends the results to the server.

[0365] Step 9:

[0366] The server adjusts the grammar and vocabulary of the new language based on the identified emotional information.

[0367] Input: Emotional data and user feedback

[0368] Output: Adjusted grammar and vocabulary

[0369] Specific operation: Based on the fed-back emotion data, the server readjusts the generative AI model and makes appropriate corrections to phrases and grammar.

[0370] (Application example 2)

[0371] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0372] In today's diverse language environment, there is a growing need for a new language that can be commonly understood by people all over the world. There is also a demand for providing user experiences based on emotions, but existing systems have had difficulty achieving this effectively. Similarly, there is also the issue of services such as food delivery not providing personalized services that take user emotions into account.

[0373] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0374] In this invention, the server includes: means for collecting language data from around the world; means for generating a natural language processing model for analyzing the collected language data; means for grouping words and phrases with common meanings and nuances from the analyzed data; means for creating a grammar and vocabulary for a new language based on the analysis results and the grouped information; means for providing the newly created language to users and collecting feedback; means for improving the new language based on the collected feedback; and means for recognizing user emotions and suggesting appropriate vocabulary and phrases based on the emotions. This enables the development of a new language that is universally understandable and flexible enough to respond to emotions. It also enables services such as food delivery to provide personalized experiences based on user emotions.

[0375] "Global language data" refers to text data, translation materials, grammar information, etc. for a wide variety of languages ​​collected from the Internet and existing databases.

[0376] A "natural language processing model" is an artificial intelligence model for analyzing collected language data, including generative AI models such as BERT and GPT-4.

[0377] "Analysis" refers to the process of using a generative AI model to analyze the vocabulary, grammar, nuances, etc. of collected language data to understand its meaning and usage.

[0378] "Grouping" refers to the process of categorizing words and phrases with common meanings and nuances from analyzed data.

[0379] "Creating a grammar and vocabulary for a new language" refers to the process of constructing a newly designed system of grammatical rules and words based on the analyzed and grouped information.

[0380] "Providing to the user" refers to providing the newly created language in a form that the user can use through the terminal.

[0381] "Collecting feedback" refers to the process of collecting user usage results and reactions via the device and obtaining them as data for analysis.

[0382] "Improving the new language" refers to the process of adjusting the generative AI model, grammar, and vocabulary based on collected feedback to improve the accuracy and usability of the language.

[0383] "Recognizing user emotions" refers to the process of identifying a user's emotional state using voice recognition technology and text emotion analysis algorithms.

[0384] "Suggesting appropriate vocabulary and phrases based on emotions" refers to the process of presenting the most appropriate words and phrases to the user based on analyzed emotional information.

[0385] This invention is a system that collects and analyzes language data from around the world to generate new languages ​​with common meanings and nuances, and further combines it with an emotion engine that recognizes user emotions to improve user experience. This system can make personalized menu suggestions based on user emotions, especially in food delivery applications.

[0386] Data collection and analysis

[0387] The first thing the server does is collect language data from around the world. The hardware used is a cloud-based server (e.g., AWS EC2 or Google Cloud Platform) that retrieves data from existing databases and the internet. Data is collected from sources such as Wikipedia articles, Google Books, and academic papers, and then integrated into a large dataset containing text, grammar information, and translation materials.

[0388] The collected data is then analyzed by a server using generative AI models, including the latest natural language processing techniques such as BERT and GPT-4. At this stage, the meaning, usage, grammar, and nuances of words in each language are analyzed, and the results are stored in a database.

[0389] Creating a new language

[0390] Based on the analysis results, the server groups words and phrases that share common meanings and nuances. For example, in this step, they are classified into categories such as "greetings," "thanks," and "honorifics." The grouping information is then used to create the grammar and vocabulary of the new language. Linguistic experts may add annotations regarding specific cultural backgrounds and nuances during this process, ultimately creating a digital dictionary and learning manual for the new language.

[0391] emotion recognition

[0392] The device's emotion engine analyzes the user's emotions from their voice and text, using software such as Google Cloud Natural Language and IBM Watson® Tone Analyzer algorithms. This emotion recognition identifies the user's emotions, such as joy, sadness, and anger.

[0393] Menu recommendation

[0394] Based on the analyzed emotion information, the server recommends the most suitable menu or service for the user. For example, comfort food may be suggested to a user who expresses negative emotion, while a special dessert or a new dish may be suggested to a user who expresses positive emotion. Examples of prompts used at this stage are as follows:

[0395] python

[0396] Dataset preparation

[0397] from transformers import GPT2Tokenizer, GPT2Model

[0398] tokenizer = GPT2Tokenizer.from_pretrained('gpt2')

[0399] model = GPT2Model.from_pretrained('gpt2')

[0400] text = "Enter text data to collect here"

[0401] inputs = tokenizer(text, return_tensors='pt')

[0402] outputs = model(inputs)

[0403] Emotion analysis

[0404] from google.cloud import language_v1

[0405] client = language_v1.LanguageServiceClient()

[0406] document = language_v1.Document(content="Enter text to parse here", type_=language_v1.Document.Type.PLAIN_TEXT)

[0407] sentiment = client.analyze_sentiment(request={'document': document}).document_sentiment

[0408] print(f'Text: {document.content}\nSentiment: {sentiment.score}')

[0409] Menu recommendation

[0410] recommendations = {

[0411] "happy": ["Special Dessert", "Celebration Cake"],

[0412] "sad": ["Comfort Soup", "Chocolate Brownie"],

[0413] "angry": ["Spicy Wings", "Satisfaction Steak"]

[0414] }

[0415] user_emotion = "happy" Parsed emotion result

[0416] recommended_menu = recommendations[user_emotion]

[0417] print(f"Recommended Menu: {recommended_menu}")

[0418] Through the above process, the present invention provides a new language that can be universally understood around the world, while realizing personalized services based on the user's emotions.

[0419] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0420] Step 1:

[0421] The server collects language data from around the world, including text, grammar information, and translation materials such as Wikipedia articles, Google Books, and academic papers, using a cloud-based server (e.g., AWS EC2 or Google Cloud Platform).

[0422] (Input): Source URL or API endpoint

[0423] (Output): Unified language dataset

[0424] (Specific operation): The server periodically runs the data collection script, obtains data from each source, and integrates it into a single database.

[0425] Step 2:

[0426] The server analyzes the collected data using a generative AI model (e.g., BERT or GPT-4).

[0427] (Input): Unified language dataset

[0428] (Output): Analysis results (word meanings, usage, grammar, nuances, etc. for each language)

[0429] (Specific operation): The server uses a generative AI model to analyze text data, extract word meanings, usage, and grammatical information, and store them in a database.

[0430] Step 3:

[0431] Based on the analysis results, the server groups words and phrases that share a common meaning or nuance.

[0432] (Input): Analysis results

[0433] (Output): Category information of grouped words and phrases

[0434] (Specific behavior): The server runs an automatic classification algorithm to group words and phrases into categories such as "greetings," "thanks," and "honorifics."

[0435] Step 4:

[0436] The server creates the grammar and vocabulary of the new language based on the grouped information.

[0437] (Input): Category information of grouped words and phrases

[0438] (Output): Grammatical and lexical information for the new language

[0439] (Specific operation): The server defines grammar rules, constructs grammar and vocabulary, and creates a dictionary and learning manual for the new language.

[0440] Step 5:

[0441] The server provides the newly created language to users through their devices and collects their feedback.

[0442] (Input): A dictionary and learning manual for a new language

[0443] (Output): User feedback data

[0444] (Specific operation): The user communicates using a new language, and the device records the results and reactions of the communication and sends them to the server as feedback data.

[0445] Step 6:

[0446] The server refines the new language based on the collected feedback.

[0447] (Input): Feedback data

[0448] (Output): Improved grammar and lexical information

[0449] (Specific operation): The server analyzes the feedback data, uses a generative AI model to improve grammar and vocabulary, and updates the results to the database.

[0450] Step 7:

[0451] The device uses an emotion engine to analyze emotions from the user's voice or text. Emotion recognition algorithms (e.g., Google Cloud Natural Language or IBM Watson Tone Analyzer) are used.

[0452] (Input): User voice or text data

[0453] (Output): User's emotional state (e.g., happy, sad, angry, etc.)

[0454] (Specific operation): The device receives the user's voice or text as input, analyzes the emotions using an emotion recognition algorithm, and sends the results to the server.

[0455] Step 8:

[0456] The server then recommends the most suitable menus and services to the user based on the analyzed emotional information.

[0457] (Input): User's emotional state

[0458] (Output): Recommended menu items and services

[0459] (Specific operation): Based on the emotional information, the server searches the database for the most suitable menu or service for the user and sends it to the terminal.

[0460] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0461] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0462] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0463] [Second embodiment]

[0464] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0465] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0466] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0467] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0468] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0469] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0470] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0471] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0472] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0473] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0474] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0475] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0476] This invention is a system for generating a new language with common meanings and nuances by collecting and analyzing language data from around the world. The system is primarily composed of a server, terminals, and users. The program processing of the system is explained in detail below.

[0477] Program processing

[0478] The server first collects language data from around the world via the internet and existing databases, such as Wikipedia articles, Google Books, and academic paper databases, and then integrates it into a single large dataset, including text, grammar information, and translation materials.

[0479] The collected data is then analyzed by a server using a generative AI model, such as machine learning techniques like BERT or GPT-4. The generative AI model performs a detailed analysis of the meaning, usage, grammar, and nuances of words in each language. The results of this analysis are stored in a database for use in later processes.

[0480] Next, the generative AI model uses the analysis results to group words and phrases that share common meanings and nuances. In this step, they are classified into categories such as "greetings," "thanks," and "honorifics." The server then performs these groupings and stores the related information in a database.

[0481] The user (a linguistics expert) then reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. This additional information is sent to the server, which updates the database. For example, a user might note that the Japanese greeting "konnichiwa" (hello) is widely used and not limited to a specific time of day.

[0482] Based on the grouped information, the user (linguist) designs the grammar and vocabulary of the new language, taking into account definitions of parts of speech, sentence structure, verb conjugation rules, etc. The user documents the grammar rules and uploads them to the server.

[0483] The generated grammar and vocabulary are then implemented by the server. For example, a common greeting, "Helkona," is created for the new language. Based on this, dictionaries and learning manuals for the new language are created by users (linguistic experts) and uploaded digitally to the server.

[0484] This new language is provided to users via their devices. Users attempt to communicate in the new language, and the results and feedback are collected via the devices. The collected feedback is analyzed by the server, and generative AI models are used to improve the system and the language.

[0485] Specific examples

[0486] Consider the following scenario as a concrete example. The server collects and analyzes the English and Japanese versions of "Thank you," identifying differences in cultural background and subtle nuances in the expressions of gratitude. For example, the Japanese version of "Thank you" is used regardless of the formality, while the English version is best suited to informal situations. Taking this difference into account, the analysis results are stored in a database, and a new word, such as "Gratalo," is generated as a common vocabulary. Users then attempt to converse using this new word via their devices, and the server uses the resulting feedback to improve the system.

[0487] This system will enable the development of new languages ​​that take into account the nuances and cultural backgrounds of different languages, in order to achieve accurate communication worldwide.

[0488] The processing flow will be explained below.

[0489] Step 1:

[0490] The server collects language data from around the world by crawling and collecting text data from internet text corpora, translation materials, linguistic research papers, etc. Specifically, it integrates data from Wikipedia articles, academic paper databases, online dictionaries, etc., and compiles it into a single large dataset.

[0491] Step 2:

[0492] The server inputs the collected language data into a natural language processing model, which uses generative AI models such as BERT and GPT-4 to analyze the meaning, usage, grammar, and nuances of each word in each language. This analysis process yields detailed information about each word and phrase.

[0493] Step 3:

[0494] The server stores the analysis results in a database that contains detailed analysis information about the meaning, usage, grammar, and nuance of words and phrases in each language.

[0495] Step 4:

[0496] The server uses a generative AI model to group words and phrases that share a common meaning or nuance, for example, into categories such as greetings, thanks, and honorifics. The results of this grouping are also stored in a database.

[0497] Step 5:

[0498] The user (a linguistics expert) retrieves the analysis results from the server and adds annotations about specific cultural backgrounds and nuances, such as noting that "hello" is used widely and not limited to a specific time of day, resulting in more precise data.

[0499] Step 6:

[0500] The information added by the user is sent again to the server, and the server stores the updated analysis results in the database.

[0501] Step 7:

[0502] The server uses a generative AI model to summarize the analysis results and provide information about grouped words and phrases, which are then stored in a database for further processing.

[0503] Step 8:

[0504] The user (linguist) designs the grammar and vocabulary of the new language based on the summarization results. At this stage, definitions of parts of speech, sentence structure, verb conjugation rules, etc. are designed.

[0505] Step 9:

[0506] A user (a linguist) documents grammar rules and uploads them to a server.

[0507] Step 10:

[0508] The server uses a generative AI model to create the vocabulary needed for the new language. For example, a common greeting, "Helkona," is generated for the new language. This vocabulary list is also stored in a database.

[0509] Step 11:

[0510] A user (a linguistics expert) creates a dictionary or study manual based on the grammar and vocabulary of a new language, including basic words, phrases, and grammar rules of the new language.

[0511] Step 12:

[0512] A user uploads a dictionary or manual created by the user to a server in digital format.

[0513] Step 13:

[0514] The server will develop an app or platform to provide new languages ​​to users, which will help them learn the new language and allow them to actually use the new language.

[0515] Step 14:

[0516] The device will present phrases and words in the new language to the user through the app, allowing the user to try communicating using the new language.

[0517] Step 15:

[0518] Users can input their results and feedback on their communication using the new language through their devices, such as whether the greeting "Helkona" was useful or if there are areas for improvement.

[0519] Step 16:

[0520] The server collects the user feedback and stores it in a database.

[0521] Step 17:

[0522] The server considers improvements to the system and language based on the feedback collected, and uses generative AI models to propose new expressions and update the entire system.

[0523] This concretely implements a series of processes from collection to analysis, development of a new language, testing, gathering feedback, and improvement.

[0524] Example 1

[0525] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0526] Communication between existing languages ​​is problematic due to the many differences in cultural background and nuances that make accurate communication difficult. To solve this problem, there is a need for a method to analyze language data from around the world, generate new languages ​​with common meanings and nuances, and make them easy for users to understand and use.

[0527] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0528] In this invention, the server includes a means for collecting language data from around the world, a means for using a generative AI model to analyze the collected language data, and a means for grouping words and phrases with common meanings and nuances from the analyzed data, thereby creating a grammar and vocabulary for a new language, providing it to users, and collecting feedback to refine it.

[0529] "Global language data" refers to data such as texts, grammar information, and translation materials written in different languages ​​around the world.

[0530] "Generative AI models" refers to machine learning techniques, such as BERT and GPT-4, used to analyze collected language data.

[0531] "Means of collection" refers to methods for acquiring and integrating language data from around the world from the Internet and existing databases.

[0532] "Means of analysis" refers to the use of generative AI models to analyze collected language data and elucidate the meaning, usage, grammar, and nuances of words in each language.

[0533] "Grouping methods" refers to methods for categorizing words and phrases with common meanings and nuances based on the analysis results.

[0534] "Method for creating a grammar and vocabulary for a new language" refers to a method for designing and documenting the grammar rules and vocabulary for a new language based on the analysis results and grouped information.

[0535] "Feedback gathering methods" refers to methods for providing the newly created language to users and gathering their thoughts and suggestions for improvement based on their usage and experiences.

[0536] "Means of improvement" refers to how generative AI models are used to improve the grammar and vocabulary of a new language based on collected feedback.

[0537] This invention is a system for generating new languages ​​with common meanings and nuances by collecting and analyzing language data from around the world. This system is mainly composed of a server, terminals, and users.

[0538] The server collects language data from around the world through the internet and existing databases, such as Wikipedia articles, Google Books, and academic paper databases, and retrieves text, grammar information, and translation materials. This data is then integrated into a single large dataset.

[0539] The collected data is then analyzed by a server. Generative AI models, specifically advanced machine learning techniques such as BERT and GPT-4, are used for the analysis. Generative AI models perform detailed analysis of the meaning, usage, grammar, and nuances of words in each language, and the analysis results are stored in a database. For example, the BERT model is used to analyze the relationships between words in a sentence.

[0540] Next, the server uses a generative AI model to group words and phrases with common meanings and nuances based on the analysis results. At this stage, they are classified into categories such as "greetings," "thanks," and "honorifics." The classified information is stored in a database. For example, "arigato" (thank you) and "thank you" are classified into the "gratitude" category.

[0541] The user (a linguistics expert) reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. For example, the Japanese word "arigatou" (thank you) is widely used, while the English word "thank you" is used mainly in casual settings. This difference is added as a note. This additional information is sent to the server, and the database is updated.

[0542] The user (linguist) designs the grammar and vocabulary of a new language based on the grouped information, taking into account definitions of parts of speech, sentence structure, verb conjugation rules, etc. The user documents the grammar rules and uploads them to the server.

[0543] The generated grammar and vocabulary are implemented by the server. For example, a common greeting word, "Helkona," is created for the new language. The dictionary and learning manual for the new language are created by users (linguistic experts) and uploaded digitally to the server.

[0544] This new language is provided to users via their devices. Users attempt to communicate using it, and the results and feedback are collected via the device. The collected feedback is analyzed by the server, and generative AI models are used to improve the system and language.

[0545] Specific examples

[0546] For example, the system collects the English and Japanese expressions of gratitude, "arigatou" (thank you) and "thank you," and analyzes their cultural backgrounds and differences in meaning. The server categorizes these into groups, and users (linguistic experts) add annotations pointing out the differences. "Gratalo" is generated as a new common vocabulary, which users can use via their terminals. The system is improved based on user feedback.

[0547] Examples of prompt statements

[0548] "Generate words for a new language based on the following dataset: The dataset contains sentences about expressions of gratitude in Japanese and English. Analyze each sentence, taking into account differences in vocabulary and nuance."

[0549] This will enable the development of new languages ​​that take into account the nuances and cultural backgrounds of different languages ​​in order to achieve accurate communication worldwide.

[0550] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0551] Step 1:

[0552] Data collection

[0553] The server collects language data from around the world from the Internet and existing databases.

[0554] Specifically, it retrieves text, grammar information, and translation materials from Wikipedia, academic paper databases, digital book repositories, etc.

[0555] Input: URL and access parameters of the target online database.

[0556] Output: A large dataset that integrates retrieved text, grammar information, and translation materials.

[0557] Step 2:

[0558] Data analysis

[0559] The server analyzes the collected data using a generative AI model (e.g., BERT or GPT-4).

[0560] At this stage, the meaning, usage, grammar, and nuances of words in each language are analyzed, and the results are stored in a database.

[0561] Specifically, it uses the BERT model to analyze the relationships between words in a sentence.

[0562] Input: A large collected dataset.

[0563] Output: Analysis results on word meaning, usage, grammar, and nuance.

[0564] Step 3:

[0565] Grouping of meanings and nuances

[0566] Based on the analysis results, the server groups words and phrases that share a common meaning or nuance.

[0567] At this stage, expressions are classified into "greetings," "thanks," "honorifics," etc.

[0568] As a specific action, "arigatou" and "thank you" are classified into the category of "gratitude."

[0569] Input: Analysis results.

[0570] Output: Words and phrases grouped by category.

[0571] Step 4:

[0572] Expertly reviewed and annotated

[0573] The user (a linguistics expert) reviews the analysis results and adds annotations regarding specific cultural backgrounds and nuances.

[0574] As a specific action, for example, notes are added about the use of "thank you" at specific times and in specific situations.

[0575] Input: Grouped words or phrases.

[0576] Output: Information annotated with cultural context and nuances.

[0577] Step 5:

[0578] Designing grammars and vocabularies for new languages

[0579] The user (a linguist) designs the grammar and vocabulary of a new language based on the grouped information.

[0580] The specific operation is designed taking into consideration definitions of parts of speech, sentence structure, and verb conjugation rules.

[0581] Input: The annotated information.

[0582] Output: Grammar rules and vocabulary of the new language.

[0583] Step 6:

[0584] The realization of a new language

[0585] The server instantiates a new language based on the generated grammar and vocabulary.

[0586] Specific actions include creating a common greeting for the new language called "Helkona" and creating a dictionary and learning manual for the new language in digital format.

[0587] Input: grammar rules and vocabulary of the new language.

[0588] Output: A dictionary and learning manual for the new language.

[0589] Step 7:

[0590] Gathering feedback and improving

[0591] The new language is provided to users via their devices, and their communication results and feedback are collected.

[0592] Specifically, users attempt to communicate in a new language and collect the results and feedback from their devices.

[0593] Input: User feedback.

[0594] Output: The grammar and vocabulary of the new language, improved based on feedback.

[0595] (Application example 1)

[0596] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0597] In today's increasingly globalized world, there are more and more situations where multilingual support is required. Communication between sales staff and customers who speak a variety of languages ​​is a particular challenge in brick-and-mortar stores. Conventional translation applications struggle to provide accurate translations that fully take into account cultural backgrounds and nuances. This leads to lower customer satisfaction and lost sales opportunities. To solve these problems, there is a need for a more accurate multilingual translation system that takes cultural backgrounds and nuances into account.

[0598] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0599] In this invention, the server includes means for collecting language data from around the world, means for generating a natural language processing model for analyzing the collected language data, means for grouping words and phrases with common meanings and nuances from the analyzed data, means for creating a grammar and vocabulary for a new language based on the analysis results and the grouped information, means for providing the newly created language to users and performing real-time multilingual translation between sales staff and customers in physical stores, means for collecting feedback on communication in physical stores, and means for improving the new language based on the collected feedback, thereby enabling advanced multilingual translation and smooth customer service in physical stores.

[0600] "Global Language Data" is a dataset that includes text data, grammar information, translation materials, and more in all languages ​​collected from many sources on the Internet.

[0601] A "collection means" is a system component that collects language data from the Internet or existing databases.

[0602] A "natural language processing model for analysis" is a generative AI model (e.g., BERT or GPT-4) used to analyze collected language data and understand word meaning, usage, grammar, nuances, etc.

[0603] A "grouping means" is a system component that categorizes words and phrases that share a common meaning or nuance from the analyzed data.

[0604] The "means for creating new language grammars and vocabularies" is a system component that designs and generates new grammar rules and vocabularies based on collected and analyzed data.

[0605] The "means to provide to users" refers to the system components that allow users to actually use the new language created.

[0606] The "means for real-time multilingual translation" is a system component that supports real-time multilingual translation between sales staff and customers in a physical store.

[0607] A "feedback gathering means" is a system component that gathers results and user comments on using the new language.

[0608] "Means for improvement" are system components that allow improvements to be made to the system or new languages ​​based on collected feedback.

[0609] This invention is a system that collects and analyzes language data from around the world to generate new languages ​​with common meanings and nuances, enabling real-time multilingual translation between sales staff and customers in physical stores. The system is primarily composed of a server, terminals, and users.

[0610] Server Functions and Processing

[0611] The server performs the following process:

[0612] 1. Collecting global language data:

[0613] The server collects language data from many sources on the Internet, including resources such as Wikipedia, Google Books, and academic paper databases.

[0614] 2. Linguistic Data Analysis:

[0615] The server uses natural language processing models (such as BERT or GPT-4) to analyze the collected data. This generative AI model performs detailed analysis of the meaning, usage, grammar, and nuance of words in each language.

[0616] 3. Grouping words and phrases that share a common meaning or nuance:

[0617] Based on the analysis results, the server groups words and phrases into categories such as "greetings," "thanks," and "honorifics."

[0618] 4. Creating a new language:

[0619] The grammar and vocabulary of the new language are created based on feedback from linguists, and this information is stored on a server for later use.

[0620] Terminal functions and processing

[0621] The following process is implemented on the terminal used by the salesperson:

[0622] 1. New language offerings:

[0623] An application will be installed that will allow salespeople and customers to communicate in real time through the new language created.

[0624] 2. Multilingual Translation:

[0625] Interactions between salespeople and customers will be translated in real time through a new common language, which requires the device to have high-performance computing power and an internet connection.

[0626] User Roles

[0627] The user (linguistics expert) plays the following roles:

[0628] 1. Review the analysis results:

[0629] The server then scrutinizes the data and adds annotations for specific cultural backgrounds and nuances.

[0630] 2. Gather feedback and improve:

[0631] Usage results and feedback from physical stores are collected through the terminals, and based on this, the server uses a generative AI model to improve the new language.

[0632] Hardware and software used

[0633] Generative AI models: Use advanced natural language processing techniques such as BERT and GPT-4.

[0634] Server: Use a server with high-performance data processing capabilities.

[0635] Device: A smartphone or tablet is used.

[0636] Specific examples

[0637] For example, consider an interaction between a Japanese salesperson and an English-speaking customer in a clothing store. When the salesperson says, "Welcome, what are you looking for?", the application translates this into the new common language and displays, "Helkona, what are you looking for?". When the customer says, "Tell me more about this item, please," the translation is displayed to the salesperson as, "Tell me more about this item, please."

[0638] Prompt Sentence Examples

[0639] Here are some examples of prompts:

[0640] Input: Welcome, what are you looking for?

[0641] Prompt: Translate the following sentence into the new common language. Consider cultural context and grammar rules: "Welcome, what are you looking for?"

[0642] Expected output: Helkona, what are you looking for?

[0643]

[0644] Input: Tell me more about this product.

[0645] Prompt: Translate the following sentence into a new common language. Consider cultural context and grammar rules: "Tell me more about this product."

[0646] Expected output: Tell me more about this item, please.

[0647] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0648] Step 1:

[0649] The server collects language data from around the world, including text, grammar information, and translation materials from online sources such as Wikipedia, Google Books, and academic paper databases, and builds a large-scale dataset.

[0650] Input: URL of the website or database to be collected

[0651] Output: A large dataset of collected language data

[0652] Step 2:

[0653] The server analyzes the collected data using natural language processing models (such as BERT and GPT-4), which analyzes the meaning, usage, grammar, and nuance of words in each language in detail.

[0654] Input: A large dataset of collected language data

[0655] Output: Parsed linguistic data (detailed information about word meanings, usage, grammar, and nuances)

[0656] Step 3:

[0657] The server uses a generative AI model to analyze data and group words and phrases with common meanings and nuances into categories such as "greetings," "thanks," and "honorifics."

[0658] Input: Parsed language data

[0659] Output: Words and phrases grouped by category

[0660] Step 4:

[0661] Users (linguistic experts) can review the results analyzed and grouped by the server and add annotations about specific cultural backgrounds and nuances, resulting in more accurate information being stored in the database.

[0662] Input: Grouped words or phrases

[0663] Output: Annotated language data

[0664] Step 5:

[0665] The server creates the grammar and vocabulary of the new language based on feedback from users (linguistic experts), designing definitions of parts of speech, sentence structure, verb conjugation rules, and so on.

[0666] Input: Annotated language data

[0667] Output: Grammar and vocabulary of the new language

[0668] Step 6:

[0669] The server generates specific translation dictionaries and study manuals based on the grammar and vocabulary of the new language, and this information is stored on the system and provided to the terminal.

[0670] Input: Grammar and vocabulary of a new language

[0671] Output: Translation dictionary, learning manual

[0672] Step 7:

[0673] The device (smartphone or tablet) will be provided to the salesperson, and will perform real-time multilingual translation using the newly created language. The salesperson will use this translation function when interacting with customers.

[0674] Input: Text entered by the salesperson

[0675] Output: Translation results in the new language

[0676] Step 8:

[0677] Users (customers and salespeople) use the language generated through interactions in physical stores and send the results and feedback to the system via their terminals.

[0678] Input: Details of the interaction in the physical store

[0679] Output: Feedback from customers and salespeople

[0680] Step 9:

[0681] The server uses the collected feedback to refine the new language using a generative AI model, thereby improving the quality of the system and the language.

[0682] Input: Feedback data from customers and salespeople

[0683] Output: New and improved language

[0684] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0685] This invention is a system that collects and analyzes language data from around the world to generate new languages ​​with common meanings and nuances, and further combines it with an emotion engine that recognizes the user's emotions to improve the user experience. The program processing of this system is explained in detail below.

[0686] Program processing

[0687] The server first collects language data from around the world via the internet and existing databases, such as Wikipedia articles, Google Books, and academic paper databases, and then integrates it into a large dataset that includes text, grammar information, and translation materials.

[0688] The collected data is then analyzed by a server using a generative AI model, such as the latest natural language processing technology like BERT or GPT-4. The generative AI model analyzes the meaning, usage, grammar, and nuance of words in each language. The analysis results are stored in a database and used in subsequent processes.

[0689] Next, the generative AI model uses the analysis results to group words and phrases that share common meanings and nuances. In this step, they are classified into categories such as "greetings," "thanks," and "honorifics." The server then performs these groupings and stores the related information in a database.

[0690] The user (a linguistics expert) then reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. This additional information is sent to the server, which updates the database. For example, a user might note that the Japanese greeting "konnichiwa" (hello) is widely used and not limited to a specific time of day.

[0691] Next, the user (a linguist) designs the grammar and vocabulary of the new language. This stage takes into account definitions of parts of speech, sentence structure, verb conjugation rules, etc. The grammar rules are documented and uploaded to the server.

[0692] The generated grammar and vocabulary are then implemented by the server. For example, a common greeting, "Helkona," is generated for the new language. Based on this, a dictionary and learning manual for the new language can be created by the user (a linguistics expert) and uploaded digitally to the server.

[0693] The new language is provided to users via their devices. Users attempt to communicate in the new language, and the results and feedback are collected via the devices. The collected feedback is analyzed by the server, and the system and language are improved using a generative AI model.

[0694] Adding an Emotion Engine

[0695] A distinctive feature of this invention is that by combining it with an emotion engine, it is possible to provide language that takes the user's emotions into consideration. The device uses the emotion engine to analyze emotions from the user's voice and text. For example, using voice recognition technology and text emotion analysis algorithms, the device can identify the user's emotions, such as "happy," "sad," or "angry."

[0696] The identified emotions are then sent to a server and stored in a database, which uses this emotional information to adapt the grammar and vocabulary of the new language accordingly, for example by providing phrases containing more comforting expressions when negative emotions are recognized.

[0697] Specific examples

[0698] Consider the following scenario: The server collects and analyzes the English and Japanese versions of "Thank you," identifying differences in cultural background and subtle nuances in the expression of gratitude. For example, the Japanese version of "Thank you" is used regardless of formality, while the English version of "Thank you" is best suited to informal situations. Taking this difference into account, the analysis results are stored in a database, and a new common vocabulary word, such as "Gratalo," is generated.

[0699] Meanwhile, the device has emotion recognition capabilities and analyzes the emotions users feel when using Gratalo. If the user is expressing positive emotions, the emotion engine will suggest additional expressions that match that emotion. Conversely, if the user is expressing negative emotions, the engine will adjust to provide more comforting phrases.

[0700] Through this process, the system will collect, analyze, develop a new language, adjust based on emotions, test, collect feedback, and refine, developing a new language that is universally understandable and flexible enough to respond to emotions.

[0701] The processing flow will be explained below.

[0702] Step 1:

[0703] The server collects language data from around the world, including internet text corpora, translations, and linguistic research papers. For example, it crawls language data from Wikipedia articles, Google Books, and academic paper databases, and combines them into one large dataset.

[0704] Step 2:

[0705] The server inputs the collected language data into a natural language processing model. Here, generative AI models such as BERT and GPT-4 are used to analyze the meaning, usage, grammar, and nuance of words in each language. Specifically, detailed information about each word is extracted based on context, frequency, analogy, and other factors.

[0706] Step 3:

[0707] The server stores the analysis results in a database that contains detailed analysis information about the meaning, usage, grammar, and nuance of words and phrases in each language.

[0708] Step 4:

[0709] The server uses a generative AI model to group words and phrases with common meanings and nuances based on the analysis results, for example, into categories such as "greetings," "thanks," and "honorifics," and stores the related information in a database.

[0710] Step 5:

[0711] Users (linguistic experts) can take the analysis results and add annotations about specific cultural backgrounds and nuances, such as noting that "hello" is used widely and not limited to a specific time of day, resulting in more precise data.

[0712] Step 6:

[0713] The information added by the user is sent again to the server, and the server stores the updated analysis results in the database.

[0714] Step 7:

[0715] The server uses a generative AI model to summarize the analysis results and provide information about grouped words and phrases, which are then stored in a database for further processing.

[0716] Step 8:

[0717] The user (linguist) designs the grammar and vocabulary of the new language based on the summarization results. At this stage, definitions of parts of speech, sentence structure, verb conjugation rules, etc. are taken into account. The grammar rules are documented and uploaded to the server.

[0718] Step 9:

[0719] The server uses a generative AI model to create the vocabulary needed for the new language. For example, a common greeting, "Helkona," is generated for the new language. This vocabulary list is also stored in a database.

[0720] Step 10:

[0721] A user (a linguistics expert) creates a dictionary or study manual based on the grammar and vocabulary of a new language, including basic words, phrases, and grammar rules of the new language.

[0722] Step 11:

[0723] A user uploads a dictionary or manual created by the user to a server in digital format.

[0724] Step 12:

[0725] The server will develop an app or platform to provide new languages ​​to users, which will help them learn the new language and allow them to actually use the new language.

[0726] Step 13:

[0727] The device will present phrases and words in the new language to the user through the app, allowing the user to try communicating using the new language.

[0728] Step 14:

[0729] The device uses an emotion engine to analyze emotions from the user's voice and text. For example, it uses voice recognition technology and text emotion analysis algorithms to identify emotions such as "happy," "sad," or "angry."

[0730] Step 15:

[0731] The device sends the identified emotions to a server, which stores the information in a database.

[0732] Step 16:

[0733] The server uses the emotional information to adjust the grammar and vocabulary of the new language depending on the user's emotions, for example by providing phrases that contain more comforting expressions if negative emotions are recognized.

[0734] Step 17:

[0735] Users can input their results and feedback on their communication using the new language through their devices, such as whether the greeting "Helkona" was useful or if there are areas for improvement.

[0736] Step 18:

[0737] The server collects the user feedback and stores it in a database.

[0738] Step 19:

[0739] The server considers improvements to the system and language based on the feedback collected, and uses generative AI models to propose new expressions and update the entire system.

[0740] Through these steps, a series of processes are concretely carried out, from collection and analysis, to new language development, adjustment based on emotions, testing, and feedback collection and refinement. This system will develop a new language that is universally understandable, flexible, and responds to emotions.

[0741] Example 2

[0742] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0743] In modern society, there are many different languages, and communication between different languages ​​is often a barrier. Differences in emotional expression also lead to misunderstandings between different cultures. While efforts have been made to develop a common language that is not dependent on a specific language or culture, it is often insufficient in addressing the nuances of language and emotional expression. To solve these issues, there is a need to develop a new language that can be understood universally and is flexible enough to respond to emotions.

[0744] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0745] In this invention, the server includes: means for collecting language data from around the world; means for using a generative AI model to analyze the collected language data; means for grouping words and phrases with common meanings and nuances from the analyzed data; means for creating the grammar and vocabulary of a new language based on the analysis results and the grouped information; means for providing the newly created language to users and collecting feedback; means for improving the new language based on the collected feedback; means for using an emotion engine to analyze user emotions; and means for adjusting the grammar and vocabulary of the new language based on the user emotions. This enables the development of a new language that is universally understandable and flexible enough to respond to emotions.

[0746] "Global language data" refers to text data, grammar information, translation materials, etc. in various languages ​​collected from the Internet and existing databases.

[0747] A "generative AI model" is an artificial intelligence model based on the latest natural language processing techniques such as BERT and GPT-4, and is used to analyze language data.

[0748] "Grouping" refers to the process of categorizing words and phrases with common meanings and nuances from analyzed data.

[0749] A "new language" refers to a language with a newly created grammar and vocabulary that has been analyzed and grouped based on linguistic data from around the world.

[0750] "User" refers to the person or group who uses this new language and provides feedback.

[0751] "Feedback" is information such as users' experiences and opinions when using a new language, and this information is collected to help improve the language.

[0752] An "emotion engine" refers to algorithms and technologies that analyze a user's voice and text data to identify emotions.

[0753] "Grammar and vocabulary adjustment" refers to the process of appropriately modifying and optimizing the grammar and vocabulary of the new language based on the identified emotional information.

[0754] "Universally understandable and emotionally responsive" refers to a language that can be commonly understood by people who speak any language, and has flexible language characteristics that can adapt to the user's emotions.

[0755] This invention is a system that collects language data from around the world, analyzes and groups the data using a generative AI model, and generates a new common language. By combining this system with an emotion engine, the system aims to provide a flexible language that also responds to the user's emotions. Detailed embodiments of this system are described below.

[0756] The server first collects language data from around the world from the Internet and existing databases. Specific sources used include Wikipedia, Google Books, and academic paper databases. The collected data includes text data, grammar information, and translation materials. The server collects this data and builds a large dataset. The data is collected using crawling techniques and APIs.

[0757] The collected language data is then analyzed by the server. Generative AI models, such as BERT and GPT-4, are used for the analysis. These models use deep learning to analyze the meaning, usage, grammar, and nuances of words in each language. The analysis results are stored in a database and used in later processes. Furthermore, based on the analysis results, words and phrases with common meanings and nuances are grouped into categories. Clustering algorithms and other techniques are used here.

[0758] Next, the user (a linguistics expert) reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. This additional information is also sent to the server, and the database is updated. For example, a note is added about the difference between the usage of "arigatou" in Japanese and the English "thank you."

[0759] Next, the user (a linguist) designs the grammar and vocabulary of the new language. At this stage, definitions of parts of speech, sentence structure, verb conjugation rules, etc. are considered in detail. The designed grammar rules are then uploaded to the server.

[0760] Based on the generated grammar and vocabulary, the server will create a new language. For example, a new common greeting called "Helkona" will be generated. The dictionary and learning manual for this new language will be created by linguistic experts and uploaded digitally to the server.

[0761] The new language is provided to users via their devices. Users attempt to communicate using this new language, and the results and feedback are collected via the devices. The feedback information is analyzed by the server, and the system and language are improved using a generative AI model.

[0762] Furthermore, an emotion engine is built into the system. The device uses voice recognition technology and text emotion analysis algorithms to analyze the user's emotions. For example, emotions such as "happy," "sad," and "angry" are identified. This emotion information is sent to the server and stored in a database. Based on this information, the server adjusts the grammar and vocabulary of the new language. For example, if a negative emotion is recognized, adjustments are made to provide more comforting expressions.

[0763] As a concrete example, the server collects and analyzes the English and Japanese versions of "Thank you," revealing differences in cultural background and subtle nuances in the expression of gratitude. For example, the Japanese version of "Thank you" is commonly used, while the English version is limited to specific situations. Taking this difference into account, the word "Gratalo" is generated as a new common vocabulary.

[0764] An example prompt is, "Use GPT-4 to analyze the subtle differences in nuance between the Japanese and English versions of 'thank you' and generate a new common vocabulary." In this way, a new language that is universally understandable and flexible enough to accommodate emotions will be developed.

[0765] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0766] Step 1:

[0767] The server collects language data from around the world from the internet and existing databases. This process uses crawling techniques and APIs to obtain text data, grammar information, translation materials, and more from various sources (e.g., Wikipedia, Google Books, academic paper databases).

[0768] Input: A list of URLs from which language data can be sourced

[0769] Output: A set of collected language data

[0770] Specific operation: The server runs the crawling script to obtain data from the URL list, and then stores the obtained data in storage.

[0771] Step 2:

[0772] The server analyzes the collected language data using generative AI models (e.g., BERT and GPT-4), which extracts the meanings, usage, grammar, and nuances of words in each language.

[0773] Input: Collected language data

[0774] Output: Parsed language data

[0775] How it works: The server runs a Python script to invoke the generative AI model, which then analyzes the language data as input. The analysis results are then stored in a database.

[0776] Step 3:

[0777] The server groups words and phrases with common meanings and nuances based on the analysis results, and then categorizes them using a clustering algorithm.

[0778] Input: Parsed language data

[0779] Output: Words and phrases grouped by category

[0780] How it works: Based on the output of the generative AI model, the server applies a clustering algorithm to group words and phrases and stores the classification results in a database.

[0781] Step 4:

[0782] The user (a linguistics expert) reviews the results and adds annotations about specific cultural backgrounds and nuances, and this additional information is sent back to the server.

[0783] Input: Grouped words or phrases

[0784] Output: Data annotated with cultural context and nuances

[0785] What it does: Linguists access the data through a dedicated interface, add any necessary annotations, and then send the data to the server, which updates the database.

[0786] Step 5:

[0787] A user (linguist) designs the grammar and vocabulary of a new language, carefully examining the definitions of parts of speech, sentence structure, verb conjugation rules, etc., and uploads the designed grammar rules to the server.

[0788] Input: Annotated analysis results

[0789] Output: Draft grammar and vocabulary of the new language

[0790] What it does: Linguists use specialized editing software to design the grammar and vocabulary of a new language, then upload the data to a server.

[0791] Step 6:

[0792] The server then creates the new language based on the generated grammar and vocabulary. At this stage, a dictionary and learning manual for the new language are created and uploaded digitally.

[0793] Input: A draft grammar and vocabulary for the new language

[0794] Output: Dictionary and learning manual for the new language

[0795] Specific operation: The server generates a digital dictionary and learning manual for the new language based on the grammar and vocabulary and stores it in a database.

[0796] Step 7:

[0797] The device provides the new language to the user and collects communication results and feedback from the user.

[0798] Input: Dictionary and learning manual for a new language

[0799] Output: User feedback

[0800] Specific operation: A dedicated application installed on the device provides the new language, collects user usage logs and feedback, and sends them to a server.

[0801] Step 8:

[0802] The device uses an emotion engine to analyze the user's emotions, using voice recognition technology and text emotion analysis algorithms.

[0803] Input: User voice or text data

[0804] Output: Emotion data

[0805] Specific operation: Using the device's voice recognition software and natural language processing library, the system analyzes the user's emotions in real time and sends the results to the server.

[0806] Step 9:

[0807] The server adjusts the grammar and vocabulary of the new language based on the identified emotional information.

[0808] Input: Emotional data and user feedback

[0809] Output: Adjusted grammar and vocabulary

[0810] Specific operation: Based on the fed-back emotion data, the server readjusts the generative AI model and makes appropriate corrections to phrases and grammar.

[0811] (Application example 2)

[0812] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0813] In today's diverse language environment, there is a growing need for a new language that can be commonly understood by people all over the world. There is also a demand for providing user experiences based on emotions, but existing systems have had difficulty achieving this effectively. Similarly, there is also the issue of services such as food delivery not providing personalized services that take user emotions into account.

[0814] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0815] In this invention, the server includes: means for collecting language data from around the world; means for generating a natural language processing model for analyzing the collected language data; means for grouping words and phrases with common meanings and nuances from the analyzed data; means for creating a grammar and vocabulary for a new language based on the analysis results and the grouped information; means for providing the newly created language to users and collecting feedback; means for improving the new language based on the collected feedback; and means for recognizing user emotions and suggesting appropriate vocabulary and phrases based on the emotions. This enables the development of a new language that is universally understandable and flexible enough to respond to emotions. It also enables services such as food delivery to provide personalized experiences based on user emotions.

[0816] "Global language data" refers to text data, translation materials, grammar information, etc. for a wide variety of languages ​​collected from the Internet and existing databases.

[0817] A "natural language processing model" is an artificial intelligence model for analyzing collected language data, including generative AI models such as BERT and GPT-4.

[0818] "Analysis" refers to the process of using a generative AI model to analyze the vocabulary, grammar, nuances, etc. of collected language data to understand its meaning and usage.

[0819] "Grouping" refers to the process of categorizing words and phrases with common meanings and nuances from analyzed data.

[0820] "Creating a grammar and vocabulary for a new language" refers to the process of constructing a newly designed system of grammatical rules and words based on the analyzed and grouped information.

[0821] "Providing to the user" refers to providing the newly created language in a form that the user can use through the terminal.

[0822] "Collecting feedback" refers to the process of collecting user usage results and reactions via the device and obtaining them as data for analysis.

[0823] "Improving the new language" refers to the process of adjusting the generative AI model, grammar, and vocabulary based on collected feedback to improve the accuracy and usability of the language.

[0824] "Recognizing user emotions" refers to the process of identifying a user's emotional state using voice recognition technology and text emotion analysis algorithms.

[0825] "Suggesting appropriate vocabulary and phrases based on emotions" refers to the process of presenting the most appropriate words and phrases to the user based on analyzed emotional information.

[0826] This invention is a system that collects and analyzes language data from around the world to generate new languages ​​with common meanings and nuances, and further combines it with an emotion engine that recognizes user emotions to improve user experience. This system can make personalized menu suggestions based on user emotions, especially in food delivery applications.

[0827] Data collection and analysis

[0828] The first thing the server does is collect language data from around the world. The hardware used is a cloud-based server (e.g., AWS EC2 or Google Cloud Platform) that retrieves data from existing databases and the internet. Data is collected from sources such as Wikipedia articles, Google Books, and academic papers, and then integrated into a large dataset containing text, grammar information, and translation materials.

[0829] The collected data is then analyzed by a server using generative AI models, including the latest natural language processing techniques such as BERT and GPT-4. At this stage, the meaning, usage, grammar, and nuances of words in each language are analyzed, and the results are stored in a database.

[0830] Creating a new language

[0831] Based on the analysis results, the server groups words and phrases that share common meanings and nuances. For example, in this step, they are classified into categories such as "greetings," "thanks," and "honorifics." The grouping information is then used to create the grammar and vocabulary of the new language. Linguistic experts may add annotations regarding specific cultural backgrounds and nuances during this process, ultimately creating a digital dictionary and learning manual for the new language.

[0832] emotion recognition

[0833] The device's emotion engine analyzes the user's voice and text to determine their emotions. Software used includes algorithms from Google Cloud Natural Language and IBM Watson Tone Analyzer. This emotion recognition identifies the user's emotions, such as joy, sadness, and anger.

[0834] Menu recommendation

[0835] Based on the analyzed emotion information, the server recommends the most suitable menu or service for the user. For example, comfort food may be suggested to a user who expresses negative emotion, while a special dessert or a new dish may be suggested to a user who expresses positive emotion. Examples of prompts used at this stage are as follows:

[0836] python

[0837] Dataset preparation

[0838] from transformers import GPT2Tokenizer, GPT2Model

[0839] tokenizer = GPT2Tokenizer.from_pretrained('gpt2')

[0840] model = GPT2Model.from_pretrained('gpt2')

[0841] text = "Enter text data to collect here"

[0842] inputs = tokenizer(text, return_tensors='pt')

[0843] outputs = model(inputs)

[0844] Emotion analysis

[0845] from google.cloud import language_v1

[0846] client = language_v1.LanguageServiceClient()

[0847] document = language_v1.Document(content="Enter text to parse here", type_=language_v1.Document.Type.PLAIN_TEXT)

[0848] sentiment = client.analyze_sentiment(request={'document': document}).document_sentiment

[0849] print(f'Text: {document.content}\nSentiment: {sentiment.score}')

[0850] Menu recommendation

[0851] recommendations = {

[0852] "happy": ["Special Dessert", "Celebration Cake"],

[0853] "sad": ["Comfort Soup", "Chocolate Brownie"],

[0854] "angry": ["Spicy Wings", "Satisfaction Steak"]

[0855] }

[0856] user_emotion = "happy" Parsed emotion result

[0857] recommended_menu = recommendations[user_emotion]

[0858] print(f"Recommended Menu: {recommended_menu}")

[0859] Through the above process, the present invention provides a new language that can be universally understood around the world, while realizing personalized services based on the user's emotions.

[0860] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0861] Step 1:

[0862] The server collects language data from around the world, including text, grammar information, and translation materials such as Wikipedia articles, Google Books, and academic papers, using a cloud-based server (e.g., AWS EC2 or Google Cloud Platform).

[0863] (Input): Source URL or API endpoint

[0864] (Output): Unified language dataset

[0865] (Specific operation): The server periodically runs the data collection script, obtains data from each source, and integrates it into a single database.

[0866] Step 2:

[0867] The server analyzes the collected data using a generative AI model (e.g., BERT or GPT-4).

[0868] (Input): Unified language dataset

[0869] (Output): Analysis results (word meanings, usage, grammar, nuances, etc. for each language)

[0870] (Specific operation): The server uses a generative AI model to analyze text data, extract word meanings, usage, and grammatical information, and store them in a database.

[0871] Step 3:

[0872] Based on the analysis results, the server groups words and phrases that share a common meaning or nuance.

[0873] (Input): Analysis results

[0874] (Output): Category information of grouped words and phrases

[0875] (Specific behavior): The server runs an automatic classification algorithm to group words and phrases into categories such as "greetings," "thanks," and "honorifics."

[0876] Step 4:

[0877] The server creates the grammar and vocabulary of the new language based on the grouped information.

[0878] (Input): Category information of grouped words and phrases

[0879] (Output): Grammatical and lexical information for the new language

[0880] (Specific operation): The server defines grammar rules, constructs grammar and vocabulary, and creates a dictionary and learning manual for the new language.

[0881] Step 5:

[0882] The server provides the newly created language to users through their devices and collects their feedback.

[0883] (Input): A dictionary and learning manual for a new language

[0884] (Output): User feedback data

[0885] (Specific operation): The user communicates using a new language, and the device records the results and reactions of the communication and sends them to the server as feedback data.

[0886] Step 6:

[0887] The server refines the new language based on the collected feedback.

[0888] (Input): Feedback data

[0889] (Output): Improved grammar and lexical information

[0890] (Specific operation): The server analyzes the feedback data, uses a generative AI model to improve grammar and vocabulary, and updates the results to the database.

[0891] Step 7:

[0892] The device uses an emotion engine to analyze emotions from the user's voice or text. Emotion recognition algorithms (e.g., Google Cloud Natural Language or IBM Watson Tone Analyzer) are used.

[0893] (Input): User voice or text data

[0894] (Output): User's emotional state (e.g., happy, sad, angry, etc.)

[0895] (Specific operation): The device receives the user's voice or text as input, analyzes the emotions using an emotion recognition algorithm, and sends the results to the server.

[0896] Step 8:

[0897] The server then recommends the most suitable menus and services to the user based on the analyzed emotional information.

[0898] (Input): User's emotional state

[0899] (Output): Recommended menu items and services

[0900] (Specific operation): Based on the emotional information, the server searches the database for the most suitable menu or service for the user and sends it to the terminal.

[0901] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0902] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0903] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0904] [Third embodiment]

[0905] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0906] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0907] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0908] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0909] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0910] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0911] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0912] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0913] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0914] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0915] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0916] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0917] This invention is a system for generating a new language with common meanings and nuances by collecting and analyzing language data from around the world. The system is primarily composed of a server, terminals, and users. The program processing of the system is explained in detail below.

[0918] Program processing

[0919] The server first collects language data from around the world via the internet and existing databases, such as Wikipedia articles, Google Books, and academic paper databases, and then integrates it into a single large dataset, including text, grammar information, and translation materials.

[0920] The collected data is then analyzed by a server using a generative AI model, such as machine learning techniques like BERT or GPT-4. The generative AI model performs a detailed analysis of the meaning, usage, grammar, and nuances of words in each language. The results of this analysis are stored in a database for use in later processes.

[0921] Next, the generative AI model uses the analysis results to group words and phrases that share common meanings and nuances. In this step, they are classified into categories such as "greetings," "thanks," and "honorifics." The server then performs these groupings and stores the related information in a database.

[0922] The user (a linguistics expert) then reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. This additional information is sent to the server, which updates the database. For example, a user might note that the Japanese greeting "konnichiwa" (hello) is widely used and not limited to a specific time of day.

[0923] Based on the grouped information, the user (linguist) designs the grammar and vocabulary of the new language, taking into account definitions of parts of speech, sentence structure, verb conjugation rules, etc. The user documents the grammar rules and uploads them to the server.

[0924] The generated grammar and vocabulary are then implemented by the server. For example, a common greeting, "Helkona," is created for the new language. Based on this, dictionaries and learning manuals for the new language are created by users (linguistic experts) and uploaded digitally to the server.

[0925] This new language is provided to users via their devices. Users attempt to communicate in the new language, and the results and feedback are collected via the devices. The collected feedback is analyzed by the server, and generative AI models are used to improve the system and the language.

[0926] Specific examples

[0927] Consider the following scenario as a concrete example. The server collects and analyzes the English and Japanese versions of "Thank you," identifying differences in cultural background and subtle nuances in the expressions of gratitude. For example, the Japanese version of "Thank you" is used regardless of the formality, while the English version is best suited to informal situations. Taking this difference into account, the analysis results are stored in a database, and a new word, such as "Gratalo," is generated as a common vocabulary. Users then attempt to converse using this new word via their devices, and the server uses the resulting feedback to improve the system.

[0928] This system will enable the development of new languages ​​that take into account the nuances and cultural backgrounds of different languages, in order to achieve accurate communication worldwide.

[0929] The processing flow will be explained below.

[0930] Step 1:

[0931] The server collects language data from around the world by crawling and collecting text data from internet text corpora, translation materials, linguistic research papers, etc. Specifically, it integrates data from Wikipedia articles, academic paper databases, online dictionaries, etc., and compiles it into a single large dataset.

[0932] Step 2:

[0933] The server inputs the collected language data into a natural language processing model, which uses generative AI models such as BERT and GPT-4 to analyze the meaning, usage, grammar, and nuances of each word in each language. This analysis process yields detailed information about each word and phrase.

[0934] Step 3:

[0935] The server stores the analysis results in a database that contains detailed analysis information about the meaning, usage, grammar, and nuance of words and phrases in each language.

[0936] Step 4:

[0937] The server uses a generative AI model to group words and phrases that share a common meaning or nuance, for example, into categories such as greetings, thanks, and honorifics. The results of this grouping are also stored in a database.

[0938] Step 5:

[0939] The user (a linguistics expert) retrieves the analysis results from the server and adds annotations about specific cultural backgrounds and nuances, such as noting that "hello" is used widely and not limited to a specific time of day, resulting in more precise data.

[0940] Step 6:

[0941] The information added by the user is sent again to the server, and the server stores the updated analysis results in the database.

[0942] Step 7:

[0943] The server uses a generative AI model to summarize the analysis results and provide information about grouped words and phrases, which are then stored in a database for further processing.

[0944] Step 8:

[0945] The user (linguist) designs the grammar and vocabulary of the new language based on the summarization results. At this stage, definitions of parts of speech, sentence structure, verb conjugation rules, etc. are designed.

[0946] Step 9:

[0947] A user (a linguist) documents grammar rules and uploads them to a server.

[0948] Step 10:

[0949] The server uses a generative AI model to create the vocabulary needed for the new language. For example, a common greeting, "Helkona," is generated for the new language. This vocabulary list is also stored in a database.

[0950] Step 11:

[0951] A user (a linguistics expert) creates a dictionary or study manual based on the grammar and vocabulary of a new language, including basic words, phrases, and grammar rules of the new language.

[0952] Step 12:

[0953] A user uploads a dictionary or manual created by the user to a server in digital format.

[0954] Step 13:

[0955] The server will develop an app or platform to provide new languages ​​to users, which will help them learn the new language and allow them to actually use the new language.

[0956] Step 14:

[0957] The device will present phrases and words in the new language to the user through the app, allowing the user to try communicating using the new language.

[0958] Step 15:

[0959] Users can input their results and feedback on their communication using the new language through their devices, such as whether the greeting "Helkona" was useful or if there are areas for improvement.

[0960] Step 16:

[0961] The server collects the user feedback and stores it in a database.

[0962] Step 17:

[0963] The server considers improvements to the system and language based on the feedback collected, and uses generative AI models to propose new expressions and update the entire system.

[0964] This concretely implements a series of processes from collection to analysis, development of a new language, testing, gathering feedback, and improvement.

[0965] Example 1

[0966] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0967] Communication between existing languages ​​is problematic due to the many differences in cultural background and nuances that make accurate communication difficult. To solve this problem, there is a need for a method to analyze language data from around the world, generate new languages ​​with common meanings and nuances, and make them easy for users to understand and use.

[0968] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0969] In this invention, the server includes a means for collecting language data from around the world, a means for using a generative AI model to analyze the collected language data, and a means for grouping words and phrases with common meanings and nuances from the analyzed data, thereby creating a grammar and vocabulary for a new language, providing it to users, and collecting feedback to refine it.

[0970] "Global language data" refers to data such as texts, grammar information, and translation materials written in different languages ​​around the world.

[0971] "Generative AI models" refers to machine learning techniques, such as BERT and GPT-4, used to analyze collected language data.

[0972] "Means of collection" refers to methods for acquiring and integrating language data from around the world from the Internet and existing databases.

[0973] "Means of analysis" refers to the use of generative AI models to analyze collected language data and elucidate the meaning, usage, grammar, and nuances of words in each language.

[0974] "Grouping methods" refers to methods for categorizing words and phrases with common meanings and nuances based on the analysis results.

[0975] "Method for creating a grammar and vocabulary for a new language" refers to a method for designing and documenting the grammar rules and vocabulary for a new language based on the analysis results and grouped information.

[0976] "Feedback gathering methods" refers to methods for providing the newly created language to users and gathering their thoughts and suggestions for improvement based on their usage and experiences.

[0977] "Means of improvement" refers to how generative AI models are used to improve the grammar and vocabulary of a new language based on collected feedback.

[0978] This invention is a system for generating new languages ​​with common meanings and nuances by collecting and analyzing language data from around the world. This system is mainly composed of a server, terminals, and users.

[0979] The server collects language data from around the world through the internet and existing databases, such as Wikipedia articles, Google Books, and academic paper databases, and retrieves text, grammar information, and translation materials. This data is then integrated into a single large dataset.

[0980] The collected data is then analyzed by a server. Generative AI models, specifically advanced machine learning techniques such as BERT and GPT-4, are used for the analysis. Generative AI models perform detailed analysis of the meaning, usage, grammar, and nuances of words in each language, and the analysis results are stored in a database. For example, the BERT model is used to analyze the relationships between words in a sentence.

[0981] Next, the server uses a generative AI model to group words and phrases with common meanings and nuances based on the analysis results. At this stage, they are classified into categories such as "greetings," "thanks," and "honorifics." The classified information is stored in a database. For example, "arigato" (thank you) and "thank you" are classified into the "gratitude" category.

[0982] The user (a linguistics expert) reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. For example, the Japanese word "arigatou" (thank you) is widely used, while the English word "thank you" is used mainly in casual settings. This difference is added as a note. This additional information is sent to the server, and the database is updated.

[0983] The user (linguist) designs the grammar and vocabulary of a new language based on the grouped information, taking into account definitions of parts of speech, sentence structure, verb conjugation rules, etc. The user documents the grammar rules and uploads them to the server.

[0984] The generated grammar and vocabulary are implemented by the server. For example, a common greeting word, "Helkona," is created for the new language. The dictionary and learning manual for the new language are created by users (linguistic experts) and uploaded digitally to the server.

[0985] This new language is provided to users via their devices. Users attempt to communicate using it, and the results and feedback are collected via the device. The collected feedback is analyzed by the server, and generative AI models are used to improve the system and language.

[0986] Specific examples

[0987] For example, the system collects the English and Japanese expressions of gratitude, "arigatou" (thank you) and "thank you," and analyzes their cultural backgrounds and differences in meaning. The server categorizes these into groups, and users (linguistic experts) add annotations pointing out the differences. "Gratalo" is generated as a new common vocabulary, which users can use via their terminals. The system is improved based on user feedback.

[0988] Examples of prompt statements

[0989] "Generate words for a new language based on the following dataset: The dataset contains sentences about expressions of gratitude in Japanese and English. Analyze each sentence, taking into account differences in vocabulary and nuance."

[0990] This will enable the development of new languages ​​that take into account the nuances and cultural backgrounds of different languages ​​in order to achieve accurate communication worldwide.

[0991] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0992] Step 1:

[0993] Data collection

[0994] The server collects language data from around the world from the Internet and existing databases.

[0995] Specifically, it retrieves text, grammar information, and translation materials from Wikipedia, academic paper databases, digital book repositories, etc.

[0996] Input: URL and access parameters of the target online database.

[0997] Output: A large dataset that integrates retrieved text, grammar information, and translation materials.

[0998] Step 2:

[0999] Data analysis

[1000] The server analyzes the collected data using a generative AI model (e.g., BERT or GPT-4).

[1001] At this stage, the meaning, usage, grammar, and nuances of words in each language are analyzed, and the results are stored in a database.

[1002] Specifically, it uses the BERT model to analyze the relationships between words in a sentence.

[1003] Input: A large collected dataset.

[1004] Output: Analysis results on word meaning, usage, grammar, and nuance.

[1005] Step 3:

[1006] Grouping of meanings and nuances

[1007] Based on the analysis results, the server groups words and phrases that share a common meaning or nuance.

[1008] At this stage, expressions are classified into "greetings," "thanks," "honorifics," etc.

[1009] As a specific action, "arigatou" and "thank you" are classified into the category of "gratitude."

[1010] Input: Analysis results.

[1011] Output: Words and phrases grouped by category.

[1012] Step 4:

[1013] Expertly reviewed and annotated

[1014] The user (a linguistics expert) reviews the analysis results and adds annotations regarding specific cultural backgrounds and nuances.

[1015] As a specific action, for example, notes are added about the use of "thank you" at specific times and in specific situations.

[1016] Input: Grouped words or phrases.

[1017] Output: Information annotated with cultural context and nuances.

[1018] Step 5:

[1019] Designing grammars and vocabularies for new languages

[1020] The user (a linguist) designs the grammar and vocabulary of a new language based on the grouped information.

[1021] The specific operation is designed taking into consideration definitions of parts of speech, sentence structure, and verb conjugation rules.

[1022] Input: The annotated information.

[1023] Output: Grammar rules and vocabulary of the new language.

[1024] Step 6:

[1025] The realization of a new language

[1026] The server instantiates a new language based on the generated grammar and vocabulary.

[1027] Specific actions include creating a common greeting for the new language called "Helkona" and creating a dictionary and learning manual for the new language in digital format.

[1028] Input: grammar rules and vocabulary of the new language.

[1029] Output: A dictionary and learning manual for the new language.

[1030] Step 7:

[1031] Gathering feedback and improving

[1032] The new language is provided to users via their devices, and their communication results and feedback are collected.

[1033] Specifically, users attempt to communicate in a new language and collect the results and feedback from their devices.

[1034] Input: User feedback.

[1035] Output: The grammar and vocabulary of the new language, improved based on feedback.

[1036] (Application example 1)

[1037] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1038] In today's increasingly globalized world, there are more and more situations where multilingual support is required. Communication between sales staff and customers who speak a variety of languages ​​is a particular challenge in brick-and-mortar stores. Conventional translation applications struggle to provide accurate translations that fully take into account cultural backgrounds and nuances. This leads to lower customer satisfaction and lost sales opportunities. To solve these problems, there is a need for a more accurate multilingual translation system that takes cultural backgrounds and nuances into account.

[1039] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1040] In this invention, the server includes means for collecting language data from around the world, means for generating a natural language processing model for analyzing the collected language data, means for grouping words and phrases with common meanings and nuances from the analyzed data, means for creating a grammar and vocabulary for a new language based on the analysis results and the grouped information, means for providing the newly created language to users and performing real-time multilingual translation between sales staff and customers in physical stores, means for collecting feedback on communication in physical stores, and means for improving the new language based on the collected feedback, thereby enabling advanced multilingual translation and smooth customer service in physical stores.

[1041] "Global Language Data" is a dataset that includes text data, grammar information, translation materials, and more in all languages ​​collected from many sources on the Internet.

[1042] A "collection means" is a system component that collects language data from the Internet or existing databases.

[1043] A "natural language processing model for analysis" is a generative AI model (e.g., BERT or GPT-4) used to analyze collected language data and understand word meaning, usage, grammar, nuances, etc.

[1044] A "grouping means" is a system component that categorizes words and phrases that share a common meaning or nuance from the analyzed data.

[1045] The "means for creating new language grammars and vocabularies" is a system component that designs and generates new grammar rules and vocabularies based on collected and analyzed data.

[1046] The "means to provide to users" refers to the system components that allow users to actually use the new language created.

[1047] The "means for real-time multilingual translation" is a system component that supports real-time multilingual translation between sales staff and customers in a physical store.

[1048] A "feedback gathering means" is a system component that gathers results and user comments on using the new language.

[1049] "Means for improvement" are system components that allow improvements to be made to the system or new languages ​​based on collected feedback.

[1050] This invention is a system that collects and analyzes language data from around the world to generate new languages ​​with common meanings and nuances, enabling real-time multilingual translation between sales staff and customers in physical stores. The system is primarily composed of a server, terminals, and users.

[1051] Server Functions and Processing

[1052] The server performs the following process:

[1053] 1. Collecting global language data:

[1054] The server collects language data from many sources on the Internet, including resources such as Wikipedia, Google Books, and academic paper databases.

[1055] 2. Linguistic Data Analysis:

[1056] The server uses natural language processing models (such as BERT or GPT-4) to analyze the collected data. This generative AI model performs detailed analysis of the meaning, usage, grammar, and nuance of words in each language.

[1057] 3. Grouping words and phrases that share a common meaning or nuance:

[1058] Based on the analysis results, the server groups words and phrases into categories such as "greetings," "thanks," and "honorifics."

[1059] 4. Creating a new language:

[1060] The grammar and vocabulary of the new language are created based on feedback from linguists, and this information is stored on a server for later use.

[1061] Terminal functions and processing

[1062] The following process is implemented on the terminal used by the salesperson:

[1063] 1. New language offerings:

[1064] An application will be installed that will allow salespeople and customers to communicate in real time through the new language created.

[1065] 2. Multilingual Translation:

[1066] Interactions between salespeople and customers will be translated in real time through a new common language, which requires the device to have high-performance computing power and an internet connection.

[1067] User Roles

[1068] The user (linguistics expert) plays the following roles:

[1069] 1. Review the analysis results:

[1070] The server then scrutinizes the data and adds annotations for specific cultural backgrounds and nuances.

[1071] 2. Gather feedback and improve:

[1072] Usage results and feedback from physical stores are collected through the terminals, and based on this, the server uses a generative AI model to improve the new language.

[1073] Hardware and software used

[1074] Generative AI models: Use advanced natural language processing techniques such as BERT and GPT-4.

[1075] Server: Use a server with high-performance data processing capabilities.

[1076] Device: A smartphone or tablet is used.

[1077] Specific examples

[1078] For example, consider an interaction between a Japanese salesperson and an English-speaking customer in a clothing store. When the salesperson says, "Welcome, what are you looking for?", the application translates this into the new common language and displays, "Helkona, what are you looking for?". When the customer says, "Tell me more about this item, please," the translation is displayed to the salesperson as, "Tell me more about this item, please."

[1079] Prompt Sentence Examples

[1080] Here are some examples of prompts:

[1081] Input: Welcome, what are you looking for?

[1082] Prompt: Translate the following sentence into the new common language. Consider cultural context and grammar rules: "Welcome, what are you looking for?"

[1083] Expected output: Helkona, what are you looking for?

[1084]

[1085] Input: Tell me more about this product.

[1086] Prompt: Translate the following sentence into a new common language. Consider cultural context and grammar rules: "Tell me more about this product."

[1087] Expected output: Tell me more about this item, please.

[1088] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1089] Step 1:

[1090] The server collects language data from around the world, including text, grammar information, and translation materials from online sources such as Wikipedia, Google Books, and academic paper databases, and builds a large-scale dataset.

[1091] Input: URL of the website or database to be collected

[1092] Output: A large dataset of collected language data

[1093] Step 2:

[1094] The server analyzes the collected data using natural language processing models (such as BERT and GPT-4), which analyzes the meaning, usage, grammar, and nuance of words in each language in detail.

[1095] Input: A large dataset of collected language data

[1096] Output: Parsed linguistic data (detailed information about word meanings, usage, grammar, and nuances)

[1097] Step 3:

[1098] The server uses a generative AI model to analyze data and group words and phrases with common meanings and nuances into categories such as "greetings," "thanks," and "honorifics."

[1099] Input: Parsed language data

[1100] Output: Words and phrases grouped by category

[1101] Step 4:

[1102] Users (linguistic experts) can review the results analyzed and grouped by the server and add annotations about specific cultural backgrounds and nuances, resulting in more accurate information being stored in the database.

[1103] Input: Grouped words or phrases

[1104] Output: Annotated language data

[1105] Step 5:

[1106] The server creates the grammar and vocabulary of the new language based on feedback from users (linguistic experts), designing definitions of parts of speech, sentence structure, verb conjugation rules, and so on.

[1107] Input: Annotated language data

[1108] Output: Grammar and vocabulary of the new language

[1109] Step 6:

[1110] The server generates specific translation dictionaries and study manuals based on the grammar and vocabulary of the new language, and this information is stored on the system and provided to the terminal.

[1111] Input: Grammar and vocabulary of a new language

[1112] Output: Translation dictionary, learning manual

[1113] Step 7:

[1114] The device (smartphone or tablet) will be provided to the salesperson, and will perform real-time multilingual translation using the newly created language. The salesperson will use this translation function when interacting with customers.

[1115] Input: Text entered by the salesperson

[1116] Output: Translation results in the new language

[1117] Step 8:

[1118] Users (customers and salespeople) use the language generated through interactions in physical stores and send the results and feedback to the system via their terminals.

[1119] Input: Details of the interaction in the physical store

[1120] Output: Feedback from customers and salespeople

[1121] Step 9:

[1122] The server uses the collected feedback to refine the new language using a generative AI model, thereby improving the quality of the system and the language.

[1123] Input: Feedback data from customers and salespeople

[1124] Output: New and improved language

[1125] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1126] This invention is a system that collects and analyzes language data from around the world to generate new languages ​​with common meanings and nuances, and further combines it with an emotion engine that recognizes the user's emotions to improve the user experience. The program processing of this system is explained in detail below.

[1127] Program processing

[1128] The server first collects language data from around the world via the internet and existing databases, such as Wikipedia articles, Google Books, and academic paper databases, and then integrates it into a large dataset that includes text, grammar information, and translation materials.

[1129] The collected data is then analyzed by a server using a generative AI model, such as the latest natural language processing technology like BERT or GPT-4. The generative AI model analyzes the meaning, usage, grammar, and nuance of words in each language. The analysis results are stored in a database and used in subsequent processes.

[1130] Next, the generative AI model uses the analysis results to group words and phrases that share common meanings and nuances. In this step, they are classified into categories such as "greetings," "thanks," and "honorifics." The server then performs these groupings and stores the related information in a database.

[1131] The user (a linguistics expert) then reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. This additional information is sent to the server, which updates the database. For example, a user might note that the Japanese greeting "konnichiwa" (hello) is widely used and not limited to a specific time of day.

[1132] Next, the user (a linguist) designs the grammar and vocabulary of the new language. This stage takes into account definitions of parts of speech, sentence structure, verb conjugation rules, etc. The grammar rules are documented and uploaded to the server.

[1133] The generated grammar and vocabulary are then implemented by the server. For example, a common greeting, "Helkona," is generated for the new language. Based on this, a dictionary and learning manual for the new language can be created by the user (a linguistics expert) and uploaded digitally to the server.

[1134] The new language is provided to users via their devices. Users attempt to communicate in the new language, and the results and feedback are collected via the devices. The collected feedback is analyzed by the server, and the system and language are improved using a generative AI model.

[1135] Adding an Emotion Engine

[1136] A distinctive feature of this invention is that by combining it with an emotion engine, it is possible to provide language that takes the user's emotions into consideration. The device uses the emotion engine to analyze emotions from the user's voice and text. For example, using voice recognition technology and text emotion analysis algorithms, the device can identify the user's emotions, such as "happy," "sad," or "angry."

[1137] The identified emotions are then sent to a server and stored in a database, which uses this emotional information to adapt the grammar and vocabulary of the new language accordingly, for example by providing phrases containing more comforting expressions when negative emotions are recognized.

[1138] Specific examples

[1139] Consider the following scenario: The server collects and analyzes the English and Japanese versions of "Thank you," identifying differences in cultural background and subtle nuances in the expression of gratitude. For example, the Japanese version of "Thank you" is used regardless of formality, while the English version of "Thank you" is best suited to informal situations. Taking this difference into account, the analysis results are stored in a database, and a new common vocabulary word, such as "Gratalo," is generated.

[1140] Meanwhile, the device has emotion recognition capabilities and analyzes the emotions users feel when using Gratalo. If the user is expressing positive emotions, the emotion engine will suggest additional expressions that match that emotion. Conversely, if the user is expressing negative emotions, the engine will adjust to provide more comforting phrases.

[1141] Through this process, the system will collect, analyze, develop a new language, adjust based on emotions, test, collect feedback, and refine, developing a new language that is universally understandable and flexible enough to respond to emotions.

[1142] The processing flow will be explained below.

[1143] Step 1:

[1144] The server collects language data from around the world, including internet text corpora, translations, and linguistic research papers. For example, it crawls language data from Wikipedia articles, Google Books, and academic paper databases, and combines them into one large dataset.

[1145] Step 2:

[1146] The server inputs the collected language data into a natural language processing model. Here, generative AI models such as BERT and GPT-4 are used to analyze the meaning, usage, grammar, and nuance of words in each language. Specifically, detailed information about each word is extracted based on context, frequency, analogy, and other factors.

[1147] Step 3:

[1148] The server stores the analysis results in a database that contains detailed analysis information about the meaning, usage, grammar, and nuance of words and phrases in each language.

[1149] Step 4:

[1150] The server uses a generative AI model to group words and phrases with common meanings and nuances based on the analysis results, for example, into categories such as "greetings," "thanks," and "honorifics," and stores the related information in a database.

[1151] Step 5:

[1152] Users (linguistic experts) can take the analysis results and add annotations about specific cultural backgrounds and nuances, such as noting that "hello" is used widely and not limited to a specific time of day, resulting in more precise data.

[1153] Step 6:

[1154] The information added by the user is sent again to the server, and the server stores the updated analysis results in the database.

[1155] Step 7:

[1156] The server uses a generative AI model to summarize the analysis results and provide information about grouped words and phrases, which are then stored in a database for further processing.

[1157] Step 8:

[1158] The user (linguist) designs the grammar and vocabulary of the new language based on the summarization results. At this stage, definitions of parts of speech, sentence structure, verb conjugation rules, etc. are taken into account. The grammar rules are documented and uploaded to the server.

[1159] Step 9:

[1160] The server uses a generative AI model to create the vocabulary needed for the new language. For example, a common greeting, "Helkona," is generated for the new language. This vocabulary list is also stored in a database.

[1161] Step 10:

[1162] A user (a linguistics expert) creates a dictionary or study manual based on the grammar and vocabulary of a new language, including basic words, phrases, and grammar rules of the new language.

[1163] Step 11:

[1164] A user uploads a dictionary or manual created by the user to a server in digital format.

[1165] Step 12:

[1166] The server will develop an app or platform to provide new languages ​​to users, which will help them learn the new language and allow them to actually use the new language.

[1167] Step 13:

[1168] The device will present phrases and words in the new language to the user through the app, allowing the user to try communicating using the new language.

[1169] Step 14:

[1170] The device uses an emotion engine to analyze emotions from the user's voice and text. For example, it uses voice recognition technology and text emotion analysis algorithms to identify emotions such as "happy," "sad," or "angry."

[1171] Step 15:

[1172] The device sends the identified emotions to a server, which stores the information in a database.

[1173] Step 16:

[1174] The server uses the emotional information to adjust the grammar and vocabulary of the new language depending on the user's emotions, for example by providing phrases that contain more comforting expressions if negative emotions are recognized.

[1175] Step 17:

[1176] Users can input their results and feedback on their communication using the new language through their devices, such as whether the greeting "Helkona" was useful or if there are areas for improvement.

[1177] Step 18:

[1178] The server collects the user feedback and stores it in a database.

[1179] Step 19:

[1180] The server considers improvements to the system and language based on the feedback collected, and uses generative AI models to propose new expressions and update the entire system.

[1181] Through these steps, a series of processes are concretely carried out, from collection and analysis, to new language development, adjustment based on emotions, testing, and feedback collection and refinement. This system will develop a new language that is universally understandable, flexible, and responds to emotions.

[1182] Example 2

[1183] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1184] In modern society, there are many different languages, and communication between different languages ​​is often a barrier. Differences in emotional expression also lead to misunderstandings between different cultures. While efforts have been made to develop a common language that is not dependent on a specific language or culture, it is often insufficient in addressing the nuances of language and emotional expression. To solve these issues, there is a need to develop a new language that can be understood universally and is flexible enough to respond to emotions.

[1185] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1186] In this invention, the server includes: means for collecting language data from around the world; means for using a generative AI model to analyze the collected language data; means for grouping words and phrases with common meanings and nuances from the analyzed data; means for creating the grammar and vocabulary of a new language based on the analysis results and the grouped information; means for providing the newly created language to users and collecting feedback; means for improving the new language based on the collected feedback; means for using an emotion engine to analyze user emotions; and means for adjusting the grammar and vocabulary of the new language based on the user emotions. This enables the development of a new language that is universally understandable and flexible enough to respond to emotions.

[1187] "Global language data" refers to text data, grammar information, translation materials, etc. in various languages ​​collected from the Internet and existing databases.

[1188] A "generative AI model" is an artificial intelligence model based on the latest natural language processing techniques such as BERT and GPT-4, and is used to analyze language data.

[1189] "Grouping" refers to the process of categorizing words and phrases with common meanings and nuances from analyzed data.

[1190] A "new language" refers to a language with a newly created grammar and vocabulary that has been analyzed and grouped based on linguistic data from around the world.

[1191] "User" refers to the person or group who uses this new language and provides feedback.

[1192] "Feedback" is information such as users' experiences and opinions when using a new language, and this information is collected to help improve the language.

[1193] An "emotion engine" refers to algorithms and technologies that analyze a user's voice and text data to identify emotions.

[1194] "Grammar and vocabulary adjustment" refers to the process of appropriately modifying and optimizing the grammar and vocabulary of the new language based on the identified emotional information.

[1195] "Universally understandable and emotionally responsive" refers to a language that can be commonly understood by people who speak any language, and has flexible language characteristics that can adapt to the user's emotions.

[1196] This invention is a system that collects language data from around the world, analyzes and groups the data using a generative AI model, and generates a new common language. By combining this system with an emotion engine, the system aims to provide a flexible language that also responds to the user's emotions. Detailed embodiments of this system are described below.

[1197] The server first collects language data from around the world from the Internet and existing databases. Specific sources used include Wikipedia, Google Books, and academic paper databases. The collected data includes text data, grammar information, and translation materials. The server collects this data and builds a large dataset. The data is collected using crawling techniques and APIs.

[1198] The collected language data is then analyzed by the server. Generative AI models, such as BERT and GPT-4, are used for the analysis. These models use deep learning to analyze the meaning, usage, grammar, and nuances of words in each language. The analysis results are stored in a database and used in later processes. Furthermore, based on the analysis results, words and phrases with common meanings and nuances are grouped into categories. Clustering algorithms and other techniques are used here.

[1199] Next, the user (a linguistics expert) reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. This additional information is also sent to the server, and the database is updated. For example, a note is added about the difference between the usage of "arigatou" in Japanese and the English "thank you."

[1200] Next, the user (a linguist) designs the grammar and vocabulary of the new language. At this stage, definitions of parts of speech, sentence structure, verb conjugation rules, etc. are considered in detail. The designed grammar rules are then uploaded to the server.

[1201] Based on the generated grammar and vocabulary, the server will create a new language. For example, a new common greeting called "Helkona" will be generated. The dictionary and learning manual for this new language will be created by linguistic experts and uploaded digitally to the server.

[1202] The new language is provided to users via their devices. Users attempt to communicate using this new language, and the results and feedback are collected via the devices. The feedback information is analyzed by the server, and the system and language are improved using a generative AI model.

[1203] Furthermore, an emotion engine is built into the system. The device uses voice recognition technology and text emotion analysis algorithms to analyze the user's emotions. For example, emotions such as "happy," "sad," and "angry" are identified. This emotion information is sent to the server and stored in a database. Based on this information, the server adjusts the grammar and vocabulary of the new language. For example, if a negative emotion is recognized, adjustments are made to provide more comforting expressions.

[1204] As a concrete example, the server collects and analyzes the English and Japanese versions of "Thank you," revealing differences in cultural background and subtle nuances in the expression of gratitude. For example, the Japanese version of "Thank you" is commonly used, while the English version is limited to specific situations. Taking this difference into account, the word "Gratalo" is generated as a new common vocabulary.

[1205] An example prompt is, "Use GPT-4 to analyze the subtle differences in nuance between the Japanese and English versions of 'thank you' and generate a new common vocabulary." In this way, a new language that is universally understandable and flexible enough to accommodate emotions will be developed.

[1206] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1207] Step 1:

[1208] The server collects language data from around the world from the internet and existing databases. This process uses crawling techniques and APIs to obtain text data, grammar information, translation materials, and more from various sources (e.g., Wikipedia, Google Books, academic paper databases).

[1209] Input: A list of URLs from which language data can be sourced

[1210] Output: A set of collected language data

[1211] Specific operation: The server runs the crawling script to obtain data from the URL list, and then stores the obtained data in storage.

[1212] Step 2:

[1213] The server analyzes the collected language data using generative AI models (e.g., BERT and GPT-4), which extracts the meanings, usage, grammar, and nuances of words in each language.

[1214] Input: Collected language data

[1215] Output: Parsed language data

[1216] How it works: The server runs a Python script to invoke the generative AI model, which then analyzes the language data as input. The analysis results are then stored in a database.

[1217] Step 3:

[1218] The server groups words and phrases with common meanings and nuances based on the analysis results, and then categorizes them using a clustering algorithm.

[1219] Input: Parsed language data

[1220] Output: Words and phrases grouped by category

[1221] How it works: Based on the output of the generative AI model, the server applies a clustering algorithm to group words and phrases and stores the classification results in a database.

[1222] Step 4:

[1223] The user (a linguistics expert) reviews the results and adds annotations about specific cultural backgrounds and nuances, and this additional information is sent back to the server.

[1224] Input: Grouped words or phrases

[1225] Output: Data annotated with cultural context and nuances

[1226] What it does: Linguists access the data through a dedicated interface, add any necessary annotations, and then send the data to the server, which updates the database.

[1227] Step 5:

[1228] A user (linguist) designs the grammar and vocabulary of a new language, carefully examining the definitions of parts of speech, sentence structure, verb conjugation rules, etc., and uploads the designed grammar rules to the server.

[1229] Input: Annotated analysis results

[1230] Output: Draft grammar and vocabulary of the new language

[1231] What it does: Linguists use specialized editing software to design the grammar and vocabulary of a new language, then upload the data to a server.

[1232] Step 6:

[1233] The server then creates the new language based on the generated grammar and vocabulary. At this stage, a dictionary and learning manual for the new language are created and uploaded digitally.

[1234] Input: A draft grammar and vocabulary for the new language

[1235] Output: Dictionary and learning manual for the new language

[1236] Specific operation: The server generates a digital dictionary and learning manual for the new language based on the grammar and vocabulary and stores it in a database.

[1237] Step 7:

[1238] The device provides the new language to the user and collects communication results and feedback from the user.

[1239] Input: Dictionary and learning manual for a new language

[1240] Output: User feedback

[1241] Specific operation: A dedicated application installed on the device provides the new language, collects user usage logs and feedback, and sends them to a server.

[1242] Step 8:

[1243] The device uses an emotion engine to analyze the user's emotions, using voice recognition technology and text emotion analysis algorithms.

[1244] Input: User voice or text data

[1245] Output: Emotion data

[1246] Specific operation: Using the device's voice recognition software and natural language processing library, the system analyzes the user's emotions in real time and sends the results to the server.

[1247] Step 9:

[1248] The server adjusts the grammar and vocabulary of the new language based on the identified emotional information.

[1249] Input: Emotional data and user feedback

[1250] Output: Adjusted grammar and vocabulary

[1251] Specific operation: Based on the fed-back emotion data, the server readjusts the generative AI model and makes appropriate corrections to phrases and grammar.

[1252] (Application example 2)

[1253] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1254] In today's diverse language environment, there is a growing need for a new language that can be commonly understood by people all over the world. There is also a demand for providing user experiences based on emotions, but existing systems have had difficulty achieving this effectively. Similarly, there is also the issue of services such as food delivery not providing personalized services that take user emotions into account.

[1255] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1256] In this invention, the server includes: means for collecting language data from around the world; means for generating a natural language processing model for analyzing the collected language data; means for grouping words and phrases with common meanings and nuances from the analyzed data; means for creating a grammar and vocabulary for a new language based on the analysis results and the grouped information; means for providing the newly created language to users and collecting feedback; means for improving the new language based on the collected feedback; and means for recognizing user emotions and suggesting appropriate vocabulary and phrases based on the emotions. This enables the development of a new language that is universally understandable and flexible enough to respond to emotions. It also enables services such as food delivery to provide personalized experiences based on user emotions.

[1257] "Global language data" refers to text data, translation materials, grammar information, etc. for a wide variety of languages ​​collected from the Internet and existing databases.

[1258] A "natural language processing model" is an artificial intelligence model for analyzing collected language data, including generative AI models such as BERT and GPT-4.

[1259] "Analysis" refers to the process of using a generative AI model to analyze the vocabulary, grammar, nuances, etc. of collected language data to understand its meaning and usage.

[1260] "Grouping" refers to the process of categorizing words and phrases with common meanings and nuances from analyzed data.

[1261] "Creating a grammar and vocabulary for a new language" refers to the process of constructing a newly designed system of grammatical rules and words based on the analyzed and grouped information.

[1262] "Providing to the user" refers to providing the newly created language in a form that the user can use through the terminal.

[1263] "Collecting feedback" refers to the process of collecting user usage results and reactions via the device and obtaining them as data for analysis.

[1264] "Improving the new language" refers to the process of adjusting the generative AI model, grammar, and vocabulary based on collected feedback to improve the accuracy and usability of the language.

[1265] "Recognizing user emotions" refers to the process of identifying a user's emotional state using voice recognition technology and text emotion analysis algorithms.

[1266] "Suggesting appropriate vocabulary and phrases based on emotions" refers to the process of presenting the most appropriate words and phrases to the user based on analyzed emotional information.

[1267] This invention is a system that collects and analyzes language data from around the world to generate new languages ​​with common meanings and nuances, and further combines it with an emotion engine that recognizes user emotions to improve user experience. This system can make personalized menu suggestions based on user emotions, especially in food delivery applications.

[1268] Data collection and analysis

[1269] The first thing the server does is collect language data from around the world. The hardware used is a cloud-based server (e.g., AWS EC2 or Google Cloud Platform) that retrieves data from existing databases and the internet. Data is collected from sources such as Wikipedia articles, Google Books, and academic papers, and then integrated into a large dataset containing text, grammar information, and translation materials.

[1270] The collected data is then analyzed by a server using generative AI models, including the latest natural language processing techniques such as BERT and GPT-4. At this stage, the meaning, usage, grammar, and nuances of words in each language are analyzed, and the results are stored in a database.

[1271] Creating a new language

[1272] Based on the analysis results, the server groups words and phrases that share common meanings and nuances. For example, in this step, they are classified into categories such as "greetings," "thanks," and "honorifics." The grouping information is then used to create the grammar and vocabulary of the new language. Linguistic experts may add annotations regarding specific cultural backgrounds and nuances during this process, ultimately creating a digital dictionary and learning manual for the new language.

[1273] emotion recognition

[1274] The device's emotion engine analyzes the user's voice and text to determine their emotions. Software used includes algorithms from Google Cloud Natural Language and IBM Watson Tone Analyzer. This emotion recognition identifies the user's emotions, such as joy, sadness, and anger.

[1275] Menu recommendation

[1276] Based on the analyzed emotion information, the server recommends the most suitable menu or service for the user. For example, comfort food may be suggested to a user who expresses negative emotion, while a special dessert or a new dish may be suggested to a user who expresses positive emotion. Examples of prompts used at this stage are as follows:

[1277] python

[1278] Dataset preparation

[1279] from transformers import GPT2Tokenizer, GPT2Model

[1280] tokenizer = GPT2Tokenizer.from_pretrained('gpt2')

[1281] model = GPT2Model.from_pretrained('gpt2')

[1282] text = "Enter text data to collect here"

[1283] inputs = tokenizer(text, return_tensors='pt')

[1284] outputs = model(inputs)

[1285] Emotion analysis

[1286] from google.cloud import language_v1

[1287] client = language_v1.LanguageServiceClient()

[1288] document = language_v1.Document(content="Enter text to parse here", type_=language_v1.Document.Type.PLAIN_TEXT)

[1289] sentiment = client.analyze_sentiment(request={'document': document}).document_sentiment

[1290] print(f'Text: {document.content}\nSentiment: {sentiment.score}')

[1291] Menu recommendation

[1292] recommendations = {

[1293] "happy": ["Special Dessert", "Celebration Cake"],

[1294] "sad": ["Comfort Soup", "Chocolate Brownie"],

[1295] "angry": ["Spicy Wings", "Satisfaction Steak"]

[1296] }

[1297] user_emotion = "happy" Parsed emotion result

[1298] recommended_menu = recommendations[user_emotion]

[1299] print(f"Recommended Menu: {recommended_menu}")

[1300] Through the above process, the present invention provides a new language that can be universally understood around the world, while realizing personalized services based on the user's emotions.

[1301] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1302] Step 1:

[1303] The server collects language data from around the world, including text, grammar information, and translation materials such as Wikipedia articles, Google Books, and academic papers, using a cloud-based server (e.g., AWS EC2 or Google Cloud Platform).

[1304] (Input): Source URL or API endpoint

[1305] (Output): Unified language dataset

[1306] (Specific operation): The server periodically runs the data collection script, obtains data from each source, and integrates it into a single database.

[1307] Step 2:

[1308] The server analyzes the collected data using a generative AI model (e.g., BERT or GPT-4).

[1309] (Input): Unified language dataset

[1310] (Output): Analysis results (word meanings, usage, grammar, nuances, etc. for each language)

[1311] (Specific operation): The server uses a generative AI model to analyze text data, extract word meanings, usage, and grammatical information, and store them in a database.

[1312] Step 3:

[1313] Based on the analysis results, the server groups words and phrases that share a common meaning or nuance.

[1314] (Input): Analysis results

[1315] (Output): Category information of grouped words and phrases

[1316] (Specific behavior): The server runs an automatic classification algorithm to group words and phrases into categories such as "greetings," "thanks," and "honorifics."

[1317] Step 4:

[1318] The server creates the grammar and vocabulary of the new language based on the grouped information.

[1319] (Input): Category information of grouped words and phrases

[1320] (Output): Grammatical and lexical information for the new language

[1321] (Specific operation): The server defines grammar rules, constructs grammar and vocabulary, and creates a dictionary and learning manual for the new language.

[1322] Step 5:

[1323] The server provides the newly created language to users through their devices and collects their feedback.

[1324] (Input): A dictionary and learning manual for a new language

[1325] (Output): User feedback data

[1326] (Specific operation): The user communicates using a new language, and the device records the results and reactions of the communication and sends them to the server as feedback data.

[1327] Step 6:

[1328] The server refines the new language based on the collected feedback.

[1329] (Input): Feedback data

[1330] (Output): Improved grammar and lexical information

[1331] (Specific operation): The server analyzes the feedback data, uses a generative AI model to improve grammar and vocabulary, and updates the results to the database.

[1332] Step 7:

[1333] The device uses an emotion engine to analyze emotions from the user's voice or text. Emotion recognition algorithms (e.g., Google Cloud Natural Language or IBM Watson Tone Analyzer) are used.

[1334] (Input): User voice or text data

[1335] (Output): User's emotional state (e.g., happy, sad, angry, etc.)

[1336] (Specific operation): The device receives the user's voice or text as input, analyzes the emotions using an emotion recognition algorithm, and sends the results to the server.

[1337] Step 8:

[1338] The server then recommends the most suitable menus and services to the user based on the analyzed emotional information.

[1339] (Input): User's emotional state

[1340] (Output): Recommended menu items and services

[1341] (Specific operation): Based on the emotional information, the server searches the database for the most suitable menu or service for the user and sends it to the terminal.

[1342] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1343] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1344] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1345] [Fourth embodiment]

[1346] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1347] 7, a 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.

[1348] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1349] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1350] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1351] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1352] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1353] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1354] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1355] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1356] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1357] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1358] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1359] This invention is a system for generating a new language with common meanings and nuances by collecting and analyzing language data from around the world. The system is primarily composed of a server, terminals, and users. The program processing of the system is explained in detail below.

[1360] Program processing

[1361] The server first collects language data from around the world via the internet and existing databases, such as Wikipedia articles, Google Books, and academic paper databases, and then integrates it into a single large dataset, including text, grammar information, and translation materials.

[1362] The collected data is then analyzed by a server using a generative AI model, such as machine learning techniques like BERT or GPT-4. The generative AI model performs a detailed analysis of the meaning, usage, grammar, and nuances of words in each language. The results of this analysis are stored in a database for use in later processes.

[1363] Next, the generative AI model uses the analysis results to group words and phrases that share common meanings and nuances. In this step, they are classified into categories such as "greetings," "thanks," and "honorifics." The server then performs these groupings and stores the related information in a database.

[1364] The user (a linguistics expert) then reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. This additional information is sent to the server, which updates the database. For example, a user might note that the Japanese greeting "konnichiwa" (hello) is widely used and not limited to a specific time of day.

[1365] Based on the grouped information, the user (linguist) designs the grammar and vocabulary of the new language, taking into account definitions of parts of speech, sentence structure, verb conjugation rules, etc. The user documents the grammar rules and uploads them to the server.

[1366] The generated grammar and vocabulary are then implemented by the server. For example, a common greeting, "Helkona," is created for the new language. Based on this, dictionaries and learning manuals for the new language are created by users (linguistic experts) and uploaded digitally to the server.

[1367] This new language is provided to users via their devices. Users attempt to communicate in the new language, and the results and feedback are collected via the devices. The collected feedback is analyzed by the server, and generative AI models are used to improve the system and the language.

[1368] Specific examples

[1369] Consider the following scenario as a concrete example. The server collects and analyzes the English and Japanese versions of "Thank you," identifying differences in cultural background and subtle nuances in the expressions of gratitude. For example, the Japanese version of "Thank you" is used regardless of the formality, while the English version is best suited to informal situations. Taking this difference into account, the analysis results are stored in a database, and a new word, such as "Gratalo," is generated as a common vocabulary. Users then attempt to converse using this new word via their devices, and the server uses the resulting feedback to improve the system.

[1370] This system will enable the development of new languages ​​that take into account the nuances and cultural backgrounds of different languages, in order to achieve accurate communication worldwide.

[1371] The processing flow will be explained below.

[1372] Step 1:

[1373] The server collects language data from around the world by crawling and collecting text data from internet text corpora, translation materials, linguistic research papers, etc. Specifically, it integrates data from Wikipedia articles, academic paper databases, online dictionaries, etc., and compiles it into a single large dataset.

[1374] Step 2:

[1375] The server inputs the collected language data into a natural language processing model, which uses generative AI models such as BERT and GPT-4 to analyze the meaning, usage, grammar, and nuances of each word in each language. This analysis process yields detailed information about each word and phrase.

[1376] Step 3:

[1377] The server stores the analysis results in a database that contains detailed analysis information about the meaning, usage, grammar, and nuance of words and phrases in each language.

[1378] Step 4:

[1379] The server uses a generative AI model to group words and phrases that share a common meaning or nuance, for example, into categories such as greetings, thanks, and honorifics. The results of this grouping are also stored in a database.

[1380] Step 5:

[1381] The user (a linguistics expert) retrieves the analysis results from the server and adds annotations about specific cultural backgrounds and nuances, such as noting that "hello" is used widely and not limited to a specific time of day, resulting in more precise data.

[1382] Step 6:

[1383] The information added by the user is sent again to the server, and the server stores the updated analysis results in the database.

[1384] Step 7:

[1385] The server uses a generative AI model to summarize the analysis results and provide information about grouped words and phrases, which are then stored in a database for further processing.

[1386] Step 8:

[1387] The user (linguist) designs the grammar and vocabulary of the new language based on the summarization results. At this stage, definitions of parts of speech, sentence structure, verb conjugation rules, etc. are designed.

[1388] Step 9:

[1389] A user (a linguist) documents grammar rules and uploads them to a server.

[1390] Step 10:

[1391] The server uses a generative AI model to create the vocabulary needed for the new language. For example, a common greeting, "Helkona," is generated for the new language. This vocabulary list is also stored in a database.

[1392] Step 11:

[1393] A user (a linguistics expert) creates a dictionary or study manual based on the grammar and vocabulary of a new language, including basic words, phrases, and grammar rules of the new language.

[1394] Step 12:

[1395] A user uploads a dictionary or manual created by the user to a server in digital format.

[1396] Step 13:

[1397] The server will develop an app or platform to provide new languages ​​to users, which will help them learn the new language and allow them to actually use the new language.

[1398] Step 14:

[1399] The device will present phrases and words in the new language to the user through the app, allowing the user to try communicating using the new language.

[1400] Step 15:

[1401] Users can input their results and feedback on their communication using the new language through their devices, such as whether the greeting "Helkona" was useful or if there are areas for improvement.

[1402] Step 16:

[1403] The server collects the user feedback and stores it in a database.

[1404] Step 17:

[1405] The server considers improvements to the system and language based on the feedback collected, and uses generative AI models to propose new expressions and update the entire system.

[1406] This concretely implements a series of processes from collection to analysis, development of a new language, testing, gathering feedback, and improvement.

[1407] Example 1

[1408] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1409] Communication between existing languages ​​is problematic due to the many differences in cultural background and nuances that make accurate communication difficult. To solve this problem, there is a need for a method to analyze language data from around the world, generate new languages ​​with common meanings and nuances, and make them easy for users to understand and use.

[1410] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1411] In this invention, the server includes a means for collecting language data from around the world, a means for using a generative AI model to analyze the collected language data, and a means for grouping words and phrases with common meanings and nuances from the analyzed data, thereby creating a grammar and vocabulary for a new language, providing it to users, and collecting feedback to refine it.

[1412] "Global language data" refers to data such as texts, grammar information, and translation materials written in different languages ​​around the world.

[1413] "Generative AI models" refers to machine learning techniques, such as BERT and GPT-4, used to analyze collected language data.

[1414] "Means of collection" refers to methods for acquiring and integrating language data from around the world from the Internet and existing databases.

[1415] "Means of analysis" refers to the use of generative AI models to analyze collected language data and elucidate the meaning, usage, grammar, and nuances of words in each language.

[1416] "Grouping methods" refers to methods for categorizing words and phrases with common meanings and nuances based on the analysis results.

[1417] "Method for creating a grammar and vocabulary for a new language" refers to a method for designing and documenting the grammar rules and vocabulary for a new language based on the analysis results and grouped information.

[1418] "Feedback gathering methods" refers to methods for providing the newly created language to users and gathering their thoughts and suggestions for improvement based on their usage and experiences.

[1419] "Means of improvement" refers to how generative AI models are used to improve the grammar and vocabulary of a new language based on collected feedback.

[1420] This invention is a system for generating new languages ​​with common meanings and nuances by collecting and analyzing language data from around the world. This system is mainly composed of a server, terminals, and users.

[1421] The server collects language data from around the world through the internet and existing databases, such as Wikipedia articles, Google Books, and academic paper databases, and retrieves text, grammar information, and translation materials. This data is then integrated into a single large dataset.

[1422] The collected data is then analyzed by a server. Generative AI models, specifically advanced machine learning techniques such as BERT and GPT-4, are used for the analysis. Generative AI models perform detailed analysis of the meaning, usage, grammar, and nuances of words in each language, and the analysis results are stored in a database. For example, the BERT model is used to analyze the relationships between words in a sentence.

[1423] Next, the server uses a generative AI model to group words and phrases with common meanings and nuances based on the analysis results. At this stage, they are classified into categories such as "greetings," "thanks," and "honorifics." The classified information is stored in a database. For example, "arigato" (thank you) and "thank you" are classified into the "gratitude" category.

[1424] The user (a linguistics expert) reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. For example, the Japanese word "arigatou" (thank you) is widely used, while the English word "thank you" is used mainly in casual settings. This difference is added as a note. This additional information is sent to the server, and the database is updated.

[1425] The user (linguist) designs the grammar and vocabulary of a new language based on the grouped information, taking into account definitions of parts of speech, sentence structure, verb conjugation rules, etc. The user documents the grammar rules and uploads them to the server.

[1426] The generated grammar and vocabulary are implemented by the server. For example, a common greeting word, "Helkona," is created for the new language. The dictionary and learning manual for the new language are created by users (linguistic experts) and uploaded digitally to the server.

[1427] This new language is provided to users via their devices. Users attempt to communicate using it, and the results and feedback are collected via the device. The collected feedback is analyzed by the server, and generative AI models are used to improve the system and language.

[1428] Specific examples

[1429] For example, the system collects the English and Japanese expressions of gratitude, "arigatou" (thank you) and "thank you," and analyzes their cultural backgrounds and differences in meaning. The server categorizes these into groups, and users (linguistic experts) add annotations pointing out the differences. "Gratalo" is generated as a new common vocabulary, which users can use via their terminals. The system is improved based on user feedback.

[1430] Examples of prompt statements

[1431] "Generate words for a new language based on the following dataset: The dataset contains sentences about expressions of gratitude in Japanese and English. Analyze each sentence, taking into account differences in vocabulary and nuance."

[1432] This will enable the development of new languages ​​that take into account the nuances and cultural backgrounds of different languages ​​in order to achieve accurate communication worldwide.

[1433] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1434] Step 1:

[1435] Data collection

[1436] The server collects language data from around the world from the Internet and existing databases.

[1437] Specifically, it retrieves text, grammar information, and translation materials from Wikipedia, academic paper databases, digital book repositories, etc.

[1438] Input: URL and access parameters of the target online database.

[1439] Output: A large dataset that integrates retrieved text, grammar information, and translation materials.

[1440] Step 2:

[1441] Data analysis

[1442] The server analyzes the collected data using a generative AI model (e.g., BERT or GPT-4).

[1443] At this stage, the meaning, usage, grammar, and nuances of words in each language are analyzed, and the results are stored in a database.

[1444] Specifically, it uses the BERT model to analyze the relationships between words in a sentence.

[1445] Input: A large collected dataset.

[1446] Output: Analysis results on word meaning, usage, grammar, and nuance.

[1447] Step 3:

[1448] Grouping of meanings and nuances

[1449] Based on the analysis results, the server groups words and phrases that share a common meaning or nuance.

[1450] At this stage, expressions are classified into "greetings," "thanks," "honorifics," etc.

[1451] As a specific action, "arigatou" and "thank you" are classified into the category of "gratitude."

[1452] Input: Analysis results.

[1453] Output: Words and phrases grouped by category.

[1454] Step 4:

[1455] Expertly reviewed and annotated

[1456] The user (a linguistics expert) reviews the analysis results and adds annotations regarding specific cultural backgrounds and nuances.

[1457] As a specific action, for example, notes are added about the use of "thank you" at specific times and in specific situations.

[1458] Input: Grouped words or phrases.

[1459] Output: Information annotated with cultural context and nuances.

[1460] Step 5:

[1461] Designing grammars and vocabularies for new languages

[1462] The user (a linguist) designs the grammar and vocabulary of a new language based on the grouped information.

[1463] The specific operation is designed taking into consideration definitions of parts of speech, sentence structure, and verb conjugation rules.

[1464] Input: The annotated information.

[1465] Output: Grammar rules and vocabulary of the new language.

[1466] Step 6:

[1467] The realization of a new language

[1468] The server instantiates a new language based on the generated grammar and vocabulary.

[1469] Specific actions include creating a common greeting for the new language called "Helkona" and creating a dictionary and learning manual for the new language in digital format.

[1470] Input: grammar rules and vocabulary of the new language.

[1471] Output: A dictionary and learning manual for the new language.

[1472] Step 7:

[1473] Gathering feedback and improving

[1474] The new language is provided to users via their devices, and their communication results and feedback are collected.

[1475] Specifically, users attempt to communicate in a new language and collect the results and feedback from their devices.

[1476] Input: User feedback.

[1477] Output: The grammar and vocabulary of the new language, improved based on feedback.

[1478] (Application example 1)

[1479] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1480] In today's increasingly globalized world, there are more and more situations where multilingual support is required. Communication between sales staff and customers who speak a variety of languages ​​is a particular challenge in brick-and-mortar stores. Conventional translation applications struggle to provide accurate translations that fully take into account cultural backgrounds and nuances. This leads to lower customer satisfaction and lost sales opportunities. To solve these problems, there is a need for a more accurate multilingual translation system that takes cultural backgrounds and nuances into account.

[1481] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1482] In this invention, the server includes means for collecting language data from around the world, means for generating a natural language processing model for analyzing the collected language data, means for grouping words and phrases with common meanings and nuances from the analyzed data, means for creating a grammar and vocabulary for a new language based on the analysis results and the grouped information, means for providing the newly created language to users and performing real-time multilingual translation between sales staff and customers in physical stores, means for collecting feedback on communication in physical stores, and means for improving the new language based on the collected feedback, thereby enabling advanced multilingual translation and smooth customer service in physical stores.

[1483] "Global Language Data" is a dataset that includes text data, grammar information, translation materials, and more in all languages ​​collected from many sources on the Internet.

[1484] A "collection means" is a system component that collects language data from the Internet or existing databases.

[1485] A "natural language processing model for analysis" is a generative AI model (e.g., BERT or GPT-4) used to analyze collected language data and understand word meaning, usage, grammar, nuances, etc.

[1486] A "grouping means" is a system component that categorizes words and phrases that share a common meaning or nuance from the analyzed data.

[1487] The "means for creating new language grammars and vocabularies" is a system component that designs and generates new grammar rules and vocabularies based on collected and analyzed data.

[1488] The "means to provide to users" refers to the system components that allow users to actually use the new language created.

[1489] The "means for real-time multilingual translation" is a system component that supports real-time multilingual translation between sales staff and customers in a physical store.

[1490] A "feedback gathering means" is a system component that gathers results and user comments on using the new language.

[1491] "Means for improvement" are system components that allow improvements to be made to the system or new languages ​​based on collected feedback.

[1492] This invention is a system that collects and analyzes language data from around the world to generate new languages ​​with common meanings and nuances, enabling real-time multilingual translation between sales staff and customers in physical stores. The system is primarily composed of a server, terminals, and users.

[1493] Server Functions and Processing

[1494] The server performs the following process:

[1495] 1. Collecting global language data:

[1496] The server collects language data from many sources on the Internet, including resources such as Wikipedia, Google Books, and academic paper databases.

[1497] 2. Linguistic Data Analysis:

[1498] The server uses natural language processing models (such as BERT or GPT-4) to analyze the collected data. This generative AI model performs detailed analysis of the meaning, usage, grammar, and nuance of words in each language.

[1499] 3. Grouping words and phrases that share a common meaning or nuance:

[1500] Based on the analysis results, the server groups words and phrases into categories such as "greetings," "thanks," and "honorifics."

[1501] 4. Creating a new language:

[1502] The grammar and vocabulary of the new language are created based on feedback from linguists, and this information is stored on a server for later use.

[1503] Terminal functions and processing

[1504] The following process is implemented on the terminal used by the salesperson:

[1505] 1. New language offerings:

[1506] An application will be installed that will allow salespeople and customers to communicate in real time through the new language created.

[1507] 2. Multilingual Translation:

[1508] Interactions between salespeople and customers will be translated in real time through a new common language, which requires the device to have high-performance computing power and an internet connection.

[1509] User Roles

[1510] The user (linguistics expert) plays the following roles:

[1511] 1. Review the analysis results:

[1512] The server then scrutinizes the data and adds annotations for specific cultural backgrounds and nuances.

[1513] 2. Gather feedback and improve:

[1514] Usage results and feedback from physical stores are collected through the terminals, and based on this, the server uses a generative AI model to improve the new language.

[1515] Hardware and software used

[1516] Generative AI models: Use advanced natural language processing techniques such as BERT and GPT-4.

[1517] Server: Use a server with high-performance data processing capabilities.

[1518] Device: A smartphone or tablet is used.

[1519] Specific examples

[1520] For example, consider an interaction between a Japanese salesperson and an English-speaking customer in a clothing store. When the salesperson says, "Welcome, what are you looking for?", the application translates this into the new common language and displays, "Helkona, what are you looking for?". When the customer says, "Tell me more about this item, please," the translation is displayed to the salesperson as, "Tell me more about this item, please."

[1521] Prompt Sentence Examples

[1522] Here are some examples of prompts:

[1523] Input: Welcome, what are you looking for?

[1524] Prompt: Translate the following sentence into the new common language. Consider cultural context and grammar rules: "Welcome, what are you looking for?"

[1525] Expected output: Helkona, what are you looking for?

[1526]

[1527] Input: Tell me more about this product.

[1528] Prompt: Translate the following sentence into a new common language. Consider cultural context and grammar rules: "Tell me more about this product."

[1529] Expected output: Tell me more about this item, please.

[1530] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1531] Step 1:

[1532] The server collects language data from around the world, including text, grammar information, and translation materials from online sources such as Wikipedia, Google Books, and academic paper databases, and builds a large-scale dataset.

[1533] Input: URL of the website or database to be collected

[1534] Output: A large dataset of collected language data

[1535] Step 2:

[1536] The server analyzes the collected data using natural language processing models (such as BERT and GPT-4), which analyzes the meaning, usage, grammar, and nuance of words in each language in detail.

[1537] Input: A large dataset of collected language data

[1538] Output: Parsed linguistic data (detailed information about word meanings, usage, grammar, and nuances)

[1539] Step 3:

[1540] The server uses a generative AI model to analyze data and group words and phrases with common meanings and nuances into categories such as "greetings," "thanks," and "honorifics."

[1541] Input: Parsed language data

[1542] Output: Words and phrases grouped by category

[1543] Step 4:

[1544] Users (linguistic experts) can review the results analyzed and grouped by the server and add annotations about specific cultural backgrounds and nuances, resulting in more accurate information being stored in the database.

[1545] Input: Grouped words or phrases

[1546] Output: Annotated language data

[1547] Step 5:

[1548] The server creates the grammar and vocabulary of the new language based on feedback from users (linguistic experts), designing definitions of parts of speech, sentence structure, verb conjugation rules, and so on.

[1549] Input: Annotated language data

[1550] Output: Grammar and vocabulary of the new language

[1551] Step 6:

[1552] The server generates specific translation dictionaries and study manuals based on the grammar and vocabulary of the new language, and this information is stored on the system and provided to the terminal.

[1553] Input: Grammar and vocabulary of a new language

[1554] Output: Translation dictionary, learning manual

[1555] Step 7:

[1556] The device (smartphone or tablet) will be provided to the salesperson, and will perform real-time multilingual translation using the newly created language. The salesperson will use this translation function when interacting with customers.

[1557] Input: Text entered by the salesperson

[1558] Output: Translation results in the new language

[1559] Step 8:

[1560] Users (customers and salespeople) use the language generated through interactions in physical stores and send the results and feedback to the system via their terminals.

[1561] Input: Details of the interaction in the physical store

[1562] Output: Feedback from customers and salespeople

[1563] Step 9:

[1564] The server uses the collected feedback to refine the new language using a generative AI model, thereby improving the quality of the system and the language.

[1565] Input: Feedback data from customers and salespeople

[1566] Output: New and improved language

[1567] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1568] This invention is a system that collects and analyzes language data from around the world to generate new languages ​​with common meanings and nuances, and further combines it with an emotion engine that recognizes the user's emotions to improve the user experience. The program processing of this system is explained in detail below.

[1569] Program processing

[1570] The server first collects language data from around the world via the internet and existing databases, such as Wikipedia articles, Google Books, and academic paper databases, and then integrates it into a large dataset that includes text, grammar information, and translation materials.

[1571] The collected data is then analyzed by a server using a generative AI model, such as the latest natural language processing technology like BERT or GPT-4. The generative AI model analyzes the meaning, usage, grammar, and nuance of words in each language. The analysis results are stored in a database and used in subsequent processes.

[1572] Next, the generative AI model uses the analysis results to group words and phrases that share common meanings and nuances. In this step, they are classified into categories such as "greetings," "thanks," and "honorifics." The server then performs these groupings and stores the related information in a database.

[1573] The user (a linguistics expert) then reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. This additional information is sent to the server, which updates the database. For example, a user might note that the Japanese greeting "konnichiwa" (hello) is widely used and not limited to a specific time of day.

[1574] Next, the user (a linguist) designs the grammar and vocabulary of the new language. This stage takes into account definitions of parts of speech, sentence structure, verb conjugation rules, etc. The grammar rules are documented and uploaded to the server.

[1575] The generated grammar and vocabulary are then implemented by the server. For example, a common greeting, "Helkona," is generated for the new language. Based on this, a dictionary and learning manual for the new language can be created by the user (a linguistics expert) and uploaded digitally to the server.

[1576] The new language is provided to users via their devices. Users attempt to communicate in the new language, and the results and feedback are collected via the devices. The collected feedback is analyzed by the server, and the system and language are improved using a generative AI model.

[1577] Adding an Emotion Engine

[1578] A distinctive feature of this invention is that by combining it with an emotion engine, it is possible to provide language that takes the user's emotions into consideration. The device uses the emotion engine to analyze emotions from the user's voice and text. For example, using voice recognition technology and text emotion analysis algorithms, the device can identify the user's emotions, such as "happy," "sad," or "angry."

[1579] The identified emotions are then sent to a server and stored in a database, which uses this emotional information to adapt the grammar and vocabulary of the new language accordingly, for example by providing phrases containing more comforting expressions when negative emotions are recognized.

[1580] Specific examples

[1581] Consider the following scenario: The server collects and analyzes the English and Japanese versions of "Thank you," identifying differences in cultural background and subtle nuances in the expression of gratitude. For example, the Japanese version of "Thank you" is used regardless of formality, while the English version of "Thank you" is best suited to informal situations. Taking this difference into account, the analysis results are stored in a database, and a new common vocabulary word, such as "Gratalo," is generated.

[1582] Meanwhile, the device has emotion recognition capabilities and analyzes the emotions users feel when using Gratalo. If the user is expressing positive emotions, the emotion engine will suggest additional expressions that match that emotion. Conversely, if the user is expressing negative emotions, the engine will adjust to provide more comforting phrases.

[1583] Through this process, the system will collect, analyze, develop a new language, adjust based on emotions, test, collect feedback, and refine, developing a new language that is universally understandable and flexible enough to respond to emotions.

[1584] The processing flow will be explained below.

[1585] Step 1:

[1586] The server collects language data from around the world, including internet text corpora, translations, and linguistic research papers. For example, it crawls language data from Wikipedia articles, Google Books, and academic paper databases, and combines them into one large dataset.

[1587] Step 2:

[1588] The server inputs the collected language data into a natural language processing model. Here, generative AI models such as BERT and GPT-4 are used to analyze the meaning, usage, grammar, and nuance of words in each language. Specifically, detailed information about each word is extracted based on context, frequency, analogy, and other factors.

[1589] Step 3:

[1590] The server stores the analysis results in a database that contains detailed analysis information about the meaning, usage, grammar, and nuance of words and phrases in each language.

[1591] Step 4:

[1592] The server uses a generative AI model to group words and phrases with common meanings and nuances based on the analysis results, for example, into categories such as "greetings," "thanks," and "honorifics," and stores the related information in a database.

[1593] Step 5:

[1594] Users (linguistic experts) can take the analysis results and add annotations about specific cultural backgrounds and nuances, such as noting that "hello" is used widely and not limited to a specific time of day, resulting in more precise data.

[1595] Step 6:

[1596] The information added by the user is sent again to the server, and the server stores the updated analysis results in the database.

[1597] Step 7:

[1598] The server uses a generative AI model to summarize the analysis results and provide information about grouped words and phrases, which are then stored in a database for further processing.

[1599] Step 8:

[1600] The user (linguist) designs the grammar and vocabulary of the new language based on the summarization results. At this stage, definitions of parts of speech, sentence structure, verb conjugation rules, etc. are taken into account. The grammar rules are documented and uploaded to the server.

[1601] Step 9:

[1602] The server uses a generative AI model to create the vocabulary needed for the new language. For example, a common greeting, "Helkona," is generated for the new language. This vocabulary list is also stored in a database.

[1603] Step 10:

[1604] A user (a linguistics expert) creates a dictionary or study manual based on the grammar and vocabulary of a new language, including basic words, phrases, and grammar rules of the new language.

[1605] Step 11:

[1606] A user uploads a dictionary or manual created by the user to a server in digital format.

[1607] Step 12:

[1608] The server will develop an app or platform to provide new languages ​​to users, which will help them learn the new language and allow them to actually use the new language.

[1609] Step 13:

[1610] The device will present phrases and words in the new language to the user through the app, allowing the user to try communicating using the new language.

[1611] Step 14:

[1612] The device uses an emotion engine to analyze emotions from the user's voice and text. For example, it uses voice recognition technology and text emotion analysis algorithms to identify emotions such as "happy," "sad," or "angry."

[1613] Step 15:

[1614] The device sends the identified emotions to a server, which stores the information in a database.

[1615] Step 16:

[1616] The server uses the emotional information to adjust the grammar and vocabulary of the new language depending on the user's emotions, for example by providing phrases that contain more comforting expressions if negative emotions are recognized.

[1617] Step 17:

[1618] Users can input their results and feedback on their communication using the new language through their devices, such as whether the greeting "Helkona" was useful or if there are areas for improvement.

[1619] Step 18:

[1620] The server collects the user feedback and stores it in a database.

[1621] Step 19:

[1622] The server considers improvements to the system and language based on the feedback collected, and uses generative AI models to propose new expressions and update the entire system.

[1623] Through these steps, a series of processes are concretely carried out, from collection and analysis, to new language development, adjustment based on emotions, testing, and feedback collection and refinement. This system will develop a new language that is universally understandable, flexible, and responds to emotions.

[1624] Example 2

[1625] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1626] In modern society, there are many different languages, and communication between different languages ​​is often a barrier. Differences in emotional expression also lead to misunderstandings between different cultures. While efforts have been made to develop a common language that is not dependent on a specific language or culture, it is often insufficient in addressing the nuances of language and emotional expression. To solve these issues, there is a need to develop a new language that can be understood universally and is flexible enough to respond to emotions.

[1627] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1628] In this invention, the server includes: means for collecting language data from around the world; means for using a generative AI model to analyze the collected language data; means for grouping words and phrases with common meanings and nuances from the analyzed data; means for creating the grammar and vocabulary of a new language based on the analysis results and the grouped information; means for providing the newly created language to users and collecting feedback; means for improving the new language based on the collected feedback; means for using an emotion engine to analyze user emotions; and means for adjusting the grammar and vocabulary of the new language based on the user emotions. This enables the development of a new language that is universally understandable and flexible enough to respond to emotions.

[1629] "Global language data" refers to text data, grammar information, translation materials, etc. in various languages ​​collected from the Internet and existing databases.

[1630] A "generative AI model" is an artificial intelligence model based on the latest natural language processing techniques such as BERT and GPT-4, and is used to analyze language data.

[1631] "Grouping" refers to the process of categorizing words and phrases with common meanings and nuances from analyzed data.

[1632] A "new language" refers to a language with a newly created grammar and vocabulary that has been analyzed and grouped based on linguistic data from around the world.

[1633] "User" refers to the person or group who uses this new language and provides feedback.

[1634] "Feedback" is information such as users' experiences and opinions when using a new language, and this information is collected to help improve the language.

[1635] An "emotion engine" refers to algorithms and technologies that analyze a user's voice and text data to identify emotions.

[1636] "Grammar and vocabulary adjustment" refers to the process of appropriately modifying and optimizing the grammar and vocabulary of the new language based on the identified emotional information.

[1637] "Universally understandable and emotionally responsive" refers to a language that can be commonly understood by people who speak any language, and has flexible language characteristics that can adapt to the user's emotions.

[1638] This invention is a system that collects language data from around the world, analyzes and groups the data using a generative AI model, and generates a new common language. By combining this system with an emotion engine, the system aims to provide a flexible language that also responds to the user's emotions. Detailed embodiments of this system are described below.

[1639] The server first collects language data from around the world from the Internet and existing databases. Specific sources used include Wikipedia, Google Books, and academic paper databases. The collected data includes text data, grammar information, and translation materials. The server collects this data and builds a large dataset. The data is collected using crawling techniques and APIs.

[1640] The collected language data is then analyzed by the server. Generative AI models, such as BERT and GPT-4, are used for the analysis. These models use deep learning to analyze the meaning, usage, grammar, and nuances of words in each language. The analysis results are stored in a database and used in later processes. Furthermore, based on the analysis results, words and phrases with common meanings and nuances are grouped into categories. Clustering algorithms and other techniques are used here.

[1641] Next, the user (a linguistics expert) reviews the analysis results and adds annotations about specific cultural backgrounds and nuances. This additional information is also sent to the server, and the database is updated. For example, a note is added about the difference between the usage of "arigatou" in Japanese and the English "thank you."

[1642] Next, the user (a linguist) designs the grammar and vocabulary of the new language. At this stage, definitions of parts of speech, sentence structure, verb conjugation rules, etc. are considered in detail. The designed grammar rules are then uploaded to the server.

[1643] Based on the generated grammar and vocabulary, the server will create a new language. For example, a new common greeting called "Helkona" will be generated. The dictionary and learning manual for this new language will be created by linguistic experts and uploaded digitally to the server.

[1644] The new language is provided to users via their devices. Users attempt to communicate using this new language, and the results and feedback are collected via the devices. The feedback information is analyzed by the server, and the system and language are improved using a generative AI model.

[1645] Furthermore, an emotion engine is built into the system. The device uses voice recognition technology and text emotion analysis algorithms to analyze the user's emotions. For example, emotions such as "happy," "sad," and "angry" are identified. This emotion information is sent to the server and stored in a database. Based on this information, the server adjusts the grammar and vocabulary of the new language. For example, if a negative emotion is recognized, adjustments are made to provide more comforting expressions.

[1646] As a concrete example, the server collects and analyzes the English and Japanese versions of "Thank you," revealing differences in cultural background and subtle nuances in the expression of gratitude. For example, the Japanese version of "Thank you" is commonly used, while the English version is limited to specific situations. Taking this difference into account, the word "Gratalo" is generated as a new common vocabulary.

[1647] An example prompt is, "Use GPT-4 to analyze the subtle differences in nuance between the Japanese and English versions of 'thank you' and generate a new common vocabulary." In this way, a new language that is universally understandable and flexible enough to accommodate emotions will be developed.

[1648] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1649] Step 1:

[1650] The server collects language data from around the world from the internet and existing databases. This process uses crawling techniques and APIs to obtain text data, grammar information, translation materials, and more from various sources (e.g., Wikipedia, Google Books, academic paper databases).

[1651] Input: A list of URLs from which language data can be sourced

[1652] Output: A set of collected language data

[1653] Specific operation: The server runs the crawling script to obtain data from the URL list, and then stores the obtained data in storage.

[1654] Step 2:

[1655] The server analyzes the collected language data using generative AI models (e.g., BERT and GPT-4), which extracts the meanings, usage, grammar, and nuances of words in each language.

[1656] Input: Collected language data

[1657] Output: Parsed language data

[1658] How it works: The server runs a Python script to invoke the generative AI model, which then analyzes the language data as input. The analysis results are then stored in a database.

[1659] Step 3:

[1660] The server groups words and phrases with common meanings and nuances based on the analysis results, and then categorizes them using a clustering algorithm.

[1661] Input: Parsed language data

[1662] Output: Words and phrases grouped by category

[1663] How it works: Based on the output of the generative AI model, the server applies a clustering algorithm to group words and phrases and stores the classification results in a database.

[1664] Step 4:

[1665] The user (a linguistics expert) reviews the results and adds annotations about specific cultural backgrounds and nuances, and this additional information is sent back to the server.

[1666] Input: Grouped words or phrases

[1667] Output: Data annotated with cultural context and nuances

[1668] What it does: Linguists access the data through a dedicated interface, add any necessary annotations, and then send the data to the server, which updates the database.

[1669] Step 5:

[1670] A user (linguist) designs the grammar and vocabulary of a new language, carefully examining the definitions of parts of speech, sentence structure, verb conjugation rules, etc., and uploads the designed grammar rules to the server.

[1671] Input: Annotated analysis results

[1672] Output: Draft grammar and vocabulary of the new language

[1673] What it does: Linguists use specialized editing software to design the grammar and vocabulary of a new language, then upload the data to a server.

[1674] Step 6:

[1675] The server then creates the new language based on the generated grammar and vocabulary. At this stage, a dictionary and learning manual for the new language are created and uploaded digitally.

[1676] Input: A draft grammar and vocabulary for the new language

[1677] Output: Dictionary and learning manual for the new language

[1678] Specific operation: The server generates a digital dictionary and learning manual for the new language based on the grammar and vocabulary and stores it in a database.

[1679] Step 7:

[1680] The device provides the new language to the user and collects communication results and feedback from the user.

[1681] Input: Dictionary and learning manual for a new language

[1682] Output: User feedback

[1683] Specific operation: A dedicated application installed on the device provides the new language, collects user usage logs and feedback, and sends them to a server.

[1684] Step 8:

[1685] The device uses an emotion engine to analyze the user's emotions, using voice recognition technology and text emotion analysis algorithms.

[1686] Input: User voice or text data

[1687] Output: Emotion data

[1688] Specific operation: Using the device's voice recognition software and natural language processing library, the system analyzes the user's emotions in real time and sends the results to the server.

[1689] Step 9:

[1690] The server adjusts the grammar and vocabulary of the new language based on the identified emotional information.

[1691] Input: Emotional data and user feedback

[1692] Output: Adjusted grammar and vocabulary

[1693] Specific operation: Based on the fed-back emotion data, the server readjusts the generative AI model and makes appropriate corrections to phrases and grammar.

[1694] (Application example 2)

[1695] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1696] In today's diverse language environment, there is a growing need for a new language that can be commonly understood by people all over the world. There is also a demand for providing user experiences based on emotions, but existing systems have had difficulty achieving this effectively. Similarly, there is also the issue of services such as food delivery not providing personalized services that take user emotions into account.

[1697] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1698] In this invention, the server includes: means for collecting language data from around the world; means for generating a natural language processing model for analyzing the collected language data; means for grouping words and phrases with common meanings and nuances from the analyzed data; means for creating a grammar and vocabulary for a new language based on the analysis results and the grouped information; means for providing the newly created language to users and collecting feedback; means for improving the new language based on the collected feedback; and means for recognizing user emotions and suggesting appropriate vocabulary and phrases based on the emotions. This enables the development of a new language that is universally understandable and flexible enough to respond to emotions. It also enables services such as food delivery to provide personalized experiences based on user emotions.

[1699] "Global language data" refers to text data, translation materials, grammar information, etc. for a wide variety of languages ​​collected from the Internet and existing databases.

[1700] A "natural language processing model" is an artificial intelligence model for analyzing collected language data, including generative AI models such as BERT and GPT-4.

[1701] "Analysis" refers to the process of using a generative AI model to analyze the vocabulary, grammar, nuances, etc. of collected language data to understand its meaning and usage.

[1702] "Grouping" refers to the process of categorizing words and phrases with common meanings and nuances from analyzed data.

[1703] "Creating a grammar and vocabulary for a new language" refers to the process of constructing a newly designed system of grammatical rules and words based on the analyzed and grouped information.

[1704] "Providing to the user" refers to providing the newly created language in a form that the user can use through the terminal.

[1705] "Collecting feedback" refers to the process of collecting user usage results and reactions via the device and obtaining them as data for analysis.

[1706] "Improving the new language" refers to the process of adjusting the generative AI model, grammar, and vocabulary based on collected feedback to improve the accuracy and usability of the language.

[1707] "Recognizing user emotions" refers to the process of identifying a user's emotional state using voice recognition technology and text emotion analysis algorithms.

[1708] "Suggesting appropriate vocabulary and phrases based on emotions" refers to the process of presenting the most appropriate words and phrases to the user based on analyzed emotional information.

[1709] This invention is a system that collects and analyzes language data from around the world to generate new languages ​​with common meanings and nuances, and further combines it with an emotion engine that recognizes user emotions to improve user experience. This system can make personalized menu suggestions based on user emotions, especially in food delivery applications.

[1710] Data collection and analysis

[1711] The first thing the server does is collect language data from around the world. The hardware used is a cloud-based server (e.g., AWS EC2 or Google Cloud Platform) that retrieves data from existing databases and the internet. Data is collected from sources such as Wikipedia articles, Google Books, and academic papers, and then integrated into a large dataset containing text, grammar information, and translation materials.

[1712] The collected data is then analyzed by a server using generative AI models, including the latest natural language processing techniques such as BERT and GPT-4. At this stage, the meaning, usage, grammar, and nuances of words in each language are analyzed, and the results are stored in a database.

[1713] Creating a new language

[1714] Based on the analysis results, the server groups words and phrases that share common meanings and nuances. For example, in this step, they are classified into categories such as "greetings," "thanks," and "honorifics." The grouping information is then used to create the grammar and vocabulary of the new language. Linguistic experts may add annotations regarding specific cultural backgrounds and nuances during this process, ultimately creating a digital dictionary and learning manual for the new language.

[1715] emotion recognition

[1716] The device's emotion engine analyzes the user's voice and text to determine their emotions. Software used includes algorithms from Google Cloud Natural Language and IBM Watson Tone Analyzer. This emotion recognition identifies the user's emotions, such as joy, sadness, and anger.

[1717] Menu recommendation

[1718] Based on the analyzed emotion information, the server recommends the most suitable menu or service for the user. For example, comfort food may be suggested to a user who expresses negative emotion, while a special dessert or a new dish may be suggested to a user who expresses positive emotion. Examples of prompts used at this stage are as follows:

[1719] python

[1720] Dataset preparation

[1721] from transformers import GPT2Tokenizer, GPT2Model

[1722] tokenizer = GPT2Tokenizer.from_pretrained('gpt2')

[1723] model = GPT2Model.from_pretrained('gpt2')

[1724] text = "Enter text data to collect here"

[1725] inputs = tokenizer(text, return_tensors='pt')

[1726] outputs = model(inputs)

[1727] Emotion analysis

[1728] from google.cloud import language_v1

[1729] client = language_v1.LanguageServiceClient()

[1730] document = language_v1.Document(content="Enter text to parse here", type_=language_v1.Document.Type.PLAIN_TEXT)

[1731] sentiment = client.analyze_sentiment(request={'document': document}).document_sentiment

[1732] print(f'Text: {document.content}\nSentiment: {sentiment.score}')

[1733] Menu recommendation

[1734] recommendations = {

[1735] "happy": ["Special Dessert", "Celebration Cake"],

[1736] "sad": ["Comfort Soup", "Chocolate Brownie"],

[1737] "angry": ["Spicy Wings", "Satisfaction Steak"]

[1738] }

[1739] user_emotion = "happy" Parsed emotion result

[1740] recommended_menu = recommendations[user_emotion]

[1741] print(f"Recommended Menu: {recommended_menu}")

[1742] Through the above process, the present invention provides a new language that can be universally understood around the world, while realizing personalized services based on the user's emotions.

[1743] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1744] Step 1:

[1745] The server collects language data from around the world, including text, grammar information, and translation materials such as Wikipedia articles, Google Books, and academic papers, using a cloud-based server (e.g., AWS EC2 or Google Cloud Platform).

[1746] (Input): Source URL or API endpoint

[1747] (Output): Unified language dataset

[1748] (Specific operation): The server periodically runs the data collection script, obtains data from each source, and integrates it into a single database.

[1749] Step 2:

[1750] The server analyzes the collected data using a generative AI model (e.g., BERT or GPT-4).

[1751] (Input): Unified language dataset

[1752] (Output): Analysis results (word meanings, usage, grammar, nuances, etc. for each language)

[1753] (Specific operation): The server uses a generative AI model to analyze text data, extract word meanings, usage, and grammatical information, and store them in a database.

[1754] Step 3:

[1755] Based on the analysis results, the server groups words and phrases that share a common meaning or nuance.

[1756] (Input): Analysis results

[1757] (Output): Category information of grouped words and phrases

[1758] (Specific behavior): The server runs an automatic classification algorithm to group words and phrases into categories such as "greetings," "thanks," and "honorifics."

[1759] Step 4:

[1760] The server creates the grammar and vocabulary of the new language based on the grouped information.

[1761] (Input): Category information of grouped words and phrases

[1762] (Output): Grammatical and lexical information for the new language

[1763] (Specific operation): The server defines grammar rules, constructs grammar and vocabulary, and creates a dictionary and learning manual for the new language.

[1764] Step 5:

[1765] The server provides the newly created language to users through their devices and collects their feedback.

[1766] (Input): A dictionary and learning manual for a new language

[1767] (Output): User feedback data

[1768] (Specific operation): The user communicates using a new language, and the device records the results and reactions of the communication and sends them to the server as feedback data.

[1769] Step 6:

[1770] The server refines the new language based on the collected feedback.

[1771] (Input): Feedback data

[1772] (Output): Improved grammar and lexical information

[1773] (Specific operation): The server analyzes the feedback data, uses a generative AI model to improve grammar and vocabulary, and updates the results to the database.

[1774] Step 7:

[1775] The device uses an emotion engine to analyze emotions from the user's voice or text. Emotion recognition algorithms (e.g., Google Cloud Natural Language or IBM Watson Tone Analyzer) are used.

[1776] (Input): User voice or text data

[1777] (Output): User's emotional state (e.g., happy, sad, angry, etc.)

[1778] (Specific operation): The device receives the user's voice or text as input, analyzes the emotions using an emotion recognition algorithm, and sends the results to the server.

[1779] Step 8:

[1780] The server then recommends the most suitable menus and services to the user based on the analyzed emotional information.

[1781] (Input): User's emotional state

[1782] (Output): Recommended menu items and services

[1783] (Specific operation): Based on the emotional information, the server searches the database for the most suitable menu or service for the user and sends it to the terminal.

[1784] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1785] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1786] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1787] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1788] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1789] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1790] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1791] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1792] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1793] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1794] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1795] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1796] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1797] 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.

[1798] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1799] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1800] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1801] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1802] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1803] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1804] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1805] The following is further disclosed regarding the above embodiment.

[1806] (Claim 1)

[1807] A means of collecting language data from around the world,

[1808] means for generating a natural language processing model for analyzing the collected language data;

[1809] A means of grouping words and phrases with common meanings and nuances from the analyzed data,

[1810] A means for creating a grammar and vocabulary for a new language based on the analysis results and grouped information;

[1811] A means of providing the newly created language to users and gathering feedback;

[1812] a means of improving the new language based on the feedback collected;

[1813] A system including:

[1814] (Claim 2)

[1815] 10. The system of claim 1, wherein all processes of collecting, analyzing, grouping, grammar and vocabulary creation, and feedback collection and refinement are automated.

[1816] (Claim 3)

[1817] 10. The system of claim 1, wherein the means for creating a common language grammar and vocabulary includes means for incorporating expert feedback to take into account specific cultural backgrounds and nuances.

[1818] "Example 1"

[1819] (Claim 1)

[1820] A means of collecting language data from around the world,

[1821] a means for using a generative AI model to analyze the collected language data;

[1822] A means of grouping words and phrases with common meanings and nuances from the analyzed data,

[1823] A means for creating a grammar and vocabulary for a new language based on the analysis results and grouped information;

[1824] A means of providing the newly created language to users and gathering feedback;

[1825] a means of improving the new language based on the feedback collected;

[1826] A system including:

[1827] (Claim 2)

[1828] 10. The system of claim 1, wherein all processes of collecting, analyzing, grouping, grammar and vocabulary creation, and feedback collection and refinement are automated.

[1829] (Claim 3)

[1830] 10. The system of claim 1, wherein the means for creating a common language grammar and vocabulary includes means for incorporating expert feedback to take into account specific cultural backgrounds and nuances.

[1831] "Application Example 1"

[1832] (Claim 1)

[1833] A means of collecting language data from around the world,

[1834] means for generating a natural language processing model for analyzing the collected language data;

[1835] A means of grouping words and phrases with common meanings and nuances from the analyzed data,

[1836] A means for creating a grammar and vocabulary for a new language based on the analysis results and grouped information;

[1837] A means of providing users with the newly created languages ​​for real-time multilingual translation between sales staff and customers in physical stores;

[1838] A means of gathering feedback on in-store communication and

[1839] a means of improving the new language based on the feedback collected;

[1840] A system including:

[1841] (Claim 2)

[1842] 10. The system of claim 1, wherein all processes of collecting, analyzing, grouping, grammar and vocabulary creation, and feedback collection and refinement are automated.

[1843] (Claim 3)

[1844] 10. The system of claim 1, wherein the means for creating a common language grammar and vocabulary includes means for incorporating expert feedback to take into account specific cultural backgrounds and nuances.

[1845] "Example 2: Combining Emotion Engines"

[1846] (Claim 1)

[1847] A means of collecting language data from around the world,

[1848] a means for using a generative AI model to analyze the collected language data;

[1849] A means of grouping words and phrases with common meanings and nuances from the analyzed data,

[1850] A means for creating a grammar and vocabulary for a new language based on the analysis results and grouped information;

[1851] A means of providing the newly created language to users and gathering feedback;

[1852] a means of improving the new language based on the feedback collected;

[1853] means for using an emotion engine to analyze the emotion of a user;

[1854] means for adjusting the grammar and vocabulary of the new language based on the user's sentiment;

[1855] A system including:

[1856] (Claim 2)

[1857] 10. The system of claim 1, wherein all processes of collecting, analyzing, grouping, grammar and vocabulary creation, and feedback collection and refinement are automated.

[1858] (Claim 3)

[1859] 10. The system of claim 1, wherein the means for creating a common language grammar and vocabulary includes means for incorporating expert feedback to take into account specific cultural backgrounds and nuances.

[1860] "Application example 2 when combining emotion engines"

[1861] (Claim 1)

[1862] A means of collecting language data from around the world,

[1863] means for generating a natural language processing model for analyzing the collected language data;

[1864] A means of grouping words and phrases with common meanings and nuances from the analyzed data,

[1865] A means for creating a grammar and vocabulary for a new language based on the analysis results and grouped information;

[1866] A means of providing the newly created language to users and gathering feedback;

[1867] a means of improving the new language based on the feedback collected;

[1868] a means for recognizing a user's emotions and suggesting appropriate vocabulary and phrases based on the emotions;

[1869] A system including:

[1870] (Claim 2)

[1871] 10. The system of claim 1, wherein all processes of collecting, analyzing, grouping, grammar and vocabulary creation, and feedback collection and refinement are automated.

[1872] (Claim 3)

[1873] 10. The system of claim 1, wherein the means for creating a common language grammar and vocabulary includes means for incorporating expert feedback to take into account specific cultural backgrounds and nuances.

[1874] (Claim 4)

[1875] 10. The system according to claim 1, further comprising means for recommending different menus and services according to different emotions based on emotion recognition.

[1876] (Claim 5)

[1877] The system according to claim 1, characterized in that the natural language processing model uses a generative AI model and includes means for performing analysis using a prompt sentence. [Explanation of symbols]

[1878] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting language data from around the world, means for generating a natural language processing model for analyzing the collected language data; A means of grouping words and phrases with common meanings and nuances from the analyzed data, A means for creating a grammar and vocabulary for a new language based on the analysis results and grouped information; A means of providing the newly created language to users and gathering feedback; a means of improving the new language based on the feedback collected; A system including:

2. 10. The system of claim 1, wherein all processes in collecting, analyzing, grouping, grammar and vocabulary creation, and feedback collection and refinement are automated.

3. 10. The system of claim 1, wherein the means for creating a common language grammar and vocabulary includes means for incorporating expert feedback to take into account specific cultural backgrounds and nuances.

Images