System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving an input from a user; means for performing natural language processing based on the input; means for generating a response using generative artificial intelligence based on a result of the natural language processing; and means for formatting and transmitting the generated response to the user.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] Modern language learning faces the challenge of lacking efficient means for users to quickly understand the usage and nuances of unfamiliar words and expressions. Traditional dictionaries and learning materials require users to look up word meanings and usages one by one, reducing learning efficiency. Furthermore, it is difficult to quickly obtain the nuances of words and specific usage examples, making them difficult to use appropriately in actual communication. Therefore, there is a demand for intuitive and interactive language learning support systems. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for receiving input from a user, a means for performing natural language processing based on the input, a means for generating a response using generative artificial intelligence based on the results of the natural language processing, and a means for formatting and sending the generated response to the user. This system allows users to efficiently understand unfamiliar words and expressions and instantly obtain specific example sentences and usage instructions. Furthermore, by adding an input assistance function and an auto-complete function, it is possible to assist users in inputting words and expressions and realize smoother interactions. This improves the efficiency of language learning and contributes to the improvement of practical communication skills.

[0006] "User" means a person or organization that uses the system to obtain language learning information.

[0007] "Input" refers to the input of characters or strings of characters by a user to provide information to a system.

[0008] "Natural language processing" is a technology for analyzing human language and understanding its meaning and intent.

[0009] "Generative AI" is a system or algorithm that uses artificial intelligence technology to generate appropriate answers or example sentences.

[0010] A "response" is an answer or piece of information that a system generates based on user input.

[0011] "Formatting" is the process of preparing the generated response in a form that is easy for the user to understand.

[0012] The "input support function" is a function that assists the user in inputting data and reduces input errors.

[0013] The "auto-complete function" is a function in which, when a user has entered text partway through, the system presents candidates to help the user complete the input.

[0014] A "database" is a system that stores and manages information such as necessary example sentences and explanations of nuances.

[0015] "Tokenization" is a process of dividing an input string into units such as words and phrases.

[0016] "Context" refers to the words and situations in which a word or expression is used.

[0017] "Intent" refers to the information or purpose that a user is trying to convey to a system through input.

[0018] An "HTTP request" is a type of protocol used by a user terminal to send information to a server.

[0019] An "HTTP response" is a type of protocol used by a server to return information to a user terminal. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[0042] System Overview

[0043] This system is an interactive dictionary service that uses natural language processing (NLP) and generative AI to support users' language learning. Its purpose is to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their devices. The operation and functionality of each major component are described in detail below.

[0044] Server Operation

[0045] 1. Receiving user input

[0046] The server receives requests entered by users into their terminals, such as "Please tell me some example sentences for ambiguous."

[0047] 2. Performing Natural Language Processing (NLP)

[0048] The server analyzes the received user input using natural language processing (NLP), and as part of the analysis, it tokenizes the input to understand its context and intent.

[0049] 3. Database Access

[0050] Based on the analysis results, the server accesses a database to retrieve data related to the relevant words and expressions, including example sentences and explanations of their nuances.

[0051] 4. Response generation using generative AI

[0052] The server passes the acquired data to the generation AI, which generates appropriate example sentences and explanations. For example, it generates "The meaning of his statement was ambiguous" as an example sentence of "ambiguous."

[0053] 5. Response Format

[0054] The server formats the generated response in a user-friendly format and sends it to the terminal.

[0055] Device behavior

[0056] 1. Submitting User Input

[0057] The device sends the information entered by the user to the server, and if the input is useful for learning, it immediately makes a request to the server.

[0058] 2. Receiving a response from the server

[0059] The device receives the response from the server and displays it to the user in an easy-to-understand format, often including concrete examples and explanations.

[0060] 3. Assistive typing and autocomplete

[0061] The device provides input assistance and auto-complete functions to help users input information efficiently, making the learning experience smoother for users.

[0062] User Actions and Interactions

[0063] 1. First time input

[0064] Users input words or phrases into their device for translation, example sentences, or nuanced understanding. For example, they might type, "Please tell me some example sentences for ambiguous."

[0065] 2. Use of the displayed results

[0066] Users can use the example sentences and explanations displayed to help them learn, and if they need more information, they can enter additional questions on the same screen.

[0067] 3. Follow-up questions and continued learning

[0068] If the user enters a subsequent question, a request is sent to the server again, and a response is generated in the same process, allowing the user to progress through the learning process interactively.

[0069] Specific examples

[0070] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[0071] The device sends input to the server.

[0072] The server parses the input and retrieves data related to "ambiguous" from the database.

[0073] The generative AI generates an example sentence, "The meaning of his statement was ambiguous," along with its explanation.

[0074] The server formats the generated response and sends it to the terminal.

[0075] The terminal receives the response and displays it to the user.

[0076] The above is an embodiment of the present invention, which allows the user to learn a language efficiently.

[0077] The processing flow will be explained below.

[0078] Step 1:

[0079] The user types into the terminal, "Please tell me some example sentences for ambiguous."

[0080] Step 2:

[0081] The terminal sends the user's input to the server. The terminal converts the input string into an HTTP request and sets the URL, header, and body of the request to send to the server.

[0082] Step 3:

[0083] The server receives a request from the user. The server receives the request sent from the terminal and extracts the content included in the request body.

[0084] Step 4:

[0085] The server performs natural language processing (NLP), tokenizing the received input and analyzing it for context and intent. Specifically, it segments words and phrases and analyzes them to determine their meaning.

[0086] Step 5:

[0087] The server accesses the database. Based on the analysis results, the server retrieves relevant data from the database. For example, it searches for example sentences and explanations of nuances related to "ambiguous."

[0088] Step 6:

[0089] The server generates a response using the generation AI. The server passes the information obtained from the database to the generation AI, which generates an appropriate example sentence and its explanation. For example, it generates the example sentence, "The meaning of his statement was ambiguous."

[0090] Step 7:

[0091] Server formats response: The server formats the generated response in a user-friendly format suitable for display.

[0092] Step 8:

[0093] The server sends the formatted response to the terminal. The server prepares the formatted response as an HTTP response and sends it to the terminal.

[0094] Step 9:

[0095] The terminal receives the response from the server, analyzes the response, and displays the content to the user.

[0096] Step 10:

[0097] The user can use the displayed results. The user can use the example sentences and explanations displayed to study, and if more information is needed, they can enter additional questions.

[0098] Example 1

[0099] 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."

[0100] Conventional language learning support systems have difficulty providing appropriate example sentences and explanations instantly for words and phrases entered by users. Furthermore, input support and auto-complete functions are inadequate, resulting in a clunky learning experience for users. Furthermore, responses to user requests are mechanical, failing to help users understand the meaning in a natural context.

[0101] 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.

[0102] In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for accessing a database and acquiring related information based on the results of the natural language processing, means for supplying the acquired information to a generative artificial intelligence model to generate a response, and means for formatting and sending the generated response to the user. This allows the server to instantly provide appropriate example sentences and explanations for words and phrases entered by the user, making the learning experience smoother and more efficient. It also enables understanding in a natural context, improving the user's learning effectiveness.

[0103] "User input" refers to the input of text or commands by a system user into a terminal.

[0104] "Natural language processing" refers to technology that enables computers to understand and analyze human language, and includes processes such as tokenization, grammar analysis, and entity extraction.

[0105] A "database" refers to a system for organizing and storing related information, including example sentences and explanations related to words and phrases.

[0106] A "generative artificial intelligence model" refers to an artificial intelligence that has algorithms for generating context-appropriate responses based on large amounts of data.

[0107] "Response formatting" refers to shaping the generated response into an appropriate format for display to the user in an easily understandable manner.

[0108] The "input support function" refers to a function that assists the user when making input, and includes functions such as suggesting candidates and spell checking.

[0109] "Autocomplete function" refers to a function that automatically completes text that a user has incompletely entered.

[0110] "Example sentence" refers to a specific sentence provided to demonstrate the usage of a word or phrase.

[0111] "Explanation" refers to a sentence that provides additional information about the meaning, grammar, and context of use of an example sentence.

[0112] MODE FOR CARRYING OUT THE INVENTION

[0113] The following describes in detail an embodiment of the present invention. This system is an interactive dictionary service that uses natural language processing (NLP) and generative AI to support users' language learning. Its purpose is to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their terminals.

[0114] System Overview

[0115] This system is primarily composed of a server and a terminal. The server receives input sent by the user, performs natural language processing, and then accesses a database to retrieve relevant information. The retrieved information is then fed into a generative AI model to generate an appropriate response, which is then sent to the user. The terminal sends the user's input to the server and displays the response received from the server to the user. It also provides input assistance and auto-complete functions.

[0116] Hardware and software used

[0117] Server: Used to receive input from users, perform natural language processing, access databases, and generate responses using generative AI models. The server can run on a common cloud service.

[0118] Terminal: A device used by a user, such as a PC, smartphone, or tablet. The terminal communicates with the server via a web browser or a dedicated application.

[0119] Database: Use a relational database management system (RDBMS) such as MySQL or PostgreSQL to manage and access data.

[0120] Natural Language Processing (NLP) libraries: Python's NLTK library and spaCy are used to tokenize input and analyze context.

[0121] Generative AI models: Generative AI models such as OpenAI's GPT-3 are used to generate natural-sounding examples and explanations.

[0122] Specific examples

[0123] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[0124] 1. User input: The user types "Please tell me an example sentence for ambiguous" into the terminal.

[0125] 2. Sending input: The device sends the input to the server.

[0126] 3. Natural Language Processing: The server receives the input and performs natural language processing using Python's NLTK library and spaCy. Specifically, it tokenizes the input, performs grammatical analysis, and identifies "ambiguous."

[0127] 4. Database access: Based on the analysis results, the server sends a query to a MySQL or PostgreSQL database to retrieve relevant example sentences and explanations.

[0128] 5. Response generation by generative AI: The server passes the acquired information to OpenAI's GPT-3, which generates appropriate example sentences and explanations for "ambiguous." For example, an example sentence such as "The meaning of his statement was ambiguous" is generated.

[0129] 6. Response formatting: The server formats the generated response in JSON format or similar and sends it to the device.

[0130] 7. Displaying the response: The terminal analyzes the response received from the server and displays it in a user-friendly format.

[0131] This process allows users to obtain appropriate example sentences and explanations in real time and advance their language learning.

[0132] Prompt Sentence Examples

[0133] The prompt uses natural questions such as "Can you give me an example of an ambiguous sentence?" By inputting such a prompt, the system can quickly provide the necessary information.

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Step 1: Receiving User Input

[0136] Input: The user types "Please tell me some example sentences for ambiguous" into the terminal.

[0137] How it works: The device sends user input to the server as an HTTP request. It is sent in the form of an HTTP POST request, with the user input included in the request body.

[0138] Output: The server parses the received request and extracts the user input.

[0139] Step 2: Performing Natural Language Processing

[0140] Input: The user input that the server extracted in step 1.

[0141] How it works: The server uses Python's NLTK library and spaCy to tokenize the text and perform grammatical analysis. For example, "Please tell me some example sentences about ambiguous" is broken down into the tokens "ambiguous," "of," "example sentences," "o," and "teach me," and identifies "ambiguous."

[0142] Output: Parsed tokens and identified keywords (in this case, "ambiguous").

[0143] Step 3: Database Access

[0144] Input: The keyword the server identified in step 2.

[0145] How it works: The server sends a query to a database such as MySQL or PostgreSQL to retrieve example sentences and explanations related to "ambiguous." It uses SQL statements to search the database, executing a query to retrieve, for example, "example sentences" and "explanations."

[0146] Output: Example sentences retrieved from the database and their explanations.

[0147] Step 4: Generative AI generates a response

[0148] Input: The example sentence and explanation obtained by the server in step 3.

[0149] How it works: The server inputs the acquired data into a generative AI model (e.g., OpenAI's GPT-3) and sets it as a prompt. The prompt includes a request for example sentence generation. The generative AI model generates example sentences that are grammatically and content-appropriate based on the input information.

[0150] Output: A new example sentence generated by the generative AI model, e.g., "The meaning of his statement was ambiguous."

[0151] Step 5: Formatting the Response

[0152] Input: The example sentence generated by the server in step 4.

[0153] How it works: The server formats the generated example sentences in a user-friendly format, such as JSON or HTML, as needed.

[0154] Output: The formatted response data.

[0155] Step 6: Sending a response from the server to the device

[0156] Input: The response data formatted by the server in step 5.

[0157] Operation: The server sends the response data to the terminal as an HTTP response. The response is in JSON or HTML format.

[0158] Output: The response data sent to the device.

[0159] Step 7: View the response

[0160] Input: The response data received by the terminal in step 6.

[0161] What happens: The device parses the data it receives and displays it in a user-friendly format, for example rendering it into HTML for display in a web browser.

[0162] Output: Generated example sentences and their explanations displayed to the user.

[0163] (Application example 1)

[0164] 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."

[0165] Modern content distribution services lack the means to instantly provide users with relevant information about the text or content they are viewing. This makes it difficult for users to deepen their understanding of an unfamiliar word or phrase on the spot. Furthermore, existing language learning support systems are unable to quickly respond to users' real-time needs, resulting in reduced learning efficiency.

[0166] 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.

[0167] In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for generating a response using generative artificial intelligence based on the results of the natural language processing, and means for formatting the generated response and displaying content, thereby enabling real-time language learning support by instantly providing related information and explanations for the content the user is viewing.

[0168] The "means for receiving input from the user" is a function for receiving text or voice input by the user into the terminal.

[0169] "Means for natural language processing" refers to a function that uses technology to analyze received user input and understand its meaning and intent.

[0170] A "means for generating responses using generative artificial intelligence" is a function that uses an AI model to generate appropriate responses based on the results of natural language processing.

[0171] "Means for formatting the generated response and displaying the content" refers to a function for formatting the response generated by AI into a format that is easy for the user to understand and displaying it on the device.

[0172] The "input assistance function" is a function that provides predictive conversion, suggestion functions, etc. when a user inputs text, thereby assisting the user in inputting text.

[0173] An "autocomplete feature" is a feature that automatically completes partially typed words or phrases when a user is entering text.

[0174] Generating "example sentences and their explanations" means generating usage examples and their explanations for specific words or phrases and providing them to the user.

[0175] The following describes in detail the mode for carrying out the present invention. The system functions as a support tool for users in real-time language learning, and is intended to provide instant example sentences and explanations for unknown words and phrases, particularly in content distribution services.

[0176] System Overview

[0177] This system consists of a server, a device, and a user. Specifically, it works by receiving user input from a device such as a smartphone or head-mounted display and sending it to the server. The server uses natural language processing (NLP) and generative AI models to generate a response based on the user input and return it to the device.

[0178] Hardware and software used

[0179] Hardware

[0180] Smartphone

[0181] head-mounted display

[0182] software

[0183] Python

[0184] Transformers library (by Hugging Face)

[0185] Requests library (for HTTP requests)

[0186] Processing flow

[0187] 1. User Input

[0188] The user inputs a prompt sentence such as "Tell me an example sentence for ambiguous" into a smartphone or head-mounted display.

[0189] 2. Receiving Input

[0190] The terminal receives user input and sends it to the server.

[0191] 3. Natural Language Processing

[0192] The server analyzes the received user input using natural language processing to extract important words (in this case, "ambiguous"). The natural language processing model used is the Transformers library from Hugging Face.

[0193] 4. Database Access

[0194] Based on the analysis results, the server retrieves related data from the virtual database.

[0195] 5. AI-generated responses

[0196] Based on the acquired data, a generative AI model is used to generate appropriate example sentences and explanations.

[0197] 6. Response Formatting and Display

[0198] The generated response is formatted in a user-friendly format and sent to the terminal for display.

[0199] Examples of prompt statements

[0200] Below are some examples of prompt sentences.

[0201] Example: "What are some examples of ambiguous?"

[0202] In this way, by using the present invention, users can progress with their language learning in real time while browsing content, which is expected to improve the efficiency of users' learning.

[0203] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0204] Step 1:

[0205] The user types "Please tell me an example sentence of ambiguous" into a smartphone or head-mounted display. The prompt "Please tell me an example sentence of ambiguous" is received as input. This becomes the input for the next step.

[0206] Step 2:

[0207] The terminal receives user input and sends it to the server as a string. In this step, the entered prompt sentence is sent to the server as an HTTP request. As a specific operation, data is sent using an HTTP POST request. The user input is passed to the server as output.

[0208] Step 3:

[0209] The server receives user input and analyzes it using natural language processing (NLP). The server uses Hugging Face's Transformers library to tokenize the input text and understand its context and intent. The data processing performed in this step is tokenization and context analysis. As an output, important words ("ambiguous") are extracted.

[0210] Step 4:

[0211] Based on the analysis results, the server accesses the virtual database to retrieve related data. The data calculation performed here is a database query corresponding to the extracted word. The server retrieves example sentences and explanations related to "ambiguous" from the virtual database. As an output, data related to the word is obtained.

[0212] Step 5:

[0213] The server passes the acquired data to the generative AI model to generate appropriate example sentences and explanations. Specifically, the data is passed as input to the generative AI model, and the generated text output is obtained. In this step, the generative AI model generates the example sentence "The meaning of his statement was ambiguous" and its explanation. The generated example sentence and explanation are obtained as output.

[0214] Step 6:

[0215] The server formats the generated response in a user-friendly format and sends it to the terminal. The specific operation here is to convert the generated text into an appropriate format and send it again to the terminal as an HTTP response. As output, the formatted response is passed to the terminal.

[0216] Step 7:

[0217] The terminal receives the response from the server and displays it in a format that is easy for the user to understand. As input, it receives the response from the server. As a specific operation, it displays the received data on the screen. As output, the example sentence and its explanation are displayed on the user's screen.

[0218] Through the above processing steps, the system allows users to receive language learning support in real time while browsing content.

[0219] 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.

[0220] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[0221] System Overview

[0222] This system is an interactive dictionary service that utilizes natural language processing (NLP), generative AI, and an emotion engine to support users' language learning. It aims to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their devices, and can also recognize the user's emotions and adjust the content and tone of the response. The operation and functionality of each major component are described in detail below.

[0223] Server Operation

[0224] 1. Receiving user input

[0225] The server receives requests entered by users into their terminals, such as "Please tell me some example sentences for ambiguous."

[0226] 2. Performing Natural Language Processing (NLP)

[0227] The server analyzes the received user input using natural language processing (NLP), and as part of the analysis, it tokenizes the input to understand its context and intent.

[0228] 3. Emotion analysis using an emotion engine

[0229] The server analyzes the user's input to determine their emotions. The emotion engine analyzes the input and identifies the user's emotional state.

[0230] 4. Database Access

[0231] Based on the analysis results, the server accesses a database to retrieve data related to the relevant words and expressions, including example sentences and explanations of their nuances.

[0232] 5. Response generation using generative AI

[0233] The server passes the acquired data to the generation AI, which generates appropriate example sentences and their explanations. It can also adjust the tone and content of the response based on the analysis results of the emotion engine.

[0234] 6. Response Format

[0235] The server formats the generated response in a user-friendly format suitable for display.

[0236] Device behavior

[0237] 1. Submitting User Input

[0238] The device sends the information entered by the user to the server, and if the input is useful for learning, it immediately makes a request to the server.

[0239] 2. Receiving a response from the server

[0240] The device receives the response from the server and displays it to the user in an easy-to-understand format, often including concrete examples, explanations, and emotional tones.

[0241] 3. Assistive typing and autocomplete

[0242] The device provides input assistance and auto-complete functions to help users input information efficiently, making the learning experience smoother for users.

[0243] User Actions and Interactions

[0244] 1. First time input

[0245] Users input words or phrases into their device for translation, example sentences, or nuanced understanding. For example, they might type, "Please tell me some example sentences for ambiguous."

[0246] 2. Use of the displayed results

[0247] Users can use the example sentences and explanations displayed to help them learn. If they need more information, they can enter additional questions on the same screen. Responses tailored to the user's emotions also help them understand more easily.

[0248] 3. Follow-up questions and continued learning

[0249] If the user enters a subsequent question, a request is sent to the server again, and a response is generated in the same process, allowing the user to progress through the learning process interactively.

[0250] Specific examples

[0251] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[0252] The device sends input to the server.

[0253] The server parses the input and retrieves data related to "ambiguous" from the database.

[0254] The emotion engine analyzes emotions from user input. For example, if a user types "Tell me some vague sentences," the emotion engine will recognize emotions like doubt and confusion.

[0255] The generative AI generates the example sentence "The meaning of his statement was ambiguous" and its explanation, and includes a specific commentary based on the emotion recognition results.

[0256] The server formats the generated response and sends it to the terminal.

[0257] The device receives the response and displays it to the user, explained in an emotionally tailored tone of voice.

[0258] The above is an embodiment of the present invention, which allows the user to learn a language efficiently.

[0259] The processing flow will be explained below.

[0260] Step 1:

[0261] The user types into the terminal, "Please tell me some example sentences for ambiguous."

[0262] Step 2:

[0263] The terminal sends the user's input to the server. The terminal converts the input string into an HTTP request and sends it to the server.

[0264] Step 3:

[0265] The server receives a request from the user. The server receives the request sent from the terminal and extracts the input content included in the request body.

[0266] Step 4:

[0267] The server performs natural language processing (NLP), tokenizing the incoming input and analyzing its context and intent. For example, it identifies the word "ambiguous" and analyzes its usage.

[0268] Step 5:

[0269] The server analyzes the user's emotions using an emotion engine, extracts emotions from the user's input sentences, and recognizes their emotional state, such as "confusion" or "doubt."

[0270] Step 6:

[0271] The server accesses the database and retrieves data related to the word identified in the input sentence from the database. For example, it searches for example sentences and explanations of nuances related to "ambiguous."

[0272] Step 7:

[0273] The server uses the generation AI to generate a response. The server passes the acquired data to the generation AI, which generates appropriate example sentences and their explanations. The server also adjusts the tone and content of the response based on the analysis results of the emotion engine.

[0274] Step 8:

[0275] The server formats the response. The server formats the generated response in a user-friendly format suitable for display, such as a response containing the example sentence "The meaning of his statement was ambiguous" and an explanation of it.

[0276] Step 9:

[0277] The server sends the formatted response to the terminal. The server prepares the formatted response as an HTTP response and sends it to the terminal.

[0278] Step 10:

[0279] The device receives the response from the server. The device analyzes the response and displays it to the user. For example, if the user expresses confusion, the response may include further explanation or a gentler tone.

[0280] Step 11:

[0281] The user can use the displayed results. The user can use the example sentences and explanations displayed to study, and if more information is needed, they can enter additional questions.

[0282] Example 2

[0283] 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."

[0284] Conventional language learning support systems simply provide example sentences and explanations in response to user input, but are unable to respond in a way that takes into account the user's emotional state. This means that when a user is confused or has questions, the system is unable to respond in an appropriate tone, resulting in insufficient learning effectiveness.

[0285] 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.

[0286] In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for analyzing emotions based on the results of the natural language processing, means for retrieving appropriate data from a database based on the analyzed emotional information, means for generating a response using the retrieved data and the analyzed emotional information with a generative artificial intelligence, and means for formatting the generated response and sending it to the user. This makes it possible to generate a response that corresponds to the emotional state of the user, thereby achieving more effective language learning support.

[0287] "User" refers to an individual who uses this system to study a language.

[0288] "Input" refers to language-related questions or phrases that a user sends to a terminal.

[0289] "Server" refers to a central processing system that receives user input and performs various processes.

[0290] "Natural language processing" refers to the technology of analyzing user input and understanding the context and intent.

[0291] An "emotion engine" refers to a technology that analyzes emotions from user input and identifies that emotional state.

[0292] A "database" refers to a collection of information that stores and makes accessible data relating to words and expressions.

[0293] "Generative artificial intelligence" refers to AI technology that generates appropriate responses based on acquired data.

[0294] A "response" refers to a reply that includes example sentences and explanations generated based on the user's input.

[0295] "Formatting" refers to the process of preparing the generated response in a form that is easy for the user to understand.

[0296] "Terminal" refers to a device (such as a personal computer or smartphone) that a user uses to make input.

[0297] The "input support function" refers to a function for assisting the user in input.

[0298] The "autocomplete function" refers to a function that automatically displays candidates while the user is typing and completes the input.

[0299] MODE FOR CARRYING OUT THE INVENTION

[0300] This invention is an interactive dictionary service that utilizes natural language processing (NLP), generative AI, and an emotion engine to support users' language learning. The system aims to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their devices, and is structured and functionally capable of recognizing the user's emotions and adjusting the content and tone of the response. The operation and functionality of each major component are described in detail below.

[0301] Server Operation

[0302] The server receives the request entered by the user on the device and analyzes the content using natural language processing (NLP) technology. NLP engines used include "SpaCy" and "NLTK."

[0303] Received user input is first tokenized to understand context and intent. An emotion engine then analyzes the input and recognizes the user's emotional state. The emotion engine used can be a platform like Affectiva or IBM Watson Tone Analyzer.

[0304] Based on the analysis results, the server accesses a database to retrieve data related to the relevant words and expressions. The database stores example sentences and explanations of their nuances. A database management system (DBMS) such as MySQL or PostgreSQL is used.

[0305] The acquired data is passed to a generation AI, which generates appropriate example sentences and their explanations. Models such as GPT-3 and BERT are used as the generation AI. The tone and content of the response are adjusted based on the analysis results of the emotion engine.

[0306] Finally, the generated response is formatted in a user-friendly format, made suitable for display, and sent to the terminal, where it is reconstructed in HTML or JSON format.

[0307] Device behavior

[0308] The terminal mainly serves to send input from the user to the server and receive and display responses from the server. For example, if a user types "Please tell me some example sentences for ambiguous," the request is sent to the server in real time.

[0309] When the response comes back from the server, the device analyzes it and displays it in a user-friendly format, including specific examples, explanations, and emotional tones. Frameworks such as "React" and "Vue.js" are used for the UI / UX design of the exhibit.

[0310] The device also provides input assistance and auto-complete functions to help users input information efficiently, making the learning experience smoother for users.

[0311] User Actions and Interactions

[0312] Users use their device to input a question about a word or phrase, such as "Can you give me an example of an ambiguous sentence?" The example sentences and explanations displayed can be used to learn, and if more information is needed, users can input additional questions on the same screen. Responses tailored to their emotions can improve comprehension.

[0313] If the user enters a subsequent question, a request is sent to the server again, and a response is generated in the same process, allowing the user to progress through the learning process interactively.

[0314] Specific examples

[0315] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[0316] 1. The device sends input to the server.

[0317] 2. The server parses the input and retrieves data related to "ambiguous" from the database.

[0318] 3. The emotion engine analyzes emotions from the user's input. For example, if a user types "Tell me some vague sentences," the emotion engine will recognize emotions such as doubt and confusion.

[0319] 4. The generative AI generates an example sentence, "The meaning of his statement was ambiguous," along with an explanation, including specific commentary based on the emotion recognition results.

[0320] 5. The server formats the generated response and sends it to the device.

[0321] 6. The device receives the response and displays it to the user, explained in an emotionally tailored tone.

[0322] Prompt Sentence Examples

[0323] An example prompt for this system:

[0324] 1. "What does ambiguous mean?"

[0325] 2. "Please give me some example sentences for ambiguous expressions in English."

[0326] 3. "Please explain how to use ambiguous with an example sentence."

[0327] This allows the user to study a language efficiently.

[0328] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0329] Step 1:

[0330] The user types a question or phrase into the terminal. For example, "Please tell me an example sentence for ambiguous." The input data is sent to the terminal as a prompt.

[0331] Step 2:

[0332] The terminal sends user input to the server. The terminal formats the received prompt and sends it to the server as an HTTP request. The input is text data, "Please tell me some example sentences for ambiguous," and is sent to the server as is.

[0333] Step 3:

[0334] The server receives user input. The server receives the prompt sent from the terminal and saves it for further processing. The input is text data included in the body of the HTTP request.

[0335] Step 4:

[0336] The server analyzes the input using an NLP engine. The server tokenizes the received text data and analyzes the context and intent. Specifically, it splits the input sentence into words and performs grammatical analysis. The input is the text data "Please tell me some example sentences for ambiguous," and the output is the keyword "ambiguous" and its context information.

[0337] Step 5:

[0338] The server uses an emotion engine to analyze the user's emotions. The server identifies the user's emotional state from the output of the NLP engine. Specifically, it performs emotion scoring of text data. The input is the analysis result of the NLP engine, and the output is emotional state information that the user is "confused."

[0339] Step 6:

[0340] The server accesses the database to retrieve relevant data. Based on the emotion and keyword, the server retrieves appropriate example sentences and explanations from the database. Specifically, it searches for related data using an SQL query. The input is the keyword "ambiguous" and emotion information, and the output is related example sentence data.

[0341] Step 7:

[0342] The server generates a response using generative AI. Based on the acquired data, the server generates appropriate example sentences and explanations for the user input. It also adjusts the tone and content of the response using the results of emotion analysis. Specifically, data is input into the generative AI model, which outputs a response. The input is example sentence data and emotion information acquired from the database, and the output is the generated example sentence and explanation.

[0343] Step 8:

[0344] The server formats the response and sends it to the terminal. The server formats the generated response in a format that is easy for the user to understand and sends the formatted data to the terminal. Specifically, it converts the data into HTML or JSON format. The input is the generated response data, and the output is the formatted data.

[0345] Step 9:

[0346] The terminal receives and displays the response from the server. The terminal receives the response sent from the server and displays it in a format that is easy for the user to understand. Specifically, it interprets the received data and displays it on the screen. The input is the formatted data sent from the server, and the output is the example sentence and explanation displayed on the screen.

[0347] Step 10:

[0348] The user enters an additional question. If the user needs more information, they enter the question again into the terminal. For example, they might enter "Tell me more example sentences." In this case, a prompt requesting further information is sent to the terminal again.

[0349] (Application example 2)

[0350] 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."

[0351] The objective of this invention is to provide a system that can provide interactive advertisements according to the user's emotional state. Conventional advertising systems can only generate a uniform response to user input, making it difficult to personalize the response to reflect the user's emotions and intentions. This results in a poor user experience and limited advertising effectiveness.

[0352] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for performing emotion analysis based on the results of the natural language processing, means for generating a response according to the user's emotion using the generative artificial intelligence, and means for formatting the generated response and sending it to the user. This makes it possible to generate personalized advertising copy that reflects the user's emotional state and intentions.

[0353] The "means for receiving input from the user" is a mechanism for receiving information input by the user through the user interface.

[0354] "Means for natural language processing" refers to technology for analyzing input text and understanding its grammar and meaning.

[0355] The "means for performing emotion analysis" is a technology for determining the psychological state of a user based on the sentences input by the user.

[0356] "Means for generating responses using generative artificial intelligence" refers to a mechanism that uses a machine learning model to create appropriate answers based on the analysis results.

[0357] The "means for formatting the generated response and sending it to the user" refers to a technique for arranging the generated response in an appropriate format and providing it to the user.

[0358] The "input assistance function or autocomplete function" is a function that assists the user in inputting information effectively, and is a technology that performs pre-reading and suggests candidates.

[0359] The "means for generating advertising copy" is a technology for creating appropriate advertising content based on the results of user sentiment analysis.

[0360] System Program Overview

[0361] A system embodying the present invention receives input from a user, performs natural language processing (NLP) and sentiment analysis, and uses generative AI to generate a response based on the user's sentiment, thereby providing personalized advertising copy based on the user's sentiment.

[0362] Detailed explanation of the process

[0363] 1. Receiving user input

[0364] The server receives information entered by the user on the device. This input is in natural language, for example, in the form of "I want a new smartphone."

[0365] 2. Performing natural language processing

[0366] The server then analyzes the received user input using NLP techniques, which include tokenizing the input and understanding its grammar, context, and intent. A suitable NLP library to use is "transformers."

[0367] 3. Performing sentiment analysis

[0368] The server performs sentiment analysis based on the results of NLP analysis. The emotion engine determines the psychological state of the input content and identifies whether the user is excited or confused. The model for sentiment analysis uses a library that provides "sentiment-analysis."

[0369] 4. Database Access

[0370] The server retrieves relevant advertising information from a database based on the analysis results, including corresponding product and service information based on the user's input.

[0371] 5. Generating the Response

[0372] The server uses a generative AI model to generate ad copy based on the acquired ad information and the user's emotional state. For example, if the user is excited, the server will provide ad copy in an exciting tone, and if the user is confused, the server will provide polite explanation. An example of a prompt sentence in this case is "Generate ad copy for a new smartphone."

[0373] 6. Response Format and Transmission

[0374] The server formats the generated response in a user-friendly format and sends it to the terminal in the appropriate format, which displays the received response to the user in real time.

[0375] Specific examples

[0376] For example, if a user types "I want a new phone," the system will do the following:

[0377] The server receives the user input and parses the input using the "transformers" library.

[0378] The emotion engine determines from the input sentence that the user is excited.

[0379] The server retrieves the latest smartphone information from the database.

[0380] The generative AI model generates an exciting ad copy that reads, "An exciting new smartphone! Boasting a revolutionary camera, a super-fast processor, and now at a special price of just ¥100,000!"

[0381] The server formats the generated copy and sends it to the device.

[0382] The terminal displays the advertisement copy to the user in real time.

[0383] In this way, the system of the present invention provides personalized advertising copy that takes user emotions into account, thereby achieving a more effective advertising experience.

[0384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0385] Step 1:

[0386] The device receives information entered by the user. When the user enters "I want a new smartphone," the device sends the input data to the server. Input: A string of natural language characters containing the user's wishes and questions. Output: The input data sent to the server.

[0387] Step 2:

[0388] The server parses the received user input using natural language processing (NLP), specifically using the "transformers" library to tokenize the input sentence and understand grammar and context. Input: User's natural language input. Output: Parsed tokenized data and intent.

[0389] Step 3:

[0390] The server performs sentiment analysis based on the results of NLP analysis. It uses an emotion engine ("sentiment-analysis" model) to determine the user's emotional state. Input: NLP analysis results. Output: User's emotional state (e.g., excited, confused).

[0391] Step 4:

[0392] The server retrieves relevant advertising information from the database based on the results of the sentiment analysis. Specifically, if a user enters "smartphone," the server searches the database for the latest smartphone information and retrieves it. Input: User input and sentiment analysis results. Output: Related advertising information (e.g., product name, features, price).

[0393] Step 5:

[0394] The server generates ad copy that corresponds to the user's emotions based on the ad information obtained using the generative AI model. The generative AI model is given a prompt such as "Generate ad copy for a new smartphone." Input: Ad information and emotional state. Output: Personalized ad copy that corresponds to the user's emotions.

[0395] Step 6:

[0396] The server formats the generated ad copy into an easy-to-understand format and sends it to the device. Specifically, it converts it into a format that is easy to format, such as HTML or plain text. Input: Generated ad copy. Output: Formatted ad copy.

[0397] Step 7:

[0398] The terminal displays the formatted ad copy received from the server to the user. If the user is excited, the user will see the ad copy in an exciting tone, and if the user is confused, the user will see the ad copy in a polite tone. Input: Formatted ad copy. Output: Display of ad copy.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] [Second embodiment]

[0403] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0404] 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.

[0405] 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).

[0406] 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.

[0407] 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.

[0408] 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).

[0409] 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.

[0410] 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.

[0411] 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.

[0412] 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.

[0413] 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.

[0414] 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."

[0415] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[0416] System Overview

[0417] This system is an interactive dictionary service that uses natural language processing (NLP) and generative AI to support users' language learning. Its purpose is to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their devices. The operation and functionality of each major component are described in detail below.

[0418] Server Operation

[0419] 1. Receiving user input

[0420] The server receives requests entered by users into their terminals, such as "Please tell me some example sentences for ambiguous."

[0421] 2. Performing Natural Language Processing (NLP)

[0422] The server analyzes the received user input using natural language processing (NLP), and as part of the analysis, it tokenizes the input to understand its context and intent.

[0423] 3. Database Access

[0424] Based on the analysis results, the server accesses a database to retrieve data related to the relevant words and expressions, including example sentences and explanations of their nuances.

[0425] 4. Response generation using generative AI

[0426] The server passes the acquired data to the generation AI, which generates appropriate example sentences and explanations. For example, it generates "The meaning of his statement was ambiguous" as an example sentence of "ambiguous."

[0427] 5. Response Format

[0428] The server formats the generated response in a user-friendly format and sends it to the terminal.

[0429] Device behavior

[0430] 1. Submitting User Input

[0431] The device sends the information entered by the user to the server, and if the input is useful for learning, it immediately makes a request to the server.

[0432] 2. Receiving a response from the server

[0433] The device receives the response from the server and displays it to the user in an easy-to-understand format, often including concrete examples and explanations.

[0434] 3. Assistive typing and autocomplete

[0435] The device provides input assistance and auto-complete functions to help users input information efficiently, making the learning experience smoother for users.

[0436] User Actions and Interactions

[0437] 1. First time input

[0438] Users input words or phrases into their device for translation, example sentences, or nuanced understanding. For example, they might type, "Please tell me some example sentences for ambiguous."

[0439] 2. Use of the displayed results

[0440] Users can use the example sentences and explanations displayed to help them learn, and if they need more information, they can enter additional questions on the same screen.

[0441] 3. Follow-up questions and continued learning

[0442] If the user enters a subsequent question, a request is sent to the server again, and a response is generated in the same process, allowing the user to progress through the learning process interactively.

[0443] Specific examples

[0444] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[0445] The device sends input to the server.

[0446] The server parses the input and retrieves data related to "ambiguous" from the database.

[0447] The generative AI generates an example sentence, "The meaning of his statement was ambiguous," along with its explanation.

[0448] The server formats the generated response and sends it to the terminal.

[0449] The terminal receives the response and displays it to the user.

[0450] The above is an embodiment of the present invention, which allows the user to learn a language efficiently.

[0451] The processing flow will be explained below.

[0452] Step 1:

[0453] The user types into the terminal, "Please tell me some example sentences for ambiguous."

[0454] Step 2:

[0455] The terminal sends the user's input to the server. The terminal converts the input string into an HTTP request and sets the URL, header, and body of the request to send to the server.

[0456] Step 3:

[0457] The server receives a request from the user. The server receives the request sent from the terminal and extracts the content included in the request body.

[0458] Step 4:

[0459] The server performs natural language processing (NLP), tokenizing the received input and analyzing it for context and intent. Specifically, it segments words and phrases and analyzes them to determine their meaning.

[0460] Step 5:

[0461] The server accesses the database. Based on the analysis results, the server retrieves relevant data from the database. For example, it searches for example sentences and explanations of nuances related to "ambiguous."

[0462] Step 6:

[0463] The server generates a response using the generation AI. The server passes the information obtained from the database to the generation AI, which generates an appropriate example sentence and its explanation. For example, it generates the example sentence, "The meaning of his statement was ambiguous."

[0464] Step 7:

[0465] Server formats response: The server formats the generated response in a user-friendly format suitable for display.

[0466] Step 8:

[0467] The server sends the formatted response to the terminal. The server prepares the formatted response as an HTTP response and sends it to the terminal.

[0468] Step 9:

[0469] The terminal receives the response from the server, analyzes the response, and displays the content to the user.

[0470] Step 10:

[0471] The user can use the displayed results. The user can use the example sentences and explanations displayed to study, and if more information is needed, they can enter additional questions.

[0472] Example 1

[0473] 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."

[0474] Conventional language learning support systems have difficulty providing appropriate example sentences and explanations instantly for words and phrases entered by users. Furthermore, input support and auto-complete functions are inadequate, resulting in a clunky learning experience for users. Furthermore, responses to user requests are mechanical, failing to help users understand the meaning in a natural context.

[0475] 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.

[0476] In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for accessing a database and acquiring related information based on the results of the natural language processing, means for supplying the acquired information to a generative artificial intelligence model to generate a response, and means for formatting and sending the generated response to the user. This allows the server to instantly provide appropriate example sentences and explanations for words and phrases entered by the user, making the learning experience smoother and more efficient. It also enables understanding in a natural context, improving the user's learning effectiveness.

[0477] "User input" refers to the input of text or commands by a system user into a terminal.

[0478] "Natural language processing" refers to technology that enables computers to understand and analyze human language, and includes processes such as tokenization, grammar analysis, and entity extraction.

[0479] A "database" refers to a system for organizing and storing related information, including example sentences and explanations related to words and phrases.

[0480] A "generative artificial intelligence model" refers to an artificial intelligence that has algorithms for generating context-appropriate responses based on large amounts of data.

[0481] "Response formatting" refers to shaping the generated response into an appropriate format for display to the user in an easily understandable manner.

[0482] The "input support function" refers to a function that assists the user when making input, and includes functions such as suggesting candidates and spell checking.

[0483] "Autocomplete function" refers to a function that automatically completes text that a user has incompletely entered.

[0484] "Example sentence" refers to a specific sentence provided to demonstrate the usage of a word or phrase.

[0485] "Explanation" refers to a sentence that provides additional information about the meaning, grammar, and context of use of an example sentence.

[0486] MODE FOR CARRYING OUT THE INVENTION

[0487] The following describes in detail an embodiment of the present invention. This system is an interactive dictionary service that uses natural language processing (NLP) and generative AI to support users' language learning. Its purpose is to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their terminals.

[0488] System Overview

[0489] This system is primarily composed of a server and a terminal. The server receives input sent by the user, performs natural language processing, and then accesses a database to retrieve relevant information. The retrieved information is then fed into a generative AI model to generate an appropriate response, which is then sent to the user. The terminal sends the user's input to the server and displays the response received from the server to the user. It also provides input assistance and auto-complete functions.

[0490] Hardware and software used

[0491] Server: Used to receive input from users, perform natural language processing, access databases, and generate responses using generative AI models. The server can run on a common cloud service.

[0492] Terminal: A device used by a user, such as a PC, smartphone, or tablet. The terminal communicates with the server via a web browser or a dedicated application.

[0493] Database: Use a relational database management system (RDBMS) such as MySQL or PostgreSQL to manage and access data.

[0494] Natural Language Processing (NLP) libraries: Python's NLTK library and spaCy are used to tokenize input and analyze context.

[0495] Generative AI models: Generative AI models such as OpenAI's GPT-3 are used to generate natural-sounding examples and explanations.

[0496] Specific examples

[0497] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[0498] 1. User input: The user types "Please tell me an example sentence for ambiguous" into the terminal.

[0499] 2. Sending input: The device sends the input to the server.

[0500] 3. Natural Language Processing: The server receives the input and performs natural language processing using Python's NLTK library and spaCy. Specifically, it tokenizes the input, performs grammatical analysis, and identifies "ambiguous."

[0501] 4. Database access: Based on the analysis results, the server sends a query to a MySQL or PostgreSQL database to retrieve relevant example sentences and explanations.

[0502] 5. Response generation by generative AI: The server passes the acquired information to OpenAI's GPT-3, which generates appropriate example sentences and explanations for "ambiguous." For example, an example sentence such as "The meaning of his statement was ambiguous" is generated.

[0503] 6. Response formatting: The server formats the generated response in JSON format or similar and sends it to the device.

[0504] 7. Displaying the response: The terminal analyzes the response received from the server and displays it in a user-friendly format.

[0505] This process allows users to obtain appropriate example sentences and explanations in real time and advance their language learning.

[0506] Prompt Sentence Examples

[0507] The prompt uses natural questions such as "Can you give me an example of an ambiguous sentence?" By inputting such a prompt, the system can quickly provide the necessary information.

[0508] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0509] Step 1: Receiving User Input

[0510] Input: The user types "Please tell me some example sentences for ambiguous" into the terminal.

[0511] How it works: The device sends user input to the server as an HTTP request. It is sent in the form of an HTTP POST request, with the user input included in the request body.

[0512] Output: The server parses the received request and extracts the user input.

[0513] Step 2: Performing Natural Language Processing

[0514] Input: The user input that the server extracted in step 1.

[0515] How it works: The server uses Python's NLTK library and spaCy to tokenize the text and perform grammatical analysis. For example, "Please tell me some example sentences about ambiguous" is broken down into the tokens "ambiguous," "of," "example sentences," "o," and "teach me," and identifies "ambiguous."

[0516] Output: Parsed tokens and identified keywords (in this case, "ambiguous").

[0517] Step 3: Database Access

[0518] Input: The keyword the server identified in step 2.

[0519] How it works: The server sends a query to a database such as MySQL or PostgreSQL to retrieve example sentences and explanations related to "ambiguous." It uses SQL statements to search the database, executing a query to retrieve, for example, "example sentences" and "explanations."

[0520] Output: Example sentences retrieved from the database and their explanations.

[0521] Step 4: Generative AI generates a response

[0522] Input: The example sentence and explanation obtained by the server in step 3.

[0523] How it works: The server inputs the acquired data into a generative AI model (e.g., OpenAI's GPT-3) and sets it as a prompt. The prompt includes a request for example sentence generation. The generative AI model generates example sentences that are grammatically and content-appropriate based on the input information.

[0524] Output: A new example sentence generated by the generative AI model, e.g., "The meaning of his statement was ambiguous."

[0525] Step 5: Formatting the Response

[0526] Input: The example sentence generated by the server in step 4.

[0527] How it works: The server formats the generated example sentences in a user-friendly format, such as JSON or HTML, as needed.

[0528] Output: The formatted response data.

[0529] Step 6: Sending a response from the server to the device

[0530] Input: The response data formatted by the server in step 5.

[0531] Operation: The server sends the response data to the terminal as an HTTP response. The response is in JSON or HTML format.

[0532] Output: The response data sent to the device.

[0533] Step 7: View the response

[0534] Input: The response data received by the terminal in step 6.

[0535] What happens: The device parses the data it receives and displays it in a user-friendly format, for example rendering it into HTML for display in a web browser.

[0536] Output: Generated example sentences and their explanations displayed to the user.

[0537] (Application example 1)

[0538] 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."

[0539] Modern content distribution services lack the means to instantly provide users with relevant information about the text or content they are viewing. This makes it difficult for users to deepen their understanding of an unfamiliar word or phrase on the spot. Furthermore, existing language learning support systems are unable to quickly respond to users' real-time needs, resulting in reduced learning efficiency.

[0540] 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.

[0541] In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for generating a response using generative artificial intelligence based on the results of the natural language processing, and means for formatting the generated response and displaying content, thereby enabling real-time language learning support by instantly providing related information and explanations for the content the user is viewing.

[0542] The "means for receiving input from the user" is a function for receiving text or voice input by the user into the terminal.

[0543] "Means for natural language processing" refers to a function that uses technology to analyze received user input and understand its meaning and intent.

[0544] A "means for generating responses using generative artificial intelligence" is a function that uses an AI model to generate appropriate responses based on the results of natural language processing.

[0545] "Means for formatting the generated response and displaying the content" refers to a function for formatting the response generated by AI into a format that is easy for the user to understand and displaying it on the device.

[0546] The "input assistance function" is a function that provides predictive conversion, suggestion functions, etc. when a user inputs text, thereby assisting the user in inputting text.

[0547] An "autocomplete feature" is a feature that automatically completes partially typed words or phrases when a user is entering text.

[0548] Generating "example sentences and their explanations" means generating usage examples and their explanations for specific words or phrases and providing them to the user.

[0549] The following describes in detail the mode for carrying out the present invention. The system functions as a support tool for users in real-time language learning, and is intended to provide instant example sentences and explanations for unknown words and phrases, particularly in content distribution services.

[0550] System Overview

[0551] This system consists of a server, a device, and a user. Specifically, it works by receiving user input from a device such as a smartphone or head-mounted display and sending it to the server. The server uses natural language processing (NLP) and generative AI models to generate a response based on the user input and return it to the device.

[0552] Hardware and software used

[0553] Hardware

[0554] Smartphone

[0555] head-mounted display

[0556] software

[0557] Python

[0558] Transformers library (by Hugging Face)

[0559] Requests library (for HTTP requests)

[0560] Processing flow

[0561] 1. User Input

[0562] The user inputs a prompt sentence such as "Tell me an example sentence for ambiguous" into a smartphone or head-mounted display.

[0563] 2. Receiving Input

[0564] The terminal receives user input and sends it to the server.

[0565] 3. Natural Language Processing

[0566] The server analyzes the received user input using natural language processing to extract important words (in this case, "ambiguous"). The natural language processing model used is the Transformers library from Hugging Face.

[0567] 4. Database Access

[0568] Based on the analysis results, the server retrieves related data from the virtual database.

[0569] 5. AI-generated responses

[0570] Based on the acquired data, a generative AI model is used to generate appropriate example sentences and explanations.

[0571] 6. Response Formatting and Display

[0572] The generated response is formatted in a user-friendly format and sent to the terminal for display.

[0573] Examples of prompt statements

[0574] Below are some examples of prompt sentences.

[0575] Example: "What are some examples of ambiguous?"

[0576] In this way, by using the present invention, users can progress with their language learning in real time while browsing content, which is expected to improve the efficiency of users' learning.

[0577] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0578] Step 1:

[0579] The user types "Please tell me an example sentence of ambiguous" into a smartphone or head-mounted display. The prompt "Please tell me an example sentence of ambiguous" is received as input. This becomes the input for the next step.

[0580] Step 2:

[0581] The terminal receives user input and sends it to the server as a string. In this step, the entered prompt sentence is sent to the server as an HTTP request. As a specific operation, data is sent using an HTTP POST request. The user input is passed to the server as output.

[0582] Step 3:

[0583] The server receives user input and analyzes it using natural language processing (NLP). The server uses Hugging Face's Transformers library to tokenize the input text and understand its context and intent. The data processing performed in this step is tokenization and context analysis. As an output, important words ("ambiguous") are extracted.

[0584] Step 4:

[0585] Based on the analysis results, the server accesses the virtual database to retrieve related data. The data calculation performed here is a database query corresponding to the extracted word. The server retrieves example sentences and explanations related to "ambiguous" from the virtual database. As an output, data related to the word is obtained.

[0586] Step 5:

[0587] The server passes the acquired data to the generative AI model to generate appropriate example sentences and explanations. Specifically, the data is passed as input to the generative AI model, and the generated text output is obtained. In this step, the generative AI model generates the example sentence "The meaning of his statement was ambiguous" and its explanation. The generated example sentence and explanation are obtained as output.

[0588] Step 6:

[0589] The server formats the generated response in a user-friendly format and sends it to the terminal. The specific operation here is to convert the generated text into an appropriate format and send it again to the terminal as an HTTP response. As output, the formatted response is passed to the terminal.

[0590] Step 7:

[0591] The terminal receives the response from the server and displays it in a format that is easy for the user to understand. As input, it receives the response from the server. As a specific operation, it displays the received data on the screen. As output, the example sentence and its explanation are displayed on the user's screen.

[0592] Through the above processing steps, the system allows users to receive language learning support in real time while browsing content.

[0593] 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.

[0594] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[0595] System Overview

[0596] This system is an interactive dictionary service that utilizes natural language processing (NLP), generative AI, and an emotion engine to support users' language learning. It aims to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their devices, and can also recognize the user's emotions and adjust the content and tone of the response. The operation and functionality of each major component are described in detail below.

[0597] Server Operation

[0598] 1. Receiving user input

[0599] The server receives requests entered by users into their terminals, such as "Please tell me some example sentences for ambiguous."

[0600] 2. Performing Natural Language Processing (NLP)

[0601] The server analyzes the received user input using natural language processing (NLP), and as part of the analysis, it tokenizes the input to understand its context and intent.

[0602] 3. Emotion analysis using an emotion engine

[0603] The server analyzes the user's input to determine their emotions. The emotion engine analyzes the input and identifies the user's emotional state.

[0604] 4. Database Access

[0605] Based on the analysis results, the server accesses a database to retrieve data related to the relevant words and expressions, including example sentences and explanations of their nuances.

[0606] 5. Response generation using generative AI

[0607] The server passes the acquired data to the generation AI, which generates appropriate example sentences and their explanations. It can also adjust the tone and content of the response based on the analysis results of the emotion engine.

[0608] 6. Response Format

[0609] The server formats the generated response in a user-friendly format suitable for display.

[0610] Device behavior

[0611] 1. Submitting User Input

[0612] The device sends the information entered by the user to the server, and if the input is useful for learning, it immediately makes a request to the server.

[0613] 2. Receiving a response from the server

[0614] The device receives the response from the server and displays it to the user in an easy-to-understand format, often including concrete examples, explanations, and emotional tones.

[0615] 3. Assistive typing and autocomplete

[0616] The device provides input assistance and auto-complete functions to help users input information efficiently, making the learning experience smoother for users.

[0617] User Actions and Interactions

[0618] 1. First time input

[0619] Users input words or phrases into their device for translation, example sentences, or nuanced understanding. For example, they might type, "Please tell me some example sentences for ambiguous."

[0620] 2. Use of the displayed results

[0621] Users can use the example sentences and explanations displayed to help them learn. If they need more information, they can enter additional questions on the same screen. Responses tailored to the user's emotions also help them understand more easily.

[0622] 3. Follow-up questions and continued learning

[0623] If the user enters a subsequent question, a request is sent to the server again, and a response is generated in the same process, allowing the user to progress through the learning process interactively.

[0624] Specific examples

[0625] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[0626] The device sends input to the server.

[0627] The server parses the input and retrieves data related to "ambiguous" from the database.

[0628] The emotion engine analyzes emotions from user input. For example, if a user types "Tell me some vague sentences," the emotion engine will recognize emotions like doubt and confusion.

[0629] The generative AI generates the example sentence "The meaning of his statement was ambiguous" and its explanation, and includes a specific commentary based on the emotion recognition results.

[0630] The server formats the generated response and sends it to the terminal.

[0631] The device receives the response and displays it to the user, explained in an emotionally tailored tone of voice.

[0632] The above is an embodiment of the present invention, which allows the user to learn a language efficiently.

[0633] The processing flow will be explained below.

[0634] Step 1:

[0635] The user types into the terminal, "Please tell me some example sentences for ambiguous."

[0636] Step 2:

[0637] The terminal sends the user's input to the server. The terminal converts the input string into an HTTP request and sends it to the server.

[0638] Step 3:

[0639] The server receives a request from the user. The server receives the request sent from the terminal and extracts the input content included in the request body.

[0640] Step 4:

[0641] The server performs natural language processing (NLP), tokenizing the incoming input and analyzing its context and intent. For example, it identifies the word "ambiguous" and analyzes its usage.

[0642] Step 5:

[0643] The server analyzes the user's emotions using an emotion engine, extracts emotions from the user's input sentences, and recognizes their emotional state, such as "confusion" or "doubt."

[0644] Step 6:

[0645] The server accesses the database and retrieves data related to the word identified in the input sentence from the database. For example, it searches for example sentences and explanations of nuances related to "ambiguous."

[0646] Step 7:

[0647] The server uses the generation AI to generate a response. The server passes the acquired data to the generation AI, which generates appropriate example sentences and their explanations. The server also adjusts the tone and content of the response based on the analysis results of the emotion engine.

[0648] Step 8:

[0649] The server formats the response. The server formats the generated response in a user-friendly format suitable for display, such as a response containing the example sentence "The meaning of his statement was ambiguous" and an explanation of it.

[0650] Step 9:

[0651] The server sends the formatted response to the terminal. The server prepares the formatted response as an HTTP response and sends it to the terminal.

[0652] Step 10:

[0653] The device receives the response from the server. The device analyzes the response and displays it to the user. For example, if the user expresses confusion, the response may include further explanation or a gentler tone.

[0654] Step 11:

[0655] The user can use the displayed results. The user can use the example sentences and explanations displayed to study, and if more information is needed, they can enter additional questions.

[0656] Example 2

[0657] 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."

[0658] Conventional language learning support systems simply provide example sentences and explanations in response to user input, but are unable to respond in a way that takes into account the user's emotional state. This means that when a user is confused or has questions, the system is unable to respond in an appropriate tone, resulting in insufficient learning effectiveness.

[0659] 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.

[0660] In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for analyzing emotions based on the results of the natural language processing, means for retrieving appropriate data from a database based on the analyzed emotional information, means for generating a response using the retrieved data and the analyzed emotional information with a generative artificial intelligence, and means for formatting the generated response and sending it to the user. This makes it possible to generate a response that corresponds to the emotional state of the user, thereby achieving more effective language learning support.

[0661] "User" refers to an individual who uses this system to study a language.

[0662] "Input" refers to language-related questions or phrases that a user sends to a terminal.

[0663] "Server" refers to a central processing system that receives user input and performs various processes.

[0664] "Natural language processing" refers to the technology of analyzing user input and understanding the context and intent.

[0665] An "emotion engine" refers to a technology that analyzes emotions from user input and identifies that emotional state.

[0666] A "database" refers to a collection of information that stores and makes accessible data relating to words and expressions.

[0667] "Generative artificial intelligence" refers to AI technology that generates appropriate responses based on acquired data.

[0668] A "response" refers to a reply that includes example sentences and explanations generated based on the user's input.

[0669] "Formatting" refers to the process of preparing the generated response in a form that is easy for the user to understand.

[0670] "Terminal" refers to a device (such as a personal computer or smartphone) that a user uses to make input.

[0671] The "input support function" refers to a function for assisting the user in input.

[0672] The "autocomplete function" refers to a function that automatically displays candidates while the user is typing and completes the input.

[0673] MODE FOR CARRYING OUT THE INVENTION

[0674] This invention is an interactive dictionary service that utilizes natural language processing (NLP), generative AI, and an emotion engine to support users' language learning. The system aims to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their devices, and is structured and functionally capable of recognizing the user's emotions and adjusting the content and tone of the response. The operation and functionality of each major component are described in detail below.

[0675] Server Operation

[0676] The server receives the request entered by the user on the device and analyzes the content using natural language processing (NLP) technology. NLP engines used include "SpaCy" and "NLTK."

[0677] Received user input is first tokenized to understand context and intent. An emotion engine then analyzes the input and recognizes the user's emotional state. The emotion engine used can be a platform like Affectiva or IBM Watson Tone Analyzer.

[0678] Based on the analysis results, the server accesses a database to retrieve data related to the relevant words and expressions. The database stores example sentences and explanations of their nuances. A database management system (DBMS) such as MySQL or PostgreSQL is used.

[0679] The acquired data is passed to a generation AI, which generates appropriate example sentences and their explanations. Models such as GPT-3 and BERT are used as the generation AI. The tone and content of the response are adjusted based on the analysis results of the emotion engine.

[0680] Finally, the generated response is formatted in a user-friendly format, made suitable for display, and sent to the terminal, where it is reconstructed in HTML or JSON format.

[0681] Device behavior

[0682] The terminal mainly serves to send input from the user to the server and receive and display responses from the server. For example, if a user types "Please tell me some example sentences for ambiguous," the request is sent to the server in real time.

[0683] When the response comes back from the server, the device analyzes it and displays it in a user-friendly format, including specific examples, explanations, and emotional tones. Frameworks such as "React" and "Vue.js" are used for the UI / UX design of the exhibit.

[0684] The device also provides input assistance and auto-complete functions to help users input information efficiently, making the learning experience smoother for users.

[0685] User Actions and Interactions

[0686] Users use their device to input a question about a word or phrase, such as "Can you give me an example of an ambiguous sentence?" The example sentences and explanations displayed can be used to learn, and if more information is needed, users can input additional questions on the same screen. Responses tailored to their emotions can improve comprehension.

[0687] If the user enters a subsequent question, a request is sent to the server again, and a response is generated in the same process, allowing the user to progress through the learning process interactively.

[0688] Specific examples

[0689] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[0690] 1. The device sends input to the server.

[0691] 2. The server parses the input and retrieves data related to "ambiguous" from the database.

[0692] 3. The emotion engine analyzes emotions from the user's input. For example, if a user types "Tell me some vague sentences," the emotion engine will recognize emotions such as doubt and confusion.

[0693] 4. The generative AI generates an example sentence, "The meaning of his statement was ambiguous," along with an explanation, including specific commentary based on the emotion recognition results.

[0694] 5. The server formats the generated response and sends it to the device.

[0695] 6. The device receives the response and displays it to the user, explained in an emotionally tailored tone.

[0696] Prompt Sentence Examples

[0697] An example prompt for this system:

[0698] 1. "What does ambiguous mean?"

[0699] 2. "Please give me some example sentences for ambiguous expressions in English."

[0700] 3. "Please explain how to use ambiguous with an example sentence."

[0701] This allows the user to study a language efficiently.

[0702] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0703] Step 1:

[0704] The user types a question or phrase into the terminal. For example, "Please tell me an example sentence for ambiguous." The input data is sent to the terminal as a prompt.

[0705] Step 2:

[0706] The terminal sends user input to the server. The terminal formats the received prompt and sends it to the server as an HTTP request. The input is text data, "Please tell me some example sentences for ambiguous," and is sent to the server as is.

[0707] Step 3:

[0708] The server receives user input. The server receives the prompt sent from the terminal and saves it for further processing. The input is text data included in the body of the HTTP request.

[0709] Step 4:

[0710] The server analyzes the input using an NLP engine. The server tokenizes the received text data and analyzes the context and intent. Specifically, it splits the input sentence into words and performs grammatical analysis. The input is the text data "Please tell me some example sentences for ambiguous," and the output is the keyword "ambiguous" and its context information.

[0711] Step 5:

[0712] The server uses an emotion engine to analyze the user's emotions. The server identifies the user's emotional state from the output of the NLP engine. Specifically, it performs emotion scoring of text data. The input is the analysis result of the NLP engine, and the output is emotional state information that the user is "confused."

[0713] Step 6:

[0714] The server accesses the database to retrieve relevant data. Based on the emotion and keyword, the server retrieves appropriate example sentences and explanations from the database. Specifically, it searches for related data using an SQL query. The input is the keyword "ambiguous" and emotion information, and the output is related example sentence data.

[0715] Step 7:

[0716] The server generates a response using generative AI. Based on the acquired data, the server generates appropriate example sentences and explanations for the user input. It also adjusts the tone and content of the response using the results of emotion analysis. Specifically, data is input into the generative AI model, which outputs a response. The input is example sentence data and emotion information acquired from the database, and the output is the generated example sentence and explanation.

[0717] Step 8:

[0718] The server formats the response and sends it to the terminal. The server formats the generated response in a format that is easy for the user to understand and sends the formatted data to the terminal. Specifically, it converts the data into HTML or JSON format. The input is the generated response data, and the output is the formatted data.

[0719] Step 9:

[0720] The terminal receives and displays the response from the server. The terminal receives the response sent from the server and displays it in a format that is easy for the user to understand. Specifically, it interprets the received data and displays it on the screen. The input is the formatted data sent from the server, and the output is the example sentence and explanation displayed on the screen.

[0721] Step 10:

[0722] The user enters an additional question. If the user needs more information, they enter the question again into the terminal. For example, they might enter "Tell me more example sentences." In this case, a prompt requesting further information is sent to the terminal again.

[0723] (Application example 2)

[0724] 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."

[0725] The objective of this invention is to provide a system that can provide interactive advertisements according to the user's emotional state. Conventional advertising systems can only generate a uniform response to user input, making it difficult to personalize the response to reflect the user's emotions and intentions. This results in a poor user experience and limited advertising effectiveness.

[0726] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for performing emotion analysis based on the results of the natural language processing, means for generating a response according to the user's emotion using the generative artificial intelligence, and means for formatting the generated response and sending it to the user. This makes it possible to generate personalized advertising copy that reflects the user's emotional state and intentions.

[0727] The "means for receiving input from the user" is a mechanism for receiving information input by the user through the user interface.

[0728] "Means for natural language processing" refers to technology for analyzing input text and understanding its grammar and meaning.

[0729] The "means for performing emotion analysis" is a technology for determining the psychological state of a user based on the sentences input by the user.

[0730] "Means for generating responses using generative artificial intelligence" refers to a mechanism that uses a machine learning model to create appropriate answers based on the analysis results.

[0731] The "means for formatting the generated response and sending it to the user" refers to a technique for arranging the generated response in an appropriate format and providing it to the user.

[0732] The "input assistance function or autocomplete function" is a function that assists the user in inputting information effectively, and is a technology that performs pre-reading and suggests candidates.

[0733] The "means for generating advertising copy" is a technology for creating appropriate advertising content based on the results of user sentiment analysis.

[0734] System Program Overview

[0735] A system embodying the present invention receives input from a user, performs natural language processing (NLP) and sentiment analysis, and uses generative AI to generate a response based on the user's sentiment, thereby providing personalized advertising copy based on the user's sentiment.

[0736] Detailed explanation of the process

[0737] 1. Receiving user input

[0738] The server receives information entered by the user on the device. This input is in natural language, for example, in the form of "I want a new smartphone."

[0739] 2. Performing natural language processing

[0740] The server then analyzes the received user input using NLP techniques, which include tokenizing the input and understanding its grammar, context, and intent. A suitable NLP library to use is "transformers."

[0741] 3. Performing sentiment analysis

[0742] The server performs sentiment analysis based on the results of NLP analysis. The emotion engine determines the psychological state of the input content and identifies whether the user is excited or confused. The model for sentiment analysis uses a library that provides "sentiment-analysis."

[0743] 4. Database Access

[0744] The server retrieves relevant advertising information from a database based on the analysis results, including corresponding product and service information based on the user's input.

[0745] 5. Generating the Response

[0746] The server uses a generative AI model to generate ad copy based on the acquired ad information and the user's emotional state. For example, if the user is excited, the server will provide ad copy in an exciting tone, and if the user is confused, the server will provide polite explanation. An example of a prompt sentence in this case is "Generate ad copy for a new smartphone."

[0747] 6. Response Format and Transmission

[0748] The server formats the generated response in a user-friendly format and sends it to the terminal in the appropriate format, which displays the received response to the user in real time.

[0749] Specific examples

[0750] For example, if a user types "I want a new phone," the system will do the following:

[0751] The server receives the user input and parses the input using the "transformers" library.

[0752] The emotion engine determines from the input sentence that the user is excited.

[0753] The server retrieves the latest smartphone information from the database.

[0754] The generative AI model generates an exciting ad copy that reads, "An exciting new smartphone! Boasting a revolutionary camera, a super-fast processor, and now at a special price of just ¥100,000!"

[0755] The server formats the generated copy and sends it to the device.

[0756] The terminal displays the advertisement copy to the user in real time.

[0757] In this way, the system of the present invention provides personalized advertising copy that takes user emotions into account, thereby achieving a more effective advertising experience.

[0758] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0759] Step 1:

[0760] The device receives information entered by the user. When the user enters "I want a new smartphone," the device sends the input data to the server. Input: A string of natural language characters containing the user's wishes and questions. Output: The input data sent to the server.

[0761] Step 2:

[0762] The server parses the received user input using natural language processing (NLP), specifically using the "transformers" library to tokenize the input sentence and understand grammar and context. Input: User's natural language input. Output: Parsed tokenized data and intent.

[0763] Step 3:

[0764] The server performs sentiment analysis based on the results of NLP analysis. It uses an emotion engine ("sentiment-analysis" model) to determine the user's emotional state. Input: NLP analysis results. Output: User's emotional state (e.g., excited, confused).

[0765] Step 4:

[0766] The server retrieves relevant advertising information from the database based on the results of the sentiment analysis. Specifically, if a user enters "smartphone," the server searches the database for the latest smartphone information and retrieves it. Input: User input and sentiment analysis results. Output: Related advertising information (e.g., product name, features, price).

[0767] Step 5:

[0768] The server generates ad copy that corresponds to the user's emotions based on the ad information obtained using the generative AI model. The generative AI model is given a prompt such as "Generate ad copy for a new smartphone." Input: Ad information and emotional state. Output: Personalized ad copy that corresponds to the user's emotions.

[0769] Step 6:

[0770] The server formats the generated ad copy into an easy-to-understand format and sends it to the device. Specifically, it converts it into a format that is easy to format, such as HTML or plain text. Input: Generated ad copy. Output: Formatted ad copy.

[0771] Step 7:

[0772] The terminal displays the formatted ad copy received from the server to the user. If the user is excited, the user will see the ad copy in an exciting tone, and if the user is confused, the user will see the ad copy in a polite tone. Input: Formatted ad copy. Output: Display of ad copy.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] [Third embodiment]

[0777] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0778] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0779] 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).

[0780] 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.

[0781] 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.

[0782] 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).

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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."

[0789] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[0790] System Overview

[0791] This system is an interactive dictionary service that uses natural language processing (NLP) and generative AI to support users' language learning. Its purpose is to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their devices. The operation and functionality of each major component are described in detail below.

[0792] Server Operation

[0793] 1. Receiving user input

[0794] The server receives requests entered by users into their terminals, such as "Please tell me some example sentences for ambiguous."

[0795] 2. Performing Natural Language Processing (NLP)

[0796] The server analyzes the received user input using natural language processing (NLP), and as part of the analysis, it tokenizes the input to understand its context and intent.

[0797] 3. Database Access

[0798] Based on the analysis results, the server accesses a database to retrieve data related to the relevant words and expressions, including example sentences and explanations of their nuances.

[0799] 4. Response generation using generative AI

[0800] The server passes the acquired data to the generation AI, which generates appropriate example sentences and explanations. For example, it generates "The meaning of his statement was ambiguous" as an example sentence of "ambiguous."

[0801] 5. Response Format

[0802] The server formats the generated response in a user-friendly format and sends it to the terminal.

[0803] Device behavior

[0804] 1. Submitting User Input

[0805] The device sends the information entered by the user to the server, and if the input is useful for learning, it immediately makes a request to the server.

[0806] 2. Receiving a response from the server

[0807] The device receives the response from the server and displays it to the user in an easy-to-understand format, often including concrete examples and explanations.

[0808] 3. Assistive typing and autocomplete

[0809] The device provides input assistance and auto-complete functions to help users input information efficiently, making the learning experience smoother for users.

[0810] User Actions and Interactions

[0811] 1. First time input

[0812] Users input words or phrases into their device for translation, example sentences, or nuanced understanding. For example, they might type, "Please tell me some example sentences for ambiguous."

[0813] 2. Use of the displayed results

[0814] Users can use the example sentences and explanations displayed to help them learn, and if they need more information, they can enter additional questions on the same screen.

[0815] 3. Follow-up questions and continued learning

[0816] If the user enters a subsequent question, a request is sent to the server again, and a response is generated in the same process, allowing the user to progress through the learning process interactively.

[0817] Specific examples

[0818] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[0819] The device sends input to the server.

[0820] The server parses the input and retrieves data related to "ambiguous" from the database.

[0821] The generative AI generates an example sentence, "The meaning of his statement was ambiguous," along with its explanation.

[0822] The server formats the generated response and sends it to the terminal.

[0823] The terminal receives the response and displays it to the user.

[0824] The above is an embodiment of the present invention, which allows the user to learn a language efficiently.

[0825] The processing flow will be explained below.

[0826] Step 1:

[0827] The user types into the terminal, "Please tell me some example sentences for ambiguous."

[0828] Step 2:

[0829] The terminal sends the user's input to the server. The terminal converts the input string into an HTTP request and sets the URL, header, and body of the request to send to the server.

[0830] Step 3:

[0831] The server receives a request from the user. The server receives the request sent from the terminal and extracts the content included in the request body.

[0832] Step 4:

[0833] The server performs natural language processing (NLP), tokenizing the received input and analyzing it for context and intent. Specifically, it segments words and phrases and analyzes them to determine their meaning.

[0834] Step 5:

[0835] The server accesses the database. Based on the analysis results, the server retrieves relevant data from the database. For example, it searches for example sentences and explanations of nuances related to "ambiguous."

[0836] Step 6:

[0837] The server generates a response using the generation AI. The server passes the information obtained from the database to the generation AI, which generates an appropriate example sentence and its explanation. For example, it generates the example sentence, "The meaning of his statement was ambiguous."

[0838] Step 7:

[0839] Server formats response: The server formats the generated response in a user-friendly format suitable for display.

[0840] Step 8:

[0841] The server sends the formatted response to the terminal. The server prepares the formatted response as an HTTP response and sends it to the terminal.

[0842] Step 9:

[0843] The terminal receives the response from the server, analyzes the response, and displays the content to the user.

[0844] Step 10:

[0845] The user can use the displayed results. The user can use the example sentences and explanations displayed to study, and if more information is needed, they can enter additional questions.

[0846] Example 1

[0847] 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."

[0848] Conventional language learning support systems have difficulty providing appropriate example sentences and explanations instantly for words and phrases entered by users. Furthermore, input support and auto-complete functions are inadequate, resulting in a clunky learning experience for users. Furthermore, responses to user requests are mechanical, failing to help users understand the meaning in a natural context.

[0849] 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.

[0850] In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for accessing a database and acquiring related information based on the results of the natural language processing, means for supplying the acquired information to a generative artificial intelligence model to generate a response, and means for formatting and sending the generated response to the user. This allows the server to instantly provide appropriate example sentences and explanations for words and phrases entered by the user, making the learning experience smoother and more efficient. It also enables understanding in a natural context, improving the user's learning effectiveness.

[0851] "User input" refers to the input of text or commands by a system user into a terminal.

[0852] "Natural language processing" refers to technology that enables computers to understand and analyze human language, and includes processes such as tokenization, grammar analysis, and entity extraction.

[0853] A "database" refers to a system for organizing and storing related information, including example sentences and explanations related to words and phrases.

[0854] A "generative artificial intelligence model" refers to an artificial intelligence that has algorithms for generating context-appropriate responses based on large amounts of data.

[0855] "Response formatting" refers to shaping the generated response into an appropriate format for display to the user in an easily understandable manner.

[0856] The "input support function" refers to a function that assists the user when making input, and includes functions such as suggesting candidates and spell checking.

[0857] "Autocomplete function" refers to a function that automatically completes text that a user has incompletely entered.

[0858] "Example sentence" refers to a specific sentence provided to demonstrate the usage of a word or phrase.

[0859] "Explanation" refers to a sentence that provides additional information about the meaning, grammar, and context of use of an example sentence.

[0860] MODE FOR CARRYING OUT THE INVENTION

[0861] The following describes in detail an embodiment of the present invention. This system is an interactive dictionary service that uses natural language processing (NLP) and generative AI to support users' language learning. Its purpose is to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their terminals.

[0862] System Overview

[0863] This system is primarily composed of a server and a terminal. The server receives input sent by the user, performs natural language processing, and then accesses a database to retrieve relevant information. The retrieved information is then fed into a generative AI model to generate an appropriate response, which is then sent to the user. The terminal sends the user's input to the server and displays the response received from the server to the user. It also provides input assistance and auto-complete functions.

[0864] Hardware and software used

[0865] Server: Used to receive input from users, perform natural language processing, access databases, and generate responses using generative AI models. The server can run on a common cloud service.

[0866] Terminal: A device used by a user, such as a PC, smartphone, or tablet. The terminal communicates with the server via a web browser or a dedicated application.

[0867] Database: Use a relational database management system (RDBMS) such as MySQL or PostgreSQL to manage and access data.

[0868] Natural Language Processing (NLP) libraries: Python's NLTK library and spaCy are used to tokenize input and analyze context.

[0869] Generative AI models: Generative AI models such as OpenAI's GPT-3 are used to generate natural-sounding examples and explanations.

[0870] Specific examples

[0871] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[0872] 1. User input: The user types "Please tell me an example sentence for ambiguous" into the terminal.

[0873] 2. Sending input: The device sends the input to the server.

[0874] 3. Natural Language Processing: The server receives the input and performs natural language processing using Python's NLTK library and spaCy. Specifically, it tokenizes the input, performs grammatical analysis, and identifies "ambiguous."

[0875] 4. Database access: Based on the analysis results, the server sends a query to a MySQL or PostgreSQL database to retrieve relevant example sentences and explanations.

[0876] 5. Response generation by generative AI: The server passes the acquired information to OpenAI's GPT-3, which generates appropriate example sentences and explanations for "ambiguous." For example, an example sentence such as "The meaning of his statement was ambiguous" is generated.

[0877] 6. Response formatting: The server formats the generated response in JSON format or similar and sends it to the device.

[0878] 7. Displaying the response: The terminal analyzes the response received from the server and displays it in a user-friendly format.

[0879] This process allows users to obtain appropriate example sentences and explanations in real time and advance their language learning.

[0880] Prompt Sentence Examples

[0881] The prompt uses natural questions such as "Can you give me an example of an ambiguous sentence?" By inputting such a prompt, the system can quickly provide the necessary information.

[0882] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0883] Step 1: Receiving User Input

[0884] Input: The user types "Please tell me some example sentences for ambiguous" into the terminal.

[0885] How it works: The device sends user input to the server as an HTTP request. It is sent in the form of an HTTP POST request, with the user input included in the request body.

[0886] Output: The server parses the received request and extracts the user input.

[0887] Step 2: Performing Natural Language Processing

[0888] Input: The user input that the server extracted in step 1.

[0889] How it works: The server uses Python's NLTK library and spaCy to tokenize the text and perform grammatical analysis. For example, "Please tell me some example sentences about ambiguous" is broken down into the tokens "ambiguous," "of," "example sentences," "o," and "teach me," and identifies "ambiguous."

[0890] Output: Parsed tokens and identified keywords (in this case, "ambiguous").

[0891] Step 3: Database Access

[0892] Input: The keyword the server identified in step 2.

[0893] How it works: The server sends a query to a database such as MySQL or PostgreSQL to retrieve example sentences and explanations related to "ambiguous." It uses SQL statements to search the database, executing a query to retrieve, for example, "example sentences" and "explanations."

[0894] Output: Example sentences retrieved from the database and their explanations.

[0895] Step 4: Generative AI generates a response

[0896] Input: The example sentence and explanation obtained by the server in step 3.

[0897] How it works: The server inputs the acquired data into a generative AI model (e.g., OpenAI's GPT-3) and sets it as a prompt. The prompt includes a request for example sentence generation. The generative AI model generates example sentences that are grammatically and content-appropriate based on the input information.

[0898] Output: A new example sentence generated by the generative AI model, e.g., "The meaning of his statement was ambiguous."

[0899] Step 5: Formatting the Response

[0900] Input: The example sentence generated by the server in step 4.

[0901] How it works: The server formats the generated example sentences in a user-friendly format, such as JSON or HTML, as needed.

[0902] Output: The formatted response data.

[0903] Step 6: Sending a response from the server to the device

[0904] Input: The response data formatted by the server in step 5.

[0905] Operation: The server sends the response data to the terminal as an HTTP response. The response is in JSON or HTML format.

[0906] Output: The response data sent to the device.

[0907] Step 7: View the response

[0908] Input: The response data received by the terminal in step 6.

[0909] What happens: The device parses the data it receives and displays it in a user-friendly format, for example rendering it into HTML for display in a web browser.

[0910] Output: Generated example sentences and their explanations displayed to the user.

[0911] (Application example 1)

[0912] 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."

[0913] Modern content distribution services lack the means to instantly provide users with relevant information about the text or content they are viewing. This makes it difficult for users to deepen their understanding of an unfamiliar word or phrase on the spot. Furthermore, existing language learning support systems are unable to quickly respond to users' real-time needs, resulting in reduced learning efficiency.

[0914] 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.

[0915] In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for generating a response using generative artificial intelligence based on the results of the natural language processing, and means for formatting the generated response and displaying content, thereby enabling real-time language learning support by instantly providing related information and explanations for the content the user is viewing.

[0916] The "means for receiving input from the user" is a function for receiving text or voice input by the user into the terminal.

[0917] "Means for natural language processing" refers to a function that uses technology to analyze received user input and understand its meaning and intent.

[0918] A "means for generating responses using generative artificial intelligence" is a function that uses an AI model to generate appropriate responses based on the results of natural language processing.

[0919] "Means for formatting the generated response and displaying the content" refers to a function for formatting the response generated by AI into a format that is easy for the user to understand and displaying it on the device.

[0920] The "input assistance function" is a function that provides predictive conversion, suggestion functions, etc. when a user inputs text, thereby assisting the user in inputting text.

[0921] An "autocomplete feature" is a feature that automatically completes partially typed words or phrases when a user is entering text.

[0922] Generating "example sentences and their explanations" means generating usage examples and their explanations for specific words or phrases and providing them to the user.

[0923] The following describes in detail the mode for carrying out the present invention. The system functions as a support tool for users in real-time language learning, and is intended to provide instant example sentences and explanations for unknown words and phrases, particularly in content distribution services.

[0924] System Overview

[0925] This system consists of a server, a device, and a user. Specifically, it works by receiving user input from a device such as a smartphone or head-mounted display and sending it to the server. The server uses natural language processing (NLP) and generative AI models to generate a response based on the user input and return it to the device.

[0926] Hardware and software used

[0927] Hardware

[0928] Smartphone

[0929] head-mounted display

[0930] software

[0931] Python

[0932] Transformers library (by Hugging Face)

[0933] Requests library (for HTTP requests)

[0934] Processing flow

[0935] 1. User Input

[0936] The user inputs a prompt sentence such as "Tell me an example sentence for ambiguous" into a smartphone or head-mounted display.

[0937] 2. Receiving Input

[0938] The terminal receives user input and sends it to the server.

[0939] 3. Natural Language Processing

[0940] The server analyzes the received user input using natural language processing to extract important words (in this case, "ambiguous"). The natural language processing model used is the Transformers library from Hugging Face.

[0941] 4. Database Access

[0942] Based on the analysis results, the server retrieves related data from the virtual database.

[0943] 5. AI-generated responses

[0944] Based on the acquired data, a generative AI model is used to generate appropriate example sentences and explanations.

[0945] 6. Response Formatting and Display

[0946] The generated response is formatted in a user-friendly format and sent to the terminal for display.

[0947] Examples of prompt statements

[0948] Below are some examples of prompt sentences.

[0949] Example: "What are some examples of ambiguous?"

[0950] In this way, by using the present invention, users can progress with their language learning in real time while browsing content, which is expected to improve the efficiency of users' learning.

[0951] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0952] Step 1:

[0953] The user types "Please tell me an example sentence of ambiguous" into a smartphone or head-mounted display. The prompt "Please tell me an example sentence of ambiguous" is received as input. This becomes the input for the next step.

[0954] Step 2:

[0955] The terminal receives user input and sends it to the server as a string. In this step, the entered prompt sentence is sent to the server as an HTTP request. As a specific operation, data is sent using an HTTP POST request. The user input is passed to the server as output.

[0956] Step 3:

[0957] The server receives user input and analyzes it using natural language processing (NLP). The server uses Hugging Face's Transformers library to tokenize the input text and understand its context and intent. The data processing performed in this step is tokenization and context analysis. As an output, important words ("ambiguous") are extracted.

[0958] Step 4:

[0959] Based on the analysis results, the server accesses the virtual database to retrieve related data. The data calculation performed here is a database query corresponding to the extracted word. The server retrieves example sentences and explanations related to "ambiguous" from the virtual database. As an output, data related to the word is obtained.

[0960] Step 5:

[0961] The server passes the acquired data to the generative AI model to generate appropriate example sentences and explanations. Specifically, the data is passed as input to the generative AI model, and the generated text output is obtained. In this step, the generative AI model generates the example sentence "The meaning of his statement was ambiguous" and its explanation. The generated example sentence and explanation are obtained as output.

[0962] Step 6:

[0963] The server formats the generated response in a user-friendly format and sends it to the terminal. The specific operation here is to convert the generated text into an appropriate format and send it again to the terminal as an HTTP response. As output, the formatted response is passed to the terminal.

[0964] Step 7:

[0965] The terminal receives the response from the server and displays it in a format that is easy for the user to understand. As input, it receives the response from the server. As a specific operation, it displays the received data on the screen. As output, the example sentence and its explanation are displayed on the user's screen.

[0966] Through the above processing steps, the system allows users to receive language learning support in real time while browsing content.

[0967] 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.

[0968] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[0969] System Overview

[0970] This system is an interactive dictionary service that utilizes natural language processing (NLP), generative AI, and an emotion engine to support users' language learning. It aims to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their devices, and can also recognize the user's emotions and adjust the content and tone of the response. The operation and functionality of each major component are described in detail below.

[0971] Server Operation

[0972] 1. Receiving user input

[0973] The server receives requests entered by users into their terminals, such as "Please tell me some example sentences for ambiguous."

[0974] 2. Performing Natural Language Processing (NLP)

[0975] The server analyzes the received user input using natural language processing (NLP), and as part of the analysis, it tokenizes the input to understand its context and intent.

[0976] 3. Emotion analysis using an emotion engine

[0977] The server analyzes the user's input to determine their emotions. The emotion engine analyzes the input and identifies the user's emotional state.

[0978] 4. Database Access

[0979] Based on the analysis results, the server accesses a database to retrieve data related to the relevant words and expressions, including example sentences and explanations of their nuances.

[0980] 5. Response generation using generative AI

[0981] The server passes the acquired data to the generation AI, which generates appropriate example sentences and their explanations. It can also adjust the tone and content of the response based on the analysis results of the emotion engine.

[0982] 6. Response Format

[0983] The server formats the generated response in a user-friendly format suitable for display.

[0984] Device behavior

[0985] 1. Submitting User Input

[0986] The device sends the information entered by the user to the server, and if the input is useful for learning, it immediately makes a request to the server.

[0987] 2. Receiving a response from the server

[0988] The device receives the response from the server and displays it to the user in an easy-to-understand format, often including concrete examples, explanations, and emotional tones.

[0989] 3. Assistive typing and autocomplete

[0990] The device provides input assistance and auto-complete functions to help users input information efficiently, making the learning experience smoother for users.

[0991] User Actions and Interactions

[0992] 1. First time input

[0993] Users input words or phrases into their device for translation, example sentences, or nuanced understanding. For example, they might type, "Please tell me some example sentences for ambiguous."

[0994] 2. Use of the displayed results

[0995] Users can use the example sentences and explanations displayed to help them learn. If they need more information, they can enter additional questions on the same screen. Responses tailored to the user's emotions also help them understand more easily.

[0996] 3. Follow-up questions and continued learning

[0997] If the user enters a subsequent question, a request is sent to the server again, and a response is generated in the same process, allowing the user to progress through the learning process interactively.

[0998] Specific examples

[0999] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[1000] The device sends input to the server.

[1001] The server parses the input and retrieves data related to "ambiguous" from the database.

[1002] The emotion engine analyzes emotions from user input. For example, if a user types "Tell me some vague sentences," the emotion engine will recognize emotions like doubt and confusion.

[1003] The generative AI generates the example sentence "The meaning of his statement was ambiguous" and its explanation, and includes a specific commentary based on the emotion recognition results.

[1004] The server formats the generated response and sends it to the terminal.

[1005] The device receives the response and displays it to the user, explained in an emotionally tailored tone of voice.

[1006] The above is an embodiment of the present invention, which allows the user to learn a language efficiently.

[1007] The processing flow will be explained below.

[1008] Step 1:

[1009] The user types into the terminal, "Please tell me some example sentences for ambiguous."

[1010] Step 2:

[1011] The terminal sends the user's input to the server. The terminal converts the input string into an HTTP request and sends it to the server.

[1012] Step 3:

[1013] The server receives a request from the user. The server receives the request sent from the terminal and extracts the input content included in the request body.

[1014] Step 4:

[1015] The server performs natural language processing (NLP), tokenizing the incoming input and analyzing its context and intent. For example, it identifies the word "ambiguous" and analyzes its usage.

[1016] Step 5:

[1017] The server analyzes the user's emotions using an emotion engine, extracts emotions from the user's input sentences, and recognizes their emotional state, such as "confusion" or "doubt."

[1018] Step 6:

[1019] The server accesses the database and retrieves data related to the word identified in the input sentence from the database. For example, it searches for example sentences and explanations of nuances related to "ambiguous."

[1020] Step 7:

[1021] The server uses the generation AI to generate a response. The server passes the acquired data to the generation AI, which generates appropriate example sentences and their explanations. The server also adjusts the tone and content of the response based on the analysis results of the emotion engine.

[1022] Step 8:

[1023] The server formats the response. The server formats the generated response in a user-friendly format suitable for display, such as a response containing the example sentence "The meaning of his statement was ambiguous" and an explanation of it.

[1024] Step 9:

[1025] The server sends the formatted response to the terminal. The server prepares the formatted response as an HTTP response and sends it to the terminal.

[1026] Step 10:

[1027] The device receives the response from the server. The device analyzes the response and displays it to the user. For example, if the user expresses confusion, the response may include further explanation or a gentler tone.

[1028] Step 11:

[1029] The user can use the displayed results. The user can use the example sentences and explanations displayed to study, and if more information is needed, they can enter additional questions.

[1030] Example 2

[1031] 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."

[1032] Conventional language learning support systems simply provide example sentences and explanations in response to user input, but are unable to respond in a way that takes into account the user's emotional state. This means that when a user is confused or has questions, the system is unable to respond in an appropriate tone, resulting in insufficient learning effectiveness.

[1033] 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.

[1034] In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for analyzing emotions based on the results of the natural language processing, means for retrieving appropriate data from a database based on the analyzed emotional information, means for generating a response using the retrieved data and the analyzed emotional information with a generative artificial intelligence, and means for formatting the generated response and sending it to the user. This makes it possible to generate a response that corresponds to the emotional state of the user, thereby achieving more effective language learning support.

[1035] "User" refers to an individual who uses this system to study a language.

[1036] "Input" refers to language-related questions or phrases that a user sends to a terminal.

[1037] "Server" refers to a central processing system that receives user input and performs various processes.

[1038] "Natural language processing" refers to the technology of analyzing user input and understanding the context and intent.

[1039] An "emotion engine" refers to a technology that analyzes emotions from user input and identifies that emotional state.

[1040] A "database" refers to a collection of information that stores and makes accessible data relating to words and expressions.

[1041] "Generative artificial intelligence" refers to AI technology that generates appropriate responses based on acquired data.

[1042] A "response" refers to a reply that includes example sentences and explanations generated based on the user's input.

[1043] "Formatting" refers to the process of preparing the generated response in a form that is easy for the user to understand.

[1044] "Terminal" refers to a device (such as a personal computer or smartphone) that a user uses to make input.

[1045] The "input support function" refers to a function for assisting the user in input.

[1046] The "autocomplete function" refers to a function that automatically displays candidates while the user is typing and completes the input.

[1047] MODE FOR CARRYING OUT THE INVENTION

[1048] This invention is an interactive dictionary service that utilizes natural language processing (NLP), generative AI, and an emotion engine to support users' language learning. The system aims to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their devices, and is structured and functionally capable of recognizing the user's emotions and adjusting the content and tone of the response. The operation and functionality of each major component are described in detail below.

[1049] Server Operation

[1050] The server receives the request entered by the user on the device and analyzes the content using natural language processing (NLP) technology. NLP engines used include "SpaCy" and "NLTK."

[1051] Received user input is first tokenized to understand context and intent. An emotion engine then analyzes the input and recognizes the user's emotional state. The emotion engine used can be a platform like Affectiva or IBM Watson Tone Analyzer.

[1052] Based on the analysis results, the server accesses a database to retrieve data related to the relevant words and expressions. The database stores example sentences and explanations of their nuances. A database management system (DBMS) such as MySQL or PostgreSQL is used.

[1053] The acquired data is passed to a generation AI, which generates appropriate example sentences and their explanations. Models such as GPT-3 and BERT are used as the generation AI. The tone and content of the response are adjusted based on the analysis results of the emotion engine.

[1054] Finally, the generated response is formatted in a user-friendly format, made suitable for display, and sent to the terminal, where it is reconstructed in HTML or JSON format.

[1055] Device behavior

[1056] The terminal mainly serves to send input from the user to the server and receive and display responses from the server. For example, if a user types "Please tell me some example sentences for ambiguous," the request is sent to the server in real time.

[1057] When the response comes back from the server, the device analyzes it and displays it in a user-friendly format, including specific examples, explanations, and emotional tones. Frameworks such as "React" and "Vue.js" are used for the UI / UX design of the exhibit.

[1058] The device also provides input assistance and auto-complete functions to help users input information efficiently, making the learning experience smoother for users.

[1059] User Actions and Interactions

[1060] Users use their device to input a question about a word or phrase, such as "Can you give me an example of an ambiguous sentence?" The example sentences and explanations displayed can be used to learn, and if more information is needed, users can input additional questions on the same screen. Responses tailored to their emotions can improve comprehension.

[1061] If the user enters a subsequent question, a request is sent to the server again, and a response is generated in the same process, allowing the user to progress through the learning process interactively.

[1062] Specific examples

[1063] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[1064] 1. The device sends input to the server.

[1065] 2. The server parses the input and retrieves data related to "ambiguous" from the database.

[1066] 3. The emotion engine analyzes emotions from the user's input. For example, if a user types "Tell me some vague sentences," the emotion engine will recognize emotions such as doubt and confusion.

[1067] 4. The generative AI generates an example sentence, "The meaning of his statement was ambiguous," along with an explanation, including specific commentary based on the emotion recognition results.

[1068] 5. The server formats the generated response and sends it to the device.

[1069] 6. The device receives the response and displays it to the user, explained in an emotionally tailored tone.

[1070] Prompt Sentence Examples

[1071] An example prompt for this system:

[1072] 1. "What does ambiguous mean?"

[1073] 2. "Please give me some example sentences for ambiguous expressions in English."

[1074] 3. "Please explain how to use ambiguous with an example sentence."

[1075] This allows the user to study a language efficiently.

[1076] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1077] Step 1:

[1078] The user types a question or phrase into the terminal. For example, "Please tell me an example sentence for ambiguous." The input data is sent to the terminal as a prompt.

[1079] Step 2:

[1080] The terminal sends user input to the server. The terminal formats the received prompt and sends it to the server as an HTTP request. The input is text data, "Please tell me some example sentences for ambiguous," and is sent to the server as is.

[1081] Step 3:

[1082] The server receives user input. The server receives the prompt sent from the terminal and saves it for further processing. The input is text data included in the body of the HTTP request.

[1083] Step 4:

[1084] The server analyzes the input using an NLP engine. The server tokenizes the received text data and analyzes the context and intent. Specifically, it splits the input sentence into words and performs grammatical analysis. The input is the text data "Please tell me some example sentences for ambiguous," and the output is the keyword "ambiguous" and its context information.

[1085] Step 5:

[1086] The server uses an emotion engine to analyze the user's emotions. The server identifies the user's emotional state from the output of the NLP engine. Specifically, it performs emotion scoring of text data. The input is the analysis result of the NLP engine, and the output is emotional state information that the user is "confused."

[1087] Step 6:

[1088] The server accesses the database to retrieve relevant data. Based on the emotion and keyword, the server retrieves appropriate example sentences and explanations from the database. Specifically, it searches for related data using an SQL query. The input is the keyword "ambiguous" and emotion information, and the output is related example sentence data.

[1089] Step 7:

[1090] The server generates a response using generative AI. Based on the acquired data, the server generates appropriate example sentences and explanations for the user input. It also adjusts the tone and content of the response using the results of emotion analysis. Specifically, data is input into the generative AI model, which outputs a response. The input is example sentence data and emotion information acquired from the database, and the output is the generated example sentence and explanation.

[1091] Step 8:

[1092] The server formats the response and sends it to the terminal. The server formats the generated response in a format that is easy for the user to understand and sends the formatted data to the terminal. Specifically, it converts the data into HTML or JSON format. The input is the generated response data, and the output is the formatted data.

[1093] Step 9:

[1094] The terminal receives and displays the response from the server. The terminal receives the response sent from the server and displays it in a format that is easy for the user to understand. Specifically, it interprets the received data and displays it on the screen. The input is the formatted data sent from the server, and the output is the example sentence and explanation displayed on the screen.

[1095] Step 10:

[1096] The user enters an additional question. If the user needs more information, they enter the question again into the terminal. For example, they might enter "Tell me more example sentences." In this case, a prompt requesting further information is sent to the terminal again.

[1097] (Application example 2)

[1098] 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."

[1099] The objective of this invention is to provide a system that can provide interactive advertisements according to the user's emotional state. Conventional advertising systems can only generate a uniform response to user input, making it difficult to personalize the response to reflect the user's emotions and intentions. This results in a poor user experience and limited advertising effectiveness.

[1100] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for performing emotion analysis based on the results of the natural language processing, means for generating a response according to the user's emotion using the generative artificial intelligence, and means for formatting the generated response and sending it to the user. This makes it possible to generate personalized advertising copy that reflects the user's emotional state and intentions.

[1101] The "means for receiving input from the user" is a mechanism for receiving information input by the user through the user interface.

[1102] "Means for natural language processing" refers to technology for analyzing input text and understanding its grammar and meaning.

[1103] The "means for performing emotion analysis" is a technology for determining the psychological state of a user based on the sentences input by the user.

[1104] "Means for generating responses using generative artificial intelligence" refers to a mechanism that uses a machine learning model to create appropriate answers based on the analysis results.

[1105] The "means for formatting the generated response and sending it to the user" refers to a technique for arranging the generated response in an appropriate format and providing it to the user.

[1106] The "input assistance function or autocomplete function" is a function that assists the user in inputting information effectively, and is a technology that performs pre-reading and suggests candidates.

[1107] The "means for generating advertising copy" is a technology for creating appropriate advertising content based on the results of user sentiment analysis.

[1108] System Program Overview

[1109] A system embodying the present invention receives input from a user, performs natural language processing (NLP) and sentiment analysis, and uses generative AI to generate a response based on the user's sentiment, thereby providing personalized advertising copy based on the user's sentiment.

[1110] Detailed explanation of the process

[1111] 1. Receiving user input

[1112] The server receives information entered by the user on the device. This input is in natural language, for example, in the form of "I want a new smartphone."

[1113] 2. Performing natural language processing

[1114] The server then analyzes the received user input using NLP techniques, which include tokenizing the input and understanding its grammar, context, and intent. A suitable NLP library to use is "transformers."

[1115] 3. Performing sentiment analysis

[1116] The server performs sentiment analysis based on the results of NLP analysis. The emotion engine determines the psychological state of the input content and identifies whether the user is excited or confused. The model for sentiment analysis uses a library that provides "sentiment-analysis."

[1117] 4. Database Access

[1118] The server retrieves relevant advertising information from a database based on the analysis results, including corresponding product and service information based on the user's input.

[1119] 5. Generating the Response

[1120] The server uses a generative AI model to generate ad copy based on the acquired ad information and the user's emotional state. For example, if the user is excited, the server will provide ad copy in an exciting tone, and if the user is confused, the server will provide polite explanation. An example of a prompt sentence in this case is "Generate ad copy for a new smartphone."

[1121] 6. Response Format and Transmission

[1122] The server formats the generated response in a user-friendly format and sends it to the terminal in the appropriate format, which displays the received response to the user in real time.

[1123] Specific examples

[1124] For example, if a user types "I want a new phone," the system will do the following:

[1125] The server receives the user input and parses the input using the "transformers" library.

[1126] The emotion engine determines from the input sentence that the user is excited.

[1127] The server retrieves the latest smartphone information from the database.

[1128] The generative AI model generates an exciting ad copy that reads, "An exciting new smartphone! Boasting a revolutionary camera, a super-fast processor, and now at a special price of just ¥100,000!"

[1129] The server formats the generated copy and sends it to the device.

[1130] The terminal displays the advertisement copy to the user in real time.

[1131] In this way, the system of the present invention provides personalized advertising copy that takes user emotions into account, thereby achieving a more effective advertising experience.

[1132] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1133] Step 1:

[1134] The device receives information entered by the user. When the user enters "I want a new smartphone," the device sends the input data to the server. Input: A string of natural language characters containing the user's wishes and questions. Output: The input data sent to the server.

[1135] Step 2:

[1136] The server parses the received user input using natural language processing (NLP), specifically using the "transformers" library to tokenize the input sentence and understand grammar and context. Input: User's natural language input. Output: Parsed tokenized data and intent.

[1137] Step 3:

[1138] The server performs sentiment analysis based on the results of NLP analysis. It uses an emotion engine ("sentiment-analysis" model) to determine the user's emotional state. Input: NLP analysis results. Output: User's emotional state (e.g., excited, confused).

[1139] Step 4:

[1140] The server retrieves relevant advertising information from the database based on the results of the sentiment analysis. Specifically, if a user enters "smartphone," the server searches the database for the latest smartphone information and retrieves it. Input: User input and sentiment analysis results. Output: Related advertising information (e.g., product name, features, price).

[1141] Step 5:

[1142] The server generates ad copy that corresponds to the user's emotions based on the ad information obtained using the generative AI model. The generative AI model is given a prompt such as "Generate ad copy for a new smartphone." Input: Ad information and emotional state. Output: Personalized ad copy that corresponds to the user's emotions.

[1143] Step 6:

[1144] The server formats the generated ad copy into an easy-to-understand format and sends it to the device. Specifically, it converts it into a format that is easy to format, such as HTML or plain text. Input: Generated ad copy. Output: Formatted ad copy.

[1145] Step 7:

[1146] The terminal displays the formatted ad copy received from the server to the user. If the user is excited, the user will see the ad copy in an exciting tone, and if the user is confused, the user will see the ad copy in a polite tone. Input: Formatted ad copy. Output: Display of ad copy.

[1147] 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.

[1148] 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.

[1149] 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.

[1150] [Fourth embodiment]

[1151] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1152] 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.

[1153] 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).

[1154] 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.

[1155] 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.

[1156] 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).

[1157] 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.

[1158] 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.

[1159] 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.

[1160] 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.

[1161] 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.

[1162] 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.

[1163] 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."

[1164] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[1165] System Overview

[1166] This system is an interactive dictionary service that uses natural language processing (NLP) and generative AI to support users' language learning. Its purpose is to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their devices. The operation and functionality of each major component are described in detail below.

[1167] Server Operation

[1168] 1. Receiving user input

[1169] The server receives requests entered by users into their terminals, such as "Please tell me some example sentences for ambiguous."

[1170] 2. Performing Natural Language Processing (NLP)

[1171] The server analyzes the received user input using natural language processing (NLP), and as part of the analysis, it tokenizes the input to understand its context and intent.

[1172] 3. Database Access

[1173] Based on the analysis results, the server accesses a database to retrieve data related to the relevant words and expressions, including example sentences and explanations of their nuances.

[1174] 4. Response generation using generative AI

[1175] The server passes the acquired data to the generation AI, which generates appropriate example sentences and explanations. For example, it generates "The meaning of his statement was ambiguous" as an example sentence of "ambiguous."

[1176] 5. Response Format

[1177] The server formats the generated response in a user-friendly format and sends it to the terminal.

[1178] Device behavior

[1179] 1. Submitting User Input

[1180] The device sends the information entered by the user to the server, and if the input is useful for learning, it immediately makes a request to the server.

[1181] 2. Receiving a response from the server

[1182] The device receives the response from the server and displays it to the user in an easy-to-understand format, often including concrete examples and explanations.

[1183] 3. Assistive typing and autocomplete

[1184] The device provides input assistance and auto-complete functions to help users input information efficiently, making the learning experience smoother for users.

[1185] User Actions and Interactions

[1186] 1. First time input

[1187] Users input words or phrases into their device for translation, example sentences, or nuanced understanding. For example, they might type, "Please tell me some example sentences for ambiguous."

[1188] 2. Use of the displayed results

[1189] Users can use the example sentences and explanations displayed to help them learn, and if they need more information, they can enter additional questions on the same screen.

[1190] 3. Follow-up questions and continued learning

[1191] If the user enters a subsequent question, a request is sent to the server again, and a response is generated in the same process, allowing the user to progress through the learning process interactively.

[1192] Specific examples

[1193] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[1194] The device sends input to the server.

[1195] The server parses the input and retrieves data related to "ambiguous" from the database.

[1196] The generative AI generates an example sentence, "The meaning of his statement was ambiguous," along with its explanation.

[1197] The server formats the generated response and sends it to the terminal.

[1198] The terminal receives the response and displays it to the user.

[1199] The above is an embodiment of the present invention, which allows the user to learn a language efficiently.

[1200] The processing flow will be explained below.

[1201] Step 1:

[1202] The user types into the terminal, "Please tell me some example sentences for ambiguous."

[1203] Step 2:

[1204] The terminal sends the user's input to the server. The terminal converts the input string into an HTTP request and sets the URL, header, and body of the request to send to the server.

[1205] Step 3:

[1206] The server receives a request from the user. The server receives the request sent from the terminal and extracts the content included in the request body.

[1207] Step 4:

[1208] The server performs natural language processing (NLP), tokenizing the received input and analyzing it for context and intent. Specifically, it segments words and phrases and analyzes them to determine their meaning.

[1209] Step 5:

[1210] The server accesses the database. Based on the analysis results, the server retrieves relevant data from the database. For example, it searches for example sentences and explanations of nuances related to "ambiguous."

[1211] Step 6:

[1212] The server generates a response using the generation AI. The server passes the information obtained from the database to the generation AI, which generates an appropriate example sentence and its explanation. For example, it generates the example sentence, "The meaning of his statement was ambiguous."

[1213] Step 7:

[1214] Server formats response: The server formats the generated response in a user-friendly format suitable for display.

[1215] Step 8:

[1216] The server sends the formatted response to the terminal. The server prepares the formatted response as an HTTP response and sends it to the terminal.

[1217] Step 9:

[1218] The terminal receives the response from the server, analyzes the response, and displays the content to the user.

[1219] Step 10:

[1220] The user can use the displayed results. The user can use the example sentences and explanations displayed to study, and if more information is needed, they can enter additional questions.

[1221] Example 1

[1222] 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."

[1223] Conventional language learning support systems have difficulty providing appropriate example sentences and explanations instantly for words and phrases entered by users. Furthermore, input support and auto-complete functions are inadequate, resulting in a clunky learning experience for users. Furthermore, responses to user requests are mechanical, failing to help users understand the meaning in a natural context.

[1224] 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.

[1225] In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for accessing a database and acquiring related information based on the results of the natural language processing, means for supplying the acquired information to a generative artificial intelligence model to generate a response, and means for formatting and sending the generated response to the user. This allows the server to instantly provide appropriate example sentences and explanations for words and phrases entered by the user, making the learning experience smoother and more efficient. It also enables understanding in a natural context, improving the user's learning effectiveness.

[1226] "User input" refers to the input of text or commands by a system user into a terminal.

[1227] "Natural language processing" refers to technology that enables computers to understand and analyze human language, and includes processes such as tokenization, grammar analysis, and entity extraction.

[1228] A "database" refers to a system for organizing and storing related information, including example sentences and explanations related to words and phrases.

[1229] A "generative artificial intelligence model" refers to an artificial intelligence that has algorithms for generating context-appropriate responses based on large amounts of data.

[1230] "Response formatting" refers to shaping the generated response into an appropriate format for display to the user in an easily understandable manner.

[1231] The "input support function" refers to a function that assists the user when making input, and includes functions such as suggesting candidates and spell checking.

[1232] "Autocomplete function" refers to a function that automatically completes text that a user has incompletely entered.

[1233] "Example sentence" refers to a specific sentence provided to demonstrate the usage of a word or phrase.

[1234] "Explanation" refers to a sentence that provides additional information about the meaning, grammar, and context of use of an example sentence.

[1235] MODE FOR CARRYING OUT THE INVENTION

[1236] The following describes in detail an embodiment of the present invention. This system is an interactive dictionary service that uses natural language processing (NLP) and generative AI to support users' language learning. Its purpose is to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their terminals.

[1237] System Overview

[1238] This system is primarily composed of a server and a terminal. The server receives input sent by the user, performs natural language processing, and then accesses a database to retrieve relevant information. The retrieved information is then fed into a generative AI model to generate an appropriate response, which is then sent to the user. The terminal sends the user's input to the server and displays the response received from the server to the user. It also provides input assistance and auto-complete functions.

[1239] Hardware and software used

[1240] Server: Used to receive input from users, perform natural language processing, access databases, and generate responses using generative AI models. The server can run on a common cloud service.

[1241] Terminal: A device used by a user, such as a PC, smartphone, or tablet. The terminal communicates with the server via a web browser or a dedicated application.

[1242] Database: Use a relational database management system (RDBMS) such as MySQL or PostgreSQL to manage and access data.

[1243] Natural Language Processing (NLP) libraries: Python's NLTK library and spaCy are used to tokenize input and analyze context.

[1244] Generative AI models: Generative AI models such as OpenAI's GPT-3 are used to generate natural-sounding examples and explanations.

[1245] Specific examples

[1246] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[1247] 1. User input: The user types "Please tell me an example sentence for ambiguous" into the terminal.

[1248] 2. Sending input: The device sends the input to the server.

[1249] 3. Natural Language Processing: The server receives the input and performs natural language processing using Python's NLTK library and spaCy. Specifically, it tokenizes the input, performs grammatical analysis, and identifies "ambiguous."

[1250] 4. Database access: Based on the analysis results, the server sends a query to a MySQL or PostgreSQL database to retrieve relevant example sentences and explanations.

[1251] 5. Response generation by generative AI: The server passes the acquired information to OpenAI's GPT-3, which generates appropriate example sentences and explanations for "ambiguous." For example, an example sentence such as "The meaning of his statement was ambiguous" is generated.

[1252] 6. Response formatting: The server formats the generated response in JSON format or similar and sends it to the device.

[1253] 7. Displaying the response: The terminal analyzes the response received from the server and displays it in a user-friendly format.

[1254] This process allows users to obtain appropriate example sentences and explanations in real time and advance their language learning.

[1255] Prompt Sentence Examples

[1256] The prompt uses natural questions such as "Can you give me an example of an ambiguous sentence?" By inputting such a prompt, the system can quickly provide the necessary information.

[1257] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1258] Step 1: Receiving User Input

[1259] Input: The user types "Please tell me some example sentences for ambiguous" into the terminal.

[1260] How it works: The device sends user input to the server as an HTTP request. It is sent in the form of an HTTP POST request, with the user input included in the request body.

[1261] Output: The server parses the received request and extracts the user input.

[1262] Step 2: Performing Natural Language Processing

[1263] Input: The user input that the server extracted in step 1.

[1264] How it works: The server uses Python's NLTK library and spaCy to tokenize the text and perform grammatical analysis. For example, "Please tell me some example sentences about ambiguous" is broken down into the tokens "ambiguous," "of," "example sentences," "o," and "teach me," and identifies "ambiguous."

[1265] Output: Parsed tokens and identified keywords (in this case, "ambiguous").

[1266] Step 3: Database Access

[1267] Input: The keyword the server identified in step 2.

[1268] How it works: The server sends a query to a database such as MySQL or PostgreSQL to retrieve example sentences and explanations related to "ambiguous." It uses SQL statements to search the database, executing a query to retrieve, for example, "example sentences" and "explanations."

[1269] Output: Example sentences retrieved from the database and their explanations.

[1270] Step 4: Generative AI generates a response

[1271] Input: The example sentence and explanation obtained by the server in step 3.

[1272] How it works: The server inputs the acquired data into a generative AI model (e.g., OpenAI's GPT-3) and sets it as a prompt. The prompt includes a request for example sentence generation. The generative AI model generates example sentences that are grammatically and content-appropriate based on the input information.

[1273] Output: A new example sentence generated by the generative AI model, e.g., "The meaning of his statement was ambiguous."

[1274] Step 5: Formatting the Response

[1275] Input: The example sentence generated by the server in step 4.

[1276] How it works: The server formats the generated example sentences in a user-friendly format, such as JSON or HTML, as needed.

[1277] Output: The formatted response data.

[1278] Step 6: Sending a response from the server to the device

[1279] Input: The response data formatted by the server in step 5.

[1280] Operation: The server sends the response data to the terminal as an HTTP response. The response is in JSON or HTML format.

[1281] Output: The response data sent to the device.

[1282] Step 7: View the response

[1283] Input: The response data received by the terminal in step 6.

[1284] What happens: The device parses the data it receives and displays it in a user-friendly format, for example rendering it into HTML for display in a web browser.

[1285] Output: Generated example sentences and their explanations displayed to the user.

[1286] (Application example 1)

[1287] 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."

[1288] Modern content distribution services lack the means to instantly provide users with relevant information about the text or content they are viewing. This makes it difficult for users to deepen their understanding of an unfamiliar word or phrase on the spot. Furthermore, existing language learning support systems are unable to quickly respond to users' real-time needs, resulting in reduced learning efficiency.

[1289] 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.

[1290] In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for generating a response using generative artificial intelligence based on the results of the natural language processing, and means for formatting the generated response and displaying content, thereby enabling real-time language learning support by instantly providing related information and explanations for the content the user is viewing.

[1291] The "means for receiving input from the user" is a function for receiving text or voice input by the user into the terminal.

[1292] "Means for natural language processing" refers to a function that uses technology to analyze received user input and understand its meaning and intent.

[1293] A "means for generating responses using generative artificial intelligence" is a function that uses an AI model to generate appropriate responses based on the results of natural language processing.

[1294] "Means for formatting the generated response and displaying the content" refers to a function for formatting the response generated by AI into a format that is easy for the user to understand and displaying it on the device.

[1295] The "input assistance function" is a function that provides predictive conversion, suggestion functions, etc. when a user inputs text, thereby assisting the user in inputting text.

[1296] An "autocomplete feature" is a feature that automatically completes partially typed words or phrases when a user is entering text.

[1297] Generating "example sentences and their explanations" means generating usage examples and their explanations for specific words or phrases and providing them to the user.

[1298] The following describes in detail the mode for carrying out the present invention. The system functions as a support tool for users in real-time language learning, and is intended to provide instant example sentences and explanations for unknown words and phrases, particularly in content distribution services.

[1299] System Overview

[1300] This system consists of a server, a device, and a user. Specifically, it works by receiving user input from a device such as a smartphone or head-mounted display and sending it to the server. The server uses natural language processing (NLP) and generative AI models to generate a response based on the user input and return it to the device.

[1301] Hardware and software used

[1302] Hardware

[1303] Smartphone

[1304] head-mounted display

[1305] software

[1306] Python

[1307] Transformers library (by Hugging Face)

[1308] Requests library (for HTTP requests)

[1309] Processing flow

[1310] 1. User Input

[1311] The user inputs a prompt sentence such as "Tell me an example sentence for ambiguous" into a smartphone or head-mounted display.

[1312] 2. Receiving Input

[1313] The terminal receives user input and sends it to the server.

[1314] 3. Natural Language Processing

[1315] The server analyzes the received user input using natural language processing to extract important words (in this case, "ambiguous"). The natural language processing model used is the Transformers library from Hugging Face.

[1316] 4. Database Access

[1317] Based on the analysis results, the server retrieves related data from the virtual database.

[1318] 5. AI-generated responses

[1319] Based on the acquired data, a generative AI model is used to generate appropriate example sentences and explanations.

[1320] 6. Response Formatting and Display

[1321] The generated response is formatted in a user-friendly format and sent to the terminal for display.

[1322] Examples of prompt statements

[1323] Below are some examples of prompt sentences.

[1324] Example: "What are some examples of ambiguous?"

[1325] In this way, by using the present invention, users can progress with their language learning in real time while browsing content, which is expected to improve the efficiency of users' learning.

[1326] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1327] Step 1:

[1328] The user types "Please tell me an example sentence of ambiguous" into a smartphone or head-mounted display. The prompt "Please tell me an example sentence of ambiguous" is received as input. This becomes the input for the next step.

[1329] Step 2:

[1330] The terminal receives user input and sends it to the server as a string. In this step, the entered prompt sentence is sent to the server as an HTTP request. As a specific operation, data is sent using an HTTP POST request. The user input is passed to the server as output.

[1331] Step 3:

[1332] The server receives user input and analyzes it using natural language processing (NLP). The server uses Hugging Face's Transformers library to tokenize the input text and understand its context and intent. The data processing performed in this step is tokenization and context analysis. As an output, important words ("ambiguous") are extracted.

[1333] Step 4:

[1334] Based on the analysis results, the server accesses the virtual database to retrieve related data. The data calculation performed here is a database query corresponding to the extracted word. The server retrieves example sentences and explanations related to "ambiguous" from the virtual database. As an output, data related to the word is obtained.

[1335] Step 5:

[1336] The server passes the acquired data to the generative AI model to generate appropriate example sentences and explanations. Specifically, the data is passed as input to the generative AI model, and the generated text output is obtained. In this step, the generative AI model generates the example sentence "The meaning of his statement was ambiguous" and its explanation. The generated example sentence and explanation are obtained as output.

[1337] Step 6:

[1338] The server formats the generated response in a user-friendly format and sends it to the terminal. The specific operation here is to convert the generated text into an appropriate format and send it again to the terminal as an HTTP response. As output, the formatted response is passed to the terminal.

[1339] Step 7:

[1340] The terminal receives the response from the server and displays it in a format that is easy for the user to understand. As input, it receives the response from the server. As a specific operation, it displays the received data on the screen. As output, the example sentence and its explanation are displayed on the user's screen.

[1341] Through the above processing steps, the system allows users to receive language learning support in real time while browsing content.

[1342] 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.

[1343] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The embodiments for carrying out the present invention will be described in detail below.

[1344] System Overview

[1345] This system is an interactive dictionary service that utilizes natural language processing (NLP), generative AI, and an emotion engine to support users' language learning. It aims to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their devices, and can also recognize the user's emotions and adjust the content and tone of the response. The operation and functionality of each major component are described in detail below.

[1346] Server Operation

[1347] 1. Receiving user input

[1348] The server receives requests entered by users into their terminals, such as "Please tell me some example sentences for ambiguous."

[1349] 2. Performing Natural Language Processing (NLP)

[1350] The server analyzes the received user input using natural language processing (NLP), and as part of the analysis, it tokenizes the input to understand its context and intent.

[1351] 3. Emotion analysis using an emotion engine

[1352] The server analyzes the user's input to determine their emotions. The emotion engine analyzes the input and identifies the user's emotional state.

[1353] 4. Database Access

[1354] Based on the analysis results, the server accesses a database to retrieve data related to the relevant words and expressions, including example sentences and explanations of their nuances.

[1355] 5. Response generation using generative AI

[1356] The server passes the acquired data to the generation AI, which generates appropriate example sentences and their explanations. It can also adjust the tone and content of the response based on the analysis results of the emotion engine.

[1357] 6. Response Format

[1358] The server formats the generated response in a user-friendly format suitable for display.

[1359] Device behavior

[1360] 1. Submitting User Input

[1361] The device sends the information entered by the user to the server, and if the input is useful for learning, it immediately makes a request to the server.

[1362] 2. Receiving a response from the server

[1363] The device receives the response from the server and displays it to the user in an easy-to-understand format, often including concrete examples, explanations, and emotional tones.

[1364] 3. Assistive typing and autocomplete

[1365] The device provides input assistance and auto-complete functions to help users input information efficiently, making the learning experience smoother for users.

[1366] User Actions and Interactions

[1367] 1. First time input

[1368] Users input words or phrases into their device for translation, example sentences, or nuanced understanding. For example, they might type, "Please tell me some example sentences for ambiguous."

[1369] 2. Use of the displayed results

[1370] Users can use the example sentences and explanations displayed to help them learn. If they need more information, they can enter additional questions on the same screen. Responses tailored to the user's emotions also help them understand more easily.

[1371] 3. Follow-up questions and continued learning

[1372] If the user enters a subsequent question, a request is sent to the server again, and a response is generated in the same process, allowing the user to progress through the learning process interactively.

[1373] Specific examples

[1374] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[1375] The device sends input to the server.

[1376] The server parses the input and retrieves data related to "ambiguous" from the database.

[1377] The emotion engine analyzes emotions from user input. For example, if a user types "Tell me some vague sentences," the emotion engine will recognize emotions like doubt and confusion.

[1378] The generative AI generates the example sentence "The meaning of his statement was ambiguous" and its explanation, and includes a specific commentary based on the emotion recognition results.

[1379] The server formats the generated response and sends it to the terminal.

[1380] The device receives the response and displays it to the user, explained in an emotionally tailored tone of voice.

[1381] The above is an embodiment of the present invention, which allows the user to learn a language efficiently.

[1382] The processing flow will be explained below.

[1383] Step 1:

[1384] The user types into the terminal, "Please tell me some example sentences for ambiguous."

[1385] Step 2:

[1386] The terminal sends the user's input to the server. The terminal converts the input string into an HTTP request and sends it to the server.

[1387] Step 3:

[1388] The server receives a request from the user. The server receives the request sent from the terminal and extracts the input content included in the request body.

[1389] Step 4:

[1390] The server performs natural language processing (NLP), tokenizing the incoming input and analyzing its context and intent. For example, it identifies the word "ambiguous" and analyzes its usage.

[1391] Step 5:

[1392] The server analyzes the user's emotions using an emotion engine, extracts emotions from the user's input sentences, and recognizes their emotional state, such as "confusion" or "doubt."

[1393] Step 6:

[1394] The server accesses the database and retrieves data related to the word identified in the input sentence from the database. For example, it searches for example sentences and explanations of nuances related to "ambiguous."

[1395] Step 7:

[1396] The server uses the generation AI to generate a response. The server passes the acquired data to the generation AI, which generates appropriate example sentences and their explanations. The server also adjusts the tone and content of the response based on the analysis results of the emotion engine.

[1397] Step 8:

[1398] The server formats the response. The server formats the generated response in a user-friendly format suitable for display, such as a response containing the example sentence "The meaning of his statement was ambiguous" and an explanation of it.

[1399] Step 9:

[1400] The server sends the formatted response to the terminal. The server prepares the formatted response as an HTTP response and sends it to the terminal.

[1401] Step 10:

[1402] The device receives the response from the server. The device analyzes the response and displays it to the user. For example, if the user expresses confusion, the response may include further explanation or a gentler tone.

[1403] Step 11:

[1404] The user can use the displayed results. The user can use the example sentences and explanations displayed to study, and if more information is needed, they can enter additional questions.

[1405] Example 2

[1406] 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."

[1407] Conventional language learning support systems simply provide example sentences and explanations in response to user input, but are unable to respond in a way that takes into account the user's emotional state. This means that when a user is confused or has questions, the system is unable to respond in an appropriate tone, resulting in insufficient learning effectiveness.

[1408] 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.

[1409] In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for analyzing emotions based on the results of the natural language processing, means for retrieving appropriate data from a database based on the analyzed emotional information, means for generating a response using the retrieved data and the analyzed emotional information with a generative artificial intelligence, and means for formatting the generated response and sending it to the user. This makes it possible to generate a response that corresponds to the emotional state of the user, thereby achieving more effective language learning support.

[1410] "User" refers to an individual who uses this system to study a language.

[1411] "Input" refers to language-related questions or phrases that a user sends to a terminal.

[1412] "Server" refers to a central processing system that receives user input and performs various processes.

[1413] "Natural language processing" refers to the technology of analyzing user input and understanding the context and intent.

[1414] An "emotion engine" refers to a technology that analyzes emotions from user input and identifies that emotional state.

[1415] A "database" refers to a collection of information that stores and makes accessible data relating to words and expressions.

[1416] "Generative artificial intelligence" refers to AI technology that generates appropriate responses based on acquired data.

[1417] A "response" refers to a reply that includes example sentences and explanations generated based on the user's input.

[1418] "Formatting" refers to the process of preparing the generated response in a form that is easy for the user to understand.

[1419] "Terminal" refers to a device (such as a personal computer or smartphone) that a user uses to make input.

[1420] The "input support function" refers to a function for assisting the user in input.

[1421] The "autocomplete function" refers to a function that automatically displays candidates while the user is typing and completes the input.

[1422] MODE FOR CARRYING OUT THE INVENTION

[1423] This invention is an interactive dictionary service that utilizes natural language processing (NLP), generative AI, and an emotion engine to support users' language learning. The system aims to provide appropriate example sentences and explanations in real time for words and phrases entered by users on their devices, and is structured and functionally capable of recognizing the user's emotions and adjusting the content and tone of the response. The operation and functionality of each major component are described in detail below.

[1424] Server Operation

[1425] The server receives the request entered by the user on the device and analyzes the content using natural language processing (NLP) technology. NLP engines used include "SpaCy" and "NLTK."

[1426] Received user input is first tokenized to understand context and intent. An emotion engine then analyzes the input and recognizes the user's emotional state. The emotion engine used can be a platform like Affectiva or IBM Watson Tone Analyzer.

[1427] Based on the analysis results, the server accesses a database to retrieve data related to the relevant words and expressions. The database stores example sentences and explanations of their nuances. A database management system (DBMS) such as MySQL or PostgreSQL is used.

[1428] The acquired data is passed to a generation AI, which generates appropriate example sentences and their explanations. Models such as GPT-3 and BERT are used as the generation AI. The tone and content of the response are adjusted based on the analysis results of the emotion engine.

[1429] Finally, the generated response is formatted in a user-friendly format, made suitable for display, and sent to the terminal, where it is reconstructed in HTML or JSON format.

[1430] Device behavior

[1431] The terminal mainly serves to send input from the user to the server and receive and display responses from the server. For example, if a user types "Please tell me some example sentences for ambiguous," the request is sent to the server in real time.

[1432] When the response comes back from the server, the device analyzes it and displays it in a user-friendly format, including specific examples, explanations, and emotional tones. Frameworks such as "React" and "Vue.js" are used for the UI / UX design of the exhibit.

[1433] The device also provides input assistance and auto-complete functions to help users input information efficiently, making the learning experience smoother for users.

[1434] User Actions and Interactions

[1435] Users use their device to input a question about a word or phrase, such as "Can you give me an example of an ambiguous sentence?" The example sentences and explanations displayed can be used to learn, and if more information is needed, users can input additional questions on the same screen. Responses tailored to their emotions can improve comprehension.

[1436] If the user enters a subsequent question, a request is sent to the server again, and a response is generated in the same process, allowing the user to progress through the learning process interactively.

[1437] Specific examples

[1438] For example, if a user types "Tell me an example sentence for ambiguous" into a terminal, the following happens:

[1439] 1. The device sends input to the server.

[1440] 2. The server parses the input and retrieves data related to "ambiguous" from the database.

[1441] 3. The emotion engine analyzes emotions from the user's input. For example, if a user types "Tell me some vague sentences," the emotion engine will recognize emotions such as doubt and confusion.

[1442] 4. The generative AI generates an example sentence, "The meaning of his statement was ambiguous," along with an explanation, including specific commentary based on the emotion recognition results.

[1443] 5. The server formats the generated response and sends it to the device.

[1444] 6. The device receives the response and displays it to the user, explained in an emotionally tailored tone.

[1445] Prompt Sentence Examples

[1446] An example prompt for this system:

[1447] 1. "What does ambiguous mean?"

[1448] 2. "Please give me some example sentences for ambiguous expressions in English."

[1449] 3. "Please explain how to use ambiguous with an example sentence."

[1450] This allows the user to study a language efficiently.

[1451] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1452] Step 1:

[1453] The user types a question or phrase into the terminal. For example, "Please tell me an example sentence for ambiguous." The input data is sent to the terminal as a prompt.

[1454] Step 2:

[1455] The terminal sends user input to the server. The terminal formats the received prompt and sends it to the server as an HTTP request. The input is text data, "Please tell me some example sentences for ambiguous," and is sent to the server as is.

[1456] Step 3:

[1457] The server receives user input. The server receives the prompt sent from the terminal and saves it for further processing. The input is text data included in the body of the HTTP request.

[1458] Step 4:

[1459] The server analyzes the input using an NLP engine. The server tokenizes the received text data and analyzes the context and intent. Specifically, it splits the input sentence into words and performs grammatical analysis. The input is the text data "Please tell me some example sentences for ambiguous," and the output is the keyword "ambiguous" and its context information.

[1460] Step 5:

[1461] The server uses an emotion engine to analyze the user's emotions. The server identifies the user's emotional state from the output of the NLP engine. Specifically, it performs emotion scoring of text data. The input is the analysis result of the NLP engine, and the output is emotional state information that the user is "confused."

[1462] Step 6:

[1463] The server accesses the database to retrieve relevant data. Based on the emotion and keyword, the server retrieves appropriate example sentences and explanations from the database. Specifically, it searches for related data using an SQL query. The input is the keyword "ambiguous" and emotion information, and the output is related example sentence data.

[1464] Step 7:

[1465] The server generates a response using generative AI. Based on the acquired data, the server generates appropriate example sentences and explanations for the user input. It also adjusts the tone and content of the response using the results of emotion analysis. Specifically, data is input into the generative AI model, which outputs a response. The input is example sentence data and emotion information acquired from the database, and the output is the generated example sentence and explanation.

[1466] Step 8:

[1467] The server formats the response and sends it to the terminal. The server formats the generated response in a format that is easy for the user to understand and sends the formatted data to the terminal. Specifically, it converts the data into HTML or JSON format. The input is the generated response data, and the output is the formatted data.

[1468] Step 9:

[1469] The terminal receives and displays the response from the server. The terminal receives the response sent from the server and displays it in a format that is easy for the user to understand. Specifically, it interprets the received data and displays it on the screen. The input is the formatted data sent from the server, and the output is the example sentence and explanation displayed on the screen.

[1470] Step 10:

[1471] The user enters an additional question. If the user needs more information, they enter the question again into the terminal. For example, they might enter "Tell me more example sentences." In this case, a prompt requesting further information is sent to the terminal again.

[1472] (Application example 2)

[1473] 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."

[1474] The objective of this invention is to provide a system that can provide interactive advertisements according to the user's emotional state. Conventional advertising systems can only generate a uniform response to user input, making it difficult to personalize the response to reflect the user's emotions and intentions. This results in a poor user experience and limited advertising effectiveness.

[1475] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving input from a user, means for performing natural language processing based on the input, means for performing emotion analysis based on the results of the natural language processing, means for generating a response according to the user's emotion using the generative artificial intelligence, and means for formatting the generated response and sending it to the user. This makes it possible to generate personalized advertising copy that reflects the user's emotional state and intentions.

[1476] The "means for receiving input from the user" is a mechanism for receiving information input by the user through the user interface.

[1477] "Means for natural language processing" refers to technology for analyzing input text and understanding its grammar and meaning.

[1478] The "means for performing emotion analysis" is a technology for determining the psychological state of a user based on the sentences input by the user.

[1479] "Means for generating responses using generative artificial intelligence" refers to a mechanism that uses a machine learning model to create appropriate answers based on the analysis results.

[1480] The "means for formatting the generated response and sending it to the user" refers to a technique for arranging the generated response in an appropriate format and providing it to the user.

[1481] The "input assistance function or autocomplete function" is a function that assists the user in inputting information effectively, and is a technology that performs pre-reading and suggests candidates.

[1482] The "means for generating advertising copy" is a technology for creating appropriate advertising content based on the results of user sentiment analysis.

[1483] System Program Overview

[1484] A system embodying the present invention receives input from a user, performs natural language processing (NLP) and sentiment analysis, and uses generative AI to generate a response based on the user's sentiment, thereby providing personalized advertising copy based on the user's sentiment.

[1485] Detailed explanation of the process

[1486] 1. Receiving user input

[1487] The server receives information entered by the user on the device. This input is in natural language, for example, in the form of "I want a new smartphone."

[1488] 2. Performing natural language processing

[1489] The server then analyzes the received user input using NLP techniques, which include tokenizing the input and understanding its grammar, context, and intent. A suitable NLP library to use is "transformers."

[1490] 3. Performing sentiment analysis

[1491] The server performs sentiment analysis based on the results of NLP analysis. The emotion engine determines the psychological state of the input content and identifies whether the user is excited or confused. The model for sentiment analysis uses a library that provides "sentiment-analysis."

[1492] 4. Database Access

[1493] The server retrieves relevant advertising information from a database based on the analysis results, including corresponding product and service information based on the user's input.

[1494] 5. Generating the Response

[1495] The server uses a generative AI model to generate ad copy based on the acquired ad information and the user's emotional state. For example, if the user is excited, the server will provide ad copy in an exciting tone, and if the user is confused, the server will provide polite explanation. An example of a prompt sentence in this case is "Generate ad copy for a new smartphone."

[1496] 6. Response Format and Transmission

[1497] The server formats the generated response in a user-friendly format and sends it to the terminal in the appropriate format, which displays the received response to the user in real time.

[1498] Specific examples

[1499] For example, if a user types "I want a new phone," the system will do the following:

[1500] The server receives the user input and parses the input using the "transformers" library.

[1501] The emotion engine determines from the input sentence that the user is excited.

[1502] The server retrieves the latest smartphone information from the database.

[1503] The generative AI model generates an exciting ad copy that reads, "An exciting new smartphone! Boasting a revolutionary camera, a super-fast processor, and now at a special price of just ¥100,000!"

[1504] The server formats the generated copy and sends it to the device.

[1505] The terminal displays the advertisement copy to the user in real time.

[1506] In this way, the system of the present invention provides personalized advertising copy that takes user emotions into account, thereby achieving a more effective advertising experience.

[1507] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1508] Step 1:

[1509] The device receives information entered by the user. When the user enters "I want a new smartphone," the device sends the input data to the server. Input: A string of natural language characters containing the user's wishes and questions. Output: The input data sent to the server.

[1510] Step 2:

[1511] The server parses the received user input using natural language processing (NLP), specifically using the "transformers" library to tokenize the input sentence and understand grammar and context. Input: User's natural language input. Output: Parsed tokenized data and intent.

[1512] Step 3:

[1513] The server performs sentiment analysis based on the results of NLP analysis. It uses an emotion engine ("sentiment-analysis" model) to determine the user's emotional state. Input: NLP analysis results. Output: User's emotional state (e.g., excited, confused).

[1514] Step 4:

[1515] The server retrieves relevant advertising information from the database based on the results of the sentiment analysis. Specifically, if a user enters "smartphone," the server searches the database for the latest smartphone information and retrieves it. Input: User input and sentiment analysis results. Output: Related advertising information (e.g., product name, features, price).

[1516] Step 5:

[1517] The server generates ad copy that corresponds to the user's emotions based on the ad information obtained using the generative AI model. The generative AI model is given a prompt such as "Generate ad copy for a new smartphone." Input: Ad information and emotional state. Output: Personalized ad copy that corresponds to the user's emotions.

[1518] Step 6:

[1519] The server formats the generated ad copy into an easy-to-understand format and sends it to the device. Specifically, it converts it into a format that is easy to format, such as HTML or plain text. Input: Generated ad copy. Output: Formatted ad copy.

[1520] Step 7:

[1521] The terminal displays the formatted ad copy received from the server to the user. If the user is excited, the user will see the ad copy in an exciting tone, and if the user is confused, the user will see the ad copy in a polite tone. Input: Formatted ad copy. Output: Display of ad copy.

[1522] 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.

[1523] 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.

[1524] 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.

[1525] 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.

[1526] FIG. 9 illustrates 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 behaviors 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.

[1527] 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.

[1528] 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).

[1529] 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.

[1530] 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."

[1531] 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.

[1532] 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).

[1533] 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.

[1534] 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.

[1535] 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.

[1536] 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.

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] The following is further disclosed regarding the above embodiment.

[1544] (Claim 1)

[1545] means for receiving input from a user;

[1546] means for performing natural language processing based on the input;

[1547] A means for generating a response using artificial intelligence based on the result of the natural language processing;

[1548] means for formatting and transmitting the generated response to a user;

[1549] A system including:

[1550] (Claim 2)

[1551] 10. The system of claim 1, further comprising means for providing an input assistance or auto-complete function.

[1552] (Claim 3)

[1553] 2. The system according to claim 1, wherein the response generation means generates an example sentence and an explanation thereof.

[1554] "Example 1"

[1555] (Claim 1)

[1556] means for receiving input from a user;

[1557] means for performing natural language processing based on the input;

[1558] means for accessing a database based on the result of the natural language processing and acquiring related information;

[1559] means for providing the acquired information to a generative artificial intelligence model to generate a response;

[1560] means for formatting and transmitting the generated response to a user;

[1561] A system including:

[1562] (Claim 2)

[1563] 10. The system of claim 1, further comprising means for providing an input assistance or auto-complete function.

[1564] (Claim 3)

[1565] 2. The system according to claim 1, wherein the response generation means generates an example sentence and an explanation thereof.

[1566] "Application Example 1"

[1567] (Claim 1)

[1568] means for receiving input from a user;

[1569] means for performing natural language processing based on the input;

[1570] A means for generating a response using artificial intelligence based on the result of the natural language processing;

[1571] means for formatting the generated response to display the content;

[1572] A system including:

[1573] (Claim 2)

[1574] 10. The system of claim 1, further comprising means for providing an input assistance or auto-complete function.

[1575] (Claim 3)

[1576] 2. The system according to claim 1, wherein the response generation means generates example sentences and their explanations and displays them in real time.

[1577] "Example 2: Combining Emotion Engines"

[1578] (Claim 1)

[1579] means for receiving input from a user;

[1580] means for performing natural language processing based on the input;

[1581] means for analyzing emotions based on the results of the natural language processing;

[1582] means for acquiring appropriate data from a database based on the analyzed emotion information;

[1583] A means for generating a response by a generation artificial intelligence using the acquired data and the analyzed emotion information;

[1584] means for formatting and transmitting the generated response to a user;

[1585] A system including:

[1586] (Claim 2)

[1587] 10. The system of claim 1, further comprising means for providing an input assistance or auto-complete function.

[1588] (Claim 3)

[1589] 2. The system according to claim 1, wherein the response generation means generates an example sentence and an explanation thereof.

[1590] "Application example 2 when combining emotion engines"

[1591] (Claim 1)

[1592] means for receiving input from a user;

[1593] means for performing natural language processing based on the input;

[1594] means for performing sentiment analysis based on the results of the natural language processing;

[1595] means for generating a response according to the user's emotion using the generation artificial intelligence;

[1596] means for formatting and transmitting the generated response to a user;

[1597] A system including:

[1598] (Claim 2)

[1599] 10. The system of claim 1, further comprising means for providing an input assistance or auto-complete function.

[1600] (Claim 3)

[1601] 2. The system of claim 1, wherein the response generating means generates advertising copy based on the emotional state of the user. [Explanation of symbols]

[1602] 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. means for receiving input from a user; means for performing natural language processing based on the input; A means for generating a response using artificial intelligence based on the result of the natural language processing; means for formatting and transmitting the generated response to a user; A system including:

2. The system of claim 1 further comprising means for providing an input assistance or auto-complete function.

3. 2. The system according to claim 1, wherein said response generating means generates an example sentence and an explanation thereof.

Images