system

Abstract

We provide the system. [Solution] A means for capturing the text to be translated from the user terminal, Means for sending the captured text to the server as a translation request, A means of translating text using generative AI based on a received translation request, means for generating additional explanations related to the translated text, Means for transmitting the translated text and additional explanations to the user terminal, means for displaying the translation result received on the user terminal A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In recent years, with the spread of the Internet, the opportunities for users to access foreign language content (such as YouTube (registered trademark), SNS, e-commerce sites, etc.) have increased. However, many existing translation tools perform mechanical translations that ignore context, and sometimes the meaning may not be conveyed. In addition, the lack of technical terms and information based on specific cultural backgrounds makes it difficult for users to understand. As a result, situations where accurate information and understanding are required occur. To solve these problems, a system that can provide high-precision translation based on context and additional explanations is needed. [[ID=:37]]

Means for Solving the Problems

[0005] This invention provides a system that captures text to be translated from a user's terminal and sends it to a server as a translation request. Based on the received translation request, the server uses generative AI to translate the text and further generates additional explanations related to the translated text (e.g., definitions of technical terms and background information). This allows the user to receive contextually accurate translations and related information, enabling accurate understanding. This system not only improves translation accuracy but also significantly enhances the usability of foreign language content.

[0006] A "user terminal" is a device operated by the user that captures the text to be translated, sends a translation request to the server, and finally receives and displays the translation result.

[0007] "Text to be translated" refers to text data that a user wishes to have translated, such as video descriptions on the internet, social media posts, and product descriptions on e-commerce sites.

[0008] "Capture" refers to the operation in which a user's device selects text to be translated and extracts it as data.

[0009] A "translation request" is a data request sent from the user's terminal to the server, and it includes the captured text to be translated.

[0010] A "server" is a system that receives translation requests from user terminals, translates text using generative AI, generates additional explanations, and sends them to the user terminal.

[0011] "Generative AI" refers to a system that uses artificial intelligence technology to perform contextual analysis, translate text, and generate additional explanations as needed.

[0012] Translation is the act of converting text written in one language into another language.

[0013] "Additional explanations" refer to supplementary information that helps users understand the translated text better, such as definitions of technical terms, background information, and cultural context.

[0014] "Display" refers to the operation of visually outputting the translation result and additional explanations on the user's terminal screen. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disk (e.g., hard disk), or magnetic tape, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional explanations when users access that content. This system is realized through the collaboration of a user terminal, a server, and a generative AI.

[0037] System configuration and operation

[0038] User terminal operation

[0039] The user's device captures text and links of content the user wishes to translate. This captured data can be processed using a dedicated app or browser extension. Examples of target text on the internet include YouTube video descriptions, social media posts, and product descriptions on e-commerce sites. When the user clicks the "Translate" button, the captured text and links are sent to the server.

[0040] Server operation

[0041] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, and the translation process begins. The generative AI analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[0042] The server sends the generated translation results and additional explanations to the user's terminal. During this process, contextual analysis is performed to improve translation accuracy, and relevant information is added to provide information that is easy for the user to understand.

[0043] Display of user actions and results

[0044] Users can receive and review the translation results and additional explanations sent from the server on their devices. This enables them to accurately and comprehensively understand foreign language content.

[0045] Specific example

[0046] Translation of YouTube video description

[0047] 1. User: Wants to translate the YouTube video description and selects the description.

[0048] 2. User terminal: Captures the selected description and sends a translation request to the server.

[0049] 3. Server: Receives translation requests and translates the explanatory text using generative AI. Based on the translation results, it generates additional explanations (e.g., definitions of technical terms and cultural background).

[0050] 4. Server: Sends the translation results and additional explanations to the user's terminal.

[0051] 5. User: Review the translation results and additional explanations displayed on the device and understand the content.

[0052] The system of this invention enables users to understand and utilize foreign language content more accurately. In particular, the inclusion of additional explanations based on specialized terminology and cultural background allows users to gain a deeper understanding of the content. This enriches the user's knowledge and significantly enhances the value of utilizing foreign language content.

[0053] The following describes the processing flow.

[0054] Step 1:

[0055] Users select text or links to be translated. This is done by selecting portions of online content, such as YouTube video descriptions, social media posts, or product descriptions on e-commerce sites.

[0056] Step 2:

[0057] The user clicks the "Translate" button and takes action to submit a translation request.

[0058] Step 3:

[0059] The user's terminal captures the selected text or links to be translated. Specifically, it extracts the text data from the selected portion and saves it to memory.

[0060] Step 4:

[0061] The user terminal generates a translation request containing the captured text data and sends this request to the server. The request includes the captured text data and associated metadata.

[0062] Step 5:

[0063] The server receives translation requests sent from the user's terminal. These requests contain captured text data to be translated.

[0064] Step 6:

[0065] The server analyzes the received text data and prepares it for transmission to the generative AI. This step involves initial analysis to understand the content of the text.

[0066] Step 7:

[0067] The server uses generative AI to analyze the text to be translated and generate a context-based, highly accurate translation. The generative AI translates the text considering sentence structure, context, and the meaning of terms.

[0068] Step 8:

[0069] The server generates additional explanations related to the translated text. These include definitions of technical terms, cultural context, and related information. The generated additional explanations help users gain a deeper understanding of the translated text.

[0070] Step 9:

[0071] The server sends the completed translation and additional explanations to the user's terminal. In this step, the translation and related information are packaged and sent to the user's terminal.

[0072] Step 10:

[0073] The user terminal receives the translation results and additional explanations sent from the server. The received data is temporarily stored in memory.

[0074] Step 11:

[0075] The user terminal displays the received translation results and additional explanations on the screen. The user reviews and understands the content.

[0076] Step 12:

[0077] Users can review the displayed translation results and additional explanations to accurately understand the foreign language content.

[0078] (Example 1)

[0079] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0080] When using foreign language content, users need not only accurate translations but also context and background information to deeply understand the content. However, conventional translation systems often only provide translation results, making it difficult for users to understand the intent and details of the content. Furthermore, the lack of additional explanations regarding specialized terminology and cultural background information means that the system cannot adequately support user understanding.

[0081] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0082] In this invention, the server includes means for selecting content to be translated from a user terminal, means for capturing the selected content, means for sending the captured content to the server as a translation request, means for translating the text using a generative AI model based on the received translation request, means for generating additional information related to the translated text, means for sending the translated text and additional information to the user terminal, and means for displaying the received translation results and additional information on the user terminal. This provides not only accurate translations but also additional explanations including context, definitions of technical terms, and cultural background information, enabling the user to gain a deeper understanding of the foreign language content.

[0083] A "user terminal" refers to a device used by a user to access content on the internet, such as a personal computer, smartphone, or tablet.

[0084] "Content" refers to all forms of information that users utilize, primarily including text data such as video descriptions, social media posts, and product descriptions.

[0085] "Capturing" refers to the operation of selecting content displayed on a user's device and capturing that data.

[0086] A "server" refers to a computer system that receives data sent from user terminals and performs data processing and translation processing using generative AI models.

[0087] A "translation request" refers to a data packet sent from a user's terminal to the server requesting translation.

[0088] A "generative AI model" refers to an artificial intelligence algorithm that analyzes received text data and generates appropriate translations and additional information.

[0089] "Contextual analysis" refers to a technical process that analyzes the content and surrounding information of text to create more accurate and appropriate translations.

[0090] "Additional information" refers to definitions of technical terms and cultural background information related to the translated text, which helps users to gain a deeper understanding of the content.

[0091] Modes for carrying out the invention

[0092] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional information when users access it. This system is realized through the collaboration of a user terminal, a server, and a generative AI.

[0093] User terminal operation

[0094] The user's device is used to select the content they wish to translate. For example, when a user selects a YouTube video description, a social media post, or a product description from an e-commerce site, the user's device captures this content using a dedicated app or browser extension. When the user clicks the "Translate" button, the captured text is sent to the server.

[0095] Server operation

[0096] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, such as OpenAI's GPT model, and translation processing is performed. The generative AI analyzes the context of the text and generates appropriate translation results. Furthermore, based on the translation results, it generates additional information such as definitions of technical terms and cultural background information.

[0097] Display of user actions and results

[0098] The user terminal receives the translation results and additional information sent from the server and displays them to the user. This allows the user to accurately and fully understand the foreign language content.

[0099] Specific example

[0100] Translation of YouTube video description

[0101] 1. User: Decides to translate a YouTube video description and selects the description.

[0102] 2. User terminal: Captures the description text and sends a translation request to the server.

[0103] 3. Server: Receives requests and translates the description using generative AI (e.g., OpenAI GPT model). Based on the translation results, it generates additional information (e.g., definitions of technical terms and cultural background).

[0104] 4. Server: Sends the translation results and additional information to the user's terminal.

[0105] 5. User: Review the translation results and additional information displayed on the device to gain a deeper understanding of the content.

[0106] Example of a prompt

[0107] Translation target: "This is a sample description of a YouTube video."

[0108] Prompt to the generating AI: "Translate this text into Japanese and provide additional information relevant to the content, including any cultural or technical terms."

[0109] This system will enable users to understand and utilize foreign language content more accurately. In particular, by providing additional information based on specialized terminology and cultural background, it is expected that users' knowledge will be enriched, and the value of using foreign language content will be significantly enhanced.

[0110] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0111] Step 1:

[0112] The user selects the content they want translated. For example, they might choose a YouTube video description or a social media post. This action inputs the selected text data into the user's device.

[0113] Step 2:

[0114] The user's device captures selected content and sends it to the server. The captured data includes text content and metadata (e.g., URL, posting date and time). This data is sent to the server as captured text.

[0115] Specific actions:

[0116] When a user clicks the "Translate" button, the browser extension automatically extracts the text from the page and sends it to the server.

[0117] Step 3:

[0118] The server analyzes the received text data and sends a prompt to the generative AI. The analysis includes understanding the context of the received text. The server sends the generative AI model the prompt: "Translate the following text: 'This is a sample description of a YouTube video.' and provide additional context information."

[0119] Specific actions:

[0120] The server analyzes the received data and generates prompt messages to send to the generative AI.

[0121] Step 4:

[0122] The generative AI receives a prompt and generates appropriate translation results and additional explanations. The generative AI performs contextual analysis to improve translation accuracy and generates the translated text along with additional information including definitions of technical terms and background information. This result is returned to the server.

[0123] Specific actions:

[0124] The generative AI translates "This is a sample description of a YouTube video." as "This is a sample description of a YouTube video." and generates additional information such as "YouTube is a video sharing service, and video descriptions typically contain information about the content and purpose of the video."

[0125] Step 5:

[0126] The server sends the translation results and additional explanations received from the generative AI to the user's terminal. In this process, the server converts the generated results into a format that is easy for the user to understand.

[0127] Specific actions:

[0128] The server sends the translation results and additional explanations to the user's terminal in JSON format. The JSON data includes the translated text and additional information.

[0129] Step 6:

[0130] The user's terminal displays the data received from the server. The user can check the translation results and additional explanations on their terminal to deepen their understanding of the foreign language content.

[0131] Specific actions:

[0132] The browser extension displays the received data and shows information such as, "Translation result: This is a sample description for a YouTube video. Additional information: YouTube is a video sharing service, and video descriptions typically include information about the content and purpose."

[0133] In this way, the system performs a series of processes to help users accurately understand foreign language content.

[0134] (Application Example 1)

[0135] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0136] Traditional translation systems simply convert text into another language, often failing to provide information to deepen understanding of specialized terminology and cultural context. As a result, users often struggled to fully understand translated content, especially when it contained specialized information. Furthermore, a lack of definitions and background information for specialized terms in certain fields created a high barrier to user access to the content.

[0137] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0138] In this invention, the server includes means for acquiring content to be translated from a user terminal, means for sending the acquired content to the server as a translation request, means for translating the text using a generative AI based on the received translation request, means for generating additional explanations related to the translated text, means for sending the translated text and additional explanations to the user terminal, and means for displaying the received translation results and additional explanations on the user terminal. This makes it possible for users to understand foreign language content more deeply and to significantly improve the value of content, especially content containing specialized information and cultural background.

[0139] A "user terminal" is a device used by a user to interact with content and input and display information.

[0140] "Acquiring" means gathering specific information or data from an external source and importing it into the local environment.

[0141] "Content" refers to a unit of information, provided in various forms such as text, images, videos, and audio.

[0142] A "translation request" is a request that a user sends to a server to translate specific content into another language.

[0143] A "server" is a computer system that processes requests from client devices on a network and provides information.

[0144] "Generative AI" refers to artificial intelligence models that use natural language processing and machine learning to generate and transform text.

[0145] "Translating text" means converting text written in one language into another language.

[0146] "Additional explanations" refer to supplementary information such as definitions of technical terms and cultural context related to the translated text.

[0147] "To send" means to move data or information from a source to a destination over a network.

[0148] "To display" means to provide information to the user visually.

[0149] Modes for carrying out the invention

[0150] The embodiments for carrying out this invention will be described in detail below.

[0151] System configuration and operation

[0152] User terminal operation

[0153] The user's device has a means of obtaining the content the user wishes to translate. For example, the user enters the URL of a YouTube video via a smartphone application. At this time, the application uses the YouTube API to obtain the video description and comments. The obtained text is sent to the server.

[0154] Server operation

[0155] The server receives translation requests sent from user terminals. These requests contain the text to be translated. The server uses generative AI to translate this text. Specifically, the server leverages a generative AI model to generate a draft translation. It also generates additional explanations related to the translated text. These explanations include definitions of technical terms and information about cultural background. This information is also derived from the generative AI model.

[0156] Display translation results and explanations

[0157] The server sends the generated translation results and additional explanations to the user's terminal. The user's terminal displays the received translation results and explanations to the user. This allows the user to understand the foreign language content more completely.

[0158] Hardware and software to be used

[0159] Hardware: Smartphones (iOS or Android®), cloud servers

[0160] Software: YouTube API, OpenAI GPT model, Flask (Python application framework)

[0161] Data processing and calculation

[0162] 1. User terminal: The video description and comments are retrieved from the YouTube API via the video URL entered by the user.

[0163] 2. Server: The server translates the received text using a generative AI (e.g., the OpenAI GPT model) and generates additional explanations. The generated information is processed based on context and provided to the user in the most optimal form.

[0164] 3. Communication: The generated data (translation results and additional explanations) is sent to the user's terminal via the internet.

[0165] Specific example

[0166] Suppose a user watches a YouTube video in a foreign language like this:

[0167] Title: "Understanding Quantum Computing"

[0168] Caption: "In this video, we'll explore the basics of quantum computing and its potential applications."

[0169] A user wants to translate a video description and enters the URL into the "DeepTranslate" app. The app then retrieves the description via the YouTube API and sends it to the server. On the server side, a generative AI (e.g., the OpenAI GPT model) translates it, generating additional definitions of technical terms and explanations of cultural context. For example, it might use prompts like the following:

[0170] Example of a prompt:

[0171] Translate the following text to Japanese and provide additional explanations:

[0172] In this video, we'll explore the basics of quantum computing and its potential applications.

[0173] Finally, the generated translations and explanations are sent to the user's smartphone, allowing them to easily review them.

[0174] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0175] Step 1:

[0176] On the user's device, the user enters specific content (e.g., a YouTube video URL). This causes the user's device to send a request to the YouTube API to retrieve the video description and comments from that URL.

[0177] Input: Video URL entered by the user

[0178] Output: Retrieved video description and comments

[0179] Step 2:

[0180] The user's device sends the video description and comments, retrieved from the YouTube API, to the server as a translation request.

[0181] Input: Retrieved video description and comments

[0182] Output: Text data as a translation request

[0183] Step 3:

[0184] The server analyzes the received translation request and sends a prompt to the generative AI for translation. A generative AI model is used to generate context-aware translations.

[0185] Input: Text data as a translation request

[0186] Output: Translated text

[0187] Step 4:

[0188] The server generates additional explanations related to the translated text. Generative AI is used to create supplementary explanations that include definitions of technical terms and information about cultural background.

[0189] Input: Translated text

[0190] Output: Additional explanation

[0191] Step 5:

[0192] The server sends the generated translation results and additional explanations to the user's terminal.

[0193] Input: Translated text and additional explanations

[0194] Output: Data sent to the user terminal

[0195] Step 6:

[0196] The user's device displays the received translation results and additional explanations. This makes it easier for the user to understand the content.

[0197] Input: Translation results and additional explanations sent from the server.

[0198] Output: Translation results and explanations that users can visually verify.

[0199] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0200] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional explanations when users access that content. This system is realized through the collaboration of a user terminal, a server, a generative AI, and an emotion engine.

[0201] System configuration and operation

[0202] User terminal operation

[0203] The user's device captures text and links of content the user wishes to translate. This captured data can be processed using a dedicated app or browser extension. Examples of target text on the internet include YouTube video descriptions, social media posts, and product descriptions on e-commerce sites. When the user clicks the "Translate" button, the captured text and links are sent to the server.

[0204] Furthermore, the user terminal has an emotion engine built in that analyzes the user's facial expressions and voice to generate emotion data. This emotion data is sent to the server and used to improve translation results and additional explanations.

[0205] Server operation

[0206] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, and the translation process begins. The generative AI analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[0207] Furthermore, the server receives sentiment data sent from the user's terminal and incorporates it into the translation results and additional explanations. For example, if it is determined that the user is experiencing stress, the translation results will be simplified and adjusted to be easier to understand.

[0208] The server sends the generated translation results and additional explanations to the user's terminal. During this process, contextual analysis is performed to improve translation accuracy, and relevant information is added to provide information that is easy for the user to understand.

[0209] Display of user actions and results

[0210] Users can receive and review the translation results and additional explanations sent from the server on their devices. This enables them to accurately and comprehensively understand foreign language content.

[0211] Specific example

[0212] Translation of YouTube video description

[0213] 1. User: Wants to translate the YouTube video description and selects the description.

[0214] 2. User terminal: Captures the selected description and sends a translation request to the server. It also analyzes the user's facial expressions and voice, generates emotion data, and sends it to the server.

[0215] 3. Server: Receives translation requests and translates the explanatory text using generative AI. Furthermore, it adjusts the translation result while considering the user's sentiment data.

[0216] 4. Server: Based on the translation results, it generates additional explanations (definitions of technical terms and cultural background).

[0217] 5. Server: Sends the translation results and additional explanations to the user's terminal.

[0218] 6. User: Review the translation results and additional explanations displayed on the device to understand the content. The inclusion of sentiment data allows users to receive information with less stress.

[0219] The system of this invention enables users to understand and utilize foreign language content more accurately. In particular, by using an emotion engine, appropriate information is provided according to the user's emotional state, making it easier for the user to deeply understand the content. As a result, the user's knowledge is enriched, and the value of using foreign language content is greatly enhanced.

[0220] The following describes the processing flow.

[0221] Step 1:

[0222] Users select text or links to be translated. This includes YouTube video descriptions, social media posts, and product descriptions on e-commerce sites.

[0223] Step 2:

[0224] The user clicks the "Translate" button to submit a translation request.

[0225] Step 3:

[0226] The user's device captures the selected text or links to be translated. Specifically, it extracts the text data from the selected portion and saves it to memory.

[0227] Step 4:

[0228] The user terminal generates a translation request containing the captured text data and sends this request to the server. The request includes the captured text data and associated metadata.

[0229] Step 5:

[0230] The user terminal uses an emotion engine to analyze the user's facial expressions and voice, generating emotion data in real time. This emotion data is also sent to the server.

[0231] Step 6:

[0232] The server receives translation requests and sentiment data sent from the user's terminal. This allows the server to understand both the information needed for translation and the user's emotional state.

[0233] Step 7:

[0234] The server uses generative AI to translate text based on the received translation request. The generative AI performs contextual analysis and generates an appropriate translation.

[0235] Step 8:

[0236] The server generates additional explanations related to the translated text, including definitions of technical terms and background information. If the sentiment data indicates "high stress," the additional explanations are adjusted to be concise and easy to understand.

[0237] Step 9:

[0238] The server adjusts the translation results and additional explanations based on sentiment data, optimizing them to suit the user.

[0239] Step 10:

[0240] The server sends the final translation results and any adjusted additional explanations to the user's terminal.

[0241] Step 11:

[0242] The user terminal receives the translation results and additional explanations sent from the server. The received data is temporarily stored in memory.

[0243] Step 12:

[0244] The user terminal displays the received translation results and additional explanations on the screen. The user reviews and understands the content.

[0245] Step 13:

[0246] Users can review the displayed translation results and additional explanations to accurately understand the foreign language content. The results, adjusted based on sentiment data, allow users to access information without experiencing stress.

[0247] (Example 2)

[0248] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0249] When using foreign language content, conventional translation systems have struggled to provide not only accurate translation results but also appropriate information tailored to the user's emotional state. Users often experience stress, which can hinder their true understanding of the translated content. Furthermore, a lack of specialized terminology or cultural background information can prevent complete comprehension. To address these challenges, this invention provides a translation system that takes user emotional data into consideration.

[0250] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for capturing text to be translated from a user terminal, means for sending the captured text to the server as a translation request, means for generating user sentiment data, means for sending the text and sentiment data to the server, means for translating the text using a generative model based on the received translation request, means for generating additional explanations related to the translated text, means for adjusting the translation result based on the user sentiment data, means for sending the translated text and additional explanations to the user terminal, and means for displaying the translation result received at the user terminal. As a result, the user can obtain accurate and easy-to-understand translation results, enabling a deeper understanding of foreign language content.

[0251] A "user terminal" is a device that a user directly operates and uses to send translation requests. Examples include smartphones, tablets, and personal computers.

[0252] "Text to be translated" refers to the text portion of content that the user wishes to have translated. This includes, for example, the text on a webpage, social media posts, and video descriptions.

[0253] "Capturing" means that the user's device takes in the specified text and saves it as digital data.

[0254] A "translation request" is a request to send captured text and necessary metadata to the server.

[0255] "Emotional data" is data generated by analyzing the user's facial expressions and voice. This allows the user's emotional state (e.g., stress level, happiness level) to be expressed as a numerical value or category.

[0256] "Generating" refers to the act of creating new information based on existing data. Examples include translating text or creating additional explanations.

[0257] A "server" is a central processing unit that receives requests sent from user terminals and performs the necessary processing.

[0258] A "generative model" is a machine learning model used for natural language processing. For example, it includes AI models that perform translation while analyzing the context of the text.

[0259] "Additional explanations" refer to more detailed information related to the translated text. For example, this may include definitions of technical terms or explanations of cultural context.

[0260] "Adjusting" means transforming the information being provided into an appropriate format. For example, this includes taking user sentiment data into consideration and revising the translation results to make them concise and easy to understand.

[0261] "Translation result" refers to the translated text generated based on the translation request.

[0262] "To display" means to visually present information on the screen of the user's terminal.

[0263] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional explanations when users access that content. This system is realized through the collaboration of a user terminal, a server, a generative AI model, and an emotion engine.

[0264] System configuration and operation

[0265] User terminal operation

[0266] The user's device captures the text and links of the content the user wishes to translate. This capture can be done using a dedicated app or browser extension. Examples include YouTube video descriptions, social media posts, and product descriptions on e-commerce sites. When the user clicks the "Translate" button, the captured text and links are sent to the server.

[0267] Furthermore, the user terminal has an emotion engine built in that analyzes the user's facial expressions and voice to generate emotion data. This emotion data is sent to the server and reflected in the translation results and additional explanations. The emotion engine uses analysis libraries such as OpenCV and DeepFace.

[0268] Server operation

[0269] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI model, and the translation process begins. Specifically, generative AI models such as OpenAI's GPT-4 (registered trademark) are used. The generative AI model analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[0270] Furthermore, the server receives sentiment data sent from the user's terminal and incorporates it into the translation results and additional explanations. For example, if it determines that the user is experiencing stress, the translation results are simplified and adjusted to be easier to understand.

[0271] The server sends the generated translation results and additional explanations to the user's terminal. In this process, contextual analysis is performed again to improve the accuracy of the translation, and relevant information is added to provide information that is easy for the user to understand.

[0272] Display of user actions and results

[0273] Users can receive and review the translation results and additional explanations sent from the server on their devices. This enables them to accurately and comprehensively understand foreign language content.

[0274] Specific example

[0275] Translation of YouTube video description

[0276] 1. User: Wants to translate a YouTube video description and selects the description.

[0277] 2. User terminal: Captures the selected description and sends a translation request to the server. It also analyzes the user's facial expressions and voice, generates emotion data, and sends it to the server.

[0278] 3. Server: Receives translation requests and translates the explanatory text using a generative AI model (e.g., GPT-4). Furthermore, it adjusts the translation result considering user sentiment data.

[0279] 4. Server: Based on the translation results, it generates additional explanations (definitions of technical terms and cultural background).

[0280] 5. Server: Sends the translation results and additional explanations to the user's terminal.

[0281] 6. User: Check the translation result and additional explanations displayed on the terminal and understand the content. Due to the result reflected by the emotional data, the user can receive information without feeling more stress.

[0282] Examples of prompt sentences to be input into the generative AI model

[0283] Examples of prompt sentences are as follows:

[0284] Please translate this text into Japanese:

[0285] "The original text captured here goes in"

[0286] This enables the user to understand and utilize foreign language content more accurately. In particular, by using the emotion engine, appropriate information is provided according to the user's emotional state, making it easier for the user to deeply understand the content. As a result, the user's knowledge becomes richer and the utilization value of foreign language content is significantly improved.

[0287] The flow of specific processing in Example 2 will be described using FIG. 13.

[0288] Step 1:

[0289] The user selects the content for which translation is desired.

[0290] As a specific operation, the user selects text such as the video description on YouTube or a post on SNS and clicks the "Translate" button.

[0291] Input: The text or link selected by the user

[0292] Output: Trigger for capture on the user terminal

[0293] Step 2:

[0294] The user terminal captures the selected text and saves it as text data.

[0295] As a specific operation, use a dedicated app or browser extension to capture the specified text as digital data.

[0296] Input: The text and links selected by the user

[0297] Output: The captured text data

[0298] Step 3:

[0299] The user terminal analyzes the user's facial expressions and voice using an emotion engine and generates emotion data.

[0300] As a specific operation, perform facial expression analysis of the user using OpenCV or DeepFace and quantify the emotional state.

[0301] Input: The facial expressions and voice of the user

[0302] Output: Emotion data

[0303] Step 4:

[0304] The user terminal sends the captured text data and emotion data to the server.

[0305] As a specific operation, use an HTTP POST request to send this data to the server.

[0306] Input: The captured text data, emotion data

[0307] Output: The translation request and emotion data sent to the server

[0308] Step 5:

[0309] The server inputs the received text data into a generative model to obtain a translation result.

[0310] Specifically, the process involves using a generative AI model such as OpenAI's GPT-4 to generate prompt text and then performing translation.

[0311] Input: Captured text data

[0312] Output: Translation result by generative model

[0313] Step 6:

[0314] Based on the translation results, the server generates additional explanations, such as definitions of relevant technical terms and background information.

[0315] Specifically, the system uses a pre-trained knowledge base to extract information relevant to the translation result.

[0316] Input: Translation result from generative model

[0317] Output: Additional explanation

[0318] Step 7:

[0319] The server adjusts the translation results based on the user's sentiment data.

[0320] As a specific action, if the stress level is high, the translation result will be revised to be more concise and easier to understand.

[0321] Input: Translation result, sentiment data

[0322] Output: Final translation result considering sentiment data

[0323] Step 8:

[0324] The server sends the final translation results and additional explanations to the user's terminal.

[0325] Specifically, the system uses an HTTP POST request to send data back to the user's terminal.

[0326] Input: Final translation result, additional explanation

[0327] Output: Data to be sent to the user terminal

[0328] Step 9:

[0329] The user checks the translation results and additional explanations on their device.

[0330] Specifically, the user's terminal displays the received translation results and additional explanations, which the user then reads and understands.

[0331] Input: Final translation result sent from the server, additional explanations

[0332] Output: User translation results and additional explanations

[0333] (Application Example 2)

[0334] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0335] In modern virtual stores, foreign language-speaking customers often have difficulty accurately understanding product descriptions and reviews. Even with accurate translations, comprehension can be challenging, especially when technical jargon or cultural context is involved. Furthermore, depending on the customer's emotional state, they may find the translation difficult to understand. This situation can potentially decrease customer purchasing intent.

[0336] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing text to be translated from a user terminal, means for sending the captured text to the server as a translation request, means for translating the text using a generative AI based on the received translation request, means for generating additional explanations related to the translated text, means for sending the translated text and additional explanations to the user terminal, means for analyzing the user's emotional data and adjusting the translation results and additional explanations considering the received emotional data, means for providing a user interface for display in a virtual store, and means for displaying the translation results received on the user terminal. This makes it possible for foreign language speaking customers to accurately understand product descriptions and reviews and receive information adjusted according to their emotional state.

[0337] A "user terminal" is a device that allows a user to capture text to be translated and send it to the server.

[0338] A "translation request" is a set of instructions and data sent from a user's terminal to the server for the purpose of translation.

[0339] "Generative AI" refers to artificial intelligence that analyzes input data and generates appropriate translation results or additional explanations.

[0340] "Additional explanations" refer to supplementary information such as definitions of technical terms and background information related to the translated text.

[0341] "Emotional data" refers to data about a user's emotional state, analyzed from their facial expressions and voice.

[0342] A "virtual store" is a virtual store that operates on the internet, providing an environment where customers can browse and purchase products online.

[0343] A "user interface" is a means of display and operation that allows the user to visually confirm translation results and additional explanations.

[0344] This invention is a language support system for enabling foreign language-speaking customers in virtual stores to accurately understand product descriptions and reviews. This system is realized through the collaboration of a user terminal, a server, a generative AI, and an emotion analysis engine.

[0345] System configuration and operation

[0346] User terminal operation

[0347] The user's device captures product descriptions and reviews that the customer wishes to have translated. This captured data is handled using a dedicated app or browser extension. The user's device also has a built-in sentiment analysis engine that analyzes the user's facial expressions and voice to generate sentiment data. This sentiment data is sent to a server and used to improve the translation results and additional explanations.

[0348] Server operation

[0349] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, and the translation process begins. The generative AI analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[0350] Furthermore, the server receives sentiment data sent from the user's terminal and incorporates it into the translation results and additional explanations. For example, if it determines that the user is feeling stressed, the translation results are made more concise and easier to understand. The server then sends the generated translation results and additional explanations to the user's terminal.

[0351] Display of user actions and results

[0352] Users can receive and review the translation results and additional explanations sent from the server on their device. This enables accurate and comprehensive understanding of foreign language content. The inclusion of sentiment data in the results allows users to receive information with less stress.

[0353] Hardware and software to be used

[0354] User terminal: Devices such as smartphones, smart glasses, and head-mounted displays.

[0355] Sentiment analysis engine: Microsoft® Azure® Face API and Google® Cloud Speech-to-Text API

[0356] Server: High-performance cloud server

[0357] Generative AI: Google Cloud Translation API, DeepL API

[0358] User interface: Web application or dedicated app

[0359] Specific example

[0360] For example, if a user wants to select a product description in a foreign language within a virtual store and request a translation, they select the description and click the "Translate" button. The user's device captures the selected description and sends it to the server. Simultaneously, the server analyzes the user's facial expressions and voice to generate sentiment data. Based on the received data, the server generates a translation result and additional explanations, adjusting them to take the sentiment data into consideration. The generated information is then sent to the user's device, where the user can review it.

[0361] Examples of prompts for generative AI models

[0362] "Translate the product description selected by the customer, provide definitions for relevant technical terms, and adjust the overall information based on sentiment data to present it in an easily understandable format."

[0363] Through concrete examples, you can understand how the system is implemented and its benefits. This will lead to a deeper understanding of customers and increased purchasing intent, as it will enable accurate comprehension of foreign language content and provide information tailored to their emotional state.

[0364] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0365] Step 1:

[0366] Users select the product description or review they want translated within the virtual store and click the translate button.

[0367] Input: Product description and reviews of the product selected by the customer.

[0368] Output: Captured text data

[0369] Specific operation: The user's terminal captures the text selected by the customer through a dedicated app or browser extension, and prepares for the next process.

[0370] Step 2:

[0371] The user's terminal sends the captured text data to the server as a translation request.

[0372] Input: Captured text data

[0373] Output: Translation request sent to the server

[0374] Specific operation: The user's terminal sends the captured text data to the server as an HTTP request.

[0375] Step 3:

[0376] The user's terminal analyzes the customer's facial expressions and voice to generate emotional data.

[0377] Input: Customer facial expression data and voice data

[0378] Output: Generated sentiment data

[0379] Specific operation: Using the emotion analysis engine installed on the user's device, data obtained from the camera and microphone is analyzed to generate emotion data.

[0380] Step 4:

[0381] The user's terminal sends the generated emotion data to the server.

[0382] Input: Generated emotion data

[0383] Output: Sentiment data sent to the server

[0384] Specific operation: The user terminal sends the generated emotion data to the server as an HTTP request.

[0385] Step 5:

[0386] The server receives the translation request and uses a generative AI to translate the text.

[0387] Input: Translation request sent to the server

[0388] Output: Generated translation result

[0389] Specific operation: The server uses generative AI such as the Google Cloud Translation API and the DeepL API to translate the received text data.

[0390] Step 6:

[0391] Based on the generated translation results, the server generates additional explanations, such as definitions of relevant technical terms and background information.

[0392] Input: Generated translation result

[0393] Output: Additional explanation

[0394] Specific operation: The server uses generative AI to generate supplementary information related to the translation result.

[0395] Step 7:

[0396] The server adjusts the translation results and additional explanations based on sentiment data received from the user's terminal.

[0397] Input: Translation result, additional explanation, sentiment data

[0398] Output: Adjusted translation results and additional explanations

[0399] Specific operation: The server's emotion engine analyzes the emotional data and, for example, adjusts it to a simple and easy-to-understand format for users who are feeling stressed.

[0400] Step 8:

[0401] The server sends the adjusted translation results and additional explanations to the user's terminal.

[0402] Input: Adjusted translation results and additional explanations

[0403] Output: Adjustment results sent to the user terminal

[0404] Specific operation: The server sends the adjusted translation results and additional explanations to the user's terminal as an HTTP response.

[0405] Step 9:

[0406] The user's terminal displays the adjusted translation results and additional explanations received.

[0407] Input: Adjustment results sent to the user terminal

[0408] Output: Displayed adjustment results

[0409] Specific operation: The user's device displays the received translation results and additional explanations through a web application or dedicated app.

[0410] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0411] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0412] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0413] [Second Embodiment]

[0414] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0415] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0416] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0417] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0418] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0419] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0420] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0421] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0422] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0423] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0424] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0425] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0426] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional explanations when users access that content. This system is realized through the collaboration of a user terminal, a server, and a generative AI.

[0427] System configuration and operation

[0428] User terminal operation

[0429] The user's device captures text and links of content the user wishes to translate. This captured data can be processed using a dedicated app or browser extension. Examples of target text on the internet include YouTube video descriptions, social media posts, and product descriptions on e-commerce sites. When the user clicks the "Translate" button, the captured text and links are sent to the server.

[0430] Server operation

[0431] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, and the translation process begins. The generative AI analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[0432] The server sends the generated translation results and additional explanations to the user's terminal. During this process, contextual analysis is performed to improve translation accuracy, and relevant information is added to provide information that is easy for the user to understand.

[0433] Display of user actions and results

[0434] Users can receive and review the translation results and additional explanations sent from the server on their devices. This enables them to accurately and comprehensively understand foreign language content.

[0435] Specific example

[0436] Translation of YouTube video description

[0437] 1. User: Wants to translate the YouTube video description and selects the description.

[0438] 2. User terminal: Captures the selected description and sends a translation request to the server.

[0439] 3. Server: Receives translation requests and translates the explanatory text using generative AI. Based on the translation results, it generates additional explanations (e.g., definitions of technical terms and cultural background).

[0440] 4. Server: Sends the translation results and additional explanations to the user's terminal.

[0441] 5. User: Review the translation results and additional explanations displayed on the device and understand the content.

[0442] The system of this invention enables users to understand and utilize foreign language content more accurately. In particular, the inclusion of additional explanations based on specialized terminology and cultural background allows users to gain a deeper understanding of the content. This enriches the user's knowledge and significantly enhances the value of utilizing foreign language content.

[0443] The following describes the processing flow.

[0444] Step 1:

[0445] Users select text or links to be translated. This is done by selecting portions of online content, such as YouTube video descriptions, social media posts, or product descriptions on e-commerce sites.

[0446] Step 2:

[0447] The user clicks the "Translate" button and takes action to submit a translation request.

[0448] Step 3:

[0449] The user's terminal captures the selected text or links to be translated. Specifically, it extracts the text data from the selected portion and saves it to memory.

[0450] Step 4:

[0451] The user terminal generates a translation request containing the captured text data and sends this request to the server. The request includes the captured text data and associated metadata.

[0452] Step 5:

[0453] The server receives translation requests sent from the user's terminal. These requests contain captured text data to be translated.

[0454] Step 6:

[0455] The server analyzes the received text data and prepares it for transmission to the generative AI. This step involves initial analysis to understand the content of the text.

[0456] Step 7:

[0457] The server uses generative AI to analyze the text to be translated and generate a context-based, highly accurate translation. The generative AI translates the text considering sentence structure, context, and the meaning of terms.

[0458] Step 8:

[0459] The server generates additional explanations related to the translated text. These include definitions of technical terms, cultural context, and related information. The generated additional explanations help users gain a deeper understanding of the translated text.

[0460] Step 9:

[0461] The server sends the completed translation and additional explanations to the user's terminal. In this step, the translation and related information are packaged and sent to the user's terminal.

[0462] Step 10:

[0463] The user terminal receives the translation results and additional explanations sent from the server. The received data is temporarily stored in memory.

[0464] Step 11:

[0465] The user terminal displays the received translation results and additional explanations on the screen. The user reviews and understands the content.

[0466] Step 12:

[0467] Users can review the displayed translation results and additional explanations to accurately understand the foreign language content.

[0468] (Example 1)

[0469] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0470] When using foreign language content, users need not only accurate translations but also context and background information to deeply understand the content. However, conventional translation systems often only provide translation results, making it difficult for users to understand the intent and details of the content. Furthermore, the lack of additional explanations regarding specialized terminology and cultural background information means that the system cannot adequately support user understanding.

[0471] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0472] In this invention, the server includes means for selecting content to be translated from a user terminal, means for capturing the selected content, means for sending the captured content to the server as a translation request, means for translating the text using a generative AI model based on the received translation request, means for generating additional information related to the translated text, means for sending the translated text and additional information to the user terminal, and means for displaying the received translation results and additional information on the user terminal. This provides not only accurate translations but also additional explanations including context, definitions of technical terms, and cultural background information, enabling the user to gain a deeper understanding of the foreign language content.

[0473] A "user terminal" refers to a device used by a user to access content on the internet, such as a personal computer, smartphone, or tablet.

[0474] "Content" refers to all forms of information that users utilize, primarily including text data such as video descriptions, social media posts, and product descriptions.

[0475] "Capturing" refers to the operation of selecting content displayed on a user's device and capturing that data.

[0476] A "server" refers to a computer system that receives data sent from user terminals and performs data processing and translation processing using generative AI models.

[0477] A "translation request" refers to a data packet sent from a user's terminal to the server requesting translation.

[0478] A "generative AI model" refers to an artificial intelligence algorithm that analyzes received text data and generates appropriate translations and additional information.

[0479] "Contextual analysis" refers to a technical process that analyzes the content and surrounding information of text to create more accurate and appropriate translations.

[0480] "Additional information" refers to definitions of technical terms and cultural background information related to the translated text, which helps users to gain a deeper understanding of the content.

[0481] Modes for carrying out the invention

[0482] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional information when users access it. This system is realized through the collaboration of a user terminal, a server, and a generative AI.

[0483] User terminal operation

[0484] The user's device is used to select the content they wish to translate. For example, when a user selects a YouTube video description, a social media post, or a product description from an e-commerce site, the user's device captures this content using a dedicated app or browser extension. When the user clicks the "Translate" button, the captured text is sent to the server.

[0485] Server operation

[0486] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, such as OpenAI's GPT model, and translation processing is performed. The generative AI analyzes the context of the text and generates appropriate translation results. Furthermore, based on the translation results, it generates additional information such as definitions of technical terms and cultural background information.

[0487] Display of user actions and results

[0488] The user terminal receives the translation results and additional information sent from the server and displays them to the user. This allows the user to accurately and fully understand the foreign language content.

[0489] Specific example

[0490] Translation of YouTube video description

[0491] 1. User: Decides to translate a YouTube video description and selects the description.

[0492] 2. User terminal: Captures the description text and sends a translation request to the server.

[0493] 3. Server: Receives requests and translates the description using generative AI (e.g., OpenAI GPT model). Based on the translation results, it generates additional information (e.g., definitions of technical terms and cultural background).

[0494] 4. Server: Sends the translation results and additional information to the user's terminal.

[0495] 5. User: Review the translation results and additional information displayed on the device to gain a deeper understanding of the content.

[0496] Example of a prompt

[0497] Translation target: "This is a sample description of a YouTube video."

[0498] Prompt to the generating AI: "Translate this text into Japanese and provide additional information relevant to the content, including any cultural or technical terms."

[0499] This system will enable users to understand and utilize foreign language content more accurately. In particular, by providing additional information based on specialized terminology and cultural background, it is expected that users' knowledge will be enriched, and the value of using foreign language content will be significantly enhanced.

[0500] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0501] Step 1:

[0502] The user selects the content they want translated. For example, they might choose a YouTube video description or a social media post. This action inputs the selected text data into the user's device.

[0503] Step 2:

[0504] The user's device captures selected content and sends it to the server. The captured data includes text content and metadata (e.g., URL, posting date and time). This data is sent to the server as captured text.

[0505] Specific actions:

[0506] When a user clicks the "Translate" button, the browser extension automatically extracts the text from the page and sends it to the server.

[0507] Step 3:

[0508] The server analyzes the received text data and sends a prompt to the generative AI. The analysis includes understanding the context of the received text. The server sends the generative AI model the prompt: "Translate the following text: 'This is a sample description of a YouTube video.' and provide additional context information."

[0509] Specific actions:

[0510] The server analyzes the received data and generates prompt messages to send to the generative AI.

[0511] Step 4:

[0512] The generative AI receives a prompt and generates an appropriate translation and additional explanations. The generative AI performs contextual analysis to improve translation accuracy and generates the text translation along with additional information including definitions of technical terms and background information. This result is then returned to the server.

[0513] Specific actions:

[0514] The generative AI translates "This is a sample description of a YouTube video." as "This is a sample description of a YouTube video." and generates additional information such as "YouTube is a video sharing service, and video descriptions typically contain information about the content and purpose of the video."

[0515] Step 5:

[0516] The server sends the translation results and additional explanations received from the generative AI to the user's terminal. In this process, the server converts the generated results into a format that is easy for the user to understand.

[0517] Specific actions:

[0518] The server sends the translation results and additional explanations to the user's terminal in JSON format. The JSON data includes the translated text and additional information.

[0519] Step 6:

[0520] The user's terminal displays the data received from the server. The user can check the translation results and additional explanations on their terminal to deepen their understanding of the foreign language content.

[0521] Specific actions:

[0522] The browser extension displays the received data and shows information such as, "Translation result: This is a sample description for a YouTube video. Additional information: YouTube is a video sharing service, and video descriptions typically include information about the content and purpose."

[0523] In this way, the system performs a series of processes to help users accurately understand foreign language content.

[0524] (Application Example 1)

[0525] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0526] Traditional translation systems simply convert text into another language, often failing to provide information to deepen understanding of specialized terminology and cultural context. As a result, users often struggled to fully understand translated content, especially when it contained specialized information. Furthermore, a lack of definitions and background information for specialized terms in certain fields created a high barrier to user access to the content.

[0527] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0528] In this invention, the server includes means for acquiring content to be translated from a user terminal, means for sending the acquired content to the server as a translation request, means for translating the text using a generative AI based on the received translation request, means for generating additional explanations related to the translated text, means for sending the translated text and additional explanations to the user terminal, and means for displaying the received translation results and additional explanations on the user terminal. This makes it possible for users to understand foreign language content more deeply and to significantly improve the value of content, especially content containing specialized information and cultural background.

[0529] A "user terminal" is a device used by a user to interact with content and input and display information.

[0530] "Acquiring" means gathering specific information or data from an external source and importing it into the local environment.

[0531] "Content" refers to a unit of information, provided in various forms such as text, images, videos, and audio.

[0532] A "translation request" is a request that a user sends to a server to translate specific content into another language.

[0533] A "server" is a computer system that processes requests from client devices on a network and provides information.

[0534] "Generative AI" refers to artificial intelligence models that use natural language processing and machine learning to generate and transform text.

[0535] "Translating text" means converting text written in one language into another language.

[0536] "Additional explanations" refer to supplementary information such as definitions of technical terms and cultural context related to the translated text.

[0537] "To send" means to move data or information from a source to a destination over a network.

[0538] "To display" means to provide information to the user visually.

[0539] Modes for carrying out the invention

[0540] The embodiments for carrying out this invention will be described in detail below.

[0541] System configuration and operation

[0542] User terminal operation

[0543] The user's device has a means of obtaining the content the user wishes to translate. For example, the user enters the URL of a YouTube video via a smartphone application. At this time, the application uses the YouTube API to obtain the video description and comments. The obtained text is sent to the server.

[0544] Server operation

[0545] The server receives translation requests sent from user terminals. These requests contain the text to be translated. The server uses generative AI to translate this text. Specifically, the server leverages a generative AI model to generate a draft translation. It also generates additional explanations related to the translated text. These explanations include definitions of technical terms and information about cultural background. This information is also derived from the generative AI model.

[0546] Display translation results and explanations

[0547] The server sends the generated translation results and additional explanations to the user's terminal. The user's terminal displays the received translation results and explanations to the user. This allows the user to understand the foreign language content more completely.

[0548] Hardware and software to be used

[0549] Hardware: Smartphone (iOS or Android), cloud server

[0550] Software: YouTube API, OpenAI GPT model, Flask (Python application framework)

[0551] Data processing and calculations

[0552] 1. User terminal: The video description and comments are retrieved from the YouTube API via the video URL entered by the user.

[0553] 2. Server: The server translates the received text using a generative AI (e.g., the OpenAI GPT model) and generates additional explanations. The generated information is processed based on context and provided to the user in the most optimal form.

[0554] 3. Communication: The generated data (translation results and additional explanations) is sent to the user's terminal via the internet.

[0555] Specific example

[0556] Suppose a user watches a YouTube video in a foreign language like this:

[0557] Title: "Understanding Quantum Computing"

[0558] Caption: "In this video, we'll explore the basics of quantum computing and its potential applications."

[0559] A user wants to translate a video description and enters the URL into the "DeepTranslate" app. The app then retrieves the description via the YouTube API and sends it to the server. On the server side, a generative AI (e.g., the OpenAI GPT model) translates it, generating additional definitions of technical terms and explanations of cultural context. For example, it might use prompts like the following:

[0560] Example of a prompt:

[0561] Translate the following text to Japanese and provide additional explanations:

[0562] In this video, we'll explore the basics of quantum computing and its potential applications.

[0563] Finally, the generated translations and explanations are sent to the user's smartphone, allowing them to easily review them.

[0564] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0565] Step 1:

[0566] On the user's device, the user enters specific content (e.g., a YouTube video URL). This causes the user's device to send a request to the YouTube API to retrieve the video description and comments from that URL.

[0567] Input: Video URL entered by the user

[0568] Output: Retrieved video description and comments

[0569] Step 2:

[0570] The user's device sends the video description and comments, retrieved from the YouTube API, to the server as a translation request.

[0571] Input: Retrieved video description and comments

[0572] Output: Text data as a translation request

[0573] Step 3:

[0574] The server analyzes the received translation request and sends a prompt to the generative AI for translation. A generative AI model is used to generate context-aware translations.

[0575] Input: Text data as a translation request

[0576] Output: Translated text

[0577] Step 4:

[0578] The server generates additional explanations related to the translated text. Generative AI is used to create supplementary explanations that include definitions of technical terms and information about cultural background.

[0579] Input: Translated text

[0580] Output: Additional explanation

[0581] Step 5:

[0582] The server sends the generated translation results and additional explanations to the user's terminal.

[0583] Input: Translated text and additional explanations

[0584] Output: Data sent to the user terminal

[0585] Step 6:

[0586] The user's device displays the received translation results and additional explanations. This makes it easier for the user to understand the content.

[0587] Input: Translation results and additional explanations sent from the server.

[0588] Output: Translation results and explanations that users can visually verify.

[0589] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0590] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional explanations when users access that content. This system is realized through the collaboration of a user terminal, a server, a generative AI, and an emotion engine.

[0591] System configuration and operation

[0592] User terminal operation

[0593] The user's device captures text and links of content the user wishes to translate. This captured data can be processed using a dedicated app or browser extension. Examples of target text on the internet include YouTube video descriptions, social media posts, and product descriptions on e-commerce sites. When the user clicks the "Translate" button, the captured text and links are sent to the server.

[0594] Furthermore, the user terminal has an emotion engine built in that analyzes the user's facial expressions and voice to generate emotion data. This emotion data is sent to the server and used to improve translation results and additional explanations.

[0595] Server operation

[0596] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, and the translation process begins. The generative AI analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[0597] Furthermore, the server receives emotional data sent from the user's terminal and incorporates it into the translation results and additional explanations. For example, if it is determined that the user is experiencing stress, the translation results are made more concise and easier to understand.

[0598] The server sends the generated translation results and additional explanations to the user's terminal. During this process, contextual analysis is performed to improve translation accuracy, and relevant information is added to provide information that is easy for the user to understand.

[0599] Display of user actions and results

[0600] Users can receive and review the translation results and additional explanations sent from the server on their devices. This enables them to accurately and comprehensively understand foreign language content.

[0601] Specific example

[0602] Translation of YouTube video description

[0603] 1. User: Wants to translate the YouTube video description and selects the description.

[0604] 2. User terminal: Captures the selected description and sends a translation request to the server. It also analyzes the user's facial expressions and voice, generates emotion data, and sends it to the server.

[0605] 3. Server: Receives translation requests and translates the explanatory text using generative AI. Furthermore, it adjusts the translation result while considering the user's sentiment data.

[0606] 4. Server: Based on the translation results, it generates additional explanations (definitions of technical terms and cultural background).

[0607] 5. Server: Sends the translation results and additional explanations to the user's terminal.

[0608] 6. User: Review the translation results and additional explanations displayed on the device to understand the content. The inclusion of sentiment data allows users to receive information with less stress.

[0609] The system of this invention enables users to understand and utilize foreign language content more accurately. In particular, by using an emotion engine, appropriate information is provided according to the user's emotional state, making it easier for the user to deeply understand the content. As a result, the user's knowledge is enriched, and the value of using foreign language content is greatly enhanced.

[0610] The following describes the processing flow.

[0611] Step 1:

[0612] Users select text or links to be translated. This includes YouTube video descriptions, social media posts, and product descriptions on e-commerce sites.

[0613] Step 2:

[0614] The user clicks the "Translate" button to submit a translation request.

[0615] Step 3:

[0616] The user's device captures the selected text or links to be translated. Specifically, it extracts the text data from the selected portion and saves it to memory.

[0617] Step 4:

[0618] The user terminal generates a translation request containing the captured text data and sends this request to the server. The request includes the captured text data and associated metadata.

[0619] Step 5:

[0620] The user terminal uses an emotion engine to analyze the user's facial expressions and voice, generating emotion data in real time. This emotion data is also sent to the server.

[0621] Step 6:

[0622] The server receives translation requests and sentiment data sent from the user's terminal. This allows the server to understand both the information needed for translation and the user's emotional state.

[0623] Step 7:

[0624] The server uses generative AI to translate text based on the received translation request. The generative AI performs contextual analysis and generates an appropriate translation.

[0625] Step 8:

[0626] The server generates additional explanations related to the translated text, including definitions of technical terms and background information. If the sentiment data indicates "high stress," the additional explanations are adjusted to be concise and easy to understand.

[0627] Step 9:

[0628] The server adjusts the translation results and additional explanations based on sentiment data, optimizing them to suit the user.

[0629] Step 10:

[0630] The server sends the final translation and any adjusted additional explanations to the user's terminal.

[0631] Step 11:

[0632] The user terminal receives the translation results and additional explanations sent from the server. The received data is temporarily stored in memory.

[0633] Step 12:

[0634] The user terminal displays the received translation results and additional explanations on the screen. The user reviews and understands the content.

[0635] Step 13:

[0636] Users can review the displayed translation results and additional explanations to accurately understand the foreign language content. The results, adjusted based on sentiment data, allow users to access information without experiencing stress.

[0637] (Example 2)

[0638] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0639] When using foreign language content, conventional translation systems have struggled to provide not only accurate translation results but also appropriate information tailored to the user's emotional state. Users often experience stress, which can hinder their true understanding of the translated content. Furthermore, a lack of specialized terminology or cultural background information can prevent complete comprehension. To address these challenges, this invention provides a translation system that takes user emotional data into consideration.

[0640] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for capturing text to be translated from a user terminal, means for sending the captured text to the server as a translation request, means for generating user sentiment data, means for sending the text and sentiment data to the server, means for translating the text using a generative model based on the received translation request, means for generating additional explanations related to the translated text, means for adjusting the translation result based on the user sentiment data, means for sending the translated text and additional explanations to the user terminal, and means for displaying the translation result received at the user terminal. As a result, the user can obtain accurate and easy-to-understand translation results, enabling a deeper understanding of foreign language content.

[0641] A "user terminal" is a device that a user directly operates and uses to send translation requests. Examples include smartphones, tablets, and personal computers.

[0642] "Text to be translated" refers to the text portion of content that the user wishes to have translated. This includes, for example, the text on a webpage, social media posts, and video descriptions.

[0643] "Capturing" means that the user's device takes in the specified text and saves it as digital data.

[0644] A "translation request" is a request to send captured text and necessary metadata to the server.

[0645] "Emotional data" is data generated by analyzing the user's facial expressions and voice. This allows the user's emotional state (e.g., stress level, happiness level) to be expressed as a numerical value or category.

[0646] "Generating" refers to the act of creating new information based on existing data. Examples include translating text or creating additional explanations.

[0647] A "server" is a central processing unit that receives requests sent from user terminals and performs the necessary processing.

[0648] A "generative model" is a machine learning model used for natural language processing. For example, it includes AI models that perform translation while analyzing the context of the text.

[0649] "Additional explanations" refer to more detailed information related to the translated text. For example, this may include definitions of technical terms or explanations of cultural context.

[0650] "Adjusting" means transforming the information being provided into an appropriate format. For example, this includes taking user sentiment data into consideration and revising the translation results to make them concise and easy to understand.

[0651] "Translation result" refers to the translated text generated based on the translation request.

[0652] "To display" means to visually present information on the screen of the user's terminal.

[0653] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional explanations when users access that content. This system is realized through the collaboration of a user terminal, a server, a generative AI model, and an emotion engine.

[0654] System configuration and operation

[0655] User terminal operation

[0656] The user's device captures the text and links of the content the user wishes to translate. This capture can be done using a dedicated app or browser extension. Examples include YouTube video descriptions, social media posts, and product descriptions on e-commerce sites. When the user clicks the "Translate" button, the captured text and links are sent to the server.

[0657] Furthermore, the user terminal has an emotion engine built in that analyzes the user's facial expressions and voice to generate emotion data. This emotion data is sent to the server and reflected in the translation results and additional explanations. The emotion engine uses analysis libraries such as OpenCV and DeepFace.

[0658] Server operation

[0659] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI model, and the translation process begins. Specifically, generative AI models such as OpenAI's GPT-4 are used. The generative AI model analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[0660] Furthermore, the server receives sentiment data sent from the user's terminal and incorporates it into the translation results and additional explanations. For example, if it determines that the user is experiencing stress, the translation results are simplified and adjusted to be easier to understand.

[0661] The server sends the generated translation results and additional explanations to the user's terminal. In this process, contextual analysis is performed again to improve the accuracy of the translation, and relevant information is added to provide information that is easy for the user to understand.

[0662] Display of user actions and results

[0663] Users can receive and review the translation results and additional explanations sent from the server on their devices. This enables them to accurately and comprehensively understand foreign language content.

[0664] Specific example

[0665] Translation of YouTube video description

[0666] 1. User: Wants to translate a YouTube video description and selects the description.

[0667] 2. User terminal: Captures the selected description and sends a translation request to the server. It also analyzes the user's facial expressions and voice, generates emotion data, and sends it to the server.

[0668] 3. Server: Receives translation requests and translates the descriptions using generative AI models (e.g., GPT-4). Furthermore, it adjusts the translation results considering user sentiment data.

[0669] 4. Server: Based on the translation results, it generates additional explanations (definitions of technical terms and cultural background).

[0670] 5. Server: Sends the translation results and additional explanations to the user's terminal.

[0671] 6. User: Review the translation results and additional explanations displayed on the device to understand the content. The inclusion of sentiment data allows users to receive information with less stress.

[0672] Examples of prompts to input into a generative AI model

[0673] Examples of prompt statements are as follows:

[0674] Please translate this text into Japanese:

[0675] "The original text of the captured image goes here."

[0676] This enables users to understand and utilize foreign language content more accurately. In particular, by using an emotion engine, appropriate information is provided according to the user's emotional state, making it easier for users to deeply understand the content. As a result, users' knowledge is enriched, and the value of using foreign language content is greatly enhanced.

[0677] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0678] Step 1:

[0679] The user selects the content they wish to translate.

[0680] Specifically, the user selects text such as a YouTube video description or a social media post and clicks the "Translate" button.

[0681] Input: User-selected text or link

[0682] Output: Capture trigger on the user terminal

[0683] Step 2:

[0684] The user's terminal captures the selected text and saves it as text data.

[0685] Specifically, it involves using a dedicated app or browser extension to capture specified text as digital data.

[0686] Input: User-selected text or link

[0687] Output: Captured text data

[0688] Step 3:

[0689] The user's device uses an emotion engine to analyze the user's facial expressions and voice, and generates emotion data.

[0690] Specifically, the system uses OpenCV and DeepFace to analyze the user's facial expressions and quantify their emotional state.

[0691] Input: User's facial expressions and voice

[0692] Output: Sentiment data

[0693] Step 4:

[0694] The user's device sends captured text data and sentiment data to the server.

[0695] Specifically, this data is sent to the server using an HTTP POST request.

[0696] Input: Captured text data, sentiment data

[0697] Output: Translation requests and sentiment data sent to the server

[0698] Step 5:

[0699] The server inputs the received text data into a generative model to obtain a translation result.

[0700] Specifically, the process involves using a generative AI model such as OpenAI's GPT-4 to generate prompt text and then performing translation.

[0701] Input: Captured text data

[0702] Output: Translation result by generative model

[0703] Step 6:

[0704] Based on the translation results, the server generates additional explanations, such as definitions of relevant technical terms and background information.

[0705] Specifically, the system uses a pre-trained knowledge base to extract information relevant to the translation result.

[0706] Input: Translation result from generative model

[0707] Output: Additional explanation

[0708] Step 7:

[0709] The server adjusts the translation results based on the user's sentiment data.

[0710] As a specific action, if the stress level is high, the translation result will be revised to be more concise and easier to understand.

[0711] Input: Translation result, sentiment data

[0712] Output: Final translation result considering sentiment data

[0713] Step 8:

[0714] The server sends the final translation results and additional explanations to the user's terminal.

[0715] Specifically, the system uses an HTTP POST request to send data back to the user's terminal.

[0716] Input: Final translation result, additional explanation

[0717] Output: Data to be sent to the user terminal

[0718] Step 9:

[0719] The user checks the translation results and additional explanations on their device.

[0720] Specifically, the user's terminal displays the received translation results and additional explanations, which the user then reads and understands.

[0721] Input: Final translation result sent from the server, additional explanations

[0722] Output: User translation results and additional explanations

[0723] (Application Example 2)

[0724] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0725] In modern virtual stores, foreign language-speaking customers often have difficulty accurately understanding product descriptions and reviews. Even with accurate translations, comprehension can be challenging, especially when technical jargon or cultural context is involved. Furthermore, depending on the customer's emotional state, they may find the translation difficult to understand. This situation can potentially decrease customer purchasing intent.

[0726] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing text to be translated from a user terminal, means for sending the captured text to the server as a translation request, means for translating the text using a generative AI based on the received translation request, means for generating additional explanations related to the translated text, means for sending the translated text and additional explanations to the user terminal, means for analyzing the user's emotional data and adjusting the translation results and additional explanations considering the received emotional data, means for providing a user interface for display in a virtual store, and means for displaying the translation results received on the user terminal. This makes it possible for foreign language speaking customers to accurately understand product descriptions and reviews and receive information adjusted according to their emotional state.

[0727] A "user terminal" is a device that allows a user to capture text to be translated and send it to the server.

[0728] A "translation request" is a set of instructions and data sent from a user's terminal to the server for the purpose of translation.

[0729] "Generative AI" refers to artificial intelligence that analyzes input data and generates appropriate translation results or additional explanations.

[0730] "Additional explanations" refer to supplementary information such as definitions of technical terms and background information related to the translated text.

[0731] "Emotional data" refers to data about a user's emotional state, analyzed from their facial expressions and voice.

[0732] A "virtual store" is a virtual store that operates on the internet, providing an environment where customers can browse and purchase products online.

[0733] A "user interface" is a means of display and operation that allows the user to visually confirm translation results and additional explanations.

[0734] This invention is a language support system for enabling foreign language-speaking customers in virtual stores to accurately understand product descriptions and reviews. This system is realized through the collaboration of a user terminal, a server, a generative AI, and an emotion analysis engine.

[0735] System configuration and operation

[0736] User terminal operation

[0737] The user's device captures product descriptions and reviews that the customer wishes to have translated. This captured data is handled using a dedicated app or browser extension. The user's device also has a built-in sentiment analysis engine that analyzes the user's facial expressions and voice to generate sentiment data. This sentiment data is sent to a server and used to improve the translation results and additional explanations.

[0738] Server operation

[0739] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, and the translation process begins. The generative AI analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[0740] Furthermore, the server receives sentiment data sent from the user's terminal and incorporates it into the translation results and additional explanations. For example, if it determines that the user is feeling stressed, the translation results are made more concise and easier to understand. The server then sends the generated translation results and additional explanations to the user's terminal.

[0741] Display of user actions and results

[0742] Users can receive and review the translation results and additional explanations sent from the server on their device. This enables accurate and comprehensive understanding of foreign language content. The inclusion of sentiment data in the results allows users to receive information with less stress.

[0743] Hardware and software to be used

[0744] User terminal: Devices such as smartphones, smart glasses, and head-mounted displays.

[0745] Sentiment analysis engines: Microsoft Azure's Face API and Google Cloud's Speech-to-Text API

[0746] Server: High-performance cloud server

[0747] Generative AI: Google Cloud Translation API, DeepL API

[0748] User interface: Web application or dedicated app

[0749] Specific example

[0750] For example, if a user wants to select a product description in a foreign language within a virtual store and request a translation, they select the description and click the "Translate" button. The user's device captures the selected description and sends it to the server. Simultaneously, the server analyzes the user's facial expressions and voice to generate sentiment data. Based on the received data, the server generates a translation result and additional explanations, adjusting them to take the sentiment data into consideration. The generated information is then sent to the user's device, where the user can review it.

[0751] Examples of prompts for generative AI models

[0752] "Translate the product description selected by the customer, provide definitions for relevant technical terms, and adjust the overall information based on sentiment data to present it in an easily understandable format."

[0753] Through concrete examples, you can understand how the system is implemented and its benefits. This will lead to a deeper understanding of customers and increased purchasing intent, as it will enable accurate comprehension of foreign language content and provide information tailored to their emotional state.

[0754] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0755] Step 1:

[0756] Users select the product description or review they want translated within the virtual store and click the translate button.

[0757] Input: Product description and reviews of the product selected by the customer.

[0758] Output: Captured text data

[0759] Specific operation: The user's terminal captures the text selected by the customer through a dedicated app or browser extension, and prepares for the next process.

[0760] Step 2:

[0761] The user's terminal sends the captured text data to the server as a translation request.

[0762] Input: Captured text data

[0763] Output: Translation request sent to the server

[0764] Specific operation: The user's terminal sends the captured text data to the server as an HTTP request.

[0765] Step 3:

[0766] The user's terminal analyzes the customer's facial expressions and voice to generate emotional data.

[0767] Input: Customer facial expression data and voice data

[0768] Output: Generated emotion data

[0769] Specific operation: Using the emotion analysis engine installed on the user's device, data obtained from the camera and microphone is analyzed to generate emotion data.

[0770] Step 4:

[0771] The user's terminal sends the generated emotion data to the server.

[0772] Input: Generated emotion data

[0773] Output: Sentiment data sent to the server

[0774] Specific operation: The user terminal sends the generated emotion data to the server as an HTTP request.

[0775] Step 5:

[0776] The server receives the translation request and uses a generative AI to translate the text.

[0777] Input: Translation request sent to the server

[0778] Output: Generated translation result

[0779] Specific operation: The server uses generative AI such as the Google Cloud Translation API and the DeepL API to translate the received text data.

[0780] Step 6:

[0781] Based on the generated translation results, the server generates additional explanations, such as definitions of relevant technical terms and background information.

[0782] Input: Generated translation result

[0783] Output: Additional explanation

[0784] Specific operation: The server uses generative AI to generate supplementary information related to the translation result.

[0785] Step 7:

[0786] The server adjusts the translation results and additional explanations based on sentiment data received from the user's terminal.

[0787] Input: Translation result, additional explanation, sentiment data

[0788] Output: Adjusted translation results and additional explanations

[0789] Specific operation: The server's emotion engine analyzes the emotional data and, for example, adjusts it to a simple and easy-to-understand format for users who are feeling stressed.

[0790] Step 8:

[0791] The server sends the adjusted translation results and additional explanations to the user's terminal.

[0792] Input: Adjusted translation results and additional explanations

[0793] Output: Adjustment results sent to the user terminal

[0794] Specific operation: The server sends the adjusted translation results and additional explanations to the user's terminal as an HTTP response.

[0795] Step 9:

[0796] The user's terminal displays the adjusted translation results and additional explanations received.

[0797] Input: Adjustment results sent to the user terminal

[0798] Output: Displayed adjustment results

[0799] Specific operation: The user's device displays the received translation results and additional explanations through a web application or dedicated app.

[0800] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0801] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0802] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0803] [Third Embodiment]

[0804] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0805] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0806] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0807] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0808] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0809] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0810] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0811] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0812] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0813] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0814] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0815] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0816] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional explanations when users access that content. This system is realized through the collaboration of a user terminal, a server, and a generative AI.

[0817] System configuration and operation

[0818] User terminal operation

[0819] The user's device captures text and links of content the user wishes to translate. This captured data can be processed using a dedicated app or browser extension. Examples of target text on the internet include YouTube video descriptions, social media posts, and product descriptions on e-commerce sites. When the user clicks the "Translate" button, the captured text and links are sent to the server.

[0820] Server operation

[0821] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, and the translation process begins. The generative AI analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[0822] The server sends the generated translation results and additional explanations to the user's terminal. During this process, contextual analysis is performed to improve translation accuracy, and relevant information is added to provide information that is easy for the user to understand.

[0823] Display of user actions and results

[0824] Users can receive and review the translation results and additional explanations sent from the server on their devices. This enables them to accurately and comprehensively understand foreign language content.

[0825] Specific example

[0826] Translation of YouTube video description

[0827] 1. User: Wants to translate the YouTube video description and selects the description.

[0828] 2. User terminal: Captures the selected description and sends a translation request to the server.

[0829] 3. Server: Receives translation requests and translates the explanatory text using generative AI. Based on the translation results, it generates additional explanations (e.g., definitions of technical terms and cultural background).

[0830] 4. Server: Sends the translation results and additional explanations to the user's terminal.

[0831] 5. User: Review the translation results and additional explanations displayed on the device and understand the content.

[0832] The system of this invention enables users to understand and utilize foreign language content more accurately. In particular, the inclusion of additional explanations based on specialized terminology and cultural background allows users to gain a deeper understanding of the content. This enriches the user's knowledge and significantly enhances the value of utilizing foreign language content.

[0833] The following describes the processing flow.

[0834] Step 1:

[0835] Users select text or links to be translated. This is done by selecting portions of online content, such as YouTube video descriptions, social media posts, or product descriptions on e-commerce sites.

[0836] Step 2:

[0837] The user clicks the "Translate" button and takes action to submit a translation request.

[0838] Step 3:

[0839] The user's terminal captures the selected text or links to be translated. Specifically, it extracts the text data from the selected portion and saves it to memory.

[0840] Step 4:

[0841] The user terminal generates a translation request containing the captured text data and sends this request to the server. The request includes the captured text data and associated metadata.

[0842] Step 5:

[0843] The server receives translation requests sent from the user's terminal. These requests contain captured text data to be translated.

[0844] Step 6:

[0845] The server analyzes the received text data and prepares it for transmission to the generative AI. This step involves initial analysis to understand the content of the text.

[0846] Step 7:

[0847] The server uses generative AI to analyze the text to be translated and generate a context-based, highly accurate translation. The generative AI translates the text considering sentence structure, context, and the meaning of terms.

[0848] Step 8:

[0849] The server generates additional explanations related to the translated text. These include definitions of technical terms, cultural context, and related information. The generated additional explanations help users gain a deeper understanding of the translated text.

[0850] Step 9:

[0851] The server sends the completed translation and additional explanations to the user's terminal. In this step, the translation and related information are packaged and sent to the user's terminal.

[0852] Step 10:

[0853] The user terminal receives the translation results and additional explanations sent from the server. The received data is temporarily stored in memory.

[0854] Step 11:

[0855] The user terminal displays the received translation results and additional explanations on the screen. The user reviews and understands the content.

[0856] Step 12:

[0857] Users can review the displayed translation results and additional explanations to accurately understand the foreign language content.

[0858] (Example 1)

[0859] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0860] When using foreign language content, users need not only accurate translations but also context and background information to deeply understand the content. However, conventional translation systems often only provide translation results, making it difficult for users to understand the intent and details of the content. Furthermore, the lack of additional explanations regarding specialized terminology and cultural background information means that the system cannot adequately support user understanding.

[0861] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0862] In this invention, the server includes means for selecting content to be translated from a user terminal, means for capturing the selected content, means for sending the captured content to the server as a translation request, means for translating the text using a generative AI model based on the received translation request, means for generating additional information related to the translated text, means for sending the translated text and additional information to the user terminal, and means for displaying the received translation results and additional information on the user terminal. This provides not only accurate translations but also additional explanations including context, definitions of technical terms, and cultural background information, enabling the user to gain a deeper understanding of the foreign language content.

[0863] A "user terminal" refers to a device used by a user to access content on the internet, such as a personal computer, smartphone, or tablet.

[0864] "Content" refers to all forms of information that users utilize, primarily including text data such as video descriptions, social media posts, and product descriptions.

[0865] "Capturing" refers to the operation of selecting content displayed on a user's device and capturing that data.

[0866] A "server" refers to a computer system that receives data sent from user terminals and performs data processing and translation processing using generative AI models.

[0867] A "translation request" refers to a data packet sent from a user's terminal to the server requesting translation.

[0868] A "generative AI model" refers to an artificial intelligence algorithm that analyzes received text data and generates appropriate translations and additional information.

[0869] "Contextual analysis" refers to a technical process that analyzes the content and surrounding information of text to create more accurate and appropriate translations.

[0870] "Additional information" refers to definitions of technical terms and cultural background information related to the translated text, which helps users to gain a deeper understanding of the content.

[0871] Modes for carrying out the invention

[0872] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional information when users access it. This system is realized through the collaboration of a user terminal, a server, and a generative AI.

[0873] User terminal operation

[0874] The user's device is used to select the content they wish to translate. For example, when a user selects a YouTube video description, a social media post, or a product description from an e-commerce site, the user's device captures this content using a dedicated app or browser extension. When the user clicks the "Translate" button, the captured text is sent to the server.

[0875] Server operation

[0876] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, such as OpenAI's GPT model, and translation processing is performed. The generative AI analyzes the context of the text and generates appropriate translation results. Furthermore, based on the translation results, it generates additional information such as definitions of technical terms and cultural background information.

[0877] Display of user actions and results

[0878] The user terminal receives the translation results and additional information sent from the server and displays them to the user. This allows the user to accurately and fully understand the foreign language content.

[0879] Specific example

[0880] Translation of YouTube video description

[0881] 1. User: Decides to translate a YouTube video description and selects the description.

[0882] 2. User terminal: Captures the description text and sends a translation request to the server.

[0883] 3. Server: Receives requests and translates the description using generative AI (e.g., OpenAI GPT model). Based on the translation results, it generates additional information (e.g., definitions of technical terms and cultural background).

[0884] 4. Server: Sends the translation results and additional information to the user's terminal.

[0885] 5. User: Review the translation results and additional information displayed on the device to gain a deeper understanding of the content.

[0886] Example of a prompt

[0887] Translation target: "This is a sample description of a YouTube video."

[0888] Prompt to the generating AI: "Translate this text into Japanese and provide additional information relevant to the content, including any cultural or technical terms."

[0889] This system will enable users to understand and utilize foreign language content more accurately. In particular, by providing additional information based on specialized terminology and cultural background, it is expected that users' knowledge will be enriched, and the value of using foreign language content will be significantly enhanced.

[0890] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0891] Step 1:

[0892] The user selects the content they want translated. For example, they might choose a YouTube video description or a social media post. This action inputs the selected text data into the user's device.

[0893] Step 2:

[0894] The user's device captures selected content and sends it to the server. The captured data includes text content and metadata (e.g., URL, posting date and time). This data is sent to the server as captured text.

[0895] Specific actions:

[0896] When a user clicks the "Translate" button, the browser extension automatically extracts the text from the page and sends it to the server.

[0897] Step 3:

[0898] The server analyzes the received text data and sends a prompt to the generative AI. The analysis includes understanding the context of the received text. The server sends the generative AI model the prompt: "Translate the following text: 'This is a sample description of a YouTube video.' and provide additional context information."

[0899] Specific actions:

[0900] The server analyzes the received data and generates prompt messages to send to the generative AI.

[0901] Step 4:

[0902] The generative AI receives a prompt and generates an appropriate translation and additional explanations. The generative AI performs contextual analysis to improve translation accuracy and generates the text translation along with additional information including definitions of technical terms and background information. This result is then returned to the server.

[0903] Specific actions:

[0904] The generative AI translates "This is a sample description of a YouTube video." as "This is a sample description of a YouTube video." and generates additional information such as "YouTube is a video sharing service, and video descriptions typically contain information about the content and purpose of the video."

[0905] Step 5:

[0906] The server sends the translation results and additional explanations received from the generative AI to the user's terminal. In this process, the server converts the generated results into a format that is easy for the user to understand.

[0907] Specific actions:

[0908] The server sends the translation results and additional explanations to the user's terminal in JSON format. The JSON data includes the translated text and additional information.

[0909] Step 6:

[0910] The user's terminal displays the data received from the server. The user can check the translation results and additional explanations on their terminal to deepen their understanding of the foreign language content.

[0911] Specific actions:

[0912] The browser extension displays the received data and shows information such as, "Translation result: This is a sample description for a YouTube video. Additional information: YouTube is a video sharing service, and video descriptions typically include information about the content and purpose."

[0913] In this way, the system performs a series of processes to help users accurately understand foreign language content.

[0914] (Application Example 1)

[0915] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0916] Traditional translation systems simply convert text into another language, often failing to provide information to deepen understanding of specialized terminology and cultural context. As a result, users often struggled to fully understand translated content, especially when it contained specialized information. Furthermore, a lack of definitions and background information for specialized terms in certain fields created a high barrier to user access to the content.

[0917] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0918] In this invention, the server includes means for acquiring content to be translated from a user terminal, means for sending the acquired content to the server as a translation request, means for translating the text using a generative AI based on the received translation request, means for generating additional explanations related to the translated text, means for sending the translated text and additional explanations to the user terminal, and means for displaying the received translation results and additional explanations on the user terminal. This makes it possible for users to understand foreign language content more deeply and to significantly improve the value of content, especially content containing specialized information and cultural background.

[0919] A "user terminal" is a device used by a user to interact with content and input and display information.

[0920] "Acquiring" means gathering specific information or data from an external source and importing it into the local environment.

[0921] "Content" refers to a unit of information, provided in various forms such as text, images, videos, and audio.

[0922] A "translation request" is a request that a user sends to a server to translate specific content into another language.

[0923] A "server" is a computer system that processes requests from client devices on a network and provides information.

[0924] "Generative AI" refers to artificial intelligence models that use natural language processing and machine learning to generate and transform text.

[0925] "Translating text" means converting text written in one language into another language.

[0926] "Additional explanations" refer to supplementary information such as definitions of technical terms and cultural context related to the translated text.

[0927] "To send" means to move data or information from a source to a destination over a network.

[0928] "To display" means to provide information to the user visually.

[0929] Modes for carrying out the invention

[0930] The embodiments for carrying out this invention will be described in detail below.

[0931] System configuration and operation

[0932] User terminal operation

[0933] The user's device has a means of obtaining the content the user wishes to translate. For example, the user enters the URL of a YouTube video via a smartphone application. At this time, the application uses the YouTube API to obtain the video description and comments. The obtained text is sent to the server.

[0934] Server operation

[0935] The server receives translation requests sent from user terminals. These requests contain the text to be translated. The server uses generative AI to translate this text. Specifically, the server leverages a generative AI model to generate a draft translation. It also generates additional explanations related to the translated text. These explanations include definitions of technical terms and information about cultural background. This information is also derived from the generative AI model.

[0936] Display translation results and explanations

[0937] The server sends the generated translation results and additional explanations to the user's terminal. The user's terminal displays the received translation results and explanations to the user. This allows the user to understand the foreign language content more completely.

[0938] Hardware and software to be used

[0939] Hardware: Smartphone (iOS or Android), cloud server

[0940] Software: YouTube API, OpenAI GPT model, Flask (Python application framework)

[0941] Data processing and calculations

[0942] 1. User terminal: The video description and comments are retrieved from the YouTube API via the video URL entered by the user.

[0943] 2. Server: The server translates the received text using a generative AI (e.g., the OpenAI GPT model) and generates additional explanations. The generated information is processed based on context and provided to the user in the most optimal form.

[0944] 3. Communication: The generated data (translation results and additional explanations) is sent to the user's terminal via the internet.

[0945] Specific example

[0946] Suppose a user watches a YouTube video in a foreign language like this:

[0947] Title: "Understanding Quantum Computing"

[0948] Caption: "In this video, we'll explore the basics of quantum computing and its potential applications."

[0949] A user wants to translate a video description and enters the URL into the "DeepTranslate" app. The app then retrieves the description via the YouTube API and sends it to the server. On the server side, a generative AI (e.g., the OpenAI GPT model) translates it, generating additional definitions of technical terms and explanations of cultural context. For example, it might use prompts like the following:

[0950] Example of a prompt:

[0951] Translate the following text to Japanese and provide additional explanations:

[0952] In this video, we'll explore the basics of quantum computing and its potential applications.

[0953] Finally, the generated translations and explanations are sent to the user's smartphone, allowing them to easily review them.

[0954] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0955] Step 1:

[0956] On the user's device, the user enters specific content (e.g., a YouTube video URL). This causes the user's device to send a request to the YouTube API to retrieve the video description and comments from that URL.

[0957] Input: Video URL entered by the user

[0958] Output: Retrieved video description and comments

[0959] Step 2:

[0960] The user's device sends the video description and comments, retrieved from the YouTube API, to the server as a translation request.

[0961] Input: Retrieved video description and comments

[0962] Output: Text data as a translation request

[0963] Step 3:

[0964] The server analyzes the received translation request and sends a prompt to the generative AI for translation. A generative AI model is used to generate context-aware translations.

[0965] Input: Text data as a translation request

[0966] Output: Translated text

[0967] Step 4:

[0968] The server generates additional explanations related to the translated text. Generative AI is used to create supplementary explanations that include definitions of technical terms and information about cultural background.

[0969] Input: Translated text

[0970] Output: Additional explanation

[0971] Step 5:

[0972] The server sends the generated translation results and additional explanations to the user's terminal.

[0973] Input: Translated text and additional explanations

[0974] Output: Data sent to the user terminal

[0975] Step 6:

[0976] The user's device displays the received translation results and additional explanations. This makes it easier for the user to understand the content.

[0977] Input: Translation results and additional explanations sent from the server.

[0978] Output: Translation results and explanations that users can visually verify.

[0979] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0980] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional explanations when users access that content. This system is realized through the collaboration of a user terminal, a server, a generative AI, and an emotion engine.

[0981] System configuration and operation

[0982] User terminal operation

[0983] The user's device captures text and links of content the user wishes to translate. This captured data can be processed using a dedicated app or browser extension. Examples of target text on the internet include YouTube video descriptions, social media posts, and product descriptions on e-commerce sites. When the user clicks the "Translate" button, the captured text and links are sent to the server.

[0984] Furthermore, the user terminal has an emotion engine built in that analyzes the user's facial expressions and voice to generate emotion data. This emotion data is sent to the server and used to improve translation results and additional explanations.

[0985] Server operation

[0986] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, and the translation process begins. The generative AI analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[0987] Furthermore, the server receives emotional data sent from the user's terminal and incorporates it into the translation results and additional explanations. For example, if it is determined that the user is experiencing stress, the translation results are made more concise and easier to understand.

[0988] The server sends the generated translation results and additional explanations to the user's terminal. During this process, contextual analysis is performed to improve translation accuracy, and relevant information is added to provide information that is easy for the user to understand.

[0989] Display of user actions and results

[0990] Users can receive and review the translation results and additional explanations sent from the server on their devices. This enables them to accurately and comprehensively understand foreign language content.

[0991] Specific example

[0992] Translation of YouTube video description

[0993] 1. User: Wants to translate the YouTube video description and selects the description.

[0994] 2. User terminal: Captures the selected description and sends a translation request to the server. It also analyzes the user's facial expressions and voice, generates emotion data, and sends it to the server.

[0995] 3. Server: Receives translation requests and translates the explanatory text using generative AI. Furthermore, it adjusts the translation result while considering the user's sentiment data.

[0996] 4. Server: Based on the translation results, it generates additional explanations (definitions of technical terms and cultural background).

[0997] 5. Server: Sends the translation results and additional explanations to the user's terminal.

[0998] 6. User: Review the translation results and additional explanations displayed on the device to understand the content. The inclusion of sentiment data allows users to receive information with less stress.

[0999] The system of this invention enables users to understand and utilize foreign language content more accurately. In particular, by using an emotion engine, appropriate information is provided according to the user's emotional state, making it easier for the user to deeply understand the content. As a result, the user's knowledge is enriched, and the value of using foreign language content is greatly enhanced.

[1000] The following describes the processing flow.

[1001] Step 1:

[1002] Users select text or links to be translated. This includes YouTube video descriptions, social media posts, and product descriptions on e-commerce sites.

[1003] Step 2:

[1004] The user clicks the "Translate" button to submit a translation request.

[1005] Step 3:

[1006] The user's device captures the selected text or links to be translated. Specifically, it extracts the text data from the selected portion and saves it to memory.

[1007] Step 4:

[1008] The user terminal generates a translation request containing the captured text data and sends this request to the server. The request includes the captured text data and associated metadata.

[1009] Step 5:

[1010] The user terminal uses an emotion engine to analyze the user's facial expressions and voice, generating emotion data in real time. This emotion data is also sent to the server.

[1011] Step 6:

[1012] The server receives translation requests and sentiment data sent from the user's terminal. This allows the server to understand both the information needed for translation and the user's emotional state.

[1013] Step 7:

[1014] The server uses generative AI to translate text based on the received translation request. The generative AI performs contextual analysis and generates an appropriate translation.

[1015] Step 8:

[1016] The server generates additional explanations related to the translated text, including definitions of technical terms and background information. If the sentiment data indicates "high stress," the additional explanations are adjusted to be concise and easy to understand.

[1017] Step 9:

[1018] The server adjusts the translation results and additional explanations based on sentiment data, optimizing them to suit the user.

[1019] Step 10:

[1020] The server sends the final translation and any adjusted additional explanations to the user's terminal.

[1021] Step 11:

[1022] The user terminal receives the translation results and additional explanations sent from the server. The received data is temporarily stored in memory.

[1023] Step 12:

[1024] The user terminal displays the received translation results and additional explanations on the screen. The user reviews and understands the content.

[1025] Step 13:

[1026] Users can review the displayed translation results and additional explanations to accurately understand the foreign language content. The results, adjusted based on sentiment data, allow users to access information without experiencing stress.

[1027] (Example 2)

[1028] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1029] When using foreign language content, conventional translation systems have struggled to provide not only accurate translation results but also appropriate information tailored to the user's emotional state. Users often experience stress, which can hinder their true understanding of the translated content. Furthermore, a lack of specialized terminology or cultural background information can prevent complete comprehension. To address these challenges, this invention provides a translation system that takes user emotional data into consideration.

[1030] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for capturing text to be translated from a user terminal, means for sending the captured text to the server as a translation request, means for generating user sentiment data, means for sending the text and sentiment data to the server, means for translating the text using a generative model based on the received translation request, means for generating additional explanations related to the translated text, means for adjusting the translation result based on the user sentiment data, means for sending the translated text and additional explanations to the user terminal, and means for displaying the translation result received at the user terminal. As a result, the user can obtain accurate and easy-to-understand translation results, enabling a deeper understanding of foreign language content.

[1031] A "user terminal" is a device that a user directly operates and uses to send translation requests. Examples include smartphones, tablets, and personal computers.

[1032] "Text to be translated" refers to the text portion of content that the user wishes to have translated. This includes, for example, the text on a webpage, social media posts, and video descriptions.

[1033] "Capturing" means that the user's device takes in the specified text and saves it as digital data.

[1034] A "translation request" is a request to send captured text and necessary metadata to the server.

[1035] "Emotional data" is data generated by analyzing the user's facial expressions and voice. This allows the user's emotional state (e.g., stress level, happiness level) to be expressed as a numerical value or category.

[1036] "Generating" refers to the act of creating new information based on existing data. Examples include translating text or creating additional explanations.

[1037] A "server" is a central processing unit that receives requests sent from user terminals and performs the necessary processing.

[1038] A "generative model" is a machine learning model used for natural language processing. For example, it includes AI models that perform translation while analyzing the context of the text.

[1039] "Additional explanations" refer to more detailed information related to the translated text. For example, this may include definitions of technical terms or explanations of cultural context.

[1040] "Adjusting" means transforming the information being provided into an appropriate format. For example, this includes taking user sentiment data into consideration and revising the translation results to make them concise and easy to understand.

[1041] "Translation result" refers to the translated text generated based on the translation request.

[1042] "To display" means to visually present information on the screen of the user's terminal.

[1043] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional explanations when users access that content. This system is realized through the collaboration of a user terminal, a server, a generative AI model, and an emotion engine.

[1044] System configuration and operation

[1045] User terminal operation

[1046] The user's device captures the text and links of the content the user wishes to translate. This capture can be done using a dedicated app or browser extension. Examples include YouTube video descriptions, social media posts, and product descriptions on e-commerce sites. When the user clicks the "Translate" button, the captured text and links are sent to the server.

[1047] Furthermore, the user terminal has an emotion engine built in that analyzes the user's facial expressions and voice to generate emotion data. This emotion data is sent to the server and reflected in the translation results and additional explanations. The emotion engine uses analysis libraries such as OpenCV and DeepFace.

[1048] Server operation

[1049] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI model, and the translation process begins. Specifically, generative AI models such as OpenAI's GPT-4 are used. The generative AI model analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[1050] Furthermore, the server receives sentiment data sent from the user's terminal and incorporates it into the translation results and additional explanations. For example, if it determines that the user is experiencing stress, the translation results are simplified and adjusted to be easier to understand.

[1051] The server sends the generated translation results and additional explanations to the user's terminal. In this process, contextual analysis is performed again to improve the accuracy of the translation, and relevant information is added to provide information that is easy for the user to understand.

[1052] Display of user actions and results

[1053] Users can receive and review the translation results and additional explanations sent from the server on their devices. This enables them to accurately and comprehensively understand foreign language content.

[1054] Specific example

[1055] Translation of YouTube video description

[1056] 1. User: Wants to translate a YouTube video description and selects the description.

[1057] 2. User terminal: Captures the selected description and sends a translation request to the server. It also analyzes the user's facial expressions and voice, generates emotion data, and sends it to the server.

[1058] 3. Server: Receives translation requests and translates the descriptions using generative AI models (e.g., GPT-4). Furthermore, it adjusts the translation results considering user sentiment data.

[1059] 4. Server: Based on the translation results, it generates additional explanations (definitions of technical terms and cultural background).

[1060] 5. Server: Sends the translation results and additional explanations to the user's terminal.

[1061] 6. User: Review the translation results and additional explanations displayed on the device to understand the content. The inclusion of sentiment data allows users to receive information with less stress.

[1062] Examples of prompts to input into a generative AI model

[1063] Examples of prompt statements are as follows:

[1064] Please translate this text into Japanese:

[1065] "The original text of the captured image goes here."

[1066] This enables users to understand and utilize foreign language content more accurately. In particular, by using an emotion engine, appropriate information is provided according to the user's emotional state, making it easier for users to deeply understand the content. As a result, users' knowledge is enriched, and the value of using foreign language content is greatly enhanced.

[1067] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1068] Step 1:

[1069] The user selects the content they wish to translate.

[1070] Specifically, the user selects text such as a YouTube video description or a social media post and clicks the "Translate" button.

[1071] Input: User-selected text or link

[1072] Output: Capture trigger on the user terminal

[1073] Step 2:

[1074] The user's terminal captures the selected text and saves it as text data.

[1075] Specifically, it involves using a dedicated app or browser extension to capture specified text as digital data.

[1076] Input: User-selected text or link

[1077] Output: Captured text data

[1078] Step 3:

[1079] The user's device uses an emotion engine to analyze the user's facial expressions and voice, and generates emotion data.

[1080] Specifically, the system uses OpenCV and DeepFace to analyze the user's facial expressions and quantify their emotional state.

[1081] Input: User's facial expressions and voice

[1082] Output: Sentiment data

[1083] Step 4:

[1084] The user's device sends captured text data and sentiment data to the server.

[1085] Specifically, this data is sent to the server using an HTTP POST request.

[1086] Input: Captured text data, sentiment data

[1087] Output: Translation requests and sentiment data sent to the server

[1088] Step 5:

[1089] The server inputs the received text data into a generative model to obtain a translation result.

[1090] Specifically, the process involves using a generative AI model such as OpenAI's GPT-4 to generate prompt text and then performing translation.

[1091] Input: Captured text data

[1092] Output: Translation result by generative model

[1093] Step 6:

[1094] Based on the translation results, the server generates additional explanations, such as definitions of relevant technical terms and background information.

[1095] Specifically, the system uses a pre-trained knowledge base to extract information relevant to the translation result.

[1096] Input: Translation result from generative model

[1097] Output: Additional explanation

[1098] Step 7:

[1099] The server adjusts the translation results based on the user's sentiment data.

[1100] As a specific action, if the stress level is high, the translation result will be revised to be more concise and easier to understand.

[1101] Input: Translation result, sentiment data

[1102] Output: Final translation result considering sentiment data

[1103] Step 8:

[1104] The server sends the final translation results and additional explanations to the user's terminal.

[1105] Specifically, the system uses an HTTP POST request to send data back to the user's terminal.

[1106] Input: Final translation result, additional explanation

[1107] Output: Data to be sent to the user terminal

[1108] Step 9:

[1109] The user checks the translation results and additional explanations on their device.

[1110] Specifically, the user's terminal displays the received translation results and additional explanations, which the user then reads and understands.

[1111] Input: Final translation result sent from the server, additional explanations

[1112] Output: User translation results and additional explanations

[1113] (Application Example 2)

[1114] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1115] In modern virtual stores, foreign language-speaking customers often have difficulty accurately understanding product descriptions and reviews. Even with accurate translations, comprehension can be challenging, especially when technical jargon or cultural context is involved. Furthermore, depending on the customer's emotional state, they may find the translation difficult to understand. This situation can potentially decrease customer purchasing intent.

[1116] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing text to be translated from a user terminal, means for sending the captured text to the server as a translation request, means for translating the text using a generative AI based on the received translation request, means for generating additional explanations related to the translated text, means for sending the translated text and additional explanations to the user terminal, means for analyzing the user's emotional data and adjusting the translation results and additional explanations considering the received emotional data, means for providing a user interface for display in a virtual store, and means for displaying the translation results received on the user terminal. This makes it possible for foreign language speaking customers to accurately understand product descriptions and reviews and receive information adjusted according to their emotional state.

[1117] A "user terminal" is a device that allows a user to capture text to be translated and send it to the server.

[1118] A "translation request" is a set of instructions and data sent from a user's terminal to the server for the purpose of translation.

[1119] "Generative AI" refers to artificial intelligence that analyzes input data and generates appropriate translation results or additional explanations.

[1120] "Additional explanations" refer to supplementary information such as definitions of technical terms and background information related to the translated text.

[1121] "Emotional data" refers to data about a user's emotional state, analyzed from their facial expressions and voice.

[1122] A "virtual store" is a virtual store that operates on the internet, providing an environment where customers can browse and purchase products online.

[1123] A "user interface" is a means of display and operation that allows the user to visually confirm translation results and additional explanations.

[1124] This invention is a language support system for enabling foreign language-speaking customers in virtual stores to accurately understand product descriptions and reviews. This system is realized through the collaboration of a user terminal, a server, a generative AI, and an emotion analysis engine.

[1125] System configuration and operation

[1126] User terminal operation

[1127] The user's device captures product descriptions and reviews that the customer wishes to have translated. This captured data is handled using a dedicated app or browser extension. The user's device also has a built-in sentiment analysis engine that analyzes the user's facial expressions and voice to generate sentiment data. This sentiment data is sent to a server and used to improve the translation results and additional explanations.

[1128] Server operation

[1129] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, and the translation process begins. The generative AI analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[1130] Furthermore, the server receives sentiment data sent from the user's terminal and incorporates it into the translation results and additional explanations. For example, if it determines that the user is feeling stressed, the translation results are made more concise and easier to understand. The server then sends the generated translation results and additional explanations to the user's terminal.

[1131] Display of user actions and results

[1132] Users can receive and review the translation results and additional explanations sent from the server on their device. This enables accurate and comprehensive understanding of foreign language content. The inclusion of sentiment data in the results allows users to receive information with less stress.

[1133] Hardware and software to be used

[1134] User terminal: Devices such as smartphones, smart glasses, and head-mounted displays.

[1135] Sentiment analysis engines: Microsoft Azure's Face API and Google Cloud's Speech-to-Text API

[1136] Server: High-performance cloud server

[1137] Generative AI: Google Cloud Translation API, DeepL API

[1138] User interface: Web application or dedicated app

[1139] Specific example

[1140] For example, if a user wants to select a product description in a foreign language within a virtual store and request a translation, they select the description and click the "Translate" button. The user's device captures the selected description and sends it to the server. Simultaneously, the server analyzes the user's facial expressions and voice to generate sentiment data. Based on the received data, the server generates a translation result and additional explanations, adjusting them to take the sentiment data into consideration. The generated information is then sent to the user's device, where the user can review it.

[1141] Examples of prompts for generative AI models

[1142] "Translate the product description selected by the customer, provide definitions for relevant technical terms, and adjust the overall information based on sentiment data to present it in an easily understandable format."

[1143] Through concrete examples, you can understand how the system is implemented and its benefits. This will lead to a deeper understanding of customers and increased purchasing intent, as it will enable accurate comprehension of foreign language content and provide information tailored to their emotional state.

[1144] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1145] Step 1:

[1146] Users select the product description or review they want translated within the virtual store and click the translate button.

[1147] Input: Product description and reviews of the product selected by the customer.

[1148] Output: Captured text data

[1149] Specific operation: The user's terminal captures the text selected by the customer through a dedicated app or browser extension, and prepares for the next process.

[1150] Step 2:

[1151] The user's terminal sends the captured text data to the server as a translation request.

[1152] Input: Captured text data

[1153] Output: Translation request sent to the server

[1154] Specific operation: The user's terminal sends the captured text data to the server as an HTTP request.

[1155] Step 3:

[1156] The user's terminal analyzes the customer's facial expressions and voice to generate emotional data.

[1157] Input: Customer facial expression data and voice data

[1158] Output: Generated emotion data

[1159] Specific operation: Using the emotion analysis engine installed on the user's device, data obtained from the camera and microphone is analyzed to generate emotion data.

[1160] Step 4:

[1161] The user's terminal sends the generated emotion data to the server.

[1162] Input: Generated emotion data

[1163] Output: Sentiment data sent to the server

[1164] Specific operation: The user terminal sends the generated emotion data to the server as an HTTP request.

[1165] Step 5:

[1166] The server receives the translation request and uses a generative AI to translate the text.

[1167] Input: Translation request sent to the server

[1168] Output: Generated translation result

[1169] Specific operation: The server uses generative AI such as the Google Cloud Translation API and the DeepL API to translate the received text data.

[1170] Step 6:

[1171] Based on the generated translation results, the server generates additional explanations, such as definitions of relevant technical terms and background information.

[1172] Input: Generated translation result

[1173] Output: Additional explanation

[1174] Specific operation: The server uses generative AI to generate supplementary information related to the translation result.

[1175] Step 7:

[1176] The server adjusts the translation results and additional explanations based on sentiment data received from the user's terminal.

[1177] Input: Translation result, additional explanation, sentiment data

[1178] Output: Adjusted translation results and additional explanations

[1179] Specific operation: The server's emotion engine analyzes the emotional data and, for example, adjusts it to a simple and easy-to-understand format for users who are feeling stressed.

[1180] Step 8:

[1181] The server sends the adjusted translation results and additional explanations to the user's terminal.

[1182] Input: Adjusted translation results and additional explanations

[1183] Output: Adjustment results sent to the user terminal

[1184] Specific operation: The server sends the adjusted translation results and additional explanations to the user's terminal as an HTTP response.

[1185] Step 9:

[1186] The user's terminal displays the adjusted translation results and additional explanations received.

[1187] Input: Adjustment results sent to the user terminal

[1188] Output: Displayed adjustment results

[1189] Specific operation: The user's device displays the received translation results and additional explanations through a web application or dedicated app.

[1190] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1191] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1192] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1193] [Fourth Embodiment]

[1194] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1195] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1196] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1197] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1198] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1199] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1200] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1201] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1202] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1203] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1204] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1205] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1206] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1207] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional explanations when users access that content. This system is realized through the collaboration of a user terminal, a server, and a generative AI.

[1208] System configuration and operation

[1209] User terminal operation

[1210] The user's device captures text and links of content the user wishes to translate. This captured data can be processed using a dedicated app or browser extension. Examples of target text on the internet include YouTube video descriptions, social media posts, and product descriptions on e-commerce sites. When the user clicks the "Translate" button, the captured text and links are sent to the server.

[1211] Server operation

[1212] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, and the translation process begins. The generative AI analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[1213] The server sends the generated translation results and additional explanations to the user's terminal. During this process, contextual analysis is performed to improve translation accuracy, and relevant information is added to provide information that is easy for the user to understand.

[1214] Display of user actions and results

[1215] Users can receive and review the translation results and additional explanations sent from the server on their devices. This enables them to accurately and comprehensively understand foreign language content.

[1216] Specific example

[1217] Translation of YouTube video description

[1218] 1. User: Wants to translate the YouTube video description and selects the description.

[1219] 2. User terminal: Captures the selected description and sends a translation request to the server.

[1220] 3. Server: Receives translation requests and translates the explanatory text using generative AI. Based on the translation results, it generates additional explanations (e.g., definitions of technical terms and cultural background).

[1221] 4. Server: Sends the translation results and additional explanations to the user's terminal.

[1222] 5. User: Review the translation results and additional explanations displayed on the device and understand the content.

[1223] The system of this invention enables users to understand and utilize foreign language content more accurately. In particular, the inclusion of additional explanations based on specialized terminology and cultural background allows users to gain a deeper understanding of the content. This enriches the user's knowledge and significantly enhances the value of utilizing foreign language content.

[1224] The following describes the processing flow.

[1225] Step 1:

[1226] Users select text or links to be translated. This is done by selecting portions of online content, such as YouTube video descriptions, social media posts, or product descriptions on e-commerce sites.

[1227] Step 2:

[1228] The user clicks the "Translate" button and takes action to submit a translation request.

[1229] Step 3:

[1230] The user's terminal captures the selected text or links to be translated. Specifically, it extracts the text data from the selected portion and saves it to memory.

[1231] Step 4:

[1232] The user terminal generates a translation request containing the captured text data and sends this request to the server. The request includes the captured text data and associated metadata.

[1233] Step 5:

[1234] The server receives translation requests sent from the user's terminal. These requests contain captured text data to be translated.

[1235] Step 6:

[1236] The server analyzes the received text data and prepares it for transmission to the generative AI. This step involves initial analysis to understand the content of the text.

[1237] Step 7:

[1238] The server uses generative AI to analyze the text to be translated and generate a context-based, highly accurate translation. The generative AI translates the text considering sentence structure, context, and the meaning of terms.

[1239] Step 8:

[1240] The server generates additional explanations related to the translated text. These include definitions of technical terms, cultural context, and related information. The generated additional explanations help users gain a deeper understanding of the translated text.

[1241] Step 9:

[1242] The server sends the completed translation and additional explanations to the user's terminal. In this step, the translation and related information are packaged and sent to the user's terminal.

[1243] Step 10:

[1244] The user terminal receives the translation results and additional explanations sent from the server. The received data is temporarily stored in memory.

[1245] Step 11:

[1246] The user terminal displays the received translation results and additional explanations on the screen. The user reviews and understands the content.

[1247] Step 12:

[1248] Users can review the displayed translation results and additional explanations to accurately understand the foreign language content.

[1249] (Example 1)

[1250] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1251] When using foreign language content, users need not only accurate translations but also context and background information to deeply understand the content. However, conventional translation systems often only provide translation results, making it difficult for users to understand the intent and details of the content. Furthermore, the lack of additional explanations regarding specialized terminology and cultural background information means that the system cannot adequately support user understanding.

[1252] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1253] In this invention, the server includes means for selecting content to be translated from a user terminal, means for capturing the selected content, means for sending the captured content to the server as a translation request, means for translating the text using a generative AI model based on the received translation request, means for generating additional information related to the translated text, means for sending the translated text and additional information to the user terminal, and means for displaying the received translation results and additional information on the user terminal. This provides not only accurate translations but also additional explanations including context, definitions of technical terms, and cultural background information, enabling the user to gain a deeper understanding of the foreign language content.

[1254] A "user terminal" refers to a device used by a user to access content on the internet, such as a personal computer, smartphone, or tablet.

[1255] "Content" refers to all forms of information that users utilize, primarily including text data such as video descriptions, social media posts, and product descriptions.

[1256] "Capturing" refers to the operation of selecting content displayed on a user's device and capturing that data.

[1257] A "server" refers to a computer system that receives data sent from user terminals and performs data processing and translation processing using generative AI models.

[1258] A "translation request" refers to a data packet sent from a user's terminal to the server requesting translation.

[1259] A "generative AI model" refers to an artificial intelligence algorithm that analyzes received text data and generates appropriate translations and additional information.

[1260] "Contextual analysis" refers to a technical process that analyzes the content and surrounding information of text to create more accurate and appropriate translations.

[1261] "Additional information" refers to definitions of technical terms and cultural background information related to the translated text, which helps users to gain a deeper understanding of the content.

[1262] Modes for carrying out the invention

[1263] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional information when users access it. This system is realized through the collaboration of a user terminal, a server, and a generative AI.

[1264] User terminal operation

[1265] The user's device is used to select the content they wish to translate. For example, when a user selects a YouTube video description, a social media post, or a product description from an e-commerce site, the user's device captures this content using a dedicated app or browser extension. When the user clicks the "Translate" button, the captured text is sent to the server.

[1266] Server operation

[1267] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, such as OpenAI's GPT model, and translation processing is performed. The generative AI analyzes the context of the text and generates appropriate translation results. Furthermore, based on the translation results, it generates additional information such as definitions of technical terms and cultural background information.

[1268] Display of user actions and results

[1269] The user terminal receives the translation results and additional information sent from the server and displays them to the user. This allows the user to accurately and fully understand the foreign language content.

[1270] Specific example

[1271] Translation of YouTube video description

[1272] 1. User: Decides to translate a YouTube video description and selects the description.

[1273] 2. User terminal: Captures the description text and sends a translation request to the server.

[1274] 3. Server: Receives requests and translates the description using generative AI (e.g., OpenAI GPT model). Based on the translation results, it generates additional information (e.g., definitions of technical terms and cultural background).

[1275] 4. Server: Sends the translation results and additional information to the user's terminal.

[1276] 5. User: Review the translation results and additional information displayed on the device to gain a deeper understanding of the content.

[1277] Example of a prompt

[1278] Translation target: "This is a sample description of a YouTube video."

[1279] Prompt to the generating AI: "Translate this text into Japanese and provide additional information relevant to the content, including any cultural or technical terms."

[1280] This system will enable users to understand and utilize foreign language content more accurately. In particular, by providing additional information based on specialized terminology and cultural background, it is expected that users' knowledge will be enriched, and the value of using foreign language content will be significantly enhanced.

[1281] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1282] Step 1:

[1283] The user selects the content they want translated. For example, they might choose a YouTube video description or a social media post. This action inputs the selected text data into the user's device.

[1284] Step 2:

[1285] The user's device captures selected content and sends it to the server. The captured data includes text content and metadata (e.g., URL, posting date and time). This data is sent to the server as captured text.

[1286] Specific actions:

[1287] When a user clicks the "Translate" button, the browser extension automatically extracts the text from the page and sends it to the server.

[1288] Step 3:

[1289] The server analyzes the received text data and sends a prompt to the generative AI. The analysis includes understanding the context of the received text. The server sends the generative AI model the prompt: "Translate the following text: 'This is a sample description of a YouTube video.' and provide additional context information."

[1290] Specific actions:

[1291] The server analyzes the received data and generates prompt messages to send to the generative AI.

[1292] Step 4:

[1293] The generative AI receives a prompt and generates an appropriate translation and additional explanations. The generative AI performs contextual analysis to improve translation accuracy and generates the text translation along with additional information including definitions of technical terms and background information. This result is then returned to the server.

[1294] Specific actions:

[1295] The generative AI translates "This is a sample description of a YouTube video." as "This is a sample description of a YouTube video." and generates additional information such as "YouTube is a video sharing service, and video descriptions typically contain information about the content and purpose of the video."

[1296] Step 5:

[1297] The server sends the translation results and additional explanations received from the generative AI to the user's terminal. In this process, the server converts the generated results into a format that is easy for the user to understand.

[1298] Specific actions:

[1299] The server sends the translation results and additional explanations to the user's terminal in JSON format. The JSON data includes the translated text and additional information.

[1300] Step 6:

[1301] The user's terminal displays the data received from the server. The user can check the translation results and additional explanations on their terminal to deepen their understanding of the foreign language content.

[1302] Specific actions:

[1303] The browser extension displays the received data and shows information such as, "Translation result: This is a sample description for a YouTube video. Additional information: YouTube is a video sharing service, and video descriptions typically include information about the content and purpose."

[1304] In this way, the system performs a series of processes to help users accurately understand foreign language content.

[1305] (Application Example 1)

[1306] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1307] Traditional translation systems simply convert text into another language, often failing to provide information to deepen understanding of specialized terminology and cultural context. As a result, users often struggled to fully understand translated content, especially when it contained specialized information. Furthermore, a lack of definitions and background information for specialized terms in certain fields created a high barrier to user access to the content.

[1308] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1309] In this invention, the server includes means for acquiring content to be translated from a user terminal, means for sending the acquired content to the server as a translation request, means for translating the text using a generative AI based on the received translation request, means for generating additional explanations related to the translated text, means for sending the translated text and additional explanations to the user terminal, and means for displaying the received translation results and additional explanations on the user terminal. This makes it possible for users to understand foreign language content more deeply and to significantly improve the value of content, especially content containing specialized information and cultural background.

[1310] A "user terminal" is a device used by a user to interact with content and input and display information.

[1311] "Acquiring" means gathering specific information or data from an external source and importing it into the local environment.

[1312] "Content" refers to a unit of information, provided in various forms such as text, images, videos, and audio.

[1313] A "translation request" is a request that a user sends to a server to translate specific content into another language.

[1314] A "server" is a computer system that processes requests from client devices on a network and provides information.

[1315] "Generative AI" refers to artificial intelligence models that use natural language processing and machine learning to generate and transform text.

[1316] "Translating text" means converting text written in one language into another language.

[1317] "Additional explanations" refer to supplementary information such as definitions of technical terms and cultural context related to the translated text.

[1318] "To send" means to move data or information from a source to a destination over a network.

[1319] "To display" means to provide information to the user visually.

[1320] Modes for carrying out the invention

[1321] The embodiments for carrying out this invention will be described in detail below.

[1322] System configuration and operation

[1323] User terminal operation

[1324] The user's device has a means of obtaining the content the user wishes to translate. For example, the user enters the URL of a YouTube video via a smartphone application. At this time, the application uses the YouTube API to obtain the video description and comments. The obtained text is sent to the server.

[1325] Server operation

[1326] The server receives translation requests sent from user terminals. These requests contain the text to be translated. The server uses generative AI to translate this text. Specifically, the server leverages a generative AI model to generate a draft translation. It also generates additional explanations related to the translated text. These explanations include definitions of technical terms and information about cultural background. This information is also derived from the generative AI model.

[1327] Display translation results and explanations

[1328] The server sends the generated translation results and additional explanations to the user's terminal. The user's terminal displays the received translation results and explanations to the user. This allows the user to understand the foreign language content more completely.

[1329] Hardware and software to be used

[1330] Hardware: Smartphone (iOS or Android), cloud server

[1331] Software: YouTube API, OpenAI GPT model, Flask (Python application framework)

[1332] Data processing and calculations

[1333] 1. User terminal: The video description and comments are retrieved from the YouTube API via the video URL entered by the user.

[1334] 2. Server: The server translates the received text using a generative AI (e.g., the OpenAI GPT model) and generates additional explanations. The generated information is processed based on context and provided to the user in the most optimal form.

[1335] 3. Communication: The generated data (translation results and additional explanations) is sent to the user's terminal via the internet.

[1336] Specific example

[1337] Suppose a user watches a YouTube video in a foreign language like this:

[1338] Title: "Understanding Quantum Computing"

[1339] Caption: "In this video, we'll explore the basics of quantum computing and its potential applications."

[1340] A user wants to translate a video description and enters the URL into the "DeepTranslate" app. The app then retrieves the description via the YouTube API and sends it to the server. On the server side, a generative AI (e.g., the OpenAI GPT model) translates it, generating additional definitions of technical terms and explanations of cultural context. For example, it might use prompts like the following:

[1341] Example of a prompt:

[1342] Translate the following text to Japanese and provide additional explanations:

[1343] In this video, we'll explore the basics of quantum computing and its potential applications.

[1344] Finally, the generated translations and explanations are sent to the user's smartphone, allowing them to easily review them.

[1345] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1346] Step 1:

[1347] On the user's device, the user enters specific content (e.g., a YouTube video URL). This causes the user's device to send a request to the YouTube API to retrieve the video description and comments from that URL.

[1348] Input: Video URL entered by the user

[1349] Output: Retrieved video description and comments

[1350] Step 2:

[1351] The user's device sends the video description and comments, retrieved from the YouTube API, to the server as a translation request.

[1352] Input: Retrieved video description and comments

[1353] Output: Text data as a translation request

[1354] Step 3:

[1355] The server analyzes the received translation request and sends a prompt to the generative AI for translation. A generative AI model is used to generate context-aware translations.

[1356] Input: Text data as a translation request

[1357] Output: Translated text

[1358] Step 4:

[1359] The server generates additional explanations related to the translated text. Generative AI is used to create supplementary explanations that include definitions of technical terms and information about cultural background.

[1360] Input: Translated text

[1361] Output: Additional explanation

[1362] Step 5:

[1363] The server sends the generated translation results and additional explanations to the user's terminal.

[1364] Input: Translated text and additional explanations

[1365] Output: Data sent to the user terminal

[1366] Step 6:

[1367] The user's device displays the received translation results and additional explanations. This makes it easier for the user to understand the content.

[1368] Input: Translation results and additional explanations sent from the server.

[1369] Output: Translation results and explanations that users can visually verify.

[1370] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1371] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional explanations when users access that content. This system is realized through the collaboration of a user terminal, a server, a generative AI, and an emotion engine.

[1372] System configuration and operation

[1373] User terminal operation

[1374] The user's device captures text and links of content the user wishes to translate. This captured data can be processed using a dedicated app or browser extension. Examples of target text on the internet include YouTube video descriptions, social media posts, and product descriptions on e-commerce sites. When the user clicks the "Translate" button, the captured text and links are sent to the server.

[1375] Furthermore, the user terminal has an emotion engine built in that analyzes the user's facial expressions and voice to generate emotion data. This emotion data is sent to the server and used to improve translation results and additional explanations.

[1376] Server operation

[1377] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, and the translation process begins. The generative AI analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[1378] Furthermore, the server receives emotional data sent from the user's terminal and incorporates it into the translation results and additional explanations. For example, if it is determined that the user is experiencing stress, the translation results are made more concise and easier to understand.

[1379] The server sends the generated translation results and additional explanations to the user's terminal. During this process, contextual analysis is performed to improve translation accuracy, and relevant information is added to provide information that is easy for the user to understand.

[1380] Display of user actions and results

[1381] Users can receive and review the translation results and additional explanations sent from the server on their devices. This enables them to accurately and comprehensively understand foreign language content.

[1382] Specific example

[1383] Translation of YouTube video description

[1384] 1. User: Wants to translate the YouTube video description and selects the description.

[1385] 2. User terminal: Captures the selected description and sends a translation request to the server. It also analyzes the user's facial expressions and voice, generates emotion data, and sends it to the server.

[1386] 3. Server: Receives translation requests and translates the explanatory text using generative AI. Furthermore, it adjusts the translation result while considering the user's sentiment data.

[1387] 4. Server: Based on the translation results, it generates additional explanations (definitions of technical terms and cultural background).

[1388] 5. Server: Sends the translation results and additional explanations to the user's terminal.

[1389] 6. User: Review the translation results and additional explanations displayed on the device to understand the content. The inclusion of sentiment data allows users to receive information with less stress.

[1390] The system of this invention enables users to understand and utilize foreign language content more accurately. In particular, by using an emotion engine, appropriate information is provided according to the user's emotional state, making it easier for the user to deeply understand the content. As a result, the user's knowledge is enriched, and the value of using foreign language content is greatly enhanced.

[1391] The following describes the processing flow.

[1392] Step 1:

[1393] Users select text or links to be translated. This includes YouTube video descriptions, social media posts, and product descriptions on e-commerce sites.

[1394] Step 2:

[1395] The user clicks the "Translate" button to submit a translation request.

[1396] Step 3:

[1397] The user's device captures the selected text or links to be translated. Specifically, it extracts the text data from the selected portion and saves it to memory.

[1398] Step 4:

[1399] The user terminal generates a translation request containing the captured text data and sends this request to the server. The request includes the captured text data and associated metadata.

[1400] Step 5:

[1401] The user terminal uses an emotion engine to analyze the user's facial expressions and voice, generating emotion data in real time. This emotion data is also sent to the server.

[1402] Step 6:

[1403] The server receives translation requests and sentiment data sent from the user's terminal. This allows the server to understand both the information needed for translation and the user's emotional state.

[1404] Step 7:

[1405] The server uses generative AI to translate text based on the received translation request. The generative AI performs contextual analysis and generates an appropriate translation.

[1406] Step 8:

[1407] The server generates additional explanations related to the translated text, including definitions of technical terms and background information. If the sentiment data indicates "high stress," the additional explanations are adjusted to be concise and easy to understand.

[1408] Step 9:

[1409] The server adjusts the translation results and additional explanations based on sentiment data, optimizing them to suit the user.

[1410] Step 10:

[1411] The server sends the final translation and any adjusted additional explanations to the user's terminal.

[1412] Step 11:

[1413] The user terminal receives the translation results and additional explanations sent from the server. The received data is temporarily stored in memory.

[1414] Step 12:

[1415] The user terminal displays the received translation results and additional explanations on the screen. The user reviews and understands the content.

[1416] Step 13:

[1417] Users can review the displayed translation results and additional explanations to accurately understand the foreign language content. The results, adjusted based on sentiment data, allow users to access information without experiencing stress.

[1418] (Example 2)

[1419] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1420] When using foreign language content, conventional translation systems have struggled to provide not only accurate translation results but also appropriate information tailored to the user's emotional state. Users often experience stress, which can hinder their true understanding of the translated content. Furthermore, a lack of specialized terminology or cultural background information can prevent complete comprehension. To address these challenges, this invention provides a translation system that takes user emotional data into consideration.

[1421] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for capturing text to be translated from a user terminal, means for sending the captured text to the server as a translation request, means for generating user sentiment data, means for sending the text and sentiment data to the server, means for translating the text using a generative model based on the received translation request, means for generating additional explanations related to the translated text, means for adjusting the translation result based on the user sentiment data, means for sending the translated text and additional explanations to the user terminal, and means for displaying the translation result received at the user terminal. As a result, the user can obtain accurate and easy-to-understand translation results, enabling a deeper understanding of foreign language content.

[1422] A "user terminal" is a device that a user directly operates and uses to send translation requests. Examples include smartphones, tablets, and personal computers.

[1423] "Text to be translated" refers to the text portion of content that the user wishes to have translated. This includes, for example, the text on a webpage, social media posts, and video descriptions.

[1424] "Capturing" means that the user's device takes in the specified text and saves it as digital data.

[1425] A "translation request" is a request to send captured text and necessary metadata to the server.

[1426] "Emotional data" is data generated by analyzing the user's facial expressions and voice. This allows the user's emotional state (e.g., stress level, happiness level) to be expressed as a numerical value or category.

[1427] "Generating" refers to the act of creating new information based on existing data. Examples include translating text or creating additional explanations.

[1428] A "server" is a central processing unit that receives requests sent from user terminals and performs the necessary processing.

[1429] A "generative model" is a machine learning model used for natural language processing. For example, it includes AI models that perform translation while analyzing the context of the text.

[1430] "Additional explanations" refer to more detailed information related to the translated text. For example, this may include definitions of technical terms or explanations of cultural context.

[1431] "Adjusting" means transforming the information being provided into an appropriate format. For example, this includes taking user sentiment data into consideration and revising the translation results to make them concise and easy to understand.

[1432] "Translation result" refers to the translated text generated based on the translation request.

[1433] "To display" means to visually present information on the screen of the user's terminal.

[1434] This invention relates to a system that enhances user understanding by accurately translating foreign language content and providing additional explanations when users access that content. This system is realized through the collaboration of a user terminal, a server, a generative AI model, and an emotion engine.

[1435] System configuration and operation

[1436] User terminal operation

[1437] The user's device captures the text and links of the content the user wishes to translate. This capture can be done using a dedicated app or browser extension. Examples include YouTube video descriptions, social media posts, and product descriptions on e-commerce sites. When the user clicks the "Translate" button, the captured text and links are sent to the server.

[1438] Furthermore, the user terminal has an emotion engine built in that analyzes the user's facial expressions and voice to generate emotion data. This emotion data is sent to the server and reflected in the translation results and additional explanations. The emotion engine uses analysis libraries such as OpenCV and DeepFace.

[1439] Server operation

[1440] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI model, and the translation process begins. Specifically, generative AI models such as OpenAI's GPT-4 are used. The generative AI model analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[1441] Furthermore, the server receives sentiment data sent from the user's terminal and incorporates it into the translation results and additional explanations. For example, if it determines that the user is experiencing stress, the translation results are simplified and adjusted to be easier to understand.

[1442] The server sends the generated translation results and additional explanations to the user's terminal. In this process, contextual analysis is performed again to improve the accuracy of the translation, and relevant information is added to provide information that is easy for the user to understand.

[1443] Display of user actions and results

[1444] Users can receive and review the translation results and additional explanations sent from the server on their devices. This enables them to accurately and comprehensively understand foreign language content.

[1445] Specific example

[1446] Translation of YouTube video description

[1447] 1. User: Wants to translate a YouTube video description and selects the description.

[1448] 2. User terminal: Captures the selected description and sends a translation request to the server. It also analyzes the user's facial expressions and voice, generates emotion data, and sends it to the server.

[1449] 3. Server: Receives translation requests and translates the descriptions using generative AI models (e.g., GPT-4). Furthermore, it adjusts the translation results considering user sentiment data.

[1450] 4. Server: Based on the translation results, it generates additional explanations (definitions of technical terms and cultural background).

[1451] 5. Server: Sends the translation results and additional explanations to the user's terminal.

[1452] 6. User: Review the translation results and additional explanations displayed on the device to understand the content. The inclusion of sentiment data allows users to receive information with less stress.

[1453] Examples of prompts to input into a generative AI model

[1454] Examples of prompt statements are as follows:

[1455] Please translate this text into Japanese:

[1456] "The original text of the captured image goes here."

[1457] This enables users to understand and utilize foreign language content more accurately. In particular, by using an emotion engine, appropriate information is provided according to the user's emotional state, making it easier for users to deeply understand the content. As a result, users' knowledge is enriched, and the value of using foreign language content is greatly enhanced.

[1458] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1459] Step 1:

[1460] The user selects the content they wish to translate.

[1461] Specifically, the user selects text such as a YouTube video description or a social media post and clicks the "Translate" button.

[1462] Input: User-selected text or link

[1463] Output: Capture trigger on the user terminal

[1464] Step 2:

[1465] The user's terminal captures the selected text and saves it as text data.

[1466] Specifically, it involves using a dedicated app or browser extension to capture specified text as digital data.

[1467] Input: User-selected text or link

[1468] Output: Captured text data

[1469] Step 3:

[1470] The user's device uses an emotion engine to analyze the user's facial expressions and voice, and generates emotion data.

[1471] Specifically, the system uses OpenCV and DeepFace to analyze the user's facial expressions and quantify their emotional state.

[1472] Input: User's facial expressions and voice

[1473] Output: Sentiment data

[1474] Step 4:

[1475] The user's device sends captured text data and sentiment data to the server.

[1476] Specifically, this data is sent to the server using an HTTP POST request.

[1477] Input: Captured text data, sentiment data

[1478] Output: Translation requests and sentiment data sent to the server

[1479] Step 5:

[1480] The server inputs the received text data into a generative model to obtain a translation result.

[1481] Specifically, the process involves using a generative AI model such as OpenAI's GPT-4 to generate prompt text and then performing translation.

[1482] Input: Captured text data

[1483] Output: Translation result by generative model

[1484] Step 6:

[1485] Based on the translation results, the server generates additional explanations, such as definitions of relevant technical terms and background information.

[1486] Specifically, the system uses a pre-trained knowledge base to extract information relevant to the translation result.

[1487] Input: Translation result from generative model

[1488] Output: Additional explanation

[1489] Step 7:

[1490] The server adjusts the translation results based on the user's sentiment data.

[1491] As a specific action, if the stress level is high, the translation result will be revised to be more concise and easier to understand.

[1492] Input: Translation result, sentiment data

[1493] Output: Final translation result considering sentiment data

[1494] Step 8:

[1495] The server sends the final translation results and additional explanations to the user's terminal.

[1496] Specifically, the system uses an HTTP POST request to send data back to the user's terminal.

[1497] Input: Final translation result, additional explanation

[1498] Output: Data to be sent to the user terminal

[1499] Step 9:

[1500] The user checks the translation results and additional explanations on their device.

[1501] Specifically, the user's terminal displays the received translation results and additional explanations, which the user then reads and understands.

[1502] Input: Final translation result sent from the server, additional explanations

[1503] Output: User translation results and additional explanations

[1504] (Application Example 2)

[1505] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1506] In modern virtual stores, foreign language-speaking customers often have difficulty accurately understanding product descriptions and reviews. Even with accurate translations, comprehension can be challenging, especially when technical jargon or cultural context is involved. Furthermore, depending on the customer's emotional state, they may find the translation difficult to understand. This situation can potentially decrease customer purchasing intent.

[1507] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing text to be translated from a user terminal, means for sending the captured text to the server as a translation request, means for translating the text using a generative AI based on the received translation request, means for generating additional explanations related to the translated text, means for sending the translated text and additional explanations to the user terminal, means for analyzing the user's emotional data and adjusting the translation results and additional explanations considering the received emotional data, means for providing a user interface for display in a virtual store, and means for displaying the translation results received on the user terminal. This makes it possible for foreign language speaking customers to accurately understand product descriptions and reviews and receive information adjusted according to their emotional state.

[1508] A "user terminal" is a device that allows a user to capture text to be translated and send it to the server.

[1509] A "translation request" is a set of instructions and data sent from a user's terminal to the server for the purpose of translation.

[1510] "Generative AI" refers to artificial intelligence that analyzes input data and generates appropriate translation results or additional explanations.

[1511] "Additional explanations" refer to supplementary information such as definitions of technical terms and background information related to the translated text.

[1512] "Emotional data" refers to data about a user's emotional state, analyzed from their facial expressions and voice.

[1513] A "virtual store" is a virtual store that operates on the internet, providing an environment where customers can browse and purchase products online.

[1514] A "user interface" is a means of display and operation that allows the user to visually confirm translation results and additional explanations.

[1515] This invention is a language support system for enabling foreign language-speaking customers in virtual stores to accurately understand product descriptions and reviews. This system is realized through the collaboration of a user terminal, a server, a generative AI, and an emotion analysis engine.

[1516] System configuration and operation

[1517] User terminal operation

[1518] The user's device captures product descriptions and reviews that the customer wishes to have translated. This captured data is handled using a dedicated app or browser extension. The user's device also has a built-in sentiment analysis engine that analyzes the user's facial expressions and voice to generate sentiment data. This sentiment data is sent to a server and used to improve the translation results and additional explanations.

[1519] Server operation

[1520] The server receives translation requests sent from user terminals. The received text is analyzed by a generative AI, and the translation process begins. The generative AI analyzes the context of the text and generates appropriate translation results. It also generates additional explanations, such as definitions of technical terms and background information related to the translated text.

[1521] Furthermore, the server receives sentiment data sent from the user's terminal and incorporates it into the translation results and additional explanations. For example, if it determines that the user is feeling stressed, the translation results are made more concise and easier to understand. The server then sends the generated translation results and additional explanations to the user's terminal.

[1522] Display of user actions and results

[1523] Users can receive and review the translation results and additional explanations sent from the server on their device. This enables accurate and comprehensive understanding of foreign language content. The inclusion of sentiment data in the results allows users to receive information with less stress.

[1524] Hardware and software to be used

[1525] User terminal: Devices such as smartphones, smart glasses, and head-mounted displays.

[1526] Sentiment analysis engines: Microsoft Azure's Face API and Google Cloud's Speech-to-Text API

[1527] Server: High-performance cloud server

[1528] Generative AI: Google Cloud Translation API, DeepL API

[1529] User interface: Web application or dedicated app

[1530] Specific example

[1531] For example, if a user wants to select a product description in a foreign language within a virtual store and request a translation, they select the description and click the "Translate" button. The user's device captures the selected description and sends it to the server. Simultaneously, the server analyzes the user's facial expressions and voice to generate sentiment data. Based on the received data, the server generates a translation result and additional explanations, adjusting them to take the sentiment data into consideration. The generated information is then sent to the user's device, where the user can review it.

[1532] Examples of prompts for generative AI models

[1533] "Translate the product description selected by the customer, provide definitions for relevant technical terms, and adjust the overall information based on sentiment data to present it in an easily understandable format."

[1534] Through concrete examples, you can understand how the system is implemented and its benefits. This will lead to a deeper understanding of customers and increased purchasing intent, as it will enable accurate comprehension of foreign language content and provide information tailored to their emotional state.

[1535] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1536] Step 1:

[1537] Users select the product description or review they want translated within the virtual store and click the translate button.

[1538] Input: Product description and reviews of the product selected by the customer.

[1539] Output: Captured text data

[1540] Specific operation: The user's terminal captures the text selected by the customer through a dedicated app or browser extension, and prepares for the next process.

[1541] Step 2:

[1542] The user's terminal sends the captured text data to the server as a translation request.

[1543] Input: Captured text data

[1544] Output: Translation request sent to the server

[1545] Specific operation: The user's terminal sends the captured text data to the server as an HTTP request.

[1546] Step 3:

[1547] The user's terminal analyzes the customer's facial expressions and voice to generate emotional data.

[1548] Input: Customer facial expression data and voice data

[1549] Output: Generated emotion data

[1550] Specific operation: Using the emotion analysis engine installed on the user's device, data obtained from the camera and microphone is analyzed to generate emotion data.

[1551] Step 4:

[1552] The user's terminal sends the generated emotion data to the server.

[1553] Input: Generated emotion data

[1554] Output: Sentiment data sent to the server

[1555] Specific operation: The user terminal sends the generated emotion data to the server as an HTTP request.

[1556] Step 5:

[1557] The server receives the translation request and uses a generative AI to translate the text.

[1558] Input: Translation request sent to the server

[1559] Output: Generated translation result

[1560] Specific operation: The server uses generative AI such as the Google Cloud Translation API and the DeepL API to translate the received text data.

[1561] Step 6:

[1562] Based on the generated translation results, the server generates additional explanations, such as definitions of relevant technical terms and background information.

[1563] Input: Generated translation result

[1564] Output: Additional explanation

[1565] Specific operation: The server uses generative AI to generate supplementary information related to the translation result.

[1566] Step 7:

[1567] The server adjusts the translation results and additional explanations based on sentiment data received from the user's terminal.

[1568] Input: Translation result, additional explanation, sentiment data

[1569] Output: Adjusted translation results and additional explanations

[1570] Specific operation: The server's emotion engine analyzes the emotional data and, for example, adjusts it to a simple and easy-to-understand format for users who are feeling stressed.

[1571] Step 8:

[1572] The server sends the adjusted translation results and additional explanations to the user's terminal.

[1573] Input: Adjusted translation results and additional explanations

[1574] Output: Adjustment results sent to the user terminal

[1575] Specific operation: The server sends the adjusted translation results and additional explanations to the user's terminal as an HTTP response.

[1576] Step 9:

[1577] The user's terminal displays the adjusted translation results and additional explanations received.

[1578] Input: Adjustment results sent to the user terminal

[1579] Output: Displayed adjustment results

[1580] Specific operation: The user's device displays the received translation results and additional explanations through a web application or dedicated app.

[1581] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1582] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1583] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1584] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1585] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1586] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1587] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1588] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1589] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1590] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1591] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1592] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1593] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1594] 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.

[1595] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1596] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1597] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1598] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1599] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1600] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1601] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1602] The following is further disclosed regarding the embodiments described above.

[1603] (Claim 1)

[1604] A means of capturing the text to be translated from the user's terminal,

[1605] Means for sending the captured text to the server as a translation request,

[1606] A means of translating text using generative AI based on a received translation request,

[1607] means for generating additional explanations related to the translated text,

[1608] Means for transmitting the translated text and additional explanations to the user terminal,

[1609] means for displaying the translation result received on the user terminal

[1610] A system that includes this.

[1611] (Claim 2)

[1612] The system according to claim 1, wherein the generative AI performs contextual analysis to improve translation accuracy.

[1613] (Claim 3)

[1614] The system according to claim 1, wherein the aforementioned additional explanation includes definitions of technical terms and background information.

[1615] "Example 1"

[1616] (Claim 1)

[1617] A means of selecting content to be translated from the user's terminal,

[1618] Means for capturing the selected content,

[1619] Means for sending the captured content to the server as a translation request,

[1620] A means of translating text using a generative AI model based on a received translation request,

[1621] Means for generating additional information related to the translated text,

[1622] Means for transmitting the translated text and additional information to the user terminal,

[1623] Means for displaying the translation results and additional information received at the user terminal.

[1624] A system that includes this.

[1625] (Claim 2)

[1626] The system according to claim 1, wherein the generation AI model performs contextual analysis to improve translation accuracy.

[1627] (Claim 3)

[1628] The system according to claim 1, wherein the additional information includes definitions of technical terms and background information.

[1629] "Application Example 1"

[1630] (Claim 1)

[1631] A means of obtaining the content to be translated from the user's terminal,

[1632] A means for sending the acquired content to the server as a translation request,

[1633] A means of translating text using generative AI based on a received translation request,

[1634] means for generating additional explanations related to the translated text,

[1635] Means for transmitting the translated text and additional explanations to the user terminal,

[1636] A means for displaying the translation results and additional explanations received on the user terminal.

[1637] A system that includes this.

[1638] (Claim 2)

[1639] The system according to claim 1, wherein the generative AI performs contextual analysis to improve translation accuracy and the quality of explanation.

[1640] (Claim 3)

[1641] The system according to claim 1, wherein the aforementioned additional explanations include definitions of technical terms and background information, and are provided in a manner that is easy for the user to understand.

[1642] "Example 2 of combining an emotion engine"

[1643] (Claim 1)

[1644] A means of capturing the text to be translated from the user's terminal,

[1645] Means for sending the captured text to the server as a translation request,

[1646] A means of generating user sentiment data,

[1647] Means for transmitting the aforementioned text and sentiment data to a server,

[1648] A means of translating text using a generative model based on a received translation request,

[1649] means for generating additional explanations related to the translated text,

[1650] A means for adjusting the translation results based on user sentiment data,

[1651] Means for transmitting the translated text and additional explanations to the user terminal,

[1652] means for displaying the translation result received on the user terminal

[1653] A system that includes this.

[1654] (Claim 2)

[1655] The system according to claim 1, wherein the generative model performs contextual analysis to improve translation accuracy.

[1656] (Claim 3)

[1657] The system according to claim 1, wherein the aforementioned additional explanation includes definitions of technical terms and background information.

[1658] "Application example 2 when combining with an emotional engine"

[1659] (Claim 1)

[1660] A means of capturing the text to be translated from the user's terminal,

[1661] Means for sending the captured text to the server as a translation request,

[1662] A means of translating text using generative AI based on a received translation request,

[1663] means for generating additional explanations related to the translated text,

[1664] Means for transmitting the translated text and additional explanations to the user terminal,

[1665] A means of analyzing user sentiment data and adjusting translation results and additional explanations based on the received sentiment data,

[1666] A means of providing a user interface for display within a virtual store,

[1667] means for displaying the translation result received on the user terminal

[1668] A system that includes this.

[1669] (Claim 2)

[1670] The system according to claim 1, wherein the generative AI performs contextual analysis to improve translation accuracy.

[1671] (Claim 3)

[1672] The system according to claim 1, wherein the aforementioned additional explanation includes definitions of technical terms and background information. [Explanation of symbols]

[1673] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of capturing the text to be translated from the user's terminal, Means for sending the captured text to the server as a translation request, A means of translating text using generative AI based on a received translation request, means for generating additional explanations related to the translated text, Means for transmitting the translated text and additional explanations to the user terminal, means for displaying the translation result received on the user terminal A system that includes this.

2. The system according to claim 1, wherein the generative AI performs contextual analysis to improve translation accuracy.

3. The system according to claim 1, wherein the additional explanation includes definitions of technical terms and background information.

Images