system

Abstract

We provide the system. [Solution] A means of receiving Japanese input from the user, A means of analyzing the received Japanese input and interpreting the context, Means for generating translation results based on the interpreted context, A means of outputting the generated translation results to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance 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] Japanese has its unique expressions and cultural backgrounds, which are difficult for foreigners to fully understand. Therefore, there is a problem that those learning Japanese and foreign visitors to Japan often misunderstand their intentions. This problem may cause communication gaps and cultural misunderstandings. Therefore, a technology that provides appropriate translations according to the context is required.

Means for Solving the Problems

[0005] This invention provides a system that receives Japanese input from a user, analyzes and interprets its context, and generates more accurate translations. This system uses a generative artificial intelligence model to analyze expressions unique to the Japanese language, and also performs analysis to understand cultural background and intent by referring to past data. As a result, the generated translation is output to the user in a format that is easy for foreigners to understand, based on the context.

[0006] A "user" refers to someone who uses the system to input Japanese text and receives the translated result.

[0007] "Japanese input" refers to the Japanese text or phrases that a user enters into the system.

[0008] "Context" refers to the meaning that includes the situation and background in which words are used within a text.

[0009] "Translation result" refers to the content of the conversion into another language generated based on the analyzed Japanese context.

[0010] A "generative artificial intelligence model" refers to an artificial intelligence technology that learns from large amounts of data and is used to analyze the context and unique expressions of the Japanese language.

[0011] "Cultural background" refers to an understanding of the historical and social background and context of a language.

[0012] "Past data" refers to information on various language examples and usage examples collected to date, which is used to perform contextual analysis and translation. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] 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]It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

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

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

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

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

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

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

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

[0021] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0034] This invention is a system that provides translations that take into account the context of the Japanese language. This system consists of a user, a terminal, and a server, and operates as follows:

[0035] First, the user inputs Japanese text using their device. The input text is then sent to the server as digital data.

[0036] The server uses a generative artificial intelligence model to analyze the received Japanese input and understand its context. This model is trained on a large amount of contextual data and is capable of detecting and understanding Japanese-specific expressions and underlying cultural elements.

[0037] For example, if a user enters the sentence, "It's started raining, but it has a certain charm, doesn't it?", the server will interpret the expression "has a certain charm" as referring to the sentimentality and sense of the seasons in Japanese culture.

[0038] Next, the server uses the analyzed information to generate a translation. This translation is contextual and may be output in the form of, for example, "It started raining, but it adds to the atmosphere in a way that's quite charming, reflecting the seasonal emotions uniquely felt in Japan."

[0039] Finally, the server sends the generated translation to the terminal. The terminal displays this result to the user, allowing them to gain a deeper understanding of both the original Japanese and the English translation.

[0040] This system enables foreigners who understand Japanese to grasp the content accurately without misunderstanding the underlying culture or context. The translation process ensures that the unique nuances of the Japanese language are preserved.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user inputs Japanese text using the terminal. After the user finishes inputting text on the text input screen, they press the input button to start processing.

[0044] Step 2:

[0045] The terminal formats the entered Japanese text as digital data and sends it to the server via the network. The data is formatted in JSON or XML format.

[0046] Step 3:

[0047] The server receives data sent from the terminal. It analyzes the received data and performs morphological analysis to divide the text into words and phrases.

[0048] Step 4:

[0049] The server inputs the analyzed data into an artificial intelligence model. This model uses pre-trained data to analyze the text and understand specific expressions and contexts within it.

[0050] Step 5:

[0051] The server generates contextually appropriate translations based on analysis results obtained from the artificial intelligence model. The generated translations take into account the unique emotions and cultural background of the Japanese language.

[0052] Step 6:

[0053] The server sends the translation results to the terminal. At this time, it sends both the original Japanese text and the translated text together.

[0054] Step 7:

[0055] The terminal displays the translation results received from the server to the user. This allows the user to compare the original Japanese text with the translated text and understand the context.

[0056] (Example 1)

[0057] 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."

[0058] Traditional translation systems often fail to fully understand the nuances and cultural context inherent in natural language, resulting in translations that do not accurately reflect the context. This lack of context is particularly problematic in languages ​​with strong cultural nuances, such as Japanese, leading to misunderstandings. Consequently, users may not receive accurate translations that reflect their intended meaning.

[0059] 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.

[0060] In this invention, the server includes means for receiving natural language from a user's device, means for using an artificial intelligence model to analyze the received natural language and understand its context, and means for generating translations into other languages ​​based on the analyzed contextual information. This enables contextually accurate translations that reflect complex cultural backgrounds and emotions.

[0061] "User device" refers to an electronic device used by a user to input natural language and send it to a server.

[0062] "Natural language" refers to the language that humans use on a daily basis, and in this invention, it specifically includes Japanese and its corresponding translated languages.

[0063] "Analysis" refers to the process by which a system recognizes and understands each element and context that makes up a received natural language text.

[0064] "Context" refers to the background information and related situations necessary to deeply understand the meaning of a given text or conversation.

[0065] An "artificial intelligence model" refers to a program or algorithm that learns from large amounts of data and has the ability to understand linguistic context and cultural elements.

[0066] "Translation" refers to the process of re-expressing content that has been written in one language into another language.

[0067] "Communication lines" refer to network infrastructure used to transmit and receive digital data.

[0068] "Emotion" refers to the feelings and atmosphere evoked by linguistic expressions.

[0069] "Cultural elements" refer to elements that have values, customs, or symbolic meanings specific to a particular language or society.

[0070] A "knowledge base" refers to a data structure or system that accumulates past data and information and utilizes it for analysis and decision-making.

[0071] The present invention aims to take into account context and cultural background in natural language translation. The system consists of a user, a terminal, and a server, and specifically has means for analyzing natural language text based on user input and providing translation using an advanced artificial intelligence model.

[0072] The user first inputs natural language text using a terminal. This terminal can include a typical personal computer or smartphone and must be connected to the internet. The input text is processed as digital data and sent from the terminal to the server. This communication is conducted via a secure protocol.

[0073] The server receives the incoming data and begins analysis. In this analysis, the server utilizes a generative AI model, specifically a publicly available natural language processing algorithm. Through the AI ​​model, the server can tokenize the input text contextually and extract relevant cultural background information. This process allows for the understanding of emotional expressions and elements specific to particular cultures within the text.

[0074] Next, the server generates a translation based on the analysis results. This translation is not simply a word substitution, but reflects the context and cultural background. For example, if a user inputs "It's as graceful as cherry blossoms dancing in the wind," the AI ​​model understands the symbolism of "cherry blossoms dancing" in Japanese culture and generates the English translation "It's as graceful as cherry blossoms dancing in the wind, a quintessential representation of Japanese spring."

[0075] An example of a prompt is the specific instruction, "Translate Japanese into English, taking cultural context into consideration." Based on this instruction, the server provides the AI ​​model with appropriate prompts, resulting in a more accurate translation.

[0076] Finally, the server sends the generated translation back to the terminal, which then displays it to the user. This allows the user to compare the original text with the translation and gain a deeper understanding.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The user inputs natural language text using a terminal. The input text is processed as digital data within the terminal. This data becomes the input information and is ready to be sent to the server in the next step.

[0080] Step 2:

[0081] The terminal sends the input natural language digital data to the server. A secure communication protocol is used for transmission. The server receives this data and stores it internally as the basis for the subsequent analysis.

[0082] Step 3:

[0083] The server uses a generative AI model to analyze the received natural language data. Specifically, it tokenizes the data and obtains contextual information for each word and phrase. This process involves data processing to understand the emotions and cultural background embedded in the text. As a result of this data processing, context-aware analysis data is obtained.

[0084] Step 4:

[0085] The server generates prompt sentences based on the analysis data. These prompt sentences are input into the generation AI model and serve as indicators to instruct it to generate appropriate translations. Once the generated prompt sentences are supplied to the AI ​​model, the translation process begins.

[0086] Step 5:

[0087] The generative AI model generates contextually appropriate translations. Because this translation process considers analyzed cultural and emotional elements, the translation results are not merely mechanical vocabulary conversions. As a final output, the server receives the completed translation data.

[0088] Step 6:

[0089] The server sends the generated translation data back to the terminal. A secure communication protocol is used during this process to ensure data security. The translation data is then prepared for display to the user on the terminal.

[0090] Step 7:

[0091] The device displays the received translation results to the user. The user can review the original text and the translated text, receiving an accurate translation that reflects the cultural background and context. At this step, the user can also evaluate the results and provide feedback as needed.

[0092] (Application Example 1)

[0093] 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."

[0094] With the increasing number of international users, there is a growing need for accurate understanding and translation of natural language, including an understanding of cultural background and context. However, conventional translation systems have difficulty appropriately interpreting the cultural context of complex languages ​​such as Japanese, and there is a problem in that they do not adequately provide information with a Japanese cultural background to foreign users.

[0095] 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.

[0096] In this invention, the server includes means for receiving natural language input from a user, means for analyzing the received natural language input and interpreting the context, means for generating semantic conversion results based on the interpreted context, and means for visually displaying the semantic conversion results using an augmented reality device. This makes it possible for international users to understand the context of natural language and easily obtain accurate information that reflects cultural backgrounds.

[0097] "Natural language" refers to the language that humans use on a daily basis, such as Japanese or English, rather than a specific programming language or code.

[0098] "Context" refers to the background information and circumstances necessary to understand the meaning of a particular expression in natural language.

[0099] "Semantic conversion result" refers to the output obtained by analyzing natural language input and converting it to another language, taking into account its context and culture.

[0100] "Augmented reality devices" are devices that overlay digital information onto real-world visual information, and include smart glasses and head-mounted displays.

[0101] A "visual recognition device" refers to a device that acquires information from the environment using cameras or other means and processes it as digital data.

[0102] A "generative artificial intelligence model" is a type of AI that has the ability to learn patterns from large amounts of data and analyze information, making it possible to understand linguistic context and cultural background.

[0103] "Past information" refers to data that has been collected or recorded previously and is used to aid in understanding a specific context or to improve accuracy.

[0104] The system for implementing this invention has the following configuration. First, the terminal has a function to receive natural language input from the user. This natural language input may be written information acquired through the terminal's camera or text directly entered by the user.

[0105] Next, the server uses a generative AI model to analyze the input natural language and interpret its context. This analysis employs a data-driven learning model known as a generative artificial intelligence model. This model can utilize large-scale language models such as OpenAI's GPT series.

[0106] After contextual interpretation, the server generates a semantic translation result based on the interpreted context. This translation result includes an explanation that takes into account the user's cultural background and context. The generated translation result is sent to the terminal and displayed visually to the user using an augmented reality device. For example, a device such as Google® Glass® is used.

[0107] As a concrete example, when a foreign user sees a product in a traditional Japanese shopping street, they scan the product description with their device's camera. This information is then sent to a server, where a generative AI model analyzes and translates it. As a result, the Japanese product description is displayed on the glasses' screen in English, taking cultural context into account. This allows foreign users to deepen their understanding not only of the product but also of the culture behind it.

[0108] Examples of prompt messages are as follows:

[0109] Prompt: "Translate the Japanese text considering cultural nuances: Enjoy the delicate aftertaste that differs with each matcha flavor."

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The user uses their device's camera to capture natural language text, such as product descriptions. Camera image data is generated as input and converted into text data using OPT (Optical Character Recognition). At this stage, a camera module and Tesseract OCR are used.

[0113] Step 2:

[0114] The terminal sends text data to the server. The input is the text data obtained in step 1, and the output is secure data communication to the server. This process uses a network communication protocol (e.g., HTTPS).

[0115] Step 3:

[0116] The server uses a generative AI model to perform contextual analysis on the received text. The input is the text data sent in step 2, and the output is the contextualized data analysis result. This analysis utilizes a generative AI model such as OpenAI's GPT series.

[0117] Step 4:

[0118] The server uses the contextual analysis results to generate semantic translation results that take cultural background into account. The input is the contextual analysis results, and the output is translated text data. A prompt sentence is used as an example of translation.

[0119] Step 5:

[0120] The server sends the generated semantic translation results to the terminal. The input is translated text data, and the output is data sent to the user's terminal. A network communication protocol (e.g., HTTPS) is used.

[0121] Step 6:

[0122] The terminal visually displays the received semantic translation results to the user via an augmented reality device. The input is the translation result data sent from the server, and the output is the visual information displayed on the augmented reality device. AR devices such as Google Glass are used.

[0123] Step 7:

[0124] Users deepen their understanding of products and their cultural background by overlaying digital information onto real-world visual information. The input is the visual information presented in step 6, and the output is the perception gained by the user.

[0125] 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.

[0126] This invention is a system that receives Japanese input from a user, analyzes its context and sentiment, and generates a translation. This system has a complex configuration that includes the user, a terminal, a server, and an sentiment engine.

[0127] First, the user inputs the Japanese text they want translated via their device. The device then converts this input into digital data and sends it to the server.

[0128] The server analyzes the received data, performs morphological analysis, and breaks down the text into words and phrases. At this stage, a generative artificial intelligence model is used to take into account expressions and context specific to the Japanese language. Here, the emotion engine is utilized to recognize the emotion of the input text. For example, if the user inputs "I'm so happy today!", the emotion engine detects the emotion of "joy".

[0129] Next, the server generates a translation based on the analyzed context and recognized emotions. By performing translations that reflect emotions, the system produces more accurate translations without losing the nuances of the original expression. For example, the sentence "I'm very happy today!" is translated as "I'm extremely happy today!", outputting the translation while preserving the original emotion.

[0130] The server then sends the resulting translation back to the terminal. The terminal displays this translation to the user, allowing the user to see both the original Japanese and the translation.

[0131] This system prioritizes the context of Japanese and reflects emotions, enabling it to accurately translate what the user intended. This provides translations that are easier to understand for foreigners learning Japanese and for foreigners communicating within Japan.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The user inputs Japanese text using the terminal. After input is complete, the terminal formats the input content as digital data.

[0135] Step 2:

[0136] The terminal sends formalized digital data to the server. The data arrives at the server via the network in the specified format.

[0137] Step 3:

[0138] The server analyzes the received Japanese input and performs morphological analysis. This divides the text into words and phrases, revealing its grammatical structure.

[0139] Step 4:

[0140] The server uses a generative artificial intelligence model to analyze the context of Japanese. This model learns from past data and understands the background and meaning of specific expressions.

[0141] Step 5:

[0142] The emotion engine activates and recognizes the emotions contained in the user's input. For example, it detects emotional expressions such as "happy" or "sad."

[0143] Step 6:

[0144] The server integrates the results of contextual analysis and sentiment recognition to generate an appropriate translation. The resulting translation retains the intent of the original text while reflecting its emotional tone.

[0145] Step 7:

[0146] The server sends the generated translation to the terminal. The translation is provided in a user-friendly format while preserving the original context and nuance.

[0147] Step 8:

[0148] The terminal displays the translation results received from the server to the user. Through the displayed results, the user can confirm the intent and emotion of the original expression.

[0149] (Example 2)

[0150] 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".

[0151] Providing accurate and nuanced translations between different languages ​​in natural language communication is a challenging task. In particular, translating Japanese grammar and its unique emotional expressions into other languages ​​without losing their nuances is difficult. Conventional translation systems often fail to properly recognize emotions, resulting in miscommunication of the user's intended meaning.

[0152] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0153] In this invention, the server includes means for receiving natural language input from a user, means for analyzing the received natural language input and performing formal analysis, means for performing sentiment recognition on the analyzed input, means for generating a translation result based on the context including sentiment information, and means for outputting the generated translation result to the user. This makes it possible to provide a translation that accurately reflects the context and sentiment of the Japanese input by the user.

[0154] "Natural language input" refers to text data entered in the language format that humans normally use in communication.

[0155] "Formal element analysis" is a method of breaking down a text into individual words and phrases and analyzing their parts of speech and meanings.

[0156] "Emotion recognition" is the process of analyzing and identifying the underlying emotions and sensibilities within the input text.

[0157] "Context" refers to the specific environment or situation in which a linguistic expression is used, and is the background information necessary to understand and interpret that linguistic expression.

[0158] "Translation result" refers to the text generated by converting sentences or phrases written in the original language into a different language.

[0159] "Output" refers to the process of presenting the analyzed and processed data and information to the user.

[0160] This invention is a system for translating natural language input by a user with high accuracy. This system is implemented using a user's terminal, communication via the internet, a server, and a generative AI model and emotion recognition engine.

[0161] First, the user uses their device to input the Japanese text they want to translate. This device then converts the input Japanese text into digital data and sends it to the server. Specifically, the data is digitized by entering text into an input field via an application or web browser installed on the device.

[0162] The server receives digital data and initiates a series of language processing steps. A generative AI model on the server performs formal analysis, breaking down the input text into words and phrases. Next, an emotion recognition engine recognizes emotions from the analyzed text and assigns those emotions as tags. This enables highly accurate translation that considers not only the linguistic context but also emotional nuances.

[0163] Next, the server, with the help of a generative AI model, generates a translation that reflects the context and sentiment of the Japanese text. The generated translation faithfully reproduces the nuances of the original text and achieves translation into a different language. The translated text is then sent back from the server to the user's terminal and displayed on the screen for the user to visually confirm.

[0164] For example, if a user enters the Japanese sentence "I have an important presentation tomorrow. I am feeling nervous." into their device, the server analyzes this text, performs sentiment recognition, generates a translation such as "I have an important presentation tomorrow. I am feeling nervous.", and displays it on the device.

[0165] This system facilitates communication across language barriers, enabling users to accurately convey their intended meaning and emotions. Users can view the original text and translation results on their device, deepening their understanding of the language.

[0166] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0167] Step 1:

[0168] The user uses their device to input the Japanese text they want to translate. The input text is encoded into digital data through the device's application or web browser. The input Japanese text is output as string data, and this data is ready to be sent to the server.

[0169] Step 2:

[0170] The terminal sends encoded digital data to the server via the internet. During this process, the string data is packetized according to a protocol and delivered to the server via the communication network. The output data arrives at the server and awaits analysis.

[0171] Step 3:

[0172] The server analyzes the received digital data. Specifically, it performs formal analysis using a generative AI model to divide Japanese sentences into words and phrases. This analysis helps understand the grammar and structure unique to Japanese, and generates word lists and morphological information as output.

[0173] Step 4:

[0174] The server performs sentiment recognition on the analyzed words and phrases. Using a sentiment engine, it tags each word and phrase with the associated emotion. For example, positive and negative emotions are recognized, and the output is sentiment-tagged data.

[0175] Step 5:

[0176] The server initiates the translation process based on formal analysis and sentiment information. It utilizes a generative AI model to generate a translation that reflects the nuances of the original text. The resulting translated text is an accurate cross-language conversion that takes into account the context and sentiment of the input.

[0177] Step 6:

[0178] The server sends the generated translated text back to the terminal. The terminal visually displays the received translation result to the user. The translated text is displayed on the screen, allowing the user to compare the original Japanese text with the translated content side by side.

[0179] (Application Example 2)

[0180] 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".

[0181] When conducting electronic transactions between users who speak different languages, simply translating messages can fail to convey emotions and intentions, potentially leading to misunderstandings and friction. Therefore, accurate and nuanced communication that takes the sender's feelings into consideration is essential in language translation.

[0182] 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.

[0183] In this invention, the server includes means for receiving language input, means for analyzing the language input to interpret the context and sentiment, and means for generating a translation result based on the interpreted context and sentiment. This enables natural and accurate communication that reflects emotions between users who speak different languages.

[0184] "Language input" refers to natural language text data entered by the user via a device.

[0185] "Means of interpreting context" refers to processing methods that analyze received linguistic data and understand the specific context and meaning that the language possesses.

[0186] A "means for analyzing emotions" refers to a processing method for identifying emotions from input linguistic data and analyzing those emotions.

[0187] "Means for generating translation results" refers to processing methods that create appropriate translations into other languages ​​based on the interpreted context and analyzed sentiment.

[0188] A "terminal" is an electronic device used by a user to input language and receive translation results.

[0189] "Generating" refers to the process of appropriately creating new output based on specific input data.

[0190] First, the user inputs the Japanese text they want to translate using their device. This device, such as a smartphone or PC, is responsible for sending the inputted Japanese text as digital data to the server.

[0191] To analyze the Japanese input it receives, the server first performs morphological analysis to interpret the context. In this process, it uses a generative artificial intelligence model to analyze the nuances and expressions unique to the Japanese language in detail. Furthermore, the server uses an emotion engine to identify the emotion of the input text and translates it based on that. For example, in the sentence "I had a very good deal today!" entered by the user, the emotion engine detects the emotion of "joy".

[0192] Based on the interpreted context and detected sentiment, the server generates translations into other languages. The generated translations are provided to the user while retaining the sentiment of the original expression. In this example, a possible translation might be "Today I made an excellent deal!"

[0193] The generated translation is sent to the device, which then displays it to the user. By reviewing the displayed translation, the user can engage in natural and emotionally responsive communication.

[0194] As a concrete example, by inputting the prompt "Analyze the sentiment of the following Japanese message and generate a translation that reflects the sentiment of the new message: I'm very happy today!" into the AI ​​generator, it is possible to achieve a translation that takes sentiment into account.

[0195] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0196] Step 1:

[0197] The user inputs Japanese text via the terminal. The terminal formats this text as digital data and sends it to the server. At this point, the input is the user's Japanese text, and the output is digital string data. The terminal uses a text input field to obtain the user's character input and sends that data to the server as an HTTP request.

[0198] Step 2:

[0199] The server analyzes the received Japanese data and performs morphological analysis. This process uses a generative AI model to break down the text into words and phrases and understand the context specific to the Japanese language. The input digital string data is converted into word lists and phrase lists. The server utilizes a natural language processing (NLP) library for this analysis.

[0200] Step 3:

[0201] The server uses an emotion engine to identify the emotion of a sentence based on the analyzed word list. The input here is the analyzed word list, and the output is the detected emotion (e.g., joy, sadness). The server uses a pre-trained emotion classification model to assign emotion labels to the input sentence.

[0202] Step 4:

[0203] The server generates translation results using the analyzed context and detected sentiment. A generative AI model is used to translate into other languages, maximizing the reflection of context and sentiment. In this step, context- and sentiment-based prompt sentences are provided to the generative AI, and the translation is obtained. The input is context and sentiment data, and the output is the translated sentence.

[0204] Step 5:

[0205] The server sends the generated translation to the terminal. The terminal displays this translation to the user. The input is the translated text, and the output is the translated result presented visually to the user. The terminal displays the translated result to the user in an easy-to-understand manner through HTML or the application's GUI.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] [Second Embodiment]

[0210] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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).

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] 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".

[0222] This invention is a system that provides translations that take into account the context of the Japanese language. This system consists of a user, a terminal, and a server, and operates as follows:

[0223] First, the user inputs Japanese text using their device. The input text is then sent to the server as digital data.

[0224] The server uses a generative artificial intelligence model to analyze the received Japanese input and understand its context. This model is trained on a large amount of contextual data and is capable of detecting and understanding Japanese-specific expressions and underlying cultural elements.

[0225] For example, if a user enters the sentence, "It's started raining, but it has a certain charm, doesn't it?", the server will interpret the expression "has a certain charm" as referring to the sentimentality and sense of the seasons in Japanese culture.

[0226] Next, the server uses the analyzed information to generate a translation. This translation is contextual and may be output in the form of, for example, "It started raining, but it adds to the atmosphere in a way that's quite charming, reflecting the seasonal emotions uniquely felt in Japan."

[0227] Finally, the server sends the generated translation to the terminal. The terminal displays this result to the user, allowing them to gain a deeper understanding of both the original Japanese and the English translation.

[0228] This system enables foreigners who understand Japanese to grasp the content accurately without misunderstanding the underlying culture or context. The translation process ensures that the unique nuances of the Japanese language are preserved.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] The user inputs Japanese text using the terminal. After the user finishes inputting text on the text input screen, they press the input button to start processing.

[0232] Step 2:

[0233] The terminal formats the entered Japanese text as digital data and sends it to the server via the network. The data is formatted in JSON or XML format.

[0234] Step 3:

[0235] The server receives data sent from the terminal. It analyzes the received data and performs morphological analysis to divide the text into words and phrases.

[0236] Step 4:

[0237] The server inputs the analyzed data into an artificial intelligence model. This model uses pre-trained data to analyze the text and understand specific expressions and contexts within it.

[0238] Step 5:

[0239] The server generates contextually appropriate translations based on analysis results obtained from the artificial intelligence model. The generated translations take into account the unique emotions and cultural background of the Japanese language.

[0240] Step 6:

[0241] The server sends the translation results to the terminal. At this time, it sends both the original Japanese text and the translated text together.

[0242] Step 7:

[0243] The terminal displays the translation results received from the server to the user. This allows the user to compare the original Japanese text with the translated text and understand the context.

[0244] (Example 1)

[0245] 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."

[0246] Traditional translation systems often fail to fully understand the nuances and cultural context inherent in natural language, resulting in translations that do not accurately reflect the context. This lack of context is particularly problematic in languages ​​with strong cultural nuances, such as Japanese, leading to misunderstandings. Consequently, users may not receive accurate translations that reflect their intended meaning.

[0247] 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.

[0248] In this invention, the server includes means for receiving natural language from a user's device, means for using an artificial intelligence model to analyze the received natural language and understand its context, and means for generating translations into other languages ​​based on the analyzed contextual information. This enables contextually accurate translations that reflect complex cultural backgrounds and emotions.

[0249] "User device" refers to an electronic device used by a user to input natural language and send it to a server.

[0250] "Natural language" refers to the language that humans use on a daily basis, and in this invention, it specifically includes Japanese and its corresponding translated languages.

[0251] "Analysis" refers to the process by which a system recognizes and understands each element and context that makes up a received natural language text.

[0252] "Context" refers to the background information and related situations necessary to deeply understand the meaning of a given text or conversation.

[0253] An "artificial intelligence model" refers to a program or algorithm that learns from large amounts of data and has the ability to understand linguistic context and cultural elements.

[0254] "Translation" refers to the process of re-expressing content that has been written in one language into another language.

[0255] "Communication lines" refer to network infrastructure used to transmit and receive digital data.

[0256] "Emotion" refers to the feelings and atmosphere evoked by linguistic expressions.

[0257] "Cultural elements" refer to elements that have values, customs, or symbolic meanings specific to a particular language or society.

[0258] A "knowledge base" refers to a data structure or system that accumulates past data and information and utilizes it for analysis and decision-making.

[0259] The system of the present invention aims to take into account context and cultural background in natural language translation. The system consists of a user, a terminal, and a server, and specifically has means for analyzing natural language text based on user input and providing translation using an advanced artificial intelligence model.

[0260] The user first inputs natural language text using a terminal. This terminal can include a typical personal computer or smartphone and must be connected to the internet. The input text is processed as digital data and sent from the terminal to the server. This communication is conducted via a secure protocol.

[0261] The server receives the incoming data and begins analysis. In this analysis, the server utilizes a generative AI model, specifically a publicly available natural language processing algorithm. Through the AI ​​model, the server can tokenize the input text contextually and extract relevant cultural background information. This process allows for the understanding of emotional expressions and elements specific to particular cultures within the text.

[0262] Next, the server generates a translation based on the analysis results. This translation is not simply a word substitution, but reflects the context and cultural background. For example, if a user inputs "It's as graceful as cherry blossoms dancing in the wind," the AI ​​model understands the symbolism of "cherry blossoms dancing" in Japanese culture and generates the English translation "It's as graceful as cherry blossoms dancing in the wind, a quintessential representation of Japanese spring."

[0263] An example of a prompt is the specific instruction, "Translate Japanese into English, taking cultural context into consideration." Based on this instruction, the server provides the AI ​​model with appropriate prompts, resulting in a more accurate translation.

[0264] Finally, the server sends the generated translation back to the terminal, which then displays it to the user. This allows the user to compare the original text with the translation and gain a deeper understanding.

[0265] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0266] Step 1:

[0267] The user inputs natural language text using a terminal. The input text is processed as digital data within the terminal. This data becomes the input information and is ready to be sent to the server in the next step.

[0268] Step 2:

[0269] The terminal sends the input natural language digital data to the server. A secure communication protocol is used for transmission. The server receives this data and stores it internally as the basis for the subsequent analysis.

[0270] Step 3:

[0271] The server uses a generative AI model to analyze the received natural language data. Specifically, it tokenizes the data and obtains contextual information for each word and phrase. This process involves data processing to understand the emotions and cultural background embedded in the text. As a result of this data processing, context-aware analysis data is obtained.

[0272] Step 4:

[0273] The server generates prompt sentences based on the analysis data. These prompt sentences are input into the generation AI model and serve as indicators to instruct it to generate appropriate translations. Once the generated prompt sentences are supplied to the AI ​​model, the translation process begins.

[0274] Step 5:

[0275] The generative AI model generates contextually appropriate translations. Because this translation process considers analyzed cultural and emotional elements, the translation results are not merely mechanical vocabulary conversions. As a final output, the server receives the completed translation data.

[0276] Step 6:

[0277] The server sends the generated translation data back to the terminal. A secure communication protocol is used during this process to ensure data security. The translation data is then prepared for display to the user on the terminal.

[0278] Step 7:

[0279] The device displays the received translation results to the user. The user can review the original text and the translated text, receiving an accurate translation that reflects the cultural background and context. At this step, the user can also evaluate the results and provide feedback as needed.

[0280] (Application Example 1)

[0281] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0282] With the increasing number of international users, accurate understanding and translation of natural languages, including cultural backgrounds and context understanding, are required. However, in conventional translation systems, it is difficult to appropriately interpret cultural contexts in complex languages such as Japanese, and there is a problem that information provision based on Japanese culture is incomplete, especially for foreign users.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0284] In this invention, the server includes means for receiving a natural language input from a user, means for analyzing the received natural language input to interpret the context, means for generating a meaning conversion result based on the interpreted context, and means for visually displaying the meaning conversion result using an augmented reality device. As a result, international users can understand the context of natural languages and easily obtain accurate information reflecting the cultural background.

[0285] "Natural language" refers to the language that humans use in daily life, and refers to languages such as Japanese and English, rather than specific programming languages or codes.

[0286] "Context" refers to the background information and situations necessary for understanding the meaning of a specific expression in natural language.

[0287] "Meaning conversion result" refers to the output obtained by analyzing a natural language input and converting it into another language in consideration of its context and culture.

[0288] "Augmented reality device" refers to a device that overlays digital information on real visual information, and includes smart glasses and head-mounted displays. <000091​​A "visual recognition device" refers to a device that acquires information from the environment using cameras or other means and processes it as digital data.

[0290] A "generative artificial intelligence model" is a type of AI that has the ability to learn patterns from large amounts of data and analyze information, making it possible to understand linguistic context and cultural background.

[0291] "Past information" refers to data that has been collected or recorded previously and is used to aid in understanding a specific context or to improve accuracy.

[0292] The system for implementing this invention has the following configuration. First, the terminal has a function to receive natural language input from the user. This natural language input may be written information acquired through the terminal's camera or text directly entered by the user.

[0293] Next, the server uses a generative AI model to analyze the input natural language and interpret its context. This analysis employs a data-driven learning model known as a generative artificial intelligence model. This model can utilize large-scale language models such as OpenAI's GPT series.

[0294] After contextual interpretation, the server generates a semantic translation result based on the interpreted context. This translation result includes an explanation that takes into account the user's cultural background and context. The generated translation result is sent to the terminal and displayed visually to the user using an augmented reality device. For example, a device like Google Glass is used.

[0295] As a concrete example, when a foreign user sees a product in a traditional Japanese shopping street, they scan the product description with their device's camera. This information is then sent to a server, where a generative AI model analyzes and translates it. As a result, the Japanese description of the product is displayed on the glasses' screen as an English description that takes cultural context into account. This allows foreign users to deepen their understanding not only of the product but also of the culture behind it.

[0296] Examples of prompt messages are as follows:

[0297] Prompt: "Translate the Japanese text considering cultural nuances: Enjoy the delicate aftertaste that differs with each matcha flavor."

[0298] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0299] Step 1:

[0300] The user uses their device's camera to capture natural language text, such as product descriptions. Camera image data is generated as input and converted into text data using OPT (Optical Character Recognition). At this stage, a camera module and Tesseract OCR are used.

[0301] Step 2:

[0302] The terminal sends text data to the server. The input is the text data obtained in step 1, and the output is secure data communication to the server. This process uses a network communication protocol (e.g., HTTPS).

[0303] Step 3:

[0304] The server uses a generative AI model to perform contextual analysis on the received text. The input is the text data sent in step 2, and the output is the contextualized data analysis result. This analysis utilizes a generative AI model such as OpenAI's GPT series.

[0305] Step 4:

[0306] The server generates a meaning conversion result considering the cultural background using the context analysis result. The input is the context analysis result, and the output is the translated text data. A prompt sentence is used as a translation example.

[0307] Step 5:

[0308] The server sends the generated meaning conversion result to the terminal. The input is the translated text data, and the output is the data transmission to the user's terminal. A network communication protocol (e.g., HTTPS) is used.

[0309] Step 6:

[0310] The terminal visually displays the received meaning conversion result to the user through an augmented reality device. The input is the translation result data sent from the server, and the output is the visual information displayed on the augmented reality device. An AR device such as Google Glass is used.

[0311] Step 7:

[0312] <0ooo0983>The user deepens their understanding of the product and its cultural background in a state where digital information is overlaid on the real visual information. The input is the visual information presented in Step 6, and the output is the cognition obtained by the user.

[0313] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0314] The present invention is a system that receives a Japanese input from a user, analyzes its context and emotion, and generates a translation. This system has a complex configuration including a user, a terminal, a server, and an emotion engine.

[0315] First, the user inputs a Japanese sentence for which translation is desired via the terminal. The terminal serves to convert this input into digital data and send it to the server.

[0316] The server analyzes the received data, performs morphological analysis, and breaks down the text into words and phrases. At this stage, a generative artificial intelligence model is used to take into account expressions and context specific to the Japanese language. Here, the emotion engine is utilized to recognize the emotion of the input text. For example, if the user inputs "I'm so happy today!", the emotion engine detects the emotion of "joy".

[0317] Next, the server generates a translation based on the analyzed context and recognized emotions. By performing translations that reflect emotions, the system produces more accurate translations without losing the nuances of the original expression. For example, the sentence "I'm very happy today!" is translated as "I'm extremely happy today!", outputting the translation while preserving the original emotion.

[0318] The server then sends the resulting translation back to the terminal. The terminal displays this translation to the user, allowing the user to see both the original Japanese and the translation.

[0319] This system prioritizes the context of Japanese and reflects emotions, enabling it to accurately translate what the user intended. This provides translations that are easier to understand for foreigners learning Japanese and for foreigners communicating within Japan.

[0320] The following describes the processing flow.

[0321] Step 1:

[0322] The user inputs Japanese text using the terminal. After input is complete, the terminal formats the input content as digital data.

[0323] Step 2:

[0324] The terminal sends formalized digital data to the server. The data arrives at the server via the network in the specified format.

[0325] Step 3:

[0326] The server analyzes the received Japanese input and performs morphological analysis. This divides the text into words and phrases, revealing its grammatical structure.

[0327] Step 4:

[0328] The server uses a generative artificial intelligence model to analyze the context of Japanese. This model learns from past data and understands the background and meaning of specific expressions.

[0329] Step 5:

[0330] The emotion engine activates and recognizes the emotions contained in the user's input. For example, it detects emotional expressions such as "happy" or "sad."

[0331] Step 6:

[0332] The server integrates the results of contextual analysis and sentiment recognition to generate an appropriate translation. The resulting translation retains the intent of the original text while reflecting its emotional tone.

[0333] Step 7:

[0334] The server sends the generated translation to the terminal. The translation is provided in a user-friendly format while preserving the original context and nuance.

[0335] Step 8:

[0336] The terminal displays the translation results received from the server to the user. Through the displayed results, the user can confirm the intent and emotion of the original expression.

[0337] (Example 2)

[0338] 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".

[0339] Providing accurate and nuanced translations between different languages ​​in natural language communication is a challenging task. In particular, translating Japanese grammar and its unique emotional expressions into other languages ​​without losing their nuances is difficult. Conventional translation systems often fail to properly recognize emotions, resulting in miscommunication of the user's intended meaning.

[0340] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0341] In this invention, the server includes means for receiving natural language input from a user, means for analyzing the received natural language input and performing formal analysis, means for performing sentiment recognition on the analyzed input, means for generating a translation result based on the context including sentiment information, and means for outputting the generated translation result to the user. This makes it possible to provide a translation that accurately reflects the context and sentiment of the Japanese input by the user.

[0342] "Natural language input" refers to text data entered in the language format that humans normally use in communication.

[0343] "Formal element analysis" is a method of breaking down a text into individual words and phrases and analyzing their parts of speech and meanings.

[0344] "Emotion recognition" is the process of analyzing and identifying the underlying emotions and sensibilities within the input text.

[0345] "Context" refers to the specific environment or situation in which a linguistic expression is used, and is the background information necessary to understand and interpret that linguistic expression.

[0346] "Translation result" refers to the text generated by converting sentences or phrases written in the original language into a different language.

[0347] "Output" refers to the process of presenting the analyzed and processed data and information to the user.

[0348] This invention is a system for translating natural language input by a user with high accuracy. This system is implemented using a user's terminal, communication via the internet, a server, and a generative AI model and emotion recognition engine.

[0349] First, the user uses their device to input the Japanese text they want to translate. This device then converts the input Japanese text into digital data and sends it to the server. Specifically, the data is digitized by entering text into an input field via an application or web browser installed on the device.

[0350] The server receives digital data and initiates a series of language processing steps. A generative AI model on the server performs formal analysis, breaking down the input text into words and phrases. Next, an emotion recognition engine recognizes emotions from the analyzed text and assigns those emotions as tags. This enables highly accurate translation that considers not only the linguistic context but also emotional nuances.

[0351] Next, the server, with the help of a generative AI model, generates a translation that reflects the context and sentiment of the Japanese text. The generated translation faithfully reproduces the nuances of the original text and achieves translation into a different language. The translated text is then sent back from the server to the user's terminal and displayed on the screen for the user to visually confirm.

[0352] For example, if a user enters the Japanese sentence "I have an important presentation tomorrow. I am feeling nervous." into their device, the server analyzes this text, performs sentiment recognition, generates a translation such as "I have an important presentation tomorrow. I am feeling nervous.", and displays it on the device.

[0353] This system facilitates communication across language barriers, enabling users to accurately convey their intended meaning and emotions. Users can view the original text and translation results on their device, deepening their understanding of the language.

[0354] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0355] Step 1:

[0356] The user uses their device to input the Japanese text they want to translate. The input text is encoded into digital data through the device's application or web browser. The input Japanese text is output as string data, and this data is ready to be sent to the server.

[0357] Step 2:

[0358] The terminal sends encoded digital data to the server via the internet. During this process, the string data is packetized according to a protocol and delivered to the server via the communication network. The output data arrives at the server and awaits analysis.

[0359] Step 3:

[0360] The server analyzes the received digital data. Specifically, it performs formal analysis using a generative AI model to divide Japanese sentences into words and phrases. This analysis helps understand the grammar and structure unique to Japanese, and generates word lists and morphological information as output.

[0361] Step 4:

[0362] The server performs sentiment recognition on the analyzed words and phrases. Using a sentiment engine, it tags each word and phrase with the associated emotion. For example, positive and negative emotions are recognized, and the output is sentiment-tagged data.

[0363] Step 5:

[0364] The server initiates the translation process based on formal analysis and sentiment information. It utilizes a generative AI model to generate a translation that reflects the nuances of the original text. The resulting translated text is an accurate cross-language conversion that takes into account the context and sentiment of the input.

[0365] Step 6:

[0366] The server sends the generated translated text back to the terminal. The terminal visually displays the received translation result to the user. The translated text is displayed on the screen, allowing the user to compare the original Japanese text with the translated content side by side.

[0367] (Application Example 2)

[0368] 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."

[0369] When conducting electronic transactions between users who speak different languages, simply translating messages can fail to convey emotions and intentions, potentially leading to misunderstandings and friction. Therefore, accurate and nuanced communication that takes the sender's feelings into consideration is essential in language translation.

[0370] 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.

[0371] In this invention, the server includes means for receiving language input, means for analyzing the language input to interpret the context and sentiment, and means for generating a translation result based on the interpreted context and sentiment. This enables natural and accurate communication that reflects emotions between users who speak different languages.

[0372] "Language input" refers to natural language text data entered by the user via a device.

[0373] "Means of interpreting context" refers to processing methods that analyze received linguistic data and understand the specific context and meaning that the language possesses.

[0374] A "means for analyzing emotions" refers to a processing method for identifying emotions from input linguistic data and analyzing those emotions.

[0375] "Means for generating translation results" refers to processing methods that create appropriate translations into other languages ​​based on the interpreted context and analyzed sentiment.

[0376] A "terminal" is an electronic device used by a user to input language and receive translation results.

[0377] "Generating" refers to the process of appropriately creating new output based on specific input data.

[0378] First, the user inputs the Japanese text they want to translate using their device. This device, such as a smartphone or PC, is responsible for sending the inputted Japanese text as digital data to the server.

[0379] To analyze the Japanese input it receives, the server first performs morphological analysis to interpret the context. In this process, it uses a generative artificial intelligence model to analyze the nuances and expressions unique to the Japanese language in detail. Furthermore, the server uses an emotion engine to identify the emotion of the input text and translates it based on that. For example, in the sentence "I had a very good deal today!" entered by the user, the emotion engine detects the emotion of "joy".

[0380] Based on the interpreted context and detected sentiment, the server generates translations into other languages. The generated translations are provided to the user while retaining the sentiment of the original expression. In this example, a possible translation might be "Today I made an excellent deal!"

[0381] The generated translation is sent to the device, which then displays it to the user. By reviewing the displayed translation, the user can engage in natural and emotionally responsive communication.

[0382] As a concrete example, by inputting the prompt "Analyze the sentiment of the following Japanese message and generate a translation that reflects the sentiment of the new message: I'm very happy today!" into the AI ​​generator, it is possible to achieve a translation that takes sentiment into account.

[0383] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0384] Step 1:

[0385] The user inputs Japanese text via the terminal. The terminal formats this text as digital data and sends it to the server. At this point, the input is the user's Japanese text, and the output is digital string data. The terminal uses a text input field to obtain the user's character input and sends that data to the server as an HTTP request.

[0386] Step 2:

[0387] The server analyzes the received Japanese data and performs morphological analysis. This process uses a generative AI model to break down the text into words and phrases and understand the context specific to the Japanese language. The input digital string data is converted into word lists and phrase lists. The server utilizes a natural language processing (NLP) library for this analysis.

[0388] Step 3:

[0389] The server uses an emotion engine to identify the emotion of a sentence based on the analyzed word list. The input here is the analyzed word list, and the output is the detected emotion (e.g., joy, sadness). The server uses a pre-trained emotion classification model to assign emotion labels to the input sentence.

[0390] Step 4:

[0391] The server generates translation results using the analyzed context and detected sentiment. A generative AI model is used to translate into other languages, maximizing the reflection of context and sentiment. In this step, context- and sentiment-based prompt sentences are provided to the generative AI, and the translation is obtained. The input is context and sentiment data, and the output is the translated sentence.

[0392] Step 5:

[0393] The server sends the generated translation to the terminal. The terminal displays this translation to the user. The input is the translated text, and the output is the translated result presented visually to the user. The terminal displays the translated result to the user in an easy-to-understand manner through HTML or the application's GUI.

[0394] 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.

[0395] 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.

[0396] 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.

[0397] [Third Embodiment]

[0398] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0399] 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.

[0400] 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).

[0401] 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.

[0402] 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.

[0403] 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).

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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".

[0410] This invention is a system that provides translations that take into account the context of the Japanese language. This system consists of a user, a terminal, and a server, and operates as follows:

[0411] First, the user inputs Japanese text using their device. The input text is then sent to the server as digital data.

[0412] The server uses a generative artificial intelligence model to analyze the received Japanese input and understand its context. This model is trained on a large amount of contextual data and is capable of detecting and understanding Japanese-specific expressions and underlying cultural elements.

[0413] For example, if a user enters the sentence, "It's started raining, but it has a certain charm, doesn't it?", the server will interpret the expression "has a certain charm" as referring to the sentimentality and sense of the seasons in Japanese culture.

[0414] Next, the server uses the analyzed information to generate a translation. This translation is contextual and may be output in the form of, for example, "It started raining, but it adds to the atmosphere in a way that's quite charming, reflecting the seasonal emotions uniquely felt in Japan."

[0415] Finally, the server sends the generated translation to the terminal. The terminal displays this result to the user, allowing them to gain a deeper understanding of both the original Japanese and the English translation.

[0416] This system enables foreigners who understand Japanese to grasp the content accurately without misunderstanding the underlying culture or context. The translation process ensures that the unique nuances of the Japanese language are preserved.

[0417] The following describes the processing flow.

[0418] Step 1:

[0419] The user inputs Japanese text using the terminal. After the user finishes inputting text on the text input screen, they press the input button to start processing.

[0420] Step 2:

[0421] The terminal formats the entered Japanese text as digital data and sends it to the server via the network. The data is formatted in JSON or XML format.

[0422] Step 3:

[0423] The server receives data sent from the terminal. It analyzes the received data and performs morphological analysis to divide the text into words and phrases.

[0424] Step 4:

[0425] The server inputs the analyzed data into an artificial intelligence model. This model uses pre-trained data to analyze the text and understand specific expressions and contexts within it.

[0426] Step 5:

[0427] The server generates contextually appropriate translations based on analysis results obtained from the artificial intelligence model. The generated translations take into account the unique emotions and cultural background of the Japanese language.

[0428] Step 6:

[0429] The server sends the translation results to the terminal. At this time, it sends both the original Japanese text and the translated text together.

[0430] Step 7:

[0431] The terminal displays the translation results received from the server to the user. This allows the user to compare the original Japanese text with the translated text and understand the context.

[0432] (Example 1)

[0433] 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."

[0434] Traditional translation systems often fail to fully understand the nuances and cultural context inherent in natural language, resulting in translations that do not accurately reflect the context. This lack of context is particularly problematic in languages ​​with strong cultural nuances, such as Japanese, leading to misunderstandings. Consequently, users may not receive accurate translations that reflect their intended meaning.

[0435] 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.

[0436] In this invention, the server includes means for receiving natural language from a user's device, means for using an artificial intelligence model to analyze the received natural language and understand its context, and means for generating translations into other languages ​​based on the analyzed contextual information. This enables contextually accurate translations that reflect complex cultural backgrounds and emotions.

[0437] "User device" refers to an electronic device used by a user to input natural language and send it to a server.

[0438] "Natural language" refers to the language that humans use on a daily basis, and in this invention, it specifically includes Japanese and its corresponding translated languages.

[0439] "Analysis" refers to the process by which a system recognizes and understands each element and context that makes up a received natural language text.

[0440] "Context" refers to the background information and related situations necessary to deeply understand the meaning of a given text or conversation.

[0441] An "artificial intelligence model" refers to a program or algorithm that learns from large amounts of data and has the ability to understand linguistic context and cultural elements.

[0442] "Translation" refers to the process of re-expressing content that has been written in one language into another language.

[0443] "Communication lines" refer to network infrastructure used to transmit and receive digital data.

[0444] "Emotion" refers to the feelings and atmosphere evoked by linguistic expressions.

[0445] "Cultural elements" refer to elements that have values, customs, or symbolic meanings specific to a particular language or society.

[0446] A "knowledge base" refers to a data structure or system that accumulates past data and information and utilizes it for analysis and decision-making.

[0447] The system of the present invention aims to take into account context and cultural background in natural language translation. The system consists of a user, a terminal, and a server, and specifically has means for analyzing natural language text based on user input and providing translation using an advanced artificial intelligence model.

[0448] The user first inputs natural language text using a terminal. This terminal can include a typical personal computer or smartphone and must be connected to the internet. The input text is processed as digital data and sent from the terminal to the server. This communication is conducted via a secure protocol.

[0449] The server receives the incoming data and begins analysis. In this analysis, the server utilizes a generative AI model, specifically a publicly available natural language processing algorithm. Through the AI ​​model, the server can tokenize the input text contextually and extract relevant cultural background information. This process allows for the understanding of emotional expressions and elements specific to particular cultures within the text.

[0450] Next, the server generates a translation based on the analysis results. This translation is not simply a word substitution, but reflects the context and cultural background. For example, if a user inputs "It's as graceful as cherry blossoms dancing in the wind," the AI ​​model understands the symbolism of "cherry blossoms dancing" in Japanese culture and generates the English translation "It's as graceful as cherry blossoms dancing in the wind, a quintessential representation of Japanese spring."

[0451] An example of a prompt is the specific instruction, "Translate Japanese into English, taking cultural context into consideration." Based on this instruction, the server provides the AI ​​model with appropriate prompts, resulting in a more accurate translation.

[0452] Finally, the server sends the generated translation back to the terminal, which then displays it to the user. This allows the user to compare the original text with the translation and gain a deeper understanding.

[0453] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0454] Step 1:

[0455] The user inputs natural language text using a terminal. The input text is processed as digital data within the terminal. This data becomes the input information and is ready to be sent to the server in the next step.

[0456] Step 2:

[0457] The terminal sends the input natural language digital data to the server. A secure communication protocol is used for transmission. The server receives this data and stores it internally as the basis for the subsequent analysis.

[0458] Step 3:

[0459] The server uses a generative AI model to analyze the received natural language data. Specifically, it tokenizes the data and obtains contextual information for each word and phrase. This process involves data processing to understand the emotions and cultural background embedded in the text. As a result of this data processing, context-aware analysis data is obtained.

[0460] Step 4:

[0461] The server generates prompt sentences based on the analysis data. These prompt sentences are input into the generation AI model and serve as indicators to instruct it to generate appropriate translations. Once the generated prompt sentences are supplied to the AI ​​model, the translation process begins.

[0462] Step 5:

[0463] The generative AI model generates contextually appropriate translations. Because this translation process considers analyzed cultural and emotional elements, the translation results are not merely mechanical vocabulary conversions. As a final output, the server receives the completed translation data.

[0464] Step 6:

[0465] The server sends the generated translation data back to the terminal. A secure communication protocol is used during this process to ensure data security. The translation data is then prepared for display to the user on the terminal.

[0466] Step 7:

[0467] The device displays the received translation results to the user. The user can review the original text and the translated text, receiving an accurate translation that reflects the cultural background and context. At this step, the user can also evaluate the results and provide feedback as needed.

[0468] (Application Example 1)

[0469] 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."

[0470] With the increasing number of international users, there is a growing need for accurate understanding and translation of natural language, including an understanding of cultural background and context. However, conventional translation systems have difficulty appropriately interpreting the cultural context of complex languages ​​such as Japanese, and there is a problem in that they do not adequately provide information with a Japanese cultural background to foreign users.

[0471] 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.

[0472] In this invention, the server includes means for receiving natural language input from a user, means for analyzing the received natural language input and interpreting the context, means for generating semantic conversion results based on the interpreted context, and means for visually displaying the semantic conversion results using an augmented reality device. This makes it possible for international users to understand the context of natural language and easily obtain accurate information that reflects cultural backgrounds.

[0473] "Natural language" refers to the language that humans use on a daily basis, such as Japanese or English, rather than a specific programming language or code.

[0474] "Context" refers to the background information and circumstances necessary to understand the meaning of a particular expression in natural language.

[0475] "Semantic conversion result" refers to the output obtained by analyzing natural language input and converting it to another language, taking into account its context and culture.

[0476] "Augmented reality devices" are devices that overlay digital information onto real-world visual information, and include smart glasses and head-mounted displays.

[0477] A "visual recognition device" refers to a device that acquires information from the environment using cameras or other means and processes it as digital data.

[0478] A "generative artificial intelligence model" is a type of AI that has the ability to learn patterns from large amounts of data and analyze information, making it possible to understand linguistic context and cultural background.

[0479] "Past information" refers to data that has been collected or recorded previously and is used to aid in understanding a specific context or to improve accuracy.

[0480] The system for implementing this invention has the following configuration. First, the terminal has a function to receive natural language input from the user. This natural language input may be written information acquired through the terminal's camera or text directly entered by the user.

[0481] Next, the server uses a generative AI model to analyze the input natural language and interpret its context. This analysis employs a data-driven learning model known as a generative artificial intelligence model. This model can utilize large-scale language models such as OpenAI's GPT series.

[0482] After contextual interpretation, the server generates a semantic translation result based on the interpreted context. This translation result includes an explanation that takes into account the user's cultural background and context. The generated translation result is sent to the terminal and displayed visually to the user using an augmented reality device. For example, a device like Google Glass is used.

[0483] As a concrete example, when a foreign user sees a product in a traditional Japanese shopping street, they scan the product description with their device's camera. This information is then sent to a server, where a generative AI model analyzes and translates it. As a result, the Japanese description of the product is displayed on the glasses' screen as an English description that takes cultural context into account. This allows foreign users to deepen their understanding not only of the product but also of the culture behind it.

[0484] Examples of prompt messages are as follows:

[0485] Prompt: "Translate the Japanese text considering cultural nuances: Enjoy the delicate aftertaste that differs with each matcha flavor."

[0486] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0487] Step 1:

[0488] The user uses their device's camera to capture natural language text, such as product descriptions. Camera image data is generated as input and converted into text data using OPT (Optical Character Recognition). At this stage, a camera module and Tesseract OCR are used.

[0489] Step 2:

[0490] The terminal sends text data to the server. The input is the text data obtained in step 1, and the output is secure data communication to the server. This process uses a network communication protocol (e.g., HTTPS).

[0491] Step 3:

[0492] The server uses a generative AI model to perform contextual analysis on the received text. The input is the text data sent in step 2, and the output is the contextualized data analysis result. This analysis utilizes a generative AI model such as OpenAI's GPT series.

[0493] Step 4:

[0494] The server uses the contextual analysis results to generate semantic translation results that take cultural background into account. The input is the contextual analysis results, and the output is translated text data. A prompt sentence is used as an example of translation.

[0495] Step 5:

[0496] The server sends the generated semantic translation results to the terminal. The input is translated text data, and the output is data sent to the user's terminal. A network communication protocol (e.g., HTTPS) is used.

[0497] Step 6:

[0498] The terminal visually displays the received semantic translation results to the user via an augmented reality device. The input is the translation result data sent from the server, and the output is the visual information displayed on the augmented reality device. AR devices such as Google Glass are used.

[0499] Step 7:

[0500] Users deepen their understanding of products and their cultural background by overlaying digital information onto real-world visual information. The input is the visual information presented in step 6, and the output is the perception gained by the user.

[0501] 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.

[0502] This invention is a system that receives Japanese input from a user, analyzes its context and sentiment, and generates a translation. This system has a complex configuration that includes the user, a terminal, a server, and an sentiment engine.

[0503] First, the user inputs the Japanese text they want translated via their device. The device then converts this input into digital data and sends it to the server.

[0504] The server analyzes the received data, performs morphological analysis, and breaks down the text into words and phrases. At this stage, a generative artificial intelligence model is used to take into account expressions and context specific to the Japanese language. Here, the emotion engine is utilized to recognize the emotion of the input text. For example, if the user inputs "I'm so happy today!", the emotion engine detects the emotion of "joy".

[0505] Next, the server generates a translation based on the analyzed context and recognized emotions. By performing translations that reflect emotions, the system produces more accurate translations without losing the nuances of the original expression. For example, the sentence "I'm very happy today!" is translated as "I'm extremely happy today!", outputting the translation while preserving the original emotion.

[0506] The server then sends the resulting translation back to the terminal. The terminal displays this translation to the user, allowing the user to see both the original Japanese and the translation.

[0507] This system prioritizes the context of Japanese and reflects emotions, enabling it to accurately translate what the user intended. This provides translations that are easier to understand for foreigners learning Japanese and for foreigners communicating within Japan.

[0508] The following describes the processing flow.

[0509] Step 1:

[0510] The user inputs Japanese text using the terminal. After input is complete, the terminal formats the input content as digital data.

[0511] Step 2:

[0512] The terminal sends formalized digital data to the server. The data arrives at the server via the network in the specified format.

[0513] Step 3:

[0514] The server analyzes the received Japanese input and performs morphological analysis. This divides the text into words and phrases, revealing its grammatical structure.

[0515] Step 4:

[0516] The server uses a generative artificial intelligence model to analyze the context of Japanese. This model learns from past data and understands the background and meaning of specific expressions.

[0517] Step 5:

[0518] The emotion engine activates and recognizes the emotions contained in the user's input. For example, it detects emotional expressions such as "happy" or "sad."

[0519] Step 6:

[0520] The server integrates the results of contextual analysis and sentiment recognition to generate an appropriate translation. The resulting translation reflects the emotions of the original text without compromising its intent.

[0521] Step 7:

[0522] The server sends the generated translation to the terminal. The translation is provided in a user-friendly format while preserving the original context and nuance.

[0523] Step 8:

[0524] The terminal displays the translation results received from the server to the user. Through the displayed results, the user can confirm the intent and emotion of the original expression.

[0525] (Example 2)

[0526] 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."

[0527] Providing accurate and nuanced translations between different languages ​​in natural language communication is a challenging task. In particular, translating Japanese grammar and its unique emotional expressions into other languages ​​without losing their nuances is difficult. Conventional translation systems often fail to properly recognize emotions, resulting in miscommunication of the user's intended meaning.

[0528] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0529] In this invention, the server includes means for receiving natural language input from a user, means for analyzing the received natural language input and performing formal analysis, means for performing sentiment recognition on the analyzed input, means for generating a translation result based on the context including sentiment information, and means for outputting the generated translation result to the user. This makes it possible to provide a translation that accurately reflects the context and sentiment of the Japanese input by the user.

[0530] "Natural language input" refers to text data entered in the language format that humans normally use in communication.

[0531] "Formal element analysis" is a method of breaking down a text into individual words and phrases and analyzing their parts of speech and meanings.

[0532] "Emotion recognition" is the process of analyzing and identifying the underlying emotions and sensibilities within the input text.

[0533] "Context" refers to the specific environment or situation in which a linguistic expression is used, and is the background information necessary to understand and interpret that linguistic expression.

[0534] "Translation result" refers to the text generated by converting sentences or phrases written in the original language into a different language.

[0535] "Output" refers to the process of presenting the analyzed and processed data and information to the user.

[0536] This invention is a system for translating user-inputted natural language with high accuracy. This system is implemented using a user's terminal, communication via the internet, a server, and a generative AI model and emotion recognition engine.

[0537] First, the user uses their device to input the Japanese text they want to translate. This device then converts the input Japanese text into digital data and sends it to the server. Specifically, the data is digitized by entering text into an input field via an application or web browser installed on the device.

[0538] The server receives digital data and initiates a series of language processing steps. A generative AI model on the server performs formal analysis, breaking down the input text into words and phrases. Next, an emotion recognition engine recognizes emotions from the analyzed text and assigns those emotions as tags. This enables highly accurate translation that considers not only the linguistic context but also emotional nuances.

[0539] Next, the server, with the help of a generative AI model, generates a translation that reflects the context and sentiment of the Japanese text. The generated translation faithfully reproduces the nuances of the original text and achieves translation into a different language. The translated text is then sent back from the server to the user's terminal and displayed on the screen for the user to visually confirm.

[0540] For example, if a user enters the Japanese sentence "I have an important presentation tomorrow. I am feeling nervous." into their device, the server analyzes this text, performs sentiment recognition, generates a translation such as "I have an important presentation tomorrow. I am feeling nervous.", and displays it on the device.

[0541] This system facilitates communication across language barriers, enabling users to accurately convey their intended meaning and emotions. Users can view the original text and translation results on their device, deepening their understanding of the language.

[0542] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0543] Step 1:

[0544] The user uses their device to input the Japanese text they want to translate. The input text is encoded into digital data through the device's application or web browser. The input Japanese text is output as string data, and this data is ready to be sent to the server.

[0545] Step 2:

[0546] The terminal sends encoded digital data to the server via the internet. During this process, the string data is packetized according to a protocol and delivered to the server via the communication network. The output data arrives at the server and awaits analysis.

[0547] Step 3:

[0548] The server analyzes the received digital data. Specifically, it performs formal analysis using a generative AI model to divide Japanese sentences into words and phrases. This analysis helps understand the grammar and structure unique to Japanese, and generates word lists and morphological information as output.

[0549] Step 4:

[0550] The server performs sentiment recognition on the analyzed words and phrases. Using a sentiment engine, it tags each word and phrase with the associated emotion. For example, positive and negative emotions are recognized, and the output is sentiment-tagged data.

[0551] Step 5:

[0552] The server initiates the translation process based on formal analysis and sentiment information. It utilizes a generative AI model to generate a translation that reflects the nuances of the original text. The resulting translated text is an accurate cross-language conversion that takes into account the context and sentiment of the input.

[0553] Step 6:

[0554] The server sends the generated translated text back to the terminal. The terminal visually displays the received translation result to the user. The translated text is displayed on the screen, allowing the user to compare the original Japanese text with the translated content side by side.

[0555] (Application Example 2)

[0556] 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."

[0557] When conducting electronic transactions between users who speak different languages, simply translating messages can fail to convey emotions and intentions, potentially leading to misunderstandings and friction. Therefore, accurate and nuanced communication that takes the sender's feelings into consideration is essential in language translation.

[0558] 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.

[0559] In this invention, the server includes means for receiving language input, means for analyzing the language input to interpret the context and sentiment, and means for generating a translation result based on the interpreted context and sentiment. This enables natural and accurate communication that reflects emotions between users who speak different languages.

[0560] "Language input" refers to natural language text data entered by the user via a device.

[0561] "Means of interpreting context" refers to processing methods that analyze received linguistic data and understand the specific context and meaning that the language possesses.

[0562] A "means for analyzing emotions" refers to a processing method for identifying emotions from input linguistic data and analyzing those emotions.

[0563] "Means for generating translation results" refers to processing methods that create appropriate translations into other languages ​​based on the interpreted context and analyzed sentiment.

[0564] A "terminal" is an electronic device used by a user to input language and receive translation results.

[0565] "Generating" refers to the process of appropriately creating new output based on specific input data.

[0566] First, the user inputs the Japanese text they want to translate using their device. This device, such as a smartphone or PC, is responsible for sending the inputted Japanese text as digital data to the server.

[0567] To analyze the Japanese input it receives, the server first performs morphological analysis to interpret the context. In this process, it uses a generative artificial intelligence model to analyze the nuances and expressions unique to the Japanese language in detail. Furthermore, the server uses an emotion engine to identify the emotion of the input text and translates it based on that. For example, in the sentence "I had a very good deal today!" entered by the user, the emotion engine detects the emotion of "joy".

[0568] Based on the interpreted context and detected sentiment, the server generates translations into other languages. The generated translations are provided to the user while retaining the sentiment of the original expression. In this example, a possible translation might be "Today I made an excellent deal!"

[0569] The generated translation is sent to the device, which then displays it to the user. By reviewing the displayed translation, the user can engage in natural and emotionally responsive communication.

[0570] As a concrete example, by inputting the prompt "Analyze the sentiment of the following Japanese message and generate a translation that reflects the sentiment of the new message: I'm very happy today!" into the AI ​​generator, it is possible to achieve a translation that takes sentiment into account.

[0571] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0572] Step 1:

[0573] The user inputs Japanese text via the terminal. The terminal formats this text as digital data and sends it to the server. At this point, the input is the user's Japanese text, and the output is digital string data. The terminal uses a text input field to obtain the user's character input and sends that data to the server as an HTTP request.

[0574] Step 2:

[0575] The server analyzes the received Japanese data and performs morphological analysis. This process uses a generative AI model to break down the text into words and phrases and understand the context specific to the Japanese language. The input digital string data is converted into word lists and phrase lists. The server utilizes a natural language processing (NLP) library for this analysis.

[0576] Step 3:

[0577] The server uses an emotion engine to identify the emotion of a sentence based on the analyzed word list. The input here is the analyzed word list, and the output is the detected emotion (e.g., joy, sadness). The server uses a pre-trained emotion classification model to assign emotion labels to the input sentence.

[0578] Step 4:

[0579] The server generates translation results using the analyzed context and detected sentiment. A generative AI model is used to translate into other languages, maximizing the reflection of context and sentiment. In this step, context- and sentiment-based prompt sentences are provided to the generative AI, and the translation is obtained. The input is context and sentiment data, and the output is the translated sentence.

[0580] Step 5:

[0581] The server sends the generated translation to the terminal. The terminal displays this translation to the user. The input is the translated text, and the output is the translated result presented visually to the user. The terminal displays the translated result to the user in an easy-to-understand manner through HTML or the application's GUI.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] [Fourth Embodiment]

[0586] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0587] 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.

[0588] 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).

[0589] 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.

[0590] 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.

[0591] 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).

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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.

[0598] 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".

[0599] This invention is a system that provides translations that take into account the context of the Japanese language. This system consists of a user, a terminal, and a server, and operates as follows:

[0600] First, the user inputs Japanese text using their device. The input text is then sent to the server as digital data.

[0601] The server uses a generative artificial intelligence model to analyze the received Japanese input and understand its context. This model is trained on a large amount of contextual data and is capable of detecting and understanding Japanese-specific expressions and underlying cultural elements.

[0602] For example, if a user enters the sentence, "It's started raining, but it has a certain charm, doesn't it?", the server will interpret the expression "has a certain charm" as referring to the sentimentality and sense of the seasons in Japanese culture.

[0603] Next, the server uses the analyzed information to generate a translation. This translation is contextual and may be output in the form of, for example, "It started raining, but it adds to the atmosphere in a way that's quite charming, reflecting the seasonal emotions uniquely felt in Japan."

[0604] Finally, the server sends the generated translation to the terminal. The terminal displays this result to the user, allowing them to gain a deeper understanding of both the original Japanese and the English translation.

[0605] This system enables foreigners who understand Japanese to grasp the content accurately without misunderstanding the underlying culture or context. The translation process ensures that the unique nuances of the Japanese language are preserved.

[0606] The following describes the processing flow.

[0607] Step 1:

[0608] The user inputs Japanese text using the terminal. After the user finishes inputting text on the text input screen, they press the input button to start processing.

[0609] Step 2:

[0610] The terminal formats the entered Japanese text as digital data and sends it to the server via the network. The data is formatted in JSON or XML format.

[0611] Step 3:

[0612] The server receives data sent from the terminal. It analyzes the received data and performs morphological analysis to divide the text into words and phrases.

[0613] Step 4:

[0614] The server inputs the analyzed data into an artificial intelligence model. This model uses pre-trained data to analyze the text and understand specific expressions and contexts within it.

[0615] Step 5:

[0616] The server generates contextually appropriate translations based on analysis results obtained from the artificial intelligence model. The generated translations take into account the unique emotions and cultural background of the Japanese language.

[0617] Step 6:

[0618] The server sends the translation results to the terminal. At this time, it sends both the original Japanese text and the translated text together.

[0619] Step 7:

[0620] The terminal displays the translation results received from the server to the user. This allows the user to compare the original Japanese text with the translated text and understand the context.

[0621] (Example 1)

[0622] 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".

[0623] Traditional translation systems often fail to fully understand the nuances and cultural context inherent in natural language, resulting in translations that do not accurately reflect the context. This lack of context is particularly problematic in languages ​​with strong cultural nuances, such as Japanese, leading to misunderstandings. Consequently, users may not receive accurate translations that reflect their intended meaning.

[0624] 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.

[0625] In this invention, the server includes means for receiving natural language from a user's device, means for using an artificial intelligence model to analyze the received natural language and understand its context, and means for generating translations into other languages ​​based on the analyzed contextual information. This enables contextually accurate translations that reflect complex cultural backgrounds and emotions.

[0626] "User device" refers to an electronic device used by a user to input natural language and send it to a server.

[0627] "Natural language" refers to the language that humans use on a daily basis, and in this invention, it specifically includes Japanese and its corresponding translated languages.

[0628] "Analysis" refers to the process by which a system recognizes and understands each element and context that makes up a received natural language text.

[0629] "Context" refers to the background information and related situations necessary to deeply understand the meaning of a given text or conversation.

[0630] An "artificial intelligence model" refers to a program or algorithm that learns from large amounts of data and has the ability to understand linguistic context and cultural elements.

[0631] "Translation" refers to the process of re-expressing content that has been written in one language into another language.

[0632] "Communication lines" refer to network infrastructure used to transmit and receive digital data.

[0633] "Emotion" refers to the feelings and atmosphere evoked by linguistic expressions.

[0634] "Cultural elements" refer to elements that have values, customs, or symbolic meanings specific to a particular language or society.

[0635] A "knowledge base" refers to a data structure or system that accumulates past data and information and utilizes it for analysis and decision-making.

[0636] The system of the present invention aims to take into account context and cultural background in natural language translation. The system consists of a user, a terminal, and a server, and specifically has means for analyzing natural language text based on user input and providing translation using an advanced artificial intelligence model.

[0637] The user first inputs natural language text using a terminal. This terminal can include a typical personal computer or smartphone and must be connected to the internet. The input text is processed as digital data and sent from the terminal to the server. This communication is conducted via a secure protocol.

[0638] The server receives the incoming data and begins analysis. In this analysis, the server utilizes a generative AI model, specifically a publicly available natural language processing algorithm. Through the AI ​​model, the server can tokenize the input text contextually and extract relevant cultural background information. This process allows for the understanding of emotional expressions and elements specific to particular cultures within the text.

[0639] Next, the server generates a translation based on the analysis results. This translation is not simply a word substitution, but reflects the context and cultural background. For example, if a user inputs "It's as graceful as cherry blossoms dancing in the wind," the AI ​​model understands the symbolism of "cherry blossoms dancing" in Japanese culture and generates the English translation "It's as graceful as cherry blossoms dancing in the wind, a quintessential representation of Japanese spring."

[0640] An example of a prompt is the specific instruction, "Translate Japanese into English, taking cultural context into consideration." Based on this instruction, the server provides the AI ​​model with appropriate prompts, resulting in a more accurate translation.

[0641] Finally, the server sends the generated translation back to the terminal, which then displays it to the user. This allows the user to compare the original text with the translation and gain a deeper understanding.

[0642] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0643] Step 1:

[0644] The user inputs natural language text using a terminal. The input text is processed as digital data within the terminal. This data becomes the input information and is ready to be sent to the server in the next step.

[0645] Step 2:

[0646] The terminal sends the input natural language digital data to the server. A secure communication protocol is used for transmission. The server receives this data and stores it internally as the basis for the subsequent analysis.

[0647] Step 3:

[0648] The server uses a generative AI model to analyze the received natural language data. Specifically, it tokenizes the data and obtains contextual information for each word and phrase. This process involves data processing to understand the emotions and cultural background embedded in the text. As a result of this data processing, context-aware analysis data is obtained.

[0649] Step 4:

[0650] The server generates prompt sentences based on the analysis data. These prompt sentences are input into the generation AI model and serve as indicators to instruct it to generate appropriate translations. Once the generated prompt sentences are supplied to the AI ​​model, the translation process begins.

[0651] Step 5:

[0652] The generative AI model generates contextually appropriate translations. Because this translation process considers analyzed cultural and emotional elements, the translation results are not merely mechanical vocabulary conversions. As a final output, the server receives the completed translation data.

[0653] Step 6:

[0654] The server sends the generated translation data back to the terminal. A secure communication protocol is used during this process to ensure data security. The translation data is then prepared for display to the user on the terminal.

[0655] Step 7:

[0656] The device displays the received translation results to the user. The user can review the original text and the translated text, receiving an accurate translation that reflects the cultural background and context. At this step, the user can also evaluate the results and provide feedback as needed.

[0657] (Application Example 1)

[0658] 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".

[0659] With the increasing number of international users, there is a growing need for accurate understanding and translation of natural language, including an understanding of cultural background and context. However, conventional translation systems have difficulty appropriately interpreting the cultural context of complex languages ​​such as Japanese, and there is a problem in that they do not adequately provide information with a Japanese cultural background to foreign users.

[0660] 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.

[0661] In this invention, the server includes means for receiving natural language input from a user, means for analyzing the received natural language input and interpreting the context, means for generating semantic conversion results based on the interpreted context, and means for visually displaying the semantic conversion results using an augmented reality device. This makes it possible for international users to understand the context of natural language and easily obtain accurate information that reflects cultural backgrounds.

[0662] "Natural language" refers to the language that humans use on a daily basis, such as Japanese or English, rather than a specific programming language or code.

[0663] "Context" refers to the background information and circumstances necessary to understand the meaning of a particular expression in natural language.

[0664] "Semantic conversion result" refers to the output obtained by analyzing natural language input and converting it to another language, taking into account its context and culture.

[0665] "Augmented reality devices" are devices that overlay digital information onto real-world visual information, and include smart glasses and head-mounted displays.

[0666] A "visual recognition device" refers to a device that acquires information from the environment using cameras or other means and processes it as digital data.

[0667] A "generative artificial intelligence model" is a type of AI that has the ability to learn patterns from large amounts of data and analyze information, making it possible to understand linguistic context and cultural background.

[0668] "Past information" refers to data that has been collected or recorded previously and is used to aid in understanding a specific context or to improve accuracy.

[0669] The system for implementing this invention has the following configuration. First, the terminal has a function to receive natural language input from the user. This natural language input may be written information acquired through the terminal's camera or text directly entered by the user.

[0670] Next, the server uses a generative AI model to analyze the input natural language and interpret its context. This analysis employs a data-driven learning model known as a generative artificial intelligence model. This model can utilize large-scale language models such as OpenAI's GPT series.

[0671] After contextual interpretation, the server generates a semantic translation result based on the interpreted context. This translation result includes an explanation that takes into account the user's cultural background and context. The generated translation result is sent to the terminal and displayed visually to the user using an augmented reality device. For example, a device like Google Glass is used.

[0672] As a concrete example, when a foreign user sees a product in a traditional Japanese shopping street, they scan the product description with their device's camera. This information is then sent to a server, where a generative AI model analyzes and translates it. As a result, the Japanese description of the product is displayed on the glasses' screen as an English description that takes cultural context into account. This allows foreign users to deepen their understanding not only of the product but also of the culture behind it.

[0673] Examples of prompt messages are as follows:

[0674] Prompt: "Translate the Japanese text considering cultural nuances: Enjoy the delicate aftertaste that differs with each matcha flavor."

[0675] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0676] Step 1:

[0677] The user uses their device's camera to capture natural language text, such as product descriptions. Camera image data is generated as input and converted into text data using OPT (Optical Character Recognition). At this stage, a camera module and Tesseract OCR are used.

[0678] Step 2:

[0679] The terminal sends text data to the server. The input is the text data obtained in step 1, and the output is secure data communication to the server. This process uses a network communication protocol (e.g., HTTPS).

[0680] Step 3:

[0681] The server uses a generative AI model to perform contextual analysis on the received text. The input is the text data sent in step 2, and the output is the contextualized data analysis result. This analysis utilizes a generative AI model such as OpenAI's GPT series.

[0682] Step 4:

[0683] The server uses the contextual analysis results to generate semantic translation results that take cultural background into account. The input is the contextual analysis results, and the output is translated text data. A prompt sentence is used as an example of translation.

[0684] Step 5:

[0685] The server sends the generated semantic translation results to the terminal. The input is translated text data, and the output is data sent to the user's terminal. A network communication protocol (e.g., HTTPS) is used.

[0686] Step 6:

[0687] The terminal visually displays the received semantic translation results to the user via an augmented reality device. The input is the translation result data sent from the server, and the output is the visual information displayed on the augmented reality device. AR devices such as Google Glass are used.

[0688] Step 7:

[0689] Users deepen their understanding of products and their cultural background by overlaying digital information onto real-world visual information. The input is the visual information presented in step 6, and the output is the perception gained by the user.

[0690] 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.

[0691] This invention is a system that receives Japanese input from a user, analyzes its context and sentiment, and generates a translation. This system has a complex configuration that includes the user, a terminal, a server, and an sentiment engine.

[0692] First, the user inputs the Japanese text they want translated via their device. The device then converts this input into digital data and sends it to the server.

[0693] The server analyzes the received data, performs morphological analysis, and breaks down the text into words and phrases. At this stage, a generative artificial intelligence model is used to take into account expressions and context specific to the Japanese language. Here, the emotion engine is utilized to recognize the emotion of the input text. For example, if the user inputs "I'm so happy today!", the emotion engine detects the emotion of "joy".

[0694] Next, the server generates a translation based on the analyzed context and recognized emotions. By performing translations that reflect emotions, the system produces more accurate translations without losing the nuances of the original expression. For example, the sentence "I'm very happy today!" is translated as "I'm extremely happy today!", outputting the translation while preserving the original emotion.

[0695] The server then sends the resulting translation back to the terminal. The terminal displays this translation to the user, allowing the user to see both the original Japanese and the translation.

[0696] This system prioritizes the context of Japanese and reflects emotions, enabling it to accurately translate what the user intended. This provides translations that are easier to understand for foreigners learning Japanese and for foreigners communicating within Japan.

[0697] The following describes the processing flow.

[0698] Step 1:

[0699] The user inputs Japanese text using the terminal. After input is complete, the terminal formats the input content as digital data.

[0700] Step 2:

[0701] The terminal sends formalized digital data to the server. The data arrives at the server via the network in the specified format.

[0702] Step 3:

[0703] The server analyzes the received Japanese input and performs morphological analysis. This divides the text into words and phrases, revealing its grammatical structure.

[0704] Step 4:

[0705] The server uses a generative artificial intelligence model to analyze the context of Japanese. This model learns from past data and understands the background and meaning of specific expressions.

[0706] Step 5:

[0707] The emotion engine activates and recognizes the emotions contained in the user's input. For example, it detects emotional expressions such as "happy" or "sad."

[0708] Step 6:

[0709] The server integrates the results of contextual analysis and sentiment recognition to generate an appropriate translation. The resulting translation reflects the emotions of the original text without compromising its intent.

[0710] Step 7:

[0711] The server sends the generated translation to the terminal. The translation is provided in a user-friendly format while preserving the original context and nuance.

[0712] Step 8:

[0713] The terminal displays the translation results received from the server to the user. Through the displayed results, the user can confirm the intent and emotion of the original expression.

[0714] (Example 2)

[0715] 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".

[0716] Providing accurate and nuanced translations between different languages ​​in natural language communication is a challenging task. In particular, translating Japanese grammar and its unique emotional expressions into other languages ​​without losing their nuances is difficult. Conventional translation systems often fail to properly recognize emotions, resulting in miscommunication of the user's intended meaning.

[0717] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0718] In this invention, the server includes means for receiving natural language input from a user, means for analyzing the received natural language input and performing formal analysis, means for performing sentiment recognition on the analyzed input, means for generating a translation result based on the context including sentiment information, and means for outputting the generated translation result to the user. This makes it possible to provide a translation that accurately reflects the context and sentiment of the Japanese input by the user.

[0719] "Natural language input" refers to text data entered in the language format that humans normally use in communication.

[0720] "Formal element analysis" is a method of breaking down a text into individual words and phrases and analyzing their parts of speech and meanings.

[0721] "Emotion recognition" is the process of analyzing and identifying the underlying emotions and sensibilities within the input text.

[0722] "Context" refers to the specific environment or situation in which a linguistic expression is used, and is the background information necessary to understand and interpret that linguistic expression.

[0723] "Translation result" refers to the text generated by converting sentences or phrases written in the original language into a different language.

[0724] "Output" refers to the process of presenting the analyzed and processed data and information to the user.

[0725] This invention is a system for translating user-inputted natural language with high accuracy. This system is implemented using a user's terminal, communication via the internet, a server, and a generative AI model and emotion recognition engine.

[0726] First, the user uses their device to input the Japanese text they want to translate. This device then converts the input Japanese text into digital data and sends it to the server. Specifically, the data is digitized by entering text into an input field via an application or web browser installed on the device.

[0727] The server receives digital data and initiates a series of language processing steps. A generative AI model on the server performs formal analysis, breaking down the input text into words and phrases. Next, an emotion recognition engine recognizes emotions from the analyzed text and assigns those emotions as tags. This enables highly accurate translation that considers not only the linguistic context but also emotional nuances.

[0728] Next, the server, with the help of a generative AI model, generates a translation that reflects the context and sentiment of the Japanese text. The generated translation faithfully reproduces the nuances of the original text and achieves translation into a different language. The translated text is then sent back from the server to the user's terminal and displayed on the screen for the user to visually confirm.

[0729] For example, if a user enters the Japanese sentence "I have an important presentation tomorrow. I am feeling nervous." into their device, the server analyzes this text, performs sentiment recognition, generates a translation such as "I have an important presentation tomorrow. I am feeling nervous.", and displays it on the device.

[0730] This system facilitates communication across language barriers, enabling users to accurately convey their intended meaning and emotions. Users can view the original text and translation results on their device, deepening their understanding of the language.

[0731] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0732] Step 1:

[0733] The user uses their device to input the Japanese text they want to translate. The input text is encoded into digital data through the device's application or web browser. The input Japanese text is output as string data, and this data is ready to be sent to the server.

[0734] Step 2:

[0735] The terminal sends encoded digital data to the server via the internet. During this process, the string data is packetized according to a protocol and delivered to the server via the communication network. The output data arrives at the server and awaits analysis.

[0736] Step 3:

[0737] The server analyzes the received digital data. Specifically, it performs formal analysis using a generative AI model to divide Japanese sentences into words and phrases. This analysis helps understand the grammar and structure unique to Japanese, and generates word lists and morphological information as output.

[0738] Step 4:

[0739] The server performs sentiment recognition on the analyzed words and phrases. Using a sentiment engine, it tags each word and phrase with the associated emotion. For example, positive and negative emotions are recognized, and the output is sentiment-tagged data.

[0740] Step 5:

[0741] The server initiates the translation process based on formal analysis and sentiment information. It utilizes a generative AI model to generate a translation that reflects the nuances of the original text. The resulting translated text is an accurate cross-language conversion that takes into account the context and sentiment of the input.

[0742] Step 6:

[0743] The server sends the generated translated text back to the terminal. The terminal visually displays the received translation result to the user. The translated text is displayed on the screen, allowing the user to compare the original Japanese text with the translated content side by side.

[0744] (Application Example 2)

[0745] 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".

[0746] When conducting electronic transactions between users who speak different languages, simply translating messages can fail to convey emotions and intentions, potentially leading to misunderstandings and friction. Therefore, accurate and nuanced communication that takes the sender's feelings into consideration is essential in language translation.

[0747] 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.

[0748] In this invention, the server includes means for receiving language input, means for analyzing the language input to interpret the context and sentiment, and means for generating a translation result based on the interpreted context and sentiment. This enables natural and accurate communication that reflects emotions between users who speak different languages.

[0749] "Language input" refers to natural language text data entered by the user via a device.

[0750] "Means of interpreting context" refers to processing methods that analyze received linguistic data and understand the specific context and meaning that the language possesses.

[0751] A "means for analyzing emotions" refers to a processing method for identifying emotions from input linguistic data and analyzing those emotions.

[0752] "Means for generating translation results" refers to processing methods that create appropriate translations into other languages ​​based on the interpreted context and analyzed sentiment.

[0753] A "terminal" is an electronic device used by a user to input language and receive translation results.

[0754] "Generating" refers to the process of appropriately creating new output based on specific input data.

[0755] First, the user inputs the Japanese text they want to translate using their device. This device, such as a smartphone or PC, is responsible for sending the inputted Japanese text as digital data to the server.

[0756] To analyze the Japanese input it receives, the server first performs morphological analysis to interpret the context. In this process, it uses a generative artificial intelligence model to analyze the nuances and expressions unique to the Japanese language in detail. Furthermore, the server uses an emotion engine to identify the emotion of the input text and translates it based on that. For example, in the sentence "I had a very good deal today!" entered by the user, the emotion engine detects the emotion of "joy".

[0757] Based on the interpreted context and detected sentiment, the server generates translations into other languages. The generated translations are provided to the user while retaining the sentiment of the original expression. In this example, a possible translation might be "Today I made an excellent deal!"

[0758] The generated translation is sent to the device, which then displays it to the user. By reviewing the displayed translation, the user can engage in natural and emotionally responsive communication.

[0759] As a concrete example, by inputting the prompt "Analyze the sentiment of the following Japanese message and generate a translation that reflects the sentiment of the new message: I'm very happy today!" into the AI ​​generator, it is possible to achieve a translation that takes sentiment into account.

[0760] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0761] Step 1:

[0762] The user inputs Japanese text via the terminal. The terminal formats this text as digital data and sends it to the server. At this point, the input is the user's Japanese text, and the output is digital string data. The terminal uses a text input field to obtain the user's character input and sends that data to the server as an HTTP request.

[0763] Step 2:

[0764] The server analyzes the received Japanese data and performs morphological analysis. This process uses a generative AI model to break down the text into words and phrases and understand the context specific to the Japanese language. The input digital string data is converted into word lists and phrase lists. The server utilizes a natural language processing (NLP) library for this analysis.

[0765] Step 3:

[0766] The server uses an emotion engine to identify the emotion of a sentence based on the analyzed word list. The input here is the analyzed word list, and the output is the detected emotion (e.g., joy, sadness). The server uses a pre-trained emotion classification model to assign emotion labels to the input sentence.

[0767] Step 4:

[0768] The server generates translation results using the analyzed context and detected sentiment. A generative AI model is used to translate into other languages, maximizing the reflection of context and sentiment. In this step, context- and sentiment-based prompt sentences are provided to the generative AI, and the translation is obtained. The input is context and sentiment data, and the output is the translated sentence.

[0769] Step 5:

[0770] The server sends the generated translation to the terminal. The terminal displays this translation to the user. The input is the translated text, and the output is the translated result presented visually to the user. The terminal displays the translated result to the user in an easy-to-understand manner through HTML or the application's GUI.

[0771] 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.

[0772] 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.

[0773] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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.

[0779] 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."

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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.

[0791] 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.

[0792] The following is further disclosed regarding the embodiments described above.

[0793] (Claim 1)

[0794] A means of receiving Japanese input from the user,

[0795] A means of analyzing the received Japanese input and interpreting the context,

[0796] Means for generating translation results based on the interpreted context,

[0797] A means of outputting the generated translation results to the user,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, comprising means for analyzing Japanese-specific expressions using a generative artificial intelligence model when interpreting context.

[0801] (Claim 3)

[0802] The system according to claim 1, comprising means for referring to past data and performing analysis to understand the cultural background and intent of expressions.

[0803] "Example 1"

[0804] (Claim 1)

[0805] A means for receiving natural language from the user's device,

[0806] A means of using an artificial intelligence model to analyze received natural language and understand its context,

[0807] A means for generating translations into other languages ​​based on analyzed contextual information,

[0808] A means of transmitting the generated translation to a user device via a communication line and displaying it to the user,

[0809] A system that includes this.

[0810] (Claim 2)

[0811] The system according to claim 1, comprising means for detecting and understanding language-specific emotions and cultural elements using a natural language model when understanding context.

[0812] (Claim 3)

[0813] The system according to claim 1, comprising means for performing analysis to evaluate the cultural background and meaning of linguistic expressions by utilizing a past knowledge base.

[0814] "Application Example 1"

[0815] (Claim 1)

[0816] A means of receiving natural language input from the user,

[0817] A means of analyzing received natural language input and interpreting the context,

[0818] A means for generating semantic transformation results based on the interpreted context,

[0819] A means of presenting the generated semantic conversion results to the user,

[0820] A means of visually displaying the semantic conversion results using an augmented reality device,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, comprising a means for analyzing expressions unique to natural language in contextual analysis using a generative artificial intelligence model and referencing past information.

[0824] (Claim 3)

[0825] The system according to claim 1, comprising means for acquiring written information in the environment as digital data using a visual recognition device and for analyzing that information.

[0826] "Example 2 of combining an emotion engine"

[0827] (Claim 1)

[0828] A means of receiving natural language input from the user,

[0829] A means of analyzing received natural language input and performing formal analysis,

[0830] A means of performing emotion recognition on the analyzed input,

[0831] A means for generating translation results based on context including emotional information,

[0832] A means of outputting the generated translation results to the user,

[0833] A system that includes this.

[0834] (Claim 2)

[0835] The system according to claim 1, comprising means for performing analysis that takes into account Japanese-specific grammar and sentiment using a generative artificial intelligence model.

[0836] (Claim 3)

[0837] The system according to claim 1, comprising means for displaying and comparing both the user's original input and the translated output.

[0838] "Application example 2 when combining with an emotional engine"

[0839] (Claim 1)

[0840] A means of receiving language input from the user,

[0841] A means of analyzing received language input and interpreting the context,

[0842] A means for analyzing emotions based on the interpreted context and generating translation results corresponding to those emotions,

[0843] A means of outputting the generated translation results to the user via a terminal,

[0844] A system that includes this.

[0845] (Claim 2)

[0846] The system according to claim 1, comprising means for analyzing language-specific expressions using a knowledge processing technology model when interpreting context and analyzing emotions.

[0847] (Claim 3)

[0848] The system according to claim 1, comprising means for referring to past information and performing analysis to understand the social background and intent of an expression. [Explanation of symbols]

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

Claims

1. A means of receiving Japanese input from the user, A means of analyzing the received Japanese input and interpreting the context, Means for generating translation results based on the interpreted context, A means of outputting the generated translation results to the user, A system that includes this.

2. The system according to claim 1, comprising means for analyzing Japanese-specific expressions using a generative artificial intelligence model when interpreting context.

3. The system according to claim 1, comprising means for referring to past data and performing analysis to understand the cultural background and intent of expressions.

Images