system

Abstract

We provide the system. [Solution] A means for receiving data, A means of extracting text information from received data, A means of analyzing the context of extracted textual information, A means of translating the analyzed text information into other languages, A means of integrating translated text information into the original data, A system that includes means for outputting translated data.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventionally, when translating Japanese video and manga contents into other languages for overseas expansion, manual translation requires time and effort, and particularly high expertise is required for translating texts in videos and dialogue lines in manga. Also, the process of integrating the translated character information into the original content is complicated, and accuracy and efficiency have been issues. Furthermore, a method capable of quickly dealing with the problem of pirated versions has been demanded.

Means for Solving the Problems

[0005] This invention provides a series of processes that receive data, extract character information using optical character recognition technology, perform contextual analysis of that character information using natural language processing, translate it into another language using a highly accurate generative AI, and automatically integrate the translated character information into the original data. This makes it possible to translate Japanese content into multiple languages ​​in a short time and disseminate it efficiently, while also addressing piracy issues and generating high-quality translation results.

[0006] "Data" refers to a collection of information that a system receives or processes, and includes media formats such as videos and images.

[0007] "Textual information" refers to text or sentences extracted from data, including video subtitles and manga dialogue.

[0008] "Optical character recognition technology" is a technology that automatically detects characters within an image and converts them into digital text data.

[0009] Natural language processing is a technology that enables computers to understand and process human language, and is used in contextual analysis and translation processes.

[0010] "Generative AI" is a type of artificial intelligence technology that refers to a model capable of generating new data based on given input data.

[0011] Translation is the process of converting text written in one language into another language, with the aim of accurately conveying meaning and nuance.

[0012] "Integration" is the process of appropriately placing translated text information into the original data and re-outputting it in a unified format. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. 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, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

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

[0018] In the following embodiments, a numbered 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, and the like.

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

[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 for efficiently translating Japanese content such as videos and manga into other languages ​​and distributing it overseas. This system operates server-centric and processes data uploaded by users. Specifically, it operates as follows:

[0035] The process begins when a user uploads video or comic data they wish to have translated to a server. The server receives this data and first uses optical character recognition (OCR) technology to extract text information from the image or video frames. This extraction process includes all text information contained within the content, such as subtitles and dialogue.

[0036] Next, the server analyzes the context of the extracted text information using natural language processing techniques. This process helps to understand sentence structure, cultural background, emotional expression, and other information necessary to improve translation accuracy.

[0037] Subsequently, an AI model is used to translate the analyzed text information into other languages. The translated text is then integrated back into the original content by the server and placed in the appropriate positions as subtitles for videos or dialogue for comics.

[0038] After these processes, the server ultimately generates new translated data, making it available for download by the user. A concrete example is a scenario where Japanese anime episodes are provided with English subtitles. In this case, the server automatically generates subtitles for the anime for English-speaking audiences, and the user can download this translated episode and provide it to viewers.

[0039] This system allows users to achieve high-quality multilingual translations without hassle, supporting the international expansion of Japan's content industry.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The user uploads the video or comic data to be translated. They access the server using their device and provide the file in the specified format (e.g., MP4, PNG).

[0043] Step 2:

[0044] The server receives the uploaded data. It checks the file format and integrity, and prepares it for appropriate processing.

[0045] Step 3:

[0046] The server analyzes the data and, in the case of video, extracts each frame as an image. Next, OCR technology is used to detect text information within the images and convert it into digital text.

[0047] Step 4:

[0048] The server performs contextual analysis of the extracted text information using natural language processing technology. It considers the dictionary meaning of words, grammatical structure, and cultural background to obtain the information necessary for accurate translation.

[0049] Step 5:

[0050] The server uses a generated AI model to translate the analyzed text information into another language. The translation result is output as text.

[0051] Step 6:

[0052] The server integrates the translated text into the original data. For videos, it inserts subtitles at appropriate times; for comics, it adjusts and positions the dialogue based on its design.

[0053] Step 7:

[0054] The server generates the final translated data in a new file format, formatting it for easy download by the user.

[0055] Step 8:

[0056] The user downloads the translated data from the server. It is retrieved via the device and prepared for distribution to viewers as needed.

[0057] (Example 1)

[0058] 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."

[0059] The present invention aims to provide a system that can efficiently translate Japanese content such as videos and manga into multiple languages, thereby reducing the manual work and time costs involved in international distribution. Conventional methods require manual translation by translators, which is problematic due to the time and effort involved. Furthermore, accurately understanding the context and cultural background of the content and producing appropriate translations is not easy.

[0060] 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.

[0061] In this invention, the server includes means for receiving digital data, means for extracting textual information from the received digital data, and means for using generative artificial intelligence to translate the extracted textual information into other languages. This enables high-quality multilingual translation that takes into account the context and cultural background of the content.

[0062] "Digital data" refers to a collection of information encoded in a format that can be processed using a computer.

[0063] "Textual information" refers to information such as sentences and words expressed in text format.

[0064] "Context" refers to a set of supplementary information that helps us understand the background and situation in which a particular piece of information is placed.

[0065] "Generative artificial intelligence" refers to systems and programs that have the ability to generate new data and content using artificial intelligence technology.

[0066] "Integration" is the process of bringing together multiple elements into a unified and consistent state.

[0067] This invention is a server-centric system designed to translate Japanese video and manga content into multiple languages ​​and distribute it to the international market. Users upload the digital data they wish to have translated to the server via their terminal. This digital data includes visual media such as videos and manga.

[0068] The server first uses optical character recognition (OCR) technology to extract text information from each frame of uploaded videos and comics. General-purpose OCR software such as "Tesseract" can be used for this process. The server then analyzes the extracted text information using natural language processing (NLP) technology. NLP libraries such as "spaCy" and "BERT" are used to perform in-depth analysis that takes context, emotions, and cultural background into account.

[0069] Next, the server translates the analyzed text information into another language using a generative AI model. In this step, a generative artificial intelligence model such as "OpenAI® GPT" or "DeepL" is used to input a prompt and obtain an appropriate translation result. For example, a possible prompt might be, "Please translate the line 'Hello' from this Japanese anime into English."

[0070] Finally, the server integrates the translated text information into the original digital data. For videos, the server uses video editing tools such as "FFmpeg" to position the new subtitles appropriately. For comics, image editing software is used to combine the translated dialogue with the images. The completed translated digital data is then made available for download by the user.

[0071] One concrete example is providing Japanese anime episodes with English subtitles. When a user uploads an anime, the server automatically generates English subtitles using the technology described above. This allows users to quickly provide high-quality translated content without any extra effort.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The user uploads digital data of videos or comics they wish to translate from their device to the server. The input is the user's local device, and the output of this step is the original digital data stored on the server. The device securely transfers the selected files using a data transfer protocol.

[0075] Step 2:

[0076] The server extracts character information from the uploaded digital data using optical character recognition (OCR). The input is the digital data obtained in step 1, and the output is the extracted text data. The server recognizes characters from the image frame using OCR software such as "Tesseract" and saves the results in text format.

[0077] Step 3:

[0078] The server analyzes the text data obtained by OCR using natural language processing (NLP) techniques. The input is the character information obtained in step 2, and the output is data with context and meaning analyzed. The server uses "spaCy" and "BERT" to analyze sentence structure, sentiment, and background information to understand the context.

[0079] Step 4:

[0080] The server translates the analyzed text data into other languages ​​using a generation AI model. The input is the data analyzed in step 3, and the output is the translated character information. The server utilizes "OpenAI GPT" and "DeepL" along with prompt text to generate contextually appropriate translations.

[0081] Step 5:

[0082] The server integrates the translated text information with the original digital data. The input is the translated data obtained in step 4 and the original digital data, and the output is the translated integrated data. The server adds subtitles to the video using editing tools such as "FFmpeg" or inserts the translated dialogue into the comic using image editing software.

[0083] Step 6:

[0084] The server makes the completed translated digital data available for download to the user. The input is the integrated data generated in step 5, and the output is the completed file accessible to the user. The server uses a storage service to ensure that the user can securely download the file via a specific link.

[0085] (Application Example 1)

[0086] 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."

[0087] In the process of translating content into other languages, there is a need for rapid and accurate translation processing, as well as the efficient provision of information on cultural background and linguistic nuances that users require. However, conventional systems have problems such as insufficient translation accuracy and time-consuming provision of additional information.

[0088] 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.

[0089] In this invention, the server includes means for receiving data, means for extracting character information from the received data, and means for providing additional information based on user selection. This enables rapid and accurate translation processing and real-time provision of additional information through a user interface.

[0090] "Means of receiving data" refers to the function by which a server receives content data sent by a user.

[0091] "Means for extracting text information" refers to a function that recognizes and extracts text from received content data.

[0092] "Means for analyzing context" refers to functions that perform natural language processing to understand the meaning and background of extracted textual information.

[0093] "Means of translation into other languages" refers to a function that uses a generative AI model to convert analyzed textual information into a different language.

[0094] "Means of integrating translated text information into the original data" refers to a function that places the translated text in the appropriate location within the original content.

[0095] "Means for outputting translated data" refers to a function that makes the translated data available to the user.

[0096] "Means of providing additional information based on user selection" refers to a function that displays related information and background details for items specified by the user.

[0097] "Means of displaying additional information through the user interface" refers to a function that shows the user additional content related to the selected information on the screen.

[0098] A system implementing this invention consists of a process that exchanges data between a server and a user terminal and translates the language information of the received data.

[0099] First, the user uploads the content data they want to translate (e.g., videos or comics) to the cloud server using their device. At this time, the user specifies the desired translation language. The server receives this data and begins the necessary processing.

[0100] The server first uses the Google Cloud Vision API to extract text information from the received data. For videos, it analyzes each frame, and for comics, it obtains text data from the entire page.

[0101] Next, the server uses the Google Cloud Natural Language API to analyze the context of the extracted text information. This deepens the understanding of the meaning of the extracted data and improves translation accuracy.

[0102] The analyzed text information is translated into other languages ​​using OpenAI's GPT model and DeepL API. Where necessary, the generative AI model also considers cultural context and nuances.

[0103] The translated text information is accurately integrated with the original data and output to the user's terminal as translated data by the server. On the terminal, translated subtitles are displayed for videos, and dialogue is appropriately placed for comics. Furthermore, based on the user's selection, additional information about specific terms and lines is displayed, including a function to learn about the cultural background.

[0104] For example, if a user selects "Character A's technology," the historical background of that technology will be explained in real time. A concrete example of a prompt given to the generating AI model could be, "Translate Character A's technology '○○' into English and explain its cultural background."

[0105] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0106] Step 1:

[0107] Users upload content data they want to translate to the server using their device. Videos and comics are used as input, and the server receives and stores this data.

[0108] Step 2:

[0109] The server uses the Google Cloud Vision API to extract text information from the received data. Specifically, it uses OCR technology to obtain text data from each frame of a video or page of a comic book. The input is the uploaded content, and the output is the extracted text information.

[0110] Step 3:

[0111] The server uses the Google Cloud Natural Language API to analyze the extracted text information. The input is the text information obtained in step 2, and the output is analyzed data including context. Specifically, it performs processing to understand emotions and sentence structure.

[0112] Step 4:

[0113] The server translates the analyzed text information into other languages ​​using OpenAI's GPT model and DeepL API. Here, prompt sentences are generated and provided to the generative AI model. The input is the analyzed data from step 3, and the output is the translated text.

[0114] Step 5:

[0115] The server integrates the translated text information into the original content data. This information is then placed as subtitles in videos and as dialogue in comics. The input consists of the translated text information and the original content, while the output is the integrated, complete data.

[0116] Step 6:

[0117] The server sends the integrated translated data to the terminal, making it available for user viewing. Here, the user can select sections requiring supplementary information and receive detailed explanations. For example, when a user selects a specific term, cultural background information related to that term is displayed. A prompt such as "Please explain the background of the term XX" might be generated.

[0118] 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.

[0119] This invention is a system that not only translates data but also recognizes the user's emotions and adjusts the tone and style of the translation to match those emotions. This system is implemented as follows:

[0120] First, the user uploads the video or manga data they want translated to the server. The server receives the data and uses optical character recognition technology to extract text information such as subtitles and dialogue.

[0121] Next, the server uses natural language processing techniques to analyze the context of the extracted text information. This analysis helps to understand the meaning and cultural background of the original language. At this stage, an emotion engine is also utilized to analyze the user's emotional state based on user feedback and past emotional history. This emotion engine uses machine learning algorithms to infer what emotions the user feels towards the content.

[0122] Based on the analysis results and sentiment analysis, the server uses a generative AI model to translate text information into other languages. This translation reflects the tone and style corresponding to the user's emotions. For example, if the user is expressing cheerful emotions, the translation will be adjusted to have a bright and friendly tone.

[0123] Finally, the translated text information is integrated into the original data. After this process, it is appropriately placed as subtitles in videos or as dialogue in comics, and becomes available for download by the user.

[0124] For example, when translating a Japanese comedy anime for an English-speaking audience, if users provide smiling feedback, consideration will be given to translating the conversation in a lighter and more humorous tone. This results in content that is more relatable and enjoyable for viewers.

[0125] This system will go beyond simple word-for-word translation, enabling content delivery that takes viewers' emotions into consideration, with the aim of promoting wider global acceptance of Japanese content.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The user uploads the video or manga data to be translated to the server via their device. The server receives the data and verifies that the data format is correct.

[0129] Step 2:

[0130] The server begins analyzing the received data. In the case of videos, it divides the data into individual frames and extracts text information from each frame using optical character recognition technology. Similarly, for comics, it detects text information from each page.

[0131] Step 3:

[0132] The server uses natural language processing techniques to perform contextual analysis on the extracted text information. During this process, the meaning and cultural nuances of the original text are understood.

[0133] Step 4:

[0134] The server activates the emotion engine and analyzes the user's emotional data. This is done by referencing feedback and reactions previously provided by the user to estimate their current emotional state.

[0135] Step 5:

[0136] The server uses a generation AI model to perform translations into other languages, reflecting the results of contextual and sentiment analysis. These translations are then adjusted to match the user's estimated emotions in terms of tone and style.

[0137] Step 6:

[0138] The server integrates the translated text information into the original data. For videos, it inserts subtitles at the appropriate timing; for comics, it arranges dialogue considering the design.

[0139] Step 7:

[0140] The server generates the final translated data and adjusts the format so that it can be downloaded by the user.

[0141] Step 8:

[0142] The user retrieves the translation results from the server and checks them on their device. This data is used to provide it to viewers and readers as needed.

[0143] (Example 2)

[0144] 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".

[0145] Traditional translation systems simply convert text information into different languages, lacking contextual understanding that takes into account user emotions and intentions. This can result in translations that lose the original tone and style of the content, potentially reducing viewer engagement. Furthermore, providing translations that reflect individual user emotions and feedback has been challenging.

[0146] 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.

[0147] In this invention, the server includes means for acquiring data, technical means for identifying text information, and technical means for evaluating the background of the identified text information. This enables flexible and appropriate translation that is tailored to the user's emotions and context.

[0148] "Means of acquiring data" refers to the function of collecting digital content provided by users into the system.

[0149] "Technical means for identifying text information" refers to technologies for detecting and reading characters in digital content.

[0150] "Technical means for evaluating the background of identified text information" refers to technologies that analyze and understand the context and cultural background of detected text information.

[0151] "Generative technology means" refers to technology for generating translations appropriate to the context using evaluated text information.

[0152] "Means of supplying the final product" refers to a function for incorporating translated content into the content and providing it to the user.

[0153] This system begins with a user uploading digital content such as videos or comics to a server. The server first uses a data acquisition method to extract text information from the received content. For this process, open-source OCR engines such as Tesseract are typically used as optical information recognition (OCR) technologies. This technology efficiently identifies text information embedded in images and videos.

[0154] Next, the server utilizes natural language processing (NLP) techniques as a means to evaluate the context of the text information. In this phase, natural language processing models such as BERT and GPT are used to analyze the context and cultural background of the extracted text in detail. Based on the results of this analysis, a dedicated sentiment engine analyzes the user's current emotional state by referring to user feedback and past sentiment history.

[0155] Subsequently, the server uses generative techniques to translate the text information into another language, taking into account the evaluated context. This process utilizes the well-known GPT series of generative AI models to achieve contextually and emotionally optimized translations. For example, if a user provides positive feedback, the translated output will reflect that positive tone.

[0156] For example, when translating subtitles for a Japanese comedy film into English, if a user provides feedback such as "very funny and entertaining," the translated English subtitles will be adjusted to also include humor. An example of a prompt might be, "Translate the fun Japanese movie subtitles into English based on user feedback, maintaining a lighthearted tone."

[0157] The final output is integrated into the original digital content and displayed as subtitles in an appropriate format. Users can download the translated content in an available format using their device and view it. In this way, the system provides a translation service that enhances the user experience.

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] Users upload digital content such as videos and comics they wish to have translated from their computer terminal to the server. The input is digital data in a file format provided by the user. The server processes the received files and imports the content data into the system. The output is the content data securely stored on the server.

[0161] Step 2:

[0162] The server uses optical image recognition (OCR) technology to extract text information from uploaded content. The input is digital data in image or video format. The OCR engine used (e.g., Tesseract) operates frame by frame, detecting text and outputting it as digital character data.

[0163] Step 3:

[0164] The server evaluates the background and context of text information extracted using natural language processing techniques. The input is character data obtained by OCR. It utilizes BERT and similar NLP models to understand the text context and analyze its cultural background. The output consists of contextual metadata and analysis results.

[0165] Step 4:

[0166] The server analyzes the user's emotional state using an emotion engine, referencing the user's emotional history and current feedback. Inputs include past user feedback and focused current feedback information. A machine learning algorithm is used to infer and output the user's emotional state data.

[0167] Step 5:

[0168] The server translates text information based on contextual and sentiment data evaluated using a generative AI model. Inputs are contextual metadata and user sentiment state. Using the GPT series or other relevant models, it generates translation results that correspond to the user's sentiment. Output is the translated text data.

[0169] Step 6:

[0170] The server integrates translated text information into the original digital content. The input consists of translated text data and original content data. It appropriately positions the translated text as subtitles or dialogue and performs visual or audio integration processing. The output is content with the new subtitles or dialogue appropriately embedded.

[0171] Step 7:

[0172] The user downloads the integrated final product using their device and then views and enjoys it. In this step, the server provides a download link or direct download functionality. The input is the integrated content file, and the output is the content data stored on the user's device.

[0173] (Application Example 2)

[0174] 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".

[0175] In multilingual environments, translating content while considering user emotions presents a significant challenge. While traditional systems can translate textual information, they struggle to adjust the tone and style of the translation based on user emotions. As a result, content is often not culturally localized appropriately, leading to a diminished viewer experience.

[0176] 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.

[0177] In this invention, the server includes means for receiving data, means for extracting textual information from the received data, means for analyzing the user's emotions, means for translating the analyzed textual information into another language and adjusting the tone and style of the translation based on the user's emotions, and means for integrating the translated textual information. This makes it possible to translate with an appropriate tone and style that corresponds to the user's emotions.

[0178] "Means of receiving data" refers to the technology and devices that retrieve user-uploaded video and manga data onto the server.

[0179] "Means for extracting text information" refers to a device that uses optical character recognition technology to extract text such as subtitles and dialogue from received data.

[0180] "Means for analyzing the context of extracted textual information" refers to technological devices that use natural language processing techniques to understand the meaning and underlying cultural background of extracted text.

[0181] "Methods for analyzing user emotions" refer to technological devices that use machine learning algorithms to infer a user's emotional state based on user feedback and past emotional history.

[0182] "Means for translating and adjusting the translation tone and style based on the user's emotions" refers to a technological device that uses a generative AI model to translate textual information and modifies the translation to an appropriate tone and style according to the user's emotions.

[0183] "Means for integrating translated text information" refers to a technological device that rearranges translated text into the original video or comic data and incorporates it into the content in a natural way.

[0184] This invention relates to a video and comic translation system that takes user emotions into consideration. First, the server receives video or comic data. From the received data, text information such as subtitles and dialogue is extracted using optical character recognition technology (e.g., pytesseract). After extraction, the context of the text information is analyzed using natural language processing technology (e.g., transformers library). This analysis allows for an understanding of the meaning and cultural background of the original language.

[0185] Next, the server performs sentiment analysis based on the user's feedback and past sentiment history. It uses a machine learning algorithm as its sentiment engine to infer the user's emotional state. Then, a generative AI model is used to translate the textual information into another language. This translation is adjusted to reflect the tone and style that matches the user's emotions, based on the analysis results and sentiment analysis. For example, if the user provides positive feedback, the translation will also be adjusted to have a bright and friendly tone.

[0186] Ultimately, the translated text information is integrated into the original video or comic data and provided in a viewable format. For example, when translating a Japanese comedy anime for English-speaking audiences, the translation will make the conversation lighter and more humorous when viewers provide feedback with smiles. This improves the user experience and makes the content more widely accessible.

[0187] Example of a prompt:

[0188] "I'm watching a Japanese comedy anime. Please translate the subtitles in a cheerful tone."

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

[0190] Step 1:

[0191] The server receives video and manga data from users. At this stage, the data is transferred to the server when the user uploads it to the system. The input is the video and manga data provided by the user, and the output is the raw data stored on the server.

[0192] Step 2:

[0193] The server extracts text information from the received data. This process uses optical character recognition (e.g., PyTesseract) to convert subtitles and dialogue from videos and comics into text data. The input is image data, and the output is the extracted text information.

[0194] Step 3:

[0195] The server analyzes the context of the extracted text information. Using natural language processing techniques (e.g., the transformers library), it understands the text's context and cultural background and obtains the information necessary for translation. In this process, the input is the extracted text information, and the output is the analyzed contextual information.

[0196] Step 4:

[0197] The server uses user feedback and past emotional history to analyze the user's emotions. In this step, a machine learning algorithm is used to infer the user's emotions from the emotion engine. The input is the user's feedback data, and the output is the inferred emotional state.

[0198] Step 5:

[0199] The server uses a generative AI model to translate textual information based on analysis results and sentiment analysis, and adjusts the tone and style of the translation. This ensures that the translation is appropriate to the user's emotions. The input is the analyzed contextual information and emotional state, and the output is the translated text with adjusted tone and style.

[0200] Step 6:

[0201] The server integrates the translated text information into the original video or comic data. At this stage, the translated text is rearranged as subtitles in the case of videos, or as dialogue in the case of comics. The input is the translated text information, and the output is the integrated data in a viewable format.

[0202] These steps aim to enable users to enjoy translated content that reflects their emotions.

[0203] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0204] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0205] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0206] [Second Embodiment]

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

[0208] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0209] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0210] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0211] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0212] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0213] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0214] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0215] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0216] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0217] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0218] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0219] This invention is a system for efficiently translating Japanese content such as videos and manga into other languages ​​and distributing it overseas. This system operates server-centric and processes data uploaded by users. Specifically, it operates as follows:

[0220] The process begins when a user uploads video or comic data they wish to have translated to a server. The server receives this data and first uses optical character recognition (OCR) technology to extract text information from the image or video frames. This extraction process includes all text information contained within the content, such as subtitles and dialogue.

[0221] Next, the server analyzes the context of the extracted text information using natural language processing techniques. This process helps to understand sentence structure, cultural background, emotional expression, and other information necessary to improve translation accuracy.

[0222] Subsequently, an AI model is used to translate the analyzed text information into other languages. The translated text is then integrated back into the original content by the server and placed in the appropriate positions as subtitles for videos or dialogue for comics.

[0223] After these processes, the server ultimately generates new translated data, making it available for download by the user. A concrete example is a scenario where Japanese anime episodes are provided with English subtitles. In this case, the server automatically generates subtitles for the anime for English-speaking audiences, and the user can download this translated episode and provide it to viewers.

[0224] This system allows users to achieve high-quality multilingual translations without hassle, supporting the international expansion of Japan's content industry.

[0225] The following describes the processing flow.

[0226] Step 1:

[0227] The user uploads the video or comic data to be translated. They access the server using their device and provide the file in the specified format (e.g., MP4, PNG).

[0228] Step 2:

[0229] The server receives the uploaded data. It checks the file format and integrity, and prepares it for appropriate processing.

[0230] Step 3:

[0231] The server analyzes the data and, in the case of video, extracts each frame as an image. Next, OCR technology is used to detect text information within the images and convert it into digital text.

[0232] Step 4:

[0233] The server performs contextual analysis of the extracted text information using natural language processing technology. It considers the dictionary meaning of words, grammatical structure, and cultural background to obtain the information necessary for accurate translation.

[0234] Step 5:

[0235] The server uses a generated AI model to translate the analyzed text information into another language. The translation result is output as text.

[0236] Step 6:

[0237] The server integrates the translated text into the original data. For videos, it inserts subtitles at appropriate times; for comics, it adjusts and positions the dialogue based on its design.

[0238] Step 7:

[0239] The server generates the final translated data in a new file format, formatting it for easy download by the user.

[0240] Step 8:

[0241] The user downloads the translated data from the server. It is retrieved via the device and prepared for distribution to viewers as needed.

[0242] (Example 1)

[0243] 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."

[0244] The present invention aims to provide a system that can efficiently translate Japanese content such as videos and manga into multiple languages, thereby reducing the manual work and time costs involved in international distribution. Conventional methods require manual translation by translators, which is problematic due to the time and effort involved. Furthermore, accurately understanding the context and cultural background of the content and producing appropriate translations is not easy.

[0245] 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.

[0246] In this invention, the server includes means for receiving digital data, means for extracting textual information from the received digital data, and means for using generative artificial intelligence to translate the extracted textual information into other languages. This enables high-quality multilingual translation that takes into account the context and cultural background of the content.

[0247] "Digital data" refers to a collection of information encoded in a format that can be processed using a computer.

[0248] "Textual information" refers to information such as sentences and words expressed in text format.

[0249] "Context" refers to a set of supplementary information that helps us understand the background and situation in which a particular piece of information is placed.

[0250] "Generative artificial intelligence" refers to systems and programs that have the ability to generate new data and content using artificial intelligence technology.

[0251] "Integration" is the process of bringing together multiple elements into a unified and consistent state.

[0252] This invention is a server-centric system designed to translate Japanese video and manga content into multiple languages ​​and distribute it to the international market. Users upload the digital data they wish to have translated to the server via their terminal. This digital data includes visual media such as videos and manga.

[0253] The server first uses optical character recognition (OCR) technology to extract text information from each frame of uploaded videos and comics. General-purpose OCR software such as "Tesseract" can be used for this process. The server then analyzes the extracted text information using natural language processing (NLP) technology. NLP libraries such as "spaCy" and "BERT" are used to perform in-depth analysis that takes context, emotions, and cultural background into account.

[0254] Next, the server translates the analyzed text information into another language using a generative AI model. In this step, a prompt sentence is input using a generative artificial intelligence model such as "OpenAI GPT" or "DeepL," and an appropriate translation result is obtained. For example, a possible prompt sentence might be, "Please translate the line 'Hello' from this Japanese anime into English."

[0255] Finally, the server integrates the translated text information into the original digital data. For videos, the server uses video editing tools such as "FFmpeg" to position the new subtitles appropriately. For comics, image editing software is used to combine the translated dialogue with the images. The completed translated digital data is then made available for download by the user.

[0256] One concrete example is providing Japanese anime episodes with English subtitles. When a user uploads an anime, the server automatically generates English subtitles using the technology described above. This allows users to quickly provide high-quality translated content without any extra effort.

[0257] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0258] Step 1:

[0259] The user uploads digital data of videos or comics they wish to translate from their device to the server. The input is the user's local device, and the output of this step is the original digital data stored on the server. The device securely transfers the selected files using a data transfer protocol.

[0260] Step 2:

[0261] The server extracts character information from the uploaded digital data using optical character recognition (OCR). The input is the digital data obtained in step 1, and the output is the extracted text data. The server recognizes characters from the image frame using OCR software such as "Tesseract" and saves the results in text format.

[0262] Step 3:

[0263] The server analyzes the text data obtained by OCR using natural language processing (NLP) techniques. The input is the character information obtained in step 2, and the output is data with context and meaning analyzed. The server uses "spaCy" and "BERT" to analyze sentence structure, sentiment, and background information to understand the context.

[0264] Step 4:

[0265] The server translates the analyzed text data into other languages ​​using a generation AI model. The input is the data analyzed in step 3, and the output is the translated character information. The server utilizes "OpenAI GPT" and "DeepL" along with prompt text to generate contextually appropriate translations.

[0266] Step 5:

[0267] The server integrates the translated text information with the original digital data. The input is the translated data obtained in step 4 and the original digital data, and the output is the translated integrated data. The server adds subtitles to the video using editing tools such as "FFmpeg" or inserts the translated dialogue into the comic using image editing software.

[0268] Step 6:

[0269] The server makes the completed translated digital data available for download to the user. The input is the integrated data generated in step 5, and the output is the completed file accessible to the user. The server uses a storage service to ensure that the user can securely download the file via a specific link.

[0270] (Application Example 1)

[0271] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0272] In the process of translating content into other languages, there is a need for rapid and accurate translation processing, as well as the efficient provision of information on cultural background and linguistic nuances that users require. However, conventional systems have problems such as insufficient translation accuracy and time-consuming provision of additional information.

[0273] 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.

[0274] In this invention, the server includes means for receiving data, means for extracting character information from the received data, and means for providing additional information based on user selection. This enables rapid and accurate translation processing and real-time provision of additional information through a user interface.

[0275] The "means for receiving data" is a function for the server to receive content data transmitted from a user.

[0276] The "means for extracting character information" is a function for recognizing and extracting text from the received content data.

[0277] The "means for analyzing context" is a function for performing natural language processing to understand the meaning and background of the extracted character information.

[0278] The "means for translating into other languages" is a function for using a generative AI model to convert the analyzed character information into a different language.

[0279] The "means for integrating the translated character information into the original data" is a function for placing the translated text at an appropriate position in the original content.

[0280] The "means for outputting the translated data" is a function for making the translated data available to the user.

[0281] The "means for providing additional information based on the user's selection" is a function for displaying relevant information and background about the item specified by the user.

[0282] The "means for displaying additional information through the user interface" is a function for showing additional content related to the selected information to the user on the screen.

[0283] The system for implementing this invention is composed of a process of exchanging data between a server and a user terminal and translating the language information of the received data.

[0284] First, the user uploads content data (such as videos or comics) to be translated using the terminal to the cloud server. At this time, the user specifies the desired translation language. The server receives this data and starts the necessary processing.

[0285] First, the server extracts character information from the received data using the Google Cloud Vision API. In the case of a video, each frame is analyzed, and in the case of a comic, the entire page is targeted to obtain text data.

[0286] Next, the server uses the Google Cloud Natural Language API to analyze the context of the extracted character information. This deepens the understanding of the meaning of the extracted data and improves the translation accuracy.

[0287] The analyzed character information is translated into other languages using the GPT model of OpenAI or the DeepL API. If necessary, the generative AI model also takes into account cultural backgrounds and nuances.

[0288] The translated text information is accurately integrated into the original data and output as translated data to the user terminal by the server. On the terminal, translated subtitles are displayed for videos, and dialogues are appropriately placed for comics. Furthermore, based on the user's selection, additional information regarding specific terms or dialogues is displayed, including a function to learn about cultural backgrounds.

[0289] For example, when the user selects "the technology of Character A", the historical background of that technology is explained in real time. As a specific example of the prompt text given to the generative AI model, something like "Please translate the technology '〇〇' of Character A into English and explain its cultural background" can be considered.

[0290] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0291] Step 1:

[0292] The user uses the terminal to upload the content data to be translated to the server. Videos or comics are used as input, and the server receives and saves this data.

[0293] Step 2:

[0294] The server uses the Google Cloud Vision API to extract text information from the received data. Specifically, it uses OCR technology to obtain text data from each frame of a video or page of a comic book. The input is the uploaded content, and the output is the extracted text information.

[0295] Step 3:

[0296] The server uses the Google Cloud Natural Language API to analyze the extracted text information. The input is the text information obtained in step 2, and the output is analyzed data including context. Specifically, it performs processing to understand emotions and sentence structure.

[0297] Step 4:

[0298] The server translates the analyzed text information into other languages ​​using OpenAI's GPT model and DeepL API. Here, prompt sentences are generated and provided to the generative AI model. The input is the analyzed data from step 3, and the output is the translated text.

[0299] Step 5:

[0300] The server integrates the translated text information into the original content data. This information is then placed as subtitles in videos and as dialogue in comics. The input consists of the translated text information and the original content, while the output is the integrated, complete data.

[0301] Step 6:

[0302] The server sends the integrated translated data to the terminal so that the user can view it. Here, the user can select the parts that require supplementary information and receive a detailed explanation. As a specific example, when the user selects a specific term, cultural background information related to that term is displayed. As a prompt sentence in this case, for example, "Please explain the background of the term ○○" is generated.

[0303] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0304] The present invention is a system that not only simply translates data, but also recognizes the user's emotion and adjusts the tone and style of the translation according to that emotion. This system is implemented as follows.

[0305] First, the user uploads video or comic data for which translation is desired to the server. The server receives the data and extracts character information such as subtitles and lines using optical character recognition technology.

[0306] Next, the server analyzes the context of the character information extracted using natural language processing technology. Through this analysis, the meaning and cultural background of the original language are grasped. Also, at this stage, the emotion engine is utilized to analyze the user's emotional state based on the feedback given by the user to the system and the past emotion history. This emotion engine uses a machine learning algorithm to infer what kind of emotion the user has towards the content.

[0307] Based on the analysis results and emotion analysis, the server translates the character information into another language using a generation AI model. In this translation, the tone and style corresponding to the user's emotion are reflected. For example, when the user shows a happy emotion, the translation is also adjusted to have a bright and friendly tone.

[0308] Finally, the translated text information is integrated into the original data. After this process, it is appropriately placed as subtitles in videos or as dialogue in comics, and becomes available for download by the user.

[0309] For example, when translating a Japanese comedy anime for an English-speaking audience, if users provide smiling feedback, consideration will be given to translating the conversation in a lighter and more humorous tone. This results in content that is more relatable and enjoyable for viewers.

[0310] This system will go beyond simple word-for-word translation, enabling content delivery that takes viewers' emotions into consideration, with the aim of promoting wider global acceptance of Japanese content.

[0311] The following describes the processing flow.

[0312] Step 1:

[0313] The user uploads the video or manga data to be translated to the server via their device. The server receives the data and verifies that the data format is correct.

[0314] Step 2:

[0315] The server begins analyzing the received data. In the case of videos, it divides the data into individual frames and extracts text information from each frame using optical character recognition technology. Similarly, for comics, it detects text information from each page.

[0316] Step 3:

[0317] The server uses natural language processing techniques to perform contextual analysis on the extracted text information. During this process, the meaning and cultural nuances of the original text are understood.

[0318] Step 4:

[0319] The server activates the emotion engine and analyzes the user's emotional data. This is done by referencing feedback and reactions previously provided by the user to estimate their current emotional state.

[0320] Step 5:

[0321] The server uses a generation AI model to perform translations into other languages, reflecting the results of contextual and sentiment analysis. These translations are then adjusted to match the user's estimated emotions in terms of tone and style.

[0322] Step 6:

[0323] The server integrates the translated text information into the original data. For videos, it inserts subtitles at the appropriate timing; for comics, it arranges dialogue considering the design.

[0324] Step 7:

[0325] The server generates the final translated data and adjusts the format so that it can be downloaded by the user.

[0326] Step 8:

[0327] The user retrieves the translation results from the server and checks them on their device. This data is used to provide it to viewers and readers as needed.

[0328] (Example 2)

[0329] 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".

[0330] Traditional translation systems simply convert text information into different languages, lacking contextual understanding that takes into account user emotions and intentions. This can result in translations that lose the original tone and style of the content, potentially reducing viewer engagement. Furthermore, providing translations that reflect individual user emotions and feedback has been challenging.

[0331] 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.

[0332] In this invention, the server includes means for acquiring data, technical means for identifying text information, and technical means for evaluating the background of the identified text information. This enables flexible and appropriate translation that is tailored to the user's emotions and context.

[0333] "Means of acquiring data" refers to the function of collecting digital content provided by users into the system.

[0334] "Technical means for identifying text information" refers to technologies for detecting and reading characters in digital content.

[0335] "Technical means for evaluating the background of identified text information" refers to technologies that analyze and understand the context and cultural background of detected text information.

[0336] "Generative technology means" refers to technology for generating translations appropriate to the context using evaluated text information.

[0337] "Means of supplying the final product" refers to a function for incorporating translated content into the content and providing it to the user.

[0338] This system begins with a user uploading digital content such as videos or comics to a server. The server first uses a data acquisition method to extract text information from the received content. For this process, open-source OCR engines such as Tesseract are typically used as optical information recognition (OCR) technologies. This technology efficiently identifies text information embedded in images and videos.

[0339] Next, the server utilizes natural language processing (NLP) techniques as a means to evaluate the context of the text information. In this phase, natural language processing models such as BERT and GPT are used to analyze the context and cultural background of the extracted text in detail. Based on the results of this analysis, a dedicated sentiment engine analyzes the user's current emotional state by referring to user feedback and past sentiment history.

[0340] Subsequently, the server uses generative techniques to translate the text information into another language, taking into account the evaluated context. This process utilizes the well-known GPT series of generative AI models to achieve contextually and emotionally optimized translations. For example, if a user provides positive feedback, the translated output will reflect that positive tone.

[0341] For example, when translating subtitles for a Japanese comedy film into English, if a user provides feedback such as "very funny and entertaining," the translated English subtitles will be adjusted to also include humor. An example of a prompt might be, "Translate the fun Japanese movie subtitles into English based on user feedback, maintaining a lighthearted tone."

[0342] The final output is integrated into the original digital content and displayed as subtitles in an appropriate format. Users can download the translated content in an available format using their device and view it. In this way, the system provides a translation service that enhances the user experience.

[0343] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0344] Step 1:

[0345] Users upload digital content such as videos and comics they wish to have translated from their computer terminal to the server. The input is digital data in a file format provided by the user. The server processes the received files and imports the content data into the system. The output is the content data securely stored on the server.

[0346] Step 2:

[0347] The server uses optical image recognition (OCR) technology to extract text information from uploaded content. The input is digital data in image or video format. The OCR engine used (e.g., Tesseract) operates frame by frame, detecting text and outputting it as digital character data.

[0348] Step 3:

[0349] The server evaluates the background and context of text information extracted using natural language processing techniques. The input is character data obtained by OCR. It utilizes BERT and similar NLP models to understand the text context and analyze its cultural background. The output consists of contextual metadata and analysis results.

[0350] Step 4:

[0351] The server analyzes the user's emotional state using an emotion engine, referencing the user's emotional history and current feedback. Inputs include past user feedback and focused current feedback information. A machine learning algorithm is used to infer and output the user's emotional state data.

[0352] Step 5:

[0353] The server translates text information based on contextual and sentiment data evaluated using a generative AI model. Inputs are contextual metadata and user sentiment state. Using the GPT series or other relevant models, it generates translation results that correspond to the user's sentiment. Output is the translated text data.

[0354] Step 6:

[0355] The server integrates translated text information into the original digital content. The input consists of translated text data and original content data. It appropriately positions the translated text as subtitles or dialogue and performs visual or audio integration processing. The output is content with the new subtitles or dialogue appropriately embedded.

[0356] Step 7:

[0357] The user downloads the integrated final product using their device and then views and enjoys it. In this step, the server provides a download link or direct download functionality. The input is the integrated content file, and the output is the content data stored on the user's device.

[0358] (Application Example 2)

[0359] 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 as the "terminal".

[0360] In multilingual environments, translating content while considering user emotions presents a significant challenge. While traditional systems can translate textual information, they struggle to adjust the tone and style of the translation based on user emotions. As a result, content is often not culturally localized appropriately, leading to a diminished viewer experience.

[0361] 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.

[0362] In this invention, the server includes means for receiving data, means for extracting textual information from the received data, means for analyzing the user's emotions, means for translating the analyzed textual information into another language and adjusting the tone and style of the translation based on the user's emotions, and means for integrating the translated textual information. This makes it possible to translate with an appropriate tone and style that corresponds to the user's emotions.

[0363] "Means of receiving data" refers to the technology and devices that retrieve user-uploaded video and manga data onto the server.

[0364] "Means for extracting text information" refers to a device that uses optical character recognition technology to extract text such as subtitles and dialogue from received data.

[0365] "Means for analyzing the context of extracted textual information" refers to technological devices that use natural language processing techniques to understand the meaning and underlying cultural background of extracted text.

[0366] "Methods for analyzing user emotions" refer to technological devices that use machine learning algorithms to infer a user's emotional state based on user feedback and past emotional history.

[0367] "Means for translating and adjusting the translation tone and style based on the user's emotions" refers to a technological device that uses a generative AI model to translate textual information and modifies the translation to an appropriate tone and style according to the user's emotions.

[0368] "Means for integrating translated text information" refers to a technological device that rearranges translated text into the original video or comic data and incorporates it into the content in a natural way.

[0369] This invention relates to a video and comic translation system that takes user emotions into consideration. First, the server receives video or comic data. From the received data, text information such as subtitles and dialogue is extracted using optical character recognition technology (e.g., pytesseract). After extraction, the context of the text information is analyzed using natural language processing technology (e.g., transformers library). This analysis allows for an understanding of the meaning and cultural background of the original language.

[0370] Next, the server performs sentiment analysis based on the user's feedback and past sentiment history. It uses a machine learning algorithm as its sentiment engine to infer the user's emotional state. Then, a generative AI model is used to translate the textual information into another language. This translation is adjusted to reflect the tone and style that matches the user's emotions, based on the analysis results and sentiment analysis. For example, if the user provides positive feedback, the translation will also be adjusted to have a bright and friendly tone.

[0371] Ultimately, the translated text information is integrated into the original video or comic data and provided in a viewable format. For example, when translating a Japanese comedy anime for English-speaking audiences, the translation will make the conversation lighter and more humorous when viewers provide feedback with smiles. This improves the user experience and makes the content more widely accessible.

[0372] Example of a prompt:

[0373] "I'm watching a Japanese comedy anime. Please translate the subtitles in a cheerful tone."

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

[0375] Step 1:

[0376] The server receives video and manga data from users. At this stage, the data is transferred to the server when the user uploads it to the system. The input is the video and manga data provided by the user, and the output is the raw data stored on the server.

[0377] Step 2:

[0378] The server extracts text information from the received data. This process uses optical character recognition (e.g., PyTesseract) to convert subtitles and dialogue from videos and comics into text data. The input is image data, and the output is the extracted text information.

[0379] Step 3:

[0380] The server analyzes the context of the extracted text information. Using natural language processing techniques (e.g., the transformers library), it understands the text's context and cultural background and obtains the information necessary for translation. In this process, the input is the extracted text information, and the output is the analyzed contextual information.

[0381] Step 4:

[0382] The server uses user feedback and past emotional history to analyze the user's emotions. In this step, a machine learning algorithm is used to infer the user's emotions from the emotion engine. The input is the user's feedback data, and the output is the inferred emotional state.

[0383] Step 5:

[0384] The server uses a generative AI model to translate textual information based on analysis results and sentiment analysis, and adjusts the tone and style of the translation. This ensures that the translation is appropriate to the user's emotions. The input is the analyzed contextual information and emotional state, and the output is the translated text with adjusted tone and style.

[0385] Step 6:

[0386] The server integrates the translated text information into the original video or comic data. At this stage, the translated text is rearranged as subtitles in the case of videos, or as dialogue in the case of comics. The input is the translated text information, and the output is the integrated data in a viewable format.

[0387] These steps aim to enable users to enjoy translated content that reflects their emotions.

[0388] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0389] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0390] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0391] [Third Embodiment]

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

[0393] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0394] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0395] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0396] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0397] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0398] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0399] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0400] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0401] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0402] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0403] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0404] This invention is a system for efficiently translating Japanese content such as videos and manga into other languages ​​and distributing it overseas. This system operates server-centric and processes data uploaded by users. Specifically, it operates as follows:

[0405] The process begins when a user uploads video or comic data they wish to have translated to a server. The server receives this data and first uses optical character recognition (OCR) technology to extract text information from the image or video frames. This extraction process includes all text information contained within the content, such as subtitles and dialogue.

[0406] Next, the server analyzes the context of the extracted text information using natural language processing techniques. This process helps to understand sentence structure, cultural background, emotional expression, and other information necessary to improve translation accuracy.

[0407] Subsequently, an AI model is used to translate the analyzed text information into other languages. The translated text is then integrated back into the original content by the server and placed in the appropriate positions as subtitles for videos or dialogue for comics.

[0408] After these processes, the server ultimately generates new translated data, making it available for download by the user. A concrete example is a scenario where Japanese anime episodes are provided with English subtitles. In this case, the server automatically generates subtitles for the anime for English-speaking audiences, and the user can download this translated episode and provide it to viewers.

[0409] This system allows users to achieve high-quality multilingual translations without hassle, supporting the international expansion of Japan's content industry.

[0410] The following describes the processing flow.

[0411] Step 1:

[0412] The user uploads the video or comic data to be translated. They access the server using their device and provide the file in the specified format (e.g., MP4, PNG).

[0413] Step 2:

[0414] The server receives the uploaded data. It checks the file format and integrity, and prepares it for appropriate processing.

[0415] Step 3:

[0416] The server analyzes the data and, in the case of video, extracts each frame as an image. Next, OCR technology is used to detect text information within the images and convert it into digital text.

[0417] Step 4:

[0418] The server performs contextual analysis of the extracted text information using natural language processing technology. It considers the dictionary meaning of words, grammatical structure, and cultural background to obtain the information necessary for accurate translation.

[0419] Step 5:

[0420] The server uses a generated AI model to translate the analyzed text information into another language. The translation result is output as text.

[0421] Step 6:

[0422] The server integrates the translated text into the original data. For videos, it inserts subtitles at appropriate times; for comics, it adjusts and positions the dialogue based on its design.

[0423] Step 7:

[0424] The server generates the final translated data in a new file format, formatting it for easy download by the user.

[0425] Step 8:

[0426] The user downloads the translated data from the server. It is retrieved via the device and prepared for distribution to viewers as needed.

[0427] (Example 1)

[0428] 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."

[0429] The present invention aims to provide a system that can efficiently translate Japanese content such as videos and manga into multiple languages, thereby reducing the manual work and time costs involved in international distribution. Conventional methods require manual translation by translators, which is problematic due to the time and effort involved. Furthermore, accurately understanding the context and cultural background of the content and producing appropriate translations is not easy.

[0430] 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.

[0431] In this invention, the server includes means for receiving digital data, means for extracting textual information from the received digital data, and means for using generative artificial intelligence to translate the extracted textual information into other languages. This enables high-quality multilingual translation that takes into account the context and cultural background of the content.

[0432] "Digital data" refers to a collection of information encoded in a format that can be processed using a computer.

[0433] "Textual information" refers to information such as sentences and words expressed in text format.

[0434] "Context" refers to a set of supplementary information that helps us understand the background and situation in which a particular piece of information is placed.

[0435] "Generative artificial intelligence" refers to systems and programs that have the ability to generate new data and content using artificial intelligence technology.

[0436] "Integration" is the process of bringing together multiple elements into a unified and consistent state.

[0437] This invention is a server-centric system designed to translate Japanese video and manga content into multiple languages ​​and distribute it to the international market. Users upload the digital data they wish to have translated to the server via their terminal. This digital data includes visual media such as videos and manga.

[0438] The server first uses optical character recognition (OCR) technology to extract text information from each frame of uploaded videos and comics. General-purpose OCR software such as "Tesseract" can be used for this process. The server then analyzes the extracted text information using natural language processing (NLP) technology. NLP libraries such as "spaCy" and "BERT" are used to perform in-depth analysis that takes context, emotions, and cultural background into account.

[0439] Next, the server translates the analyzed text information into another language using a generative AI model. In this step, a prompt sentence is input using a generative artificial intelligence model such as "OpenAI GPT" or "DeepL," and an appropriate translation result is obtained. For example, a possible prompt sentence might be, "Please translate the line 'Hello' from this Japanese anime into English."

[0440] Finally, the server integrates the translated text information into the original digital data. For videos, the server uses video editing tools such as "FFmpeg" to position the new subtitles appropriately. For comics, image editing software is used to combine the translated dialogue with the images. The completed translated digital data is then made available for download by the user.

[0441] One concrete example is providing Japanese anime episodes with English subtitles. When a user uploads an anime, the server automatically generates English subtitles using the technology described above. This allows users to quickly provide high-quality translated content without any extra effort.

[0442] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0443] Step 1:

[0444] The user uploads digital data of videos or comics they wish to translate from their device to the server. The input is the user's local device, and the output of this step is the original digital data stored on the server. The device securely transfers the selected files using a data transfer protocol.

[0445] Step 2:

[0446] The server extracts character information from the uploaded digital data using optical character recognition (OCR). The input is the digital data obtained in step 1, and the output is the extracted text data. The server recognizes characters from the image frame using OCR software such as "Tesseract" and saves the results in text format.

[0447] Step 3:

[0448] The server analyzes the text data obtained by OCR using natural language processing (NLP) techniques. The input is the character information obtained in step 2, and the output is data with context and meaning analyzed. The server uses "spaCy" and "BERT" to analyze sentence structure, sentiment, and background information to understand the context.

[0449] Step 4:

[0450] The server translates the analyzed text data into other languages ​​using a generation AI model. The input is the data analyzed in step 3, and the output is the translated character information. The server utilizes "OpenAI GPT" and "DeepL" along with prompt text to generate contextually appropriate translations.

[0451] Step 5:

[0452] The server integrates the translated text information with the original digital data. The input is the translated data obtained in step 4 and the original digital data, and the output is the translated integrated data. The server adds subtitles to the video using editing tools such as "FFmpeg" or inserts the translated dialogue into the comic using image editing software.

[0453] Step 6:

[0454] The server makes the completed translated digital data available for download to the user. The input is the integrated data generated in step 5, and the output is the completed file accessible to the user. The server uses a storage service to ensure that the user can securely download the file via a specific link.

[0455] (Application Example 1)

[0456] 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."

[0457] In the process of translating content into other languages, there is a need for rapid and accurate translation processing, as well as the efficient provision of information on cultural background and linguistic nuances that users require. However, conventional systems have problems such as insufficient translation accuracy and time-consuming provision of additional information.

[0458] 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.

[0459] In this invention, the server includes means for receiving data, means for extracting character information from the received data, and means for providing additional information based on user selection. This enables rapid and accurate translation processing and real-time provision of additional information through a user interface.

[0460] "Means of receiving data" refers to the function by which a server receives content data sent by a user.

[0461] "Means for extracting text information" refers to a function that recognizes and extracts text from received content data.

[0462] "Means for analyzing context" refers to functions that perform natural language processing to understand the meaning and background of extracted textual information.

[0463] "Means of translation into other languages" refers to a function that uses a generative AI model to convert analyzed textual information into a different language.

[0464] "Means of integrating translated text information into the original data" refers to a function that places the translated text in the appropriate location within the original content.

[0465] "Means for outputting translated data" refers to a function that makes the translated data available to the user.

[0466] "Means of providing additional information based on user selection" refers to a function that displays related information and background details for items specified by the user.

[0467] "Means of displaying additional information through the user interface" refers to a function that shows the user additional content related to the selected information on the screen.

[0468] A system implementing this invention consists of a process that exchanges data between a server and a user terminal and translates the language information of the received data.

[0469] First, the user uploads the content data they want to translate (e.g., videos or comics) to the cloud server using their device. At this time, the user specifies the desired translation language. The server receives this data and begins the necessary processing.

[0470] The server first uses the Google Cloud Vision API to extract text information from the received data. For videos, it analyzes each frame, and for comics, it obtains text data from the entire page.

[0471] Next, the server uses the Google Cloud Natural Language API to analyze the context of the extracted text information. This deepens the understanding of the meaning of the extracted data and improves translation accuracy.

[0472] The analyzed text information is translated into other languages ​​using OpenAI's GPT model and DeepL API. Where necessary, the generative AI model also considers cultural context and nuances.

[0473] The translated text information is accurately integrated with the original data and output to the user's terminal as translated data by the server. On the terminal, translated subtitles are displayed for videos, and dialogue is appropriately placed for comics. Furthermore, based on the user's selection, additional information about specific terms and lines is displayed, including a function to learn about the cultural background.

[0474] For example, if a user selects "Character A's technology," the historical background of that technology will be explained in real time. A concrete example of a prompt given to the generating AI model could be, "Translate Character A's technology '○○' into English and explain its cultural background."

[0475] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0476] Step 1:

[0477] Users upload content data they want to translate to the server using their device. Videos and comics are used as input, and the server receives and stores this data.

[0478] Step 2:

[0479] The server uses the Google Cloud Vision API to extract text information from the received data. Specifically, it uses OCR technology to obtain text data from each frame of a video or page of a comic book. The input is the uploaded content, and the output is the extracted text information.

[0480] Step 3:

[0481] The server uses the Google Cloud Natural Language API to analyze the extracted text information. The input is the text information obtained in step 2, and the output is analyzed data including context. Specifically, it performs processing to understand emotions and sentence structure.

[0482] Step 4:

[0483] The server translates the analyzed text information into other languages ​​using OpenAI's GPT model and DeepL API. Here, prompt sentences are generated and provided to the generative AI model. The input is the analyzed data from step 3, and the output is the translated text.

[0484] Step 5:

[0485] The server integrates the translated text information into the original content data. This information is then placed as subtitles in videos and as dialogue in comics. The input consists of the translated text information and the original content, while the output is the integrated, complete data.

[0486] Step 6:

[0487] The server sends the integrated translated data to the terminal, making it available for user viewing. Here, the user can select sections requiring supplementary information and receive detailed explanations. For example, when a user selects a specific term, cultural background information related to that term is displayed. A prompt such as "Please explain the background of the term XX" might be generated.

[0488] 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.

[0489] This invention is a system that not only translates data but also recognizes the user's emotions and adjusts the tone and style of the translation to match those emotions. This system is implemented as follows:

[0490] First, the user uploads the video or manga data they want translated to the server. The server receives the data and uses optical character recognition technology to extract text information such as subtitles and dialogue.

[0491] Next, the server uses natural language processing techniques to analyze the context of the extracted text information. This analysis helps to understand the meaning and cultural background of the original language. At this stage, an emotion engine is also utilized to analyze the user's emotional state based on user feedback and past emotional history. This emotion engine uses machine learning algorithms to infer what emotions the user feels towards the content.

[0492] Based on the analysis results and sentiment analysis, the server uses a generative AI model to translate text information into other languages. This translation reflects the tone and style corresponding to the user's emotions. For example, if the user is expressing cheerful emotions, the translation will be adjusted to have a bright and friendly tone.

[0493] Finally, the translated text information is integrated into the original data. After this process, it is appropriately placed as subtitles in videos or as dialogue in comics, and becomes available for download by the user.

[0494] For example, when translating a Japanese comedy anime for an English-speaking audience, if users provide smiling feedback, consideration will be given to translating the conversation in a lighter and more humorous tone. This results in content that is more relatable and enjoyable for viewers.

[0495] This system will go beyond simple word-for-word translation, enabling content delivery that takes viewers' emotions into consideration, with the aim of promoting wider global acceptance of Japanese content.

[0496] The following describes the processing flow.

[0497] Step 1:

[0498] The user uploads the video or manga data to be translated to the server via their device. The server receives the data and verifies that the data format is correct.

[0499] Step 2:

[0500] The server begins analyzing the received data. In the case of videos, it divides the data into individual frames and extracts text information from each frame using optical character recognition technology. Similarly, for comics, it detects text information from each page.

[0501] Step 3:

[0502] The server uses natural language processing techniques to perform contextual analysis on the extracted text information. During this process, the meaning and cultural nuances of the original text are understood.

[0503] Step 4:

[0504] The server activates the emotion engine and analyzes the user's emotional data. This is done by referencing feedback and reactions previously provided by the user to estimate their current emotional state.

[0505] Step 5:

[0506] The server uses a generation AI model to perform translations into other languages, reflecting the results of contextual and sentiment analysis. These translations are then adjusted to match the user's estimated emotions in terms of tone and style.

[0507] Step 6:

[0508] The server integrates the translated text information into the original data. For videos, it inserts subtitles at the appropriate timing; for comics, it arranges dialogue considering the design.

[0509] Step 7:

[0510] The server generates the final translated data and adjusts the format so that it can be downloaded by the user.

[0511] Step 8:

[0512] The user retrieves the translation results from the server and checks them on their device. This data is used to provide it to viewers and readers as needed.

[0513] (Example 2)

[0514] 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."

[0515] Traditional translation systems simply convert text information into different languages, lacking contextual understanding that takes into account user emotions and intentions. This can result in translations that lose the original tone and style of the content, potentially reducing viewer engagement. Furthermore, providing translations that reflect individual user emotions and feedback has been challenging.

[0516] 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.

[0517] In this invention, the server includes means for acquiring data, technical means for identifying text information, and technical means for evaluating the background of the identified text information. This enables flexible and appropriate translation that is tailored to the user's emotions and context.

[0518] "Means of acquiring data" refers to the function of collecting digital content provided by users into the system.

[0519] "Technical means for identifying text information" refers to technologies for detecting and reading characters in digital content.

[0520] "Technical means for evaluating the background of identified text information" refers to technologies that analyze and understand the context and cultural background of detected text information.

[0521] "Generative technology means" refers to technology for generating translations appropriate to the context using evaluated text information.

[0522] "Means of supplying the final product" refers to a function for incorporating translated content into the content and providing it to the user.

[0523] This system begins with a user uploading digital content such as videos or comics to a server. The server first uses a data acquisition method to extract text information from the received content. For this process, open-source OCR engines such as Tesseract are typically used as optical information recognition (OCR) technologies. This technology efficiently identifies text information embedded in images and videos.

[0524] Next, the server utilizes natural language processing (NLP) techniques as a means to evaluate the context of the text information. In this phase, natural language processing models such as BERT and GPT are used to analyze the context and cultural background of the extracted text in detail. Based on the results of this analysis, a dedicated sentiment engine analyzes the user's current emotional state by referring to user feedback and past sentiment history.

[0525] Subsequently, the server uses generative techniques to translate the text information into another language, taking into account the evaluated context. This process utilizes the well-known GPT series of generative AI models to achieve contextually and emotionally optimized translations. For example, if a user provides positive feedback, the translated output will reflect that positive tone.

[0526] For example, when translating subtitles for a Japanese comedy film into English, if a user provides feedback such as "very funny and entertaining," the translated English subtitles will be adjusted to also include humor. An example of a prompt might be, "Translate the fun Japanese movie subtitles into English based on user feedback, maintaining a lighthearted tone."

[0527] The final output is integrated into the original digital content and displayed as subtitles in an appropriate format. Users can download the translated content in an available format using their device and view it. In this way, the system provides a translation service that enhances the user experience.

[0528] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0529] Step 1:

[0530] Users upload digital content such as videos and comics they wish to have translated from their computer terminal to the server. The input is digital data in a file format provided by the user. The server processes the received files and imports the content data into the system. The output is the content data securely stored on the server.

[0531] Step 2:

[0532] The server uses optical image recognition (OCR) technology to extract text information from uploaded content. The input is digital data in image or video format. The OCR engine used (e.g., Tesseract) operates frame by frame, detecting text and outputting it as digital character data.

[0533] Step 3:

[0534] The server evaluates the background and context of text information extracted using natural language processing techniques. The input is character data obtained by OCR. It utilizes BERT and similar NLP models to understand the text context and analyze its cultural background. The output consists of contextual metadata and analysis results.

[0535] Step 4:

[0536] The server analyzes the user's emotional state using an emotion engine, referencing the user's emotional history and current feedback. Inputs include past user feedback and focused current feedback information. A machine learning algorithm is used to infer and output the user's emotional state data.

[0537] Step 5:

[0538] The server translates text information based on contextual and sentiment data evaluated using a generative AI model. Inputs are contextual metadata and user sentiment state. Using the GPT series or other relevant models, it generates translation results that correspond to the user's sentiment. Output is the translated text data.

[0539] Step 6:

[0540] The server integrates translated text information into the original digital content. The input consists of translated text data and original content data. It appropriately positions the translated text as subtitles or dialogue and performs visual or audio integration processing. The output is content with the new subtitles or dialogue appropriately embedded.

[0541] Step 7:

[0542] The user downloads the integrated final product using their device and then views and enjoys it. In this step, the server provides a download link or direct download functionality. The input is the integrated content file, and the output is the content data stored on the user's device.

[0543] (Application Example 2)

[0544] 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."

[0545] In multilingual environments, translating content while considering user emotions presents a significant challenge. While traditional systems can translate textual information, they struggle to adjust the tone and style of the translation based on user emotions. As a result, content is often not culturally localized appropriately, leading to a diminished viewer experience.

[0546] 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.

[0547] In this invention, the server includes means for receiving data, means for extracting textual information from the received data, means for analyzing the user's emotions, means for translating the analyzed textual information into another language and adjusting the tone and style of the translation based on the user's emotions, and means for integrating the translated textual information. This makes it possible to translate with an appropriate tone and style that corresponds to the user's emotions.

[0548] "Means of receiving data" refers to the technology and devices that retrieve user-uploaded video and manga data onto the server.

[0549] "Means for extracting text information" refers to a device that uses optical character recognition technology to extract text such as subtitles and dialogue from received data.

[0550] "Means for analyzing the context of extracted textual information" refers to technological devices that use natural language processing techniques to understand the meaning and underlying cultural background of extracted text.

[0551] "Methods for analyzing user emotions" refer to technological devices that use machine learning algorithms to infer a user's emotional state based on user feedback and past emotional history.

[0552] "Means for translating and adjusting the translation tone and style based on the user's emotions" refers to a technological device that uses a generative AI model to translate textual information and modifies the translation to an appropriate tone and style according to the user's emotions.

[0553] "Means for integrating translated text information" refers to a technological device that rearranges translated text into the original video or comic data and incorporates it into the content in a natural way.

[0554] This invention relates to a video and comic translation system that takes user emotions into consideration. First, the server receives video or comic data. From the received data, text information such as subtitles and dialogue is extracted using optical character recognition technology (e.g., pytesseract). After extraction, the context of the text information is analyzed using natural language processing technology (e.g., transformers library). This analysis allows for an understanding of the meaning and cultural background of the original language.

[0555] Next, the server performs sentiment analysis based on the user's feedback and past sentiment history. It uses a machine learning algorithm as its sentiment engine to infer the user's emotional state. Then, a generative AI model is used to translate the textual information into another language. This translation is adjusted to reflect the tone and style that matches the user's emotions, based on the analysis results and sentiment analysis. For example, if the user provides positive feedback, the translation will also be adjusted to have a bright and friendly tone.

[0556] Ultimately, the translated text information is integrated into the original video or comic data and provided in a viewable format. For example, when translating a Japanese comedy anime for English-speaking audiences, the translation will make the conversation lighter and more humorous when viewers provide feedback with smiles. This improves the user experience and makes the content more widely accessible.

[0557] Example of a prompt:

[0558] "I'm watching a Japanese comedy anime. Please translate the subtitles in a cheerful tone."

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

[0560] Step 1:

[0561] The server receives video and manga data from users. At this stage, the data is transferred to the server when the user uploads it to the system. The input is the video and manga data provided by the user, and the output is the raw data stored on the server.

[0562] Step 2:

[0563] The server extracts text information from the received data. This process uses optical character recognition (e.g., PyTesseract) to convert subtitles and dialogue from videos and comics into text data. The input is image data, and the output is the extracted text information.

[0564] Step 3:

[0565] The server analyzes the context of the extracted text information. Using natural language processing techniques (e.g., the transformers library), it understands the text's context and cultural background and obtains the information necessary for translation. In this process, the input is the extracted text information, and the output is the analyzed contextual information.

[0566] Step 4:

[0567] The server uses user feedback and past emotional history to analyze the user's emotions. In this step, a machine learning algorithm is used to infer the user's emotions from the emotion engine. The input is the user's feedback data, and the output is the inferred emotional state.

[0568] Step 5:

[0569] The server uses a generative AI model to translate textual information based on analysis results and sentiment analysis, and adjusts the tone and style of the translation. This ensures that the translation is appropriate to the user's emotions. The input is the analyzed contextual information and emotional state, and the output is the translated text with adjusted tone and style.

[0570] Step 6:

[0571] The server integrates the translated text information into the original video or comic data. At this stage, the translated text is rearranged as subtitles in the case of videos, or as dialogue in the case of comics. The input is the translated text information, and the output is the integrated data in a viewable format.

[0572] These steps aim to enable users to enjoy translated content that reflects their emotions.

[0573] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0574] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0575] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0576] [Fourth Embodiment]

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

[0578] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0579] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0580] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0581] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0582] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0583] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0584] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0585] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0586] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0587] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0588] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0589] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0590] This invention is a system for efficiently translating Japanese content such as videos and manga into other languages ​​and distributing it overseas. This system operates server-centric and processes data uploaded by users. Specifically, it operates as follows:

[0591] The process begins when a user uploads video or comic data they wish to have translated to a server. The server receives this data and first uses optical character recognition (OCR) technology to extract text information from the image or video frames. This extraction process includes all text information contained within the content, such as subtitles and dialogue.

[0592] Next, the server analyzes the context of the extracted text information using natural language processing techniques. This process helps to understand sentence structure, cultural background, emotional expression, and other information necessary to improve translation accuracy.

[0593] Subsequently, an AI model is used to translate the analyzed text information into other languages. The translated text is then integrated back into the original content by the server and placed in the appropriate positions as subtitles for videos or dialogue for comics.

[0594] After these processes, the server ultimately generates new translated data, making it available for download by the user. A concrete example is a scenario where Japanese anime episodes are provided with English subtitles. In this case, the server automatically generates subtitles for the anime for English-speaking audiences, and the user can download this translated episode and provide it to viewers.

[0595] This system allows users to achieve high-quality multilingual translations without hassle, supporting the international expansion of Japan's content industry.

[0596] The following describes the processing flow.

[0597] Step 1:

[0598] The user uploads the video or comic data to be translated. They access the server using their device and provide the file in the specified format (e.g., MP4, PNG).

[0599] Step 2:

[0600] The server receives the uploaded data. It checks the file format and integrity, and prepares it for appropriate processing.

[0601] Step 3:

[0602] The server analyzes the data and, in the case of video, extracts each frame as an image. Next, OCR technology is used to detect text information within the images and convert it into digital text.

[0603] Step 4:

[0604] The server performs contextual analysis of the extracted text information using natural language processing technology. It considers the dictionary meaning of words, grammatical structure, and cultural background to obtain the information necessary for accurate translation.

[0605] Step 5:

[0606] The server uses a generated AI model to translate the analyzed text information into another language. The translation result is output as text.

[0607] Step 6:

[0608] The server integrates the translated text into the original data. For videos, it inserts subtitles at appropriate times; for comics, it adjusts and positions the dialogue based on its design.

[0609] Step 7:

[0610] The server generates the final translated data in a new file format, formatting it for easy download by the user.

[0611] Step 8:

[0612] The user downloads the translated data from the server. It is retrieved via the device and prepared for distribution to viewers as needed.

[0613] (Example 1)

[0614] 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".

[0615] The present invention aims to provide a system that can efficiently translate Japanese content such as videos and manga into multiple languages, thereby reducing the manual work and time costs involved in international distribution. Conventional methods require manual translation by translators, which is problematic due to the time and effort involved. Furthermore, accurately understanding the context and cultural background of the content and producing appropriate translations is not easy.

[0616] 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.

[0617] In this invention, the server includes means for receiving digital data, means for extracting textual information from the received digital data, and means for using generative artificial intelligence to translate the extracted textual information into other languages. This enables high-quality multilingual translation that takes into account the context and cultural background of the content.

[0618] "Digital data" refers to a collection of information encoded in a format that can be processed using a computer.

[0619] "Textual information" refers to information such as sentences and words expressed in text format.

[0620] "Context" refers to a set of supplementary information that helps us understand the background and situation in which a particular piece of information is placed.

[0621] "Generative artificial intelligence" refers to systems and programs that have the ability to generate new data and content using artificial intelligence technology.

[0622] "Integration" is the process of bringing together multiple elements into a unified and consistent state.

[0623] This invention is a server-centric system designed to translate Japanese video and manga content into multiple languages ​​and distribute it to the international market. Users upload the digital data they wish to have translated to the server via their terminal. This digital data includes visual media such as videos and manga.

[0624] The server first uses optical character recognition (OCR) technology to extract text information from each frame of uploaded videos and comics. General-purpose OCR software such as "Tesseract" can be used for this process. The server then analyzes the extracted text information using natural language processing (NLP) technology. NLP libraries such as "spaCy" and "BERT" are used to perform in-depth analysis that takes context, emotions, and cultural background into account.

[0625] Next, the server translates the analyzed text information into another language using a generative AI model. In this step, a prompt sentence is input using a generative artificial intelligence model such as "OpenAI GPT" or "DeepL," and an appropriate translation result is obtained. For example, a possible prompt sentence might be, "Please translate the line 'Hello' from this Japanese anime into English."

[0626] Finally, the server integrates the translated text information into the original digital data. For videos, the server uses video editing tools such as "FFmpeg" to position the new subtitles appropriately. For comics, image editing software is used to combine the translated dialogue with the images. The completed translated digital data is then made available for download by the user.

[0627] One concrete example is providing Japanese anime episodes with English subtitles. When a user uploads an anime, the server automatically generates English subtitles using the technology described above. This allows users to quickly provide high-quality translated content without any extra effort.

[0628] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0629] Step 1:

[0630] The user uploads digital data of videos or comics they wish to translate from their device to the server. The input is the user's local device, and the output of this step is the original digital data stored on the server. The device securely transfers the selected files using a data transfer protocol.

[0631] Step 2:

[0632] The server extracts character information from the uploaded digital data using optical character recognition (OCR). The input is the digital data obtained in step 1, and the output is the extracted text data. The server recognizes characters from the image frame using OCR software such as "Tesseract" and saves the results in text format.

[0633] Step 3:

[0634] The server analyzes the text data obtained by OCR using natural language processing (NLP) techniques. The input is the character information obtained in step 2, and the output is data with context and meaning analyzed. The server uses "spaCy" and "BERT" to analyze sentence structure, sentiment, and background information to understand the context.

[0635] Step 4:

[0636] The server translates the analyzed text data into other languages ​​using a generation AI model. The input is the data analyzed in step 3, and the output is the translated character information. The server utilizes "OpenAI GPT" and "DeepL" along with prompt text to generate contextually appropriate translations.

[0637] Step 5:

[0638] The server integrates the translated text information with the original digital data. The input is the translated data obtained in step 4 and the original digital data, and the output is the translated integrated data. The server adds subtitles to the video using editing tools such as "FFmpeg" or inserts the translated dialogue into the comic using image editing software.

[0639] Step 6:

[0640] The server makes the completed translated digital data available for download to the user. The input is the integrated data generated in step 5, and the output is the completed file accessible to the user. The server uses a storage service to ensure that the user can securely download the file via a specific link.

[0641] (Application Example 1)

[0642] 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".

[0643] In the process of translating content into other languages, there is a need for rapid and accurate translation processing, as well as the efficient provision of information on cultural background and linguistic nuances that users require. However, conventional systems have problems such as insufficient translation accuracy and time-consuming provision of additional information.

[0644] 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.

[0645] In this invention, the server includes means for receiving data, means for extracting character information from the received data, and means for providing additional information based on user selection. This enables rapid and accurate translation processing and real-time provision of additional information through a user interface.

[0646] "Means of receiving data" refers to the function by which a server receives content data sent by a user.

[0647] "Means for extracting text information" refers to a function that recognizes and extracts text from received content data.

[0648] "Means for analyzing context" refers to functions that perform natural language processing to understand the meaning and background of extracted textual information.

[0649] "Means of translation into other languages" refers to a function that uses a generative AI model to convert analyzed textual information into a different language.

[0650] "Means of integrating translated text information into the original data" refers to a function that places the translated text in the appropriate location within the original content.

[0651] "Means for outputting translated data" refers to a function that makes the translated data available to the user.

[0652] "Means of providing additional information based on user selection" refers to a function that displays related information and background details for items specified by the user.

[0653] "Means of displaying additional information through the user interface" refers to a function that shows the user additional content related to the selected information on the screen.

[0654] A system implementing this invention consists of a process that exchanges data between a server and a user terminal and translates the language information of the received data.

[0655] First, the user uploads the content data they want to translate (e.g., videos or comics) to the cloud server using their device. At this time, the user specifies the desired translation language. The server receives this data and begins the necessary processing.

[0656] The server first uses the Google Cloud Vision API to extract text information from the received data. For videos, it analyzes each frame, and for comics, it obtains text data from the entire page.

[0657] Next, the server uses the Google Cloud Natural Language API to analyze the context of the extracted text information. This deepens the understanding of the meaning of the extracted data and improves translation accuracy.

[0658] The analyzed text information is translated into other languages ​​using OpenAI's GPT model and DeepL API. Where necessary, the generative AI model also considers cultural context and nuances.

[0659] The translated text information is accurately integrated with the original data and output to the user's terminal as translated data by the server. On the terminal, translated subtitles are displayed for videos, and dialogue is appropriately placed for comics. Furthermore, based on the user's selection, additional information about specific terms and lines is displayed, including a function to learn about the cultural background.

[0660] For example, if a user selects "Character A's technology," the historical background of that technology will be explained in real time. A concrete example of a prompt given to the generating AI model could be, "Translate Character A's technology '○○' into English and explain its cultural background."

[0661] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0662] Step 1:

[0663] Users upload content data they want to translate to the server using their device. Videos and comics are used as input, and the server receives and stores this data.

[0664] Step 2:

[0665] The server uses the Google Cloud Vision API to extract text information from the received data. Specifically, it uses OCR technology to obtain text data from each frame of a video or page of a comic book. The input is the uploaded content, and the output is the extracted text information.

[0666] Step 3:

[0667] The server uses the Google Cloud Natural Language API to analyze the extracted text information. The input is the text information obtained in step 2, and the output is analyzed data including context. Specifically, it performs processing to understand emotions and sentence structure.

[0668] Step 4:

[0669] The server translates the analyzed text information into other languages ​​using OpenAI's GPT model and DeepL API. Here, prompt sentences are generated and provided to the generative AI model. The input is the analyzed data from step 3, and the output is the translated text.

[0670] Step 5:

[0671] The server integrates the translated text information into the original content data. This information is then placed as subtitles in videos and as dialogue in comics. The input consists of the translated text information and the original content, while the output is the integrated, complete data.

[0672] Step 6:

[0673] The server sends the integrated translated data to the terminal, making it available for user viewing. Here, the user can select sections requiring supplementary information and receive detailed explanations. For example, when a user selects a specific term, cultural background information related to that term is displayed. A prompt such as "Please explain the background of the term XX" might be generated.

[0674] 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.

[0675] This invention is a system that not only translates data but also recognizes the user's emotions and adjusts the tone and style of the translation to match those emotions. This system is implemented as follows:

[0676] First, the user uploads the video or manga data they want translated to the server. The server receives the data and uses optical character recognition technology to extract text information such as subtitles and dialogue.

[0677] Next, the server uses natural language processing techniques to analyze the context of the extracted text information. This analysis helps to understand the meaning and cultural background of the original language. At this stage, an emotion engine is also utilized to analyze the user's emotional state based on user feedback and past emotional history. This emotion engine uses machine learning algorithms to infer what emotions the user feels towards the content.

[0678] Based on the analysis results and sentiment analysis, the server uses a generative AI model to translate text information into other languages. This translation reflects the tone and style corresponding to the user's emotions. For example, if the user is expressing cheerful emotions, the translation will be adjusted to have a bright and friendly tone.

[0679] Finally, the translated text information is integrated into the original data. After this process, it is appropriately placed as subtitles in videos or as dialogue in comics, and becomes available for download by the user.

[0680] For example, when translating a Japanese comedy anime for an English-speaking audience, if users provide smiling feedback, consideration will be given to translating the conversation in a lighter and more humorous tone. This results in content that is more relatable and enjoyable for viewers.

[0681] This system will go beyond simple word-for-word translation, enabling content delivery that takes viewers' emotions into consideration, with the aim of promoting wider global acceptance of Japanese content.

[0682] The following describes the processing flow.

[0683] Step 1:

[0684] The user uploads the video or manga data to be translated to the server via their device. The server receives the data and verifies that the data format is correct.

[0685] Step 2:

[0686] The server begins analyzing the received data. In the case of videos, it divides the data into individual frames and extracts text information from each frame using optical character recognition technology. Similarly, for comics, it detects text information from each page.

[0687] Step 3:

[0688] The server uses natural language processing techniques to perform contextual analysis on the extracted text information. During this process, the meaning and cultural nuances of the original text are understood.

[0689] Step 4:

[0690] The server activates the emotion engine and analyzes the user's emotional data. This is done by referencing feedback and reactions previously provided by the user to estimate their current emotional state.

[0691] Step 5:

[0692] The server uses a generation AI model to perform translations into other languages, reflecting the results of contextual and sentiment analysis. These translations are then adjusted to match the user's estimated emotions in terms of tone and style.

[0693] Step 6:

[0694] The server integrates the translated text information into the original data. For videos, it inserts subtitles at the appropriate timing; for comics, it arranges dialogue considering the design.

[0695] Step 7:

[0696] The server generates the final translated data and adjusts the format so that it can be downloaded by the user.

[0697] Step 8:

[0698] The user retrieves the translation results from the server and checks them on their device. This data is used to provide it to viewers and readers as needed.

[0699] (Example 2)

[0700] 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".

[0701] Traditional translation systems simply convert text information into different languages, lacking contextual understanding that takes into account user emotions and intentions. This can result in translations that lose the original tone and style of the content, potentially reducing viewer engagement. Furthermore, providing translations that reflect individual user emotions and feedback has been challenging.

[0702] 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.

[0703] In this invention, the server includes means for acquiring data, technical means for identifying text information, and technical means for evaluating the background of the identified text information. This enables flexible and appropriate translation that is tailored to the user's emotions and context.

[0704] "Means of acquiring data" refers to the function of collecting digital content provided by users into the system.

[0705] "Technical means for identifying text information" refers to technologies for detecting and reading characters in digital content.

[0706] "Technical means for evaluating the background of identified text information" refers to technologies that analyze and understand the context and cultural background of detected text information.

[0707] "Generative technology means" refers to technology for generating translations appropriate to the context using evaluated text information.

[0708] "Means of supplying the final product" refers to a function for incorporating translated content into the content and providing it to the user.

[0709] This system begins with a user uploading digital content such as videos or comics to a server. The server first uses a data acquisition method to extract text information from the received content. For this process, open-source OCR engines such as Tesseract are typically used as optical information recognition (OCR) technologies. This technology efficiently identifies text information embedded in images and videos.

[0710] Next, the server utilizes natural language processing (NLP) techniques as a means to evaluate the context of the text information. In this phase, natural language processing models such as BERT and GPT are used to analyze the context and cultural background of the extracted text in detail. Based on the results of this analysis, a dedicated sentiment engine analyzes the user's current emotional state by referring to user feedback and past sentiment history.

[0711] Subsequently, the server uses generative techniques to translate the text information into another language, taking into account the evaluated context. This process utilizes the well-known GPT series of generative AI models to achieve contextually and emotionally optimized translations. For example, if a user provides positive feedback, the translated output will reflect that positive tone.

[0712] For example, when translating subtitles for a Japanese comedy film into English, if a user provides feedback such as "very funny and entertaining," the translated English subtitles will be adjusted to also include humor. An example of a prompt might be, "Translate the fun Japanese movie subtitles into English based on user feedback, maintaining a lighthearted tone."

[0713] The final output is integrated into the original digital content and displayed as subtitles in an appropriate format. Users can download the translated content in an available format using their device and view it. In this way, the system provides a translation service that enhances the user experience.

[0714] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0715] Step 1:

[0716] Users upload digital content such as videos and comics they wish to have translated from their computer terminal to the server. The input is digital data in a file format provided by the user. The server processes the received files and imports the content data into the system. The output is the content data securely stored on the server.

[0717] Step 2:

[0718] The server uses optical image recognition (OCR) technology to extract text information from uploaded content. The input is digital data in image or video format. The OCR engine used (e.g., Tesseract) operates frame by frame, detecting text and outputting it as digital character data.

[0719] Step 3:

[0720] The server evaluates the background and context of text information extracted using natural language processing techniques. The input is character data obtained by OCR. It utilizes BERT and similar NLP models to understand the text context and analyze its cultural background. The output consists of contextual metadata and analysis results.

[0721] Step 4:

[0722] The server analyzes the user's emotional state using an emotion engine, referencing the user's emotional history and current feedback. Inputs include past user feedback and focused current feedback information. A machine learning algorithm is used to infer and output the user's emotional state data.

[0723] Step 5:

[0724] The server translates text information based on contextual and sentiment data evaluated using a generative AI model. Inputs are contextual metadata and user sentiment state. Using the GPT series or other relevant models, it generates translation results that correspond to the user's sentiment. Output is the translated text data.

[0725] Step 6:

[0726] The server integrates translated text information into the original digital content. The input consists of translated text data and original content data. It appropriately positions the translated text as subtitles or dialogue and performs visual or audio integration processing. The output is content with the new subtitles or dialogue appropriately embedded.

[0727] Step 7:

[0728] The user downloads the integrated final product using their device and then views and enjoys it. In this step, the server provides a download link or direct download functionality. The input is the integrated content file, and the output is the content data stored on the user's device.

[0729] (Application Example 2)

[0730] 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".

[0731] In multilingual environments, translating content while considering user emotions presents a significant challenge. While traditional systems can translate textual information, they struggle to adjust the tone and style of the translation based on user emotions. As a result, content is often not culturally localized appropriately, leading to a diminished viewer experience.

[0732] 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.

[0733] In this invention, the server includes means for receiving data, means for extracting textual information from the received data, means for analyzing the user's emotions, means for translating the analyzed textual information into another language and adjusting the tone and style of the translation based on the user's emotions, and means for integrating the translated textual information. This makes it possible to translate with an appropriate tone and style that corresponds to the user's emotions.

[0734] "Means of receiving data" refers to the technology and devices that retrieve user-uploaded video and manga data onto the server.

[0735] "Means for extracting text information" refers to a device that uses optical character recognition technology to extract text such as subtitles and dialogue from received data.

[0736] "Means for analyzing the context of extracted textual information" refers to technological devices that use natural language processing techniques to understand the meaning and underlying cultural background of extracted text.

[0737] "Methods for analyzing user emotions" refer to technological devices that use machine learning algorithms to infer a user's emotional state based on user feedback and past emotional history.

[0738] "Means for translating and adjusting the translation tone and style based on the user's emotions" refers to a technological device that uses a generative AI model to translate textual information and modifies the translation to an appropriate tone and style according to the user's emotions.

[0739] "Means for integrating translated text information" refers to a technological device that rearranges translated text into the original video or comic data and incorporates it into the content in a natural way.

[0740] This invention relates to a video and comic translation system that takes user emotions into consideration. First, the server receives video or comic data. From the received data, text information such as subtitles and dialogue is extracted using optical character recognition technology (e.g., pytesseract). After extraction, the context of the text information is analyzed using natural language processing technology (e.g., transformers library). This analysis allows for an understanding of the meaning and cultural background of the original language.

[0741] Next, the server performs sentiment analysis based on the user's feedback and past sentiment history. It uses a machine learning algorithm as its sentiment engine to infer the user's emotional state. Then, a generative AI model is used to translate the textual information into another language. This translation is adjusted to reflect the tone and style that matches the user's emotions, based on the analysis results and sentiment analysis. For example, if the user provides positive feedback, the translation will also be adjusted to have a bright and friendly tone.

[0742] Ultimately, the translated text information is integrated into the original video or comic data and provided in a viewable format. For example, when translating a Japanese comedy anime for English-speaking audiences, the translation will make the conversation lighter and more humorous when viewers provide feedback with smiles. This improves the user experience and makes the content more widely accessible.

[0743] Example of a prompt:

[0744] "I'm watching a Japanese comedy anime. Please translate the subtitles in a cheerful tone."

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

[0746] Step 1:

[0747] The server receives video and manga data from users. At this stage, the data is transferred to the server when the user uploads it to the system. The input is the video and manga data provided by the user, and the output is the raw data stored on the server.

[0748] Step 2:

[0749] The server extracts text information from the received data. This process uses optical character recognition (e.g., PyTesseract) to convert subtitles and dialogue from videos and comics into text data. The input is image data, and the output is the extracted text information.

[0750] Step 3:

[0751] The server analyzes the context of the extracted text information. Using natural language processing techniques (e.g., the transformers library), it understands the text's context and cultural background and obtains the information necessary for translation. In this process, the input is the extracted text information, and the output is the analyzed contextual information.

[0752] Step 4:

[0753] The server uses user feedback and past emotional history to analyze the user's emotions. In this step, a machine learning algorithm is used to infer the user's emotions from the emotion engine. The input is the user's feedback data, and the output is the inferred emotional state.

[0754] Step 5:

[0755] The server uses a generative AI model to translate textual information based on analysis results and sentiment analysis, and adjusts the tone and style of the translation. This ensures that the translation is appropriate to the user's emotions. The input is the analyzed contextual information and emotional state, and the output is the translated text with adjusted tone and style.

[0756] Step 6:

[0757] The server integrates the translated text information into the original video or comic data. At this stage, the translated text is rearranged as subtitles in the case of videos, or as dialogue in the case of comics. The input is the translated text information, and the output is the integrated data in a viewable format.

[0758] These steps aim to enable users to enjoy translated content that reflects their emotions.

[0759] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0760] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0761] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0762] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0763] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0764] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0765] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0766] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0767] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0768] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0769] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0770] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0771] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0772] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0773] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0774] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0775] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0776] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0777] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0778] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0779] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

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

[0781] (Claim 1)

[0782] A means for receiving data,

[0783] A means of extracting text information from received data,

[0784] A means of analyzing the context of extracted textual information,

[0785] A means of translating the analyzed text information into other languages,

[0786] A means of integrating translated text information into the original data,

[0787] A system that includes means for outputting translated data.

[0788] (Claim 2)

[0789] The system according to claim 1, which uses optical character recognition technology to extract character information.

[0790] (Claim 3)

[0791] The system according to claim 1, which uses natural language processing techniques to analyze context.

[0792] "Example 1"

[0793] (Claim 1)

[0794] Means for receiving digital data,

[0795] A means of extracting textual information from received digital data,

[0796] A means of analyzing the context of extracted textual information,

[0797] A means of using generative artificial intelligence to translate analyzed text information into other languages,

[0798] A means of integrating translated text information into the original digital data,

[0799] A system including means for outputting integrated translated digital data.

[0800] (Claim 2)

[0801] The system according to claim 1, which extracts character information using optical character recognition technology.

[0802] (Claim 3)

[0803] The system according to claim 1, which analyzes context using natural language processing techniques.

[0804] "Application Example 1"

[0805] (Claim 1)

[0806] A means for receiving data,

[0807] A means of extracting text information from received data,

[0808] A means of analyzing the context of extracted textual information,

[0809] A means of translating the analyzed text information into other languages,

[0810] A means of integrating translated text information into the original data,

[0811] A means of outputting translated data,

[0812] A means of providing additional information based on the user's selection,

[0813] Means for displaying additional information through a user interface

[0814] A system that includes this.

[0815] (Claim 2)

[0816] The system according to claim 1, which uses optical character recognition technology to extract character information.

[0817] (Claim 3)

[0818] The system according to claim 1, which uses natural language processing techniques to analyze context.

[0819] "Example 2 of combining an emotion engine"

[0820] (Claim 1)

[0821] Means of acquiring data,

[0822] Technical means for identifying text information from acquired data,

[0823] Technical means for evaluating the background of identified text information,

[0824] A generation technology means for converting evaluated text information into a different language,

[0825] A means of incorporating the generated text information into the original data,

[0826] A system including means for supplying the final product.

[0827] (Claim 2)

[0828] The system according to claim 1, which uses optical information recognition technology to identify text information.

[0829] (Claim 3)

[0830] The system according to claim 1, which uses natural language processing techniques to evaluate the background.

[0831] "Application example 2 when combining with an emotional engine"

[0832] (Claim 1)

[0833] A means for receiving data,

[0834] A means of extracting text information from received data,

[0835] A means of analyzing the context of extracted textual information,

[0836] Methods for analyzing user emotions,

[0837] A means of translating analyzed text information into other languages ​​and adjusting the tone and style of the translation based on the user's emotions,

[0838] A means of integrating translated text information into the original data,

[0839] A system that includes means for outputting translated data.

[0840] (Claim 2)

[0841] The system according to claim 1, which uses optical character recognition technology to extract character information.

[0842] (Claim 3)

[0843] The system according to claim 1, which uses natural language processing techniques to analyze context. [Explanation of symbols]

[0844] 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 for receiving data, A means of extracting text information from received data, A means of analyzing the context of extracted textual information, A means of translating the analyzed text information into other languages, A means of integrating translated text information into the original data, A system that includes means for outputting translated data.

2. The system according to claim 1, which uses optical character recognition technology to extract character information.

3. The system according to claim 1, which uses natural language processing techniques to analyze context.

Images