system

Abstract

We provide the system. [Solution] A voice analysis means that receives an audio signal and converts it into encoded information in real time, Translation means for converting the encoded information into multiple languages, A code editing proposal means that proposes a display style that takes visibility into consideration based on the converted coded information, A presentation means for applying the proposed display style to visual information, Image generation means for generating image data related to the encoded information and inserting it into the visual information, A material generation means for generating and displaying related visual materials based on the aforementioned encoded information, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot 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 chatbot character, 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] With the expansion of the video content market, quick and highly accurate subtitle creation corresponding to multiple languages has become important. However, conventional subtitle creation methods require a great deal of time and labor for speech-to-text conversion, multilingual translation, and subtitle editing, and it is particularly difficult to handle multiple languages. In addition, there has been a lack of proposals for styles to enhance subtitle visibility and methods for effectively inserting images related to video. There is a need for a method that can solve such problems and provide users with more efficient and visually excellent content.

Means for Solving the Problems

[0005] This invention provides a voice analysis means for receiving audio signals and converting them into text data in real time, and a translation means for translating the text data into multiple languages, enabling the rapid generation of highly accurate multilingual subtitles. Furthermore, by including a subtitle editing suggestion means that proposes a subtitle style that takes legibility into consideration based on the translated text data, visually superior display is possible. In addition, by providing an image generation means that generates image data related to the text data and inserts it into the video data, the content of the video is visually complemented, thereby enhancing the appeal of the content.

[0006] "Speech analysis means" refers to a device or system equipped with the function of receiving speech signals and converting them into text data in real time.

[0007] A "translation means" is a device or system that has the function of receiving text data and translating it quickly and accurately into multiple languages.

[0008] A "subtitle editing suggestion means" is a device or system that has the function of suggesting the color, size, font, and position of subtitles based on translated text data, taking into consideration visibility.

[0009] "Display means" refers to a device or system that has the function of applying the proposed subtitle style to video data and presenting it visually to the viewer.

[0010] "Image generation means" refers to a device or system equipped with the function of generating image data related to subtitle text data and inserting it into video data. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the 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.

[0015] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. 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.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. 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).

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] The system for implementing the present invention mainly includes a server, a terminal, and a user interface. The specific operation of each element is described below.

[0033] The server begins processing upon receiving audio signal data sent from the user. The received audio signal is converted into text data in real time through a speech analysis system. This speech analysis supports multiple languages ​​and uses machine learning models to enhance the recognition of local pronunciation and technical terms as needed.

[0034] Next, the server translates the text data into the target language specified by the user using a translation tool. This process employs natural language processing techniques to improve context-based translation accuracy. The translated text is synchronized within the server and can be accessed quickly as needed.

[0035] The server also uses a subtitle editing suggestion mechanism based on the translated text data to suggest a style to the user that takes into account the readability of the subtitles. The suggested style includes the subtitle's color, size, font, and position. This information is presented to the user through the user interface, allowing the user to edit and confirm the style with intuitive operations.

[0036] Furthermore, the server uses image generation means to generate image data related to the content of the subtitles. This data is used to highlight specific scenes in the video and complements the visual information. For example, if the server analyzes the word "global warming," it will suggest inserting related graphics or diagrams.

[0037] The terminal receives video data, including styles and images determined by the server, and performs final rendering. During this process, it optimizes the display according to the terminal's processing power and display settings.

[0038] Through this series of processes, users can quickly and effectively create and deliver visually appealing video content that supports multiple languages. For example, in live streaming of international conferences, multilingual subtitles can be generated and styled, and relevant images inserted in real time, ensuring effective information transmission to viewers worldwide.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server receives audio signal data streamed from the user. This audio data is then passed to an audio analysis unit for real-time processing.

[0042] Step 2:

[0043] The server converts the audio data received via the speech analysis unit into text data. This process applies machine learning algorithms to achieve high-precision speech recognition.

[0044] Step 3:

[0045] The server transfers the converted text data to the translation unit, which then performs the translation into the specified target language. It utilizes natural language processing techniques to provide context-aware translations.

[0046] Step 4:

[0047] Based on the translation results, the server uses a subtitle editing suggestion unit to suggest subtitle styles. This includes recommended settings for subtitle color, size, font, and position.

[0048] Step 5:

[0049] Users can review the subtitle style suggested by the server through the interface and make adjustments as needed. The user interface is designed to be simple and intuitive to use.

[0050] Step 6:

[0051] The server applies the confirmed subtitle style to the video data and generates the final video with subtitles. This video data is then sent to the terminal.

[0052] Step 7:

[0053] The server generates image data related to the subtitle text and inserts it into the video as needed. The image generation unit automatically creates visual content based on specific keywords.

[0054] Step 8:

[0055] The terminal renders the subtitled video and image data received from the server and displays them in the optimal format according to the user's display settings.

[0056] (Example 1)

[0057] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0058] Currently, in systems that convert audio signals into text data in real time and translate them into multiple languages, the challenges are reducing misrecognition and improving the accuracy of translations based on appropriate context. Furthermore, there is a need to quickly suggest highly visible subtitle styles based on the translated text and insert images that visually supplement relevant information into the content. This creates a need for a system that enables users to effectively communicate information to a wide range of language audiences.

[0059] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0060] In this invention, the server includes: an audio analysis means for receiving audio signals and converting them into text data in real time; a translation means for translating the text data into multiple languages; a subtitle editing suggestion means for proposing a subtitle style that takes legibility into consideration based on the translated text data; a display means for applying the proposed subtitle style to visual data; and an image generation means for generating visual information related to the text data and inserting it into the visual data. This enables improved accuracy in multilingual translation and the creation of highly legible video content.

[0061] A "speech analysis means" is a component that has the function of receiving a speech signal and converting it into string data in real time.

[0062] "Translation means" refers to technical components for accurately translating the aforementioned string data into multiple languages.

[0063] "Subtitle editing suggestion means" refers to components for suggesting a style that takes into account the readability of subtitles, based on translated string data.

[0064] "Display means" refers to components for applying the proposed subtitle style to visual data and outputting it visually as content.

[0065] An "image generation means" is a component that has the function of generating visual information related to string data and appropriately inserting it into the visual data.

[0066] A "generative model" is an advanced data processing technique for automatically generating relevant visual information based on prompt text.

[0067] One embodiment of this invention is a system for generating video content that supports multiple languages ​​from audio data. The specific operation is described below.

[0068] First, the user inputs audio signal data into the system through a dedicated interface. This input audio signal is received by a server. The server uses speech analysis tools to convert this audio signal into text data in real time. At this time, the server uses general speech recognition software. For example, it utilizes a widely used speech recognition service.

[0069] Next, the server translates the converted string data into the target language specified by the user. This is done using natural language processing techniques, such as translation APIs. Online translation services are particularly useful for this purpose.

[0070] Furthermore, the server suggests visually optimized subtitle styles to the user based on the translated text data. Subtitle editing software is used here, allowing the user to select the appropriate style. The suggested styles include subtitle color, size, font, and position.

[0071] Furthermore, the server uses a generative AI model to generate image data related to the string data. An example of a generation prompt is, "Create a graphic related to global warming." This image generation is intended to complement visual information, and the generated images are used to highlight specific scenes in the video.

[0072] The device receives visual data, including styles and images, sent from the server and performs the final rendering. The device optimizes the data according to the display settings and the device's own processing power to produce visually superior content.

[0073] This enables users to quickly and effectively create and distribute visually rich video content that supports multiple languages. For example, in live streaming of international conferences, multilingual subtitles are automatically generated and relevant images are added, allowing information to be effectively conveyed to viewers worldwide.

[0074] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0075] Step 1:

[0076] The user inputs audio signal data into the system through an interface. The server receives this audio signal and begins processing it. The input audio signal is analyzed using the server's audio analysis capabilities and converted into text data in real time. Specifically, speech recognition software extracts sound features and converts them into text. The output of this process is text data.

[0077] Step 2:

[0078] The server sends the string data obtained in step 1 to the translation tool, which translates it into the target language specified by the user. This translation uses natural language processing techniques to achieve high accuracy. Specifically, the translation API converts the string into a different language while analyzing the grammatical structure and considering the context. The output of this process is the translated string data.

[0079] Step 3:

[0080] The server uses the translated string data to generate a subtitle style that takes readability into consideration using a subtitle editing suggestion mechanism. Specifically, it uses a visual elements algorithm to calculate the appropriate subtitle color, size, font, and position, and provides the user with style options. The output of this step is the suggested subtitle style.

[0081] Step 4:

[0082] The server uses a generative AI model to generate images related to the translated string data. Here, a pre-defined prompt, such as "Create a graphic related to global warming," is input to the model, and visual information is generated based on it. The specific operation involves the AI ​​identifying relevant elements and generating the graphic. The output of this step is the generated image data.

[0083] Step 5:

[0084] The terminal receives visual data, including subtitle styles and image data, from the server, and renders the final video content based on that data. Specifically, the video rendering software performs optimizations according to the terminal's display settings and processing power. The output of this step is the final content with superior visual appeal.

[0085] This series of steps enables users to effectively create and distribute multilingual video content.

[0086] (Application Example 1)

[0087] 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."

[0088] In modern times, video content is consumed in many languages, and there is a demand for accurate, real-time translation of audio and presentation in a visually easy-to-understand format. However, generating and displaying multilingual subtitles is time-consuming and laborious, and effectively integrating related visual information is a difficult challenge. This invention aims to solve these problems and realize a technology that provides multilingual video content quickly and effectively.

[0089] 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.

[0090] In this invention, the server includes: an audio analysis means for receiving audio signals and converting them into encoded information in real time; a translation means for converting the encoded information into multiple languages; and a code editing suggestion means for proposing a display style that takes visibility into consideration based on the converted encoded information. This makes it possible to improve reliability and efficiency in multilingual translation and visual information presentation, and to optimize the transmission of information to the viewer.

[0091] "Speech analysis means" refers to a device or process that has the function of converting a received speech signal into encoded information in real time.

[0092] "Translation means" refers to a process or technology for converting encoded information into multiple languages.

[0093] "Code editing suggestion means" refers to an apparatus or process that has the function of suggesting a display style that takes legibility into consideration based on converted coded information.

[0094] "Presentation means" refers to an apparatus or method for applying a proposed display style to visual information.

[0095] "Image generation means" refers to a device or process that has the ability to generate image data related to encoded information and insert it into visual information.

[0096] "Material generation means" refers to a device or method that has the function of generating and presenting relevant visual materials based on encoded information.

[0097] The system for carrying out this invention mainly consists of a voice analysis means, a translation means, a code editing suggestion means, a presentation means, an image generation means, and a data generation means. The server converts the voice signal into encoded information in real time and converts this encoded information into multiple languages. Based on the converted encoded information, it proposes a display style that takes visibility into consideration and applies it to the visual information. This realizes the provision of visually effective information to the viewer.

[0098] The server uses the "speech_recognition" library for speech analysis, converting the audio signal into text data. This text data is then translated into multiple languages ​​using the "googletrans" library. Based on the translated data, it provides a visually appealing subtitle style that matches the video and generates image data using the "PIL" library to complement the relevant visual information.

[0099] The device receives this generated visual information and displays it in a way that is optimized for the device. This allows users to enjoy multilingual video content in real time.

[0100] Specific examples include live broadcasts of international conferences and film festivals, where real-time language translations and related images are provided to deliver accurate information in multiple languages ​​to viewers worldwide.

[0101] An example of a prompt for a generative AI model is: "Translate the English audio data into Spanish and display it as visually sophisticated subtitles along with the associated images."

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The server receives an audio signal. Using this audio data as input, the server converts it into encoded information in real time using the "speech_recognition" library. As a result, the audio signal is output as text data. Specifically, the server analyzes the audio signal, recognizes the speech patterns of each language, and converts them into text.

[0105] Step 2:

[0106] The server translates the text data obtained in step 1 into the specified target language using the "googletrans" library. This translation method performs context-aware natural language processing to convert text data into multiple languages. The input is the original text data, and the output is the translated text data. Specifically, it uses a machine translation algorithm to improve translation accuracy.

[0107] Step 3:

[0108] The server uses the translated text data to propose a display style that considers readability through a code editing suggestion mechanism. The input is the translated text data, and the output is the proposed display style. This process determines visually appealing fonts, color schemes, and subtitle placement. Specifically, it performs a process to suggest the optimal style settings according to the context of the video.

[0109] Step 4:

[0110] The server uses the "PIL" library to generate image data related to the translated text. It creates visual materials related to the text, taking into account the display style obtained in step 3. The input is the translated text and related information, and the output is the generated image data. Specifically, it designs appropriate images based on the text content and prepares them for insertion into the video.

[0111] Step 5:

[0112] The terminal receives the final visual information sent from the server and displays it in the appropriate format. Based on the image data and display style generated in step 4, it optimizes the video content and provides it to the viewer. Specifically, it displays the visual information at the optimal resolution and layout according to the terminal's processing power.

[0113] Step 6:

[0114] Users utilize the delivered content while viewing generated multilingual subtitles and related images. The input is the information displayed on the device, and the output is the user's understanding and learning. Specifically, users interact with the interface to customize subtitles and access further information.

[0115] 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.

[0116] The system for carrying out the present invention comprises a server, a terminal, and a user interface. This system integrates real-time voice analysis, translation, subtitle style suggestion, sentiment analysis, and image generation functions.

[0117] The server starts operating upon receiving an audio signal provided by the user. This audio signal is converted into text data in real time by the speech analysis unit. Advanced speech recognition technology is used for speech analysis to achieve highly accurate text conversion.

[0118] The converted text data is passed to a translation unit, where it is translated into multiple specified languages ​​in a natural and contextual manner. Advanced natural language processing techniques are applied during the translation process to preserve nuances and contextual information.

[0119] The subtitle editing suggestion unit implements style suggestions to optimize subtitle readability based on the translated text. This involves considering subtitle color, size, font, and position to provide suggestions best suited to the user's viewing environment.

[0120] Furthermore, the system incorporates an emotion engine, where the server analyzes the user's emotional state from the audio data and adjusts the tone and imagery of the subtitles accordingly. By reflecting the user's emotions, deeper communication becomes possible. For example, if the server detects joy in the user's voice, it will incorporate brighter colors into the subtitles and appropriately generate and insert related images.

[0121] The device receives information from the server and renders the final video data, taking into account the user's display settings. Emotion-based visual expression provides viewers with a more sensory-driven content experience.

[0122] Through the system, users can create videos with multilingual subtitles in real time and easily add visuals that match the emotions. For example, in live broadcasts of international sporting events, it is possible to reflect emotionally rich comments in each country's language into the video, effectively conveying information to viewers worldwide while creating a sense of realism.

[0123] The following describes the processing flow.

[0124] Step 1:

[0125] The server receives audio signal data from the user. The received audio signal is immediately sent to the audio analysis unit. The audio analysis unit converts the audio into text data in real time using a specified algorithm.

[0126] Step 2:

[0127] The server passes the text data obtained from speech analysis to the translation unit. The translation unit utilizes multilingual support to translate quickly and accurately into the specified target language. The translation results are adjusted to preserve appropriate context and produce natural-sounding expressions.

[0128] Step 3:

[0129] The server analyzes text data using an emotion engine to identify the user's emotional state from their speech. The emotion engine identifies speech features associated with emotion and makes an emotion judgment based on them.

[0130] Step 4:

[0131] Based on the translated text and sentiment analysis results, the server utilizes a subtitle editing suggestion unit to propose an appropriate subtitle style to the user. This suggestion adjusts the subtitle's color, size, font, and position to match the sentiment.

[0132] Step 5:

[0133] Users can review the subtitle style suggested by the server through the user interface and make changes as needed. Sentiment-based customization options are provided during this process.

[0134] Step 6:

[0135] The server applies the user-defined subtitle style to the video data and uses an image generation unit to generate emotion-related visual content along with the translated subtitles. This includes illustrations and graphics appropriate to the scene.

[0136] Step 7:

[0137] The terminal receives the final subtitled video and generated image data from the server and renders them. The terminal takes into account the user's display settings and viewing conditions to provide the viewer with optimized video.

[0138] (Example 2)

[0139] 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".

[0140] Conventional speech analysis systems faced challenges in providing real-time multilingual support and visual representations that reflected user emotions. Furthermore, the visibility of subtitles and their integration with the visuals were often insufficient, resulting in a limited user experience.

[0141] 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.

[0142] In this invention, the server includes an analysis means for receiving audio signals and converting them into text data in real time, a conversion means for translating the text data into multiple languages, and an editing suggestion means for proposing subtitle styles that take legibility into consideration based on the translated text data. This makes it possible to provide multilingual audio translation and visually superior video expression based on emotion in real time.

[0143] "Analysis means" refers to a device that receives audio signals and converts them into text data in real time.

[0144] A "conversion device" is a device that has the function of translating text data into multiple languages.

[0145] An "editing suggestion device" is a device that has the function of suggesting a subtitle style that takes readability into consideration based on translated text data.

[0146] "Display means" refers to a device that has the function of applying the proposed subtitle style to video data.

[0147] An "emotion analysis device" is a device that analyzes the user's emotional state from audio data and adjusts the visual representation according to that emotion.

[0148] A "generation means" is a device that has the function of generating image data related to text data and inserting it into video data.

[0149] The present invention relates to a system configuration including a server, a terminal, and a user interface. This system provides the functionality to analyze audio data in real time and integrate translation, sentiment analysis, and visual representation. The software used by the server to receive audio signals, analyze them, and convert them into text data includes an audio analysis algorithm incorporating a generative AI model.

[0150] The analyzed text data is translated into multiple languages ​​by a translation unit on the server. Natural language processing techniques are applied here. Generative AI models are used in this translation process, ensuring that nuances and context are accurately preserved.

[0151] On the user terminal, a subtitle editing suggestion system automatically presents subtitle styles that take readability into consideration, based on translation data sent from the server. This allows the user to select or automatically apply the optimal style. The server also has an emotion analysis unit that analyzes the user's emotions from their voice and adjusts the visual representation accordingly. For example, if joy is detected from the user's voice, it suggests a subtitle style with bright colors and generates related positive images.

[0152] Furthermore, the generated subtitles and images are provided to the user through a display device on the terminal. This allows users to create videos with emotionally nuanced, multilingual subtitles in real time. For example, in live broadcasts of international events, it is possible to visually represent emotionally rich comments in each country's language in real time, thereby promoting a stronger understanding and engagement among viewers.

[0153] As an example of a prompt, you can give the system specific instructions such as, "Translate this audio in real time into English, Spanish, and Japanese, and suggest a sentiment-based subtitle style."

[0154] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0155] Step 1:

[0156] The server receives an audio signal from the user and sends it to the audio analysis unit. The input is the user's audio signal, which is converted into text data in real time by the analysis unit. This process uses a generative AI model that leverages deep learning to achieve highly accurate speech recognition. As output, the user's audio is converted into corresponding text data.

[0157] Step 2:

[0158] The server receives text data from the speech analysis unit and passes it to the translation unit. The input is text data, which is translated into multiple specified languages ​​using a translation mechanism. Specifically, natural language processing techniques are used to provide natural translations that preserve context. Generative AI models are again utilized in this process. The output is translated multilingual text.

[0159] Step 3:

[0160] The server provides the translated text received from the translation unit to the subtitle editing suggestion unit. The input is translated text in multiple languages, and based on this data, the editing suggestion means generates a subtitle style optimized for readability. Specifically, it considers the characteristics of the translated text and the user environment to suggest the optimal subtitle color, size, font, position, etc. The output is the suggested subtitle style information.

[0161] Step 4:

[0162] The server performs emotion analysis using audio data. The input is the user's audio data, and the emotion analysis tool determines the emotional state. Specifically, it analyzes the user's emotions from the tone of voice and word choice, and applies emotion-based visual changes to the video as needed. For example, if joy is detected, a subtitle style with brighter colors is selected. The output is the analyzed user emotion information.

[0163] Step 5:

[0164] The terminal receives the final data sent from the server and displays it on the screen. The input consists of subtitle style information, translated text, and associated image data. The terminal uses a display mechanism to render all data based on the user's display settings. Specifically, it renders the optimal image according to the user's visual environment. The output is the image visible to the user.

[0165] (Application Example 2)

[0166] 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".

[0167] In modern visual content distribution, multilingual support and visual expression that responds to the viewer's emotions are crucial. However, there are few systems capable of real-time, high-precision audio-to-text conversion, and generating subtitles and images that take emotional impact into account. Furthermore, displaying translated text in the most appropriate format to match the audience's emotions has been challenging until now.

[0168] 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.

[0169] In this invention, the server includes data analysis means for receiving audio signals and converting them into text data in real time, conversion means for translating the text data into multiple natural languages, and subtitle suggestion means for suggesting subtitle styles that take legibility into consideration based on the translated text data. This makes it possible to provide multilingual visual information in real time that adapts to the emotions of the viewer.

[0170] "Audio signals" are data that represents sound as electrical signals and are used for communication and analysis.

[0171] "Data analysis means" refers to a device or program for analyzing audio signals and converting them into text data in real time.

[0172] "Conversion means" refers to a device or program that has the function of translating text data into a different natural language.

[0173] The "subtitle suggestion method" is a function that suggests ways to display translated text data in a format that is easy to read.

[0174] "Information display means" refers to a device or program for presenting visual information to a user.

[0175] "Image generation means" refers to a device or program for generating relevant image information based on text data and integrating it into visual information.

[0176] "Emotional analysis means" refers to a device or program that extracts emotional information from audio signals and reflects it in the display of visual information.

[0177] This invention is a system that analyzes audio signals in real time, translates them into multiple languages, and then presents them to the audience in a visually easy-to-understand format. The server receives the audio signal and converts it into text data using an audio analysis means. This process uses speech recognition technology such as Google® Cloud Speech-to-Text API.

[0178] The converted text is translated into multiple languages ​​through a translation tool. This translation process utilizes natural language processing technologies such as the Google Translate API to achieve contextually appropriate translations.

[0179] The subtitle suggestion method proposes subtitle styles in a format suitable for visual information to improve readability. This suggestion selects appropriate subtitle colors, fonts, and positions based on the video content and viewer sentiment information. In this process, sentiment analysis is performed using IBM Watson® Tone Analyzer and other tools to adjust the subtitle colors and display.

[0180] The image generation means generates visual information based on text data, and the information display means integrates this information. Finally, the terminal presents the video in the optimal format for the viewer's display. This allows users to enjoy rich visual content that goes beyond simple subtitles and responds to emotional context.

[0181] As a concrete example, this system can be used in live streaming of international sporting events to provide viewers with real-time subtitles in each language and colorful visuals that reflect the emotions expressed.

[0182] An example of a prompt for a generative AI model is: "Analyze the following audio data and generate translated subtitles based on the emotions you capture. In particular, display subtitles in a bright color when the emotion is joy."

[0183] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0184] Step 1:

[0185] The server receives the audio signal and converts it into text data using speech analysis tools. The input is a real-time audio signal, and the output is the converted text data. The Google Cloud Speech-to-Text API is used to convert the audio to text, and data correction is performed to improve accuracy.

[0186] Step 2:

[0187] The server receives the converted text data and performs multilingual translation using a translation tool. The input is text data, and the output is multiple translated natural language data. The Google Translate API is used to generate contextually natural translation results.

[0188] Step 3:

[0189] The server passes the translated text data to the subtitle suggestion system, which then proposes the most suitable subtitle style for the visual information. The input is the translated text data and the results of sentiment analysis, while the output is a style proposal including subtitle color, font, and position. Sentiment analysis is performed using IBM Watson Tone Analyzer to determine the proposed style, taking legibility into consideration, and this analysis is used in the subtitle suggestion.

[0190] Step 4:

[0191] The server uses the generated subtitle style to apply it to the video data via the information display device. The input is a proposed subtitle style, and the output is visual information with subtitles. The terminal renders and presents it to the viewer in the optimal format according to the display settings.

[0192] Step 5:

[0193] The server uses image generation means to generate visual aids based on text data. The input is text data and the results of sentiment analysis, and the output is customized image data according to the sentiment. This allows the system to analyze the data, render appropriate visual information, and integrate it into the video.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] [Second Embodiment]

[0198] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0199] 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.

[0200] 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).

[0201] 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.

[0202] 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.

[0203] 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).

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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".

[0210] The system for implementing the present invention mainly includes a server, a terminal, and a user interface. The specific operation of each element is described below.

[0211] The server begins processing upon receiving audio signal data sent from the user. The received audio signal is converted into text data in real time through a speech analysis system. This speech analysis supports multiple languages ​​and uses machine learning models to enhance the recognition of local pronunciation and technical terms as needed.

[0212] Next, the server translates the text data into the target language specified by the user using a translation tool. This process employs natural language processing techniques to improve context-based translation accuracy. The translated text is synchronized within the server and can be accessed quickly as needed.

[0213] The server also uses a subtitle editing suggestion mechanism based on the translated text data to suggest a style to the user that takes into account the readability of the subtitles. The suggested style includes the subtitle's color, size, font, and position. This information is presented to the user through the user interface, allowing the user to edit and confirm the style with intuitive operations.

[0214] Furthermore, the server uses image generation means to generate image data related to the content of the subtitles. This data is used to highlight specific scenes in the video and complements the visual information. For example, if the server analyzes the word "global warming," it will suggest inserting related graphics or diagrams.

[0215] The terminal receives video data, including styles and images determined by the server, and performs final rendering. During this process, it optimizes the display according to the terminal's processing power and display settings.

[0216] Through this series of processes, users can quickly and effectively create and deliver visually appealing video content that supports multiple languages. For example, in live streaming of international conferences, multilingual subtitles can be generated and styled, and relevant images inserted in real time, ensuring effective information transmission to viewers worldwide.

[0217] The following describes the processing flow.

[0218] Step 1:

[0219] The server receives audio signal data streamed from the user. This audio data is then passed to an audio analysis unit for real-time processing.

[0220] Step 2:

[0221] The server converts the audio data received via the speech analysis unit into text data. This process applies machine learning algorithms to achieve high-precision speech recognition.

[0222] Step 3:

[0223] The server transfers the converted text data to the translation unit, which then performs the translation into the specified target language. It utilizes natural language processing techniques to provide context-aware translations.

[0224] Step 4:

[0225] Based on the translation results, the server uses a subtitle editing suggestion unit to suggest subtitle styles. This includes recommended settings for subtitle color, size, font, and position.

[0226] Step 5:

[0227] Users can review the subtitle style suggested by the server through the interface and make adjustments as needed. The user interface is designed to be simple and intuitive to use.

[0228] Step 6:

[0229] The server applies the confirmed subtitle style to the video data and generates the final video with subtitles. This video data is then sent to the terminal.

[0230] Step 7:

[0231] The server generates image data related to the subtitle text and inserts it into the video as needed. The image generation unit automatically creates visual content based on specific keywords.

[0232] Step 8:

[0233] The terminal renders the subtitled video and image data received from the server and displays them in the optimal format according to the user's display settings.

[0234] (Example 1)

[0235] 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."

[0236] Currently, in systems that convert audio signals into text data in real time and translate them into multiple languages, the challenges are reducing misrecognition and improving the accuracy of translations based on appropriate context. Furthermore, there is a need to quickly suggest highly visible subtitle styles based on the translated text and insert images that visually supplement relevant information into the content. This creates a need for a system that enables users to effectively communicate information to a wide range of language audiences.

[0237] 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.

[0238] In this invention, the server includes: an audio analysis means for receiving audio signals and converting them into text data in real time; a translation means for translating the text data into multiple languages; a subtitle editing suggestion means for proposing a subtitle style that takes legibility into consideration based on the translated text data; a display means for applying the proposed subtitle style to visual data; and an image generation means for generating visual information related to the text data and inserting it into the visual data. This enables improved accuracy in multilingual translation and the creation of highly legible video content.

[0239] A "speech analysis means" is a component that has the function of receiving a speech signal and converting it into string data in real time.

[0240] "Translation means" refers to technical components for accurately translating the aforementioned string data into multiple languages.

[0241] "Subtitle editing suggestion means" refers to components for suggesting a style that takes into account the readability of subtitles, based on translated string data.

[0242] "Display means" refers to components for applying the proposed subtitle style to visual data and outputting it visually as content.

[0243] An "image generation means" is a component that has the function of generating visual information related to string data and appropriately inserting it into the visual data.

[0244] A "generative model" is an advanced data processing technique for automatically generating relevant visual information based on prompt text.

[0245] One embodiment of this invention is a system for generating video content that supports multiple languages ​​from audio data. The specific operation is described below.

[0246] First, the user inputs audio signal data into the system through a dedicated interface. This input audio signal is received by a server. The server uses speech analysis tools to convert this audio signal into text data in real time. At this time, the server uses general speech recognition software. For example, it utilizes a widely used speech recognition service.

[0247] Next, the server translates the converted string data into the target language specified by the user. This is done using natural language processing techniques, such as translation APIs. Online translation services are particularly useful for this purpose.

[0248] Furthermore, the server suggests visually optimized subtitle styles to the user based on the translated text data. Subtitle editing software is used here, allowing the user to select the appropriate style. The suggested styles include subtitle color, size, font, and position.

[0249] Furthermore, the server uses a generative AI model to generate image data related to the string data. An example of a generation prompt is, "Create a graphic related to global warming." This image generation is intended to complement visual information, and the generated images are used to highlight specific scenes in the video.

[0250] The device receives visual data, including styles and images, sent from the server and performs the final rendering. The device optimizes the data according to the display settings and the device's own processing power to produce visually superior content.

[0251] This enables users to quickly and effectively create and distribute visually rich video content that supports multiple languages. For example, in live streaming of international conferences, multilingual subtitles are automatically generated and relevant images are added, allowing information to be effectively conveyed to viewers worldwide.

[0252] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0253] Step 1:

[0254] The user inputs audio signal data into the system through an interface. The server receives this audio signal and begins processing it. The input audio signal is analyzed using the server's audio analysis capabilities and converted into text data in real time. Specifically, speech recognition software extracts sound features and converts them into text. The output of this process is text data.

[0255] Step 2:

[0256] The server sends the string data obtained in step 1 to the translation tool, which translates it into the target language specified by the user. This translation uses natural language processing techniques to achieve high accuracy. Specifically, the translation API converts the string into a different language while analyzing the grammatical structure and considering the context. The output of this process is the translated string data.

[0257] Step 3:

[0258] The server uses the translated string data to generate a subtitle style that takes readability into consideration using a subtitle editing suggestion mechanism. Specifically, it uses a visual elements algorithm to calculate the appropriate subtitle color, size, font, and position, and provides the user with style options. The output of this step is the suggested subtitle style.

[0259] Step 4:

[0260] The server uses a generative AI model to generate images related to the translated string data. Here, a pre-defined prompt, such as "Create a graphic related to global warming," is input to the model, and visual information is generated based on it. The specific operation involves the AI ​​identifying relevant elements and generating the graphic. The output of this step is the generated image data.

[0261] Step 5:

[0262] The terminal receives visual data, including subtitle styles and image data, from the server, and renders the final video content based on that data. Specifically, the video rendering software performs optimizations according to the terminal's display settings and processing power. The output of this step is the final content with superior visual appeal.

[0263] This series of steps enables users to effectively create and distribute multilingual video content.

[0264] (Application Example 1)

[0265] 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."

[0266] In modern times, video content is consumed in many languages, and there is a demand for accurate, real-time translation of audio and presentation in a visually easy-to-understand format. However, generating and displaying multilingual subtitles is time-consuming and laborious, and effectively integrating related visual information is a difficult challenge. This invention aims to solve these problems and realize a technology that provides multilingual video content quickly and effectively.

[0267] 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.

[0268] In this invention, the server includes: an audio analysis means for receiving audio signals and converting them into encoded information in real time; a translation means for converting the encoded information into multiple languages; and a code editing suggestion means for proposing a display style that takes visibility into consideration based on the converted encoded information. This makes it possible to improve reliability and efficiency in multilingual translation and visual information presentation, and to optimize the transmission of information to the viewer.

[0269] "Speech analysis means" refers to a device or process that has the function of converting a received speech signal into encoded information in real time.

[0270] "Translation means" refers to a process or technology for converting encoded information into multiple languages.

[0271] "Code editing suggestion means" refers to an apparatus or process that has the function of suggesting a display style that takes legibility into consideration based on converted coded information.

[0272] "Presentation means" refers to an apparatus or method for applying a proposed display style to visual information.

[0273] "Image generation means" refers to a device or process that has the ability to generate image data related to encoded information and insert it into visual information.

[0274] "Material generation means" refers to a device or method that has the function of generating and presenting relevant visual materials based on encoded information.

[0275] The system for carrying out this invention mainly consists of a voice analysis means, a translation means, a code editing suggestion means, a presentation means, an image generation means, and a data generation means. The server converts the voice signal into encoded information in real time and converts this encoded information into multiple languages. Based on the converted encoded information, it proposes a display style that takes visibility into consideration and applies it to the visual information. This realizes the provision of visually effective information to the viewer.

[0276] The server uses the "speech_recognition" library for speech analysis, converting the audio signal into text data. This text data is then translated into multiple languages ​​using the "googletrans" library. Based on the translated data, it provides a visually appealing subtitle style that matches the video and generates image data using the "PIL" library to complement the relevant visual information.

[0277] The terminal receives this generated visual information and performs an optimized display for the device. As a result, the user can enjoy real-time multilingual video content.

[0278] As a specific example, there is a scenario where, during an international conference or a live broadcast of a film festival, real-time language translation and presentation of related images are carried out to provide accurate information in multiple languages to viewers around the world.

[0279] An example of a prompt sentence for the generation AI model is "Please translate the English audio data into Spanish and display it as visually refined subtitles together with related images."

[0280] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0281] Step 1:

[0282] The server receives an audio signal. Using this audio data as input, the server uses the "speech_recognition" library to convert it into encoded information in real time. As a result, the audio signal is output as text data. As a specific operation, it performs a process of analyzing the audio signal, recognizing the speech patterns of each language, and converting them into text.

[0283] Step 2:

[0284] The server translates the text data obtained in Step 1 into the specified target language using the "googletrans" library. In this translation method, natural language processing considering the context is performed to convert the text data into multiple languages. The input is the original text data, and the output is the translated text data. As a specific operation, it performs a process of improving the translation accuracy using a machine translation algorithm.

[0285] Step 3:

[0286] The server uses the translated text data to propose a display style considering visibility by the code editing proposal means. The input is the translated text data, and the output is the proposed display style. In this process, visually easy-to-read fonts, colorings, and the positions of subtitles are determined. As a specific operation, a process of proposing an optimal style setting according to the context of the video is performed.

[0287] Step 4:

[0288] The server uses the "PIL" library to generate image data related to the translated text. While considering the display style obtained in Step 3, visual materials related to the text are created. The input is the translated text and related information, and the output is the generated image data. As a specific operation, an appropriate image is designed based on the text content and preparations for insertion into the video are made.

[0289] Step 5:

[0290] The terminal receives the final visual information sent from the server and displays it in an appropriate format. Based on the image data and display style generated in Step 4, the video content is optimized and provided to the viewer. As a specific operation, the visual information is displayed at an optimal resolution and layout according to the processing ability of the terminal.

[0291] Step 6:

[0292] The user uses the delivered content while viewing the generated multilingual subtitles and related images. The input includes the information displayed on the terminal, and the output is the user's understanding and learning. As a specific operation, the user operates the interface to customize the subtitles and access further information.

[0293] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0294] The system for carrying out the present invention comprises a server, a terminal, and a user interface. This system integrates real-time voice analysis, translation, subtitle style suggestion, sentiment analysis, and image generation functions.

[0295] The server starts operating upon receiving an audio signal provided by the user. This audio signal is converted into text data in real time by the speech analysis unit. Advanced speech recognition technology is used for speech analysis to achieve highly accurate text conversion.

[0296] The converted text data is passed to a translation unit, where it is translated into multiple specified languages ​​in a natural and contextual manner. Advanced natural language processing techniques are applied during the translation process to preserve nuances and contextual information.

[0297] The subtitle editing suggestion unit implements style suggestions to optimize subtitle readability based on the translated text. This involves considering subtitle color, size, font, and position to provide suggestions best suited to the user's viewing environment.

[0298] Furthermore, the system incorporates an emotion engine, where the server analyzes the user's emotional state from the audio data and adjusts the tone and imagery of the subtitles accordingly. By reflecting the user's emotions, deeper communication becomes possible. For example, if the server detects joy in the user's voice, it will incorporate brighter colors into the subtitles and appropriately generate and insert related images.

[0299] The device receives information from the server and renders the final video data, taking into account the user's display settings. Emotion-based visual expression provides viewers with a more sensory-driven content experience.

[0300] Through the system, users can create real-time videos with multilingual subtitles and easily add visuals that match the emotions. As a specific example, in the live broadcast of an international sports competition, it is possible to reflect richly emotional comments in the languages of various countries in the video, effectively transmitting information while giving a sense of presence to viewers around the world.

[0301] The following describes the processing flow.

[0302] Step 1:

[0303] The server receives audio signal data from the user. The received audio signal is immediately sent to the audio analysis unit. The audio analysis unit uses a specified algorithm to convert the audio into text data in real time.

[0304] Step 2:

[0305] The server passes the text data obtained from the audio analysis to the translation unit. The translation unit utilizes multilingual support to translate quickly and accurately into the specified target language. The translation result is adjusted to maintain an appropriate context and be presented in natural expressions.

[0306] Step 3:

[0307] The server analyzes the text data with an emotion engine to identify the emotional state from the user's speech. The emotion engine identifies the characteristics of the audio related to emotions and makes an emotion judgment based on them.

[0308] Step 4:

[0309] Based on the translated text and the emotion analysis result, the server uses a subtitle editing proposal unit to propose an appropriate subtitle style to the user. In this proposal, the color, size, font, and position of the subtitle are adjusted according to the emotion.

[0310] Step 5:

[0311] Users can review the subtitle style suggested by the server through the user interface and make changes as needed. Sentiment-based customization options are provided during this process.

[0312] Step 6:

[0313] The server applies the user-defined subtitle style to the video data and uses an image generation unit to generate emotion-related visual content along with the translated subtitles. This includes illustrations and graphics appropriate to the scene.

[0314] Step 7:

[0315] The terminal receives the final subtitled video and generated image data from the server and renders them. The terminal takes into account the user's display settings and viewing conditions to provide the viewer with optimized video.

[0316] (Example 2)

[0317] 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".

[0318] Conventional speech analysis systems faced challenges in providing real-time multilingual support and visual representations that reflected user emotions. Furthermore, the visibility of subtitles and their integration with the visuals were often insufficient, resulting in a limited user experience.

[0319] 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.

[0320] In this invention, the server includes an analysis means for receiving audio signals and converting them into text data in real time, a conversion means for translating the text data into multiple languages, and an editing suggestion means for proposing subtitle styles that take legibility into consideration based on the translated text data. This makes it possible to provide multilingual audio translation and visually superior video expression based on emotion in real time.

[0321] "Analysis means" refers to a device that receives audio signals and converts them into text data in real time.

[0322] A "conversion device" is a device that has the function of translating text data into multiple languages.

[0323] An "editing suggestion device" is a device that has the function of suggesting a subtitle style that takes readability into consideration based on translated text data.

[0324] "Display means" refers to a device that has the function of applying the proposed subtitle style to video data.

[0325] An "emotion analysis device" is a device that analyzes the user's emotional state from audio data and adjusts the visual representation according to that emotion.

[0326] A "generation means" is a device that has the function of generating image data related to text data and inserting it into video data.

[0327] The present invention relates to a system configuration including a server, a terminal, and a user interface. This system provides the functionality to analyze audio data in real time and integrate translation, sentiment analysis, and visual representation. The software used by the server to receive audio signals, analyze them, and convert them into text data includes an audio analysis algorithm incorporating a generative AI model.

[0328] The analyzed text data is translated into multiple languages ​​by a translation unit on the server. Natural language processing techniques are applied here. Generative AI models are used in this translation process, ensuring that nuances and context are accurately preserved.

[0329] On the user terminal, a subtitle editing suggestion system automatically presents subtitle styles that take readability into consideration, based on translation data sent from the server. This allows the user to select or automatically apply the optimal style. The server also has an emotion analysis unit that analyzes the user's emotions from their voice and adjusts the visual representation accordingly. For example, if joy is detected from the user's voice, it suggests a subtitle style with bright colors and generates related positive images.

[0330] Furthermore, the generated subtitles and images are provided to the user through a display device on the terminal. This allows users to create videos with emotionally nuanced, multilingual subtitles in real time. For example, in live broadcasts of international events, it is possible to visually represent emotionally rich comments in each country's language in real time, thereby promoting a stronger understanding and engagement among viewers.

[0331] As an example of a prompt, you can give the system specific instructions such as, "Translate this audio in real time into English, Spanish, and Japanese, and suggest a sentiment-based subtitle style."

[0332] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0333] Step 1:

[0334] The server receives an audio signal from the user and sends it to the audio analysis unit. The input is the user's audio signal, which is converted into text data in real time by the analysis unit. This process uses a generative AI model that leverages deep learning to achieve highly accurate speech recognition. As output, the user's audio is converted into corresponding text data.

[0335] Step 2:

[0336] The server receives text data from the speech analysis unit and passes it to the translation unit. The input is text data, which is translated into multiple specified languages ​​using a translation mechanism. Specifically, natural language processing techniques are used to provide natural translations that preserve context. Generative AI models are again utilized in this process. The output is translated multilingual text.

[0337] Step 3:

[0338] The server provides the translated text received from the translation unit to the subtitle editing suggestion unit. The input is translated text in multiple languages, and based on this data, the editing suggestion means generates a subtitle style optimized for readability. Specifically, it considers the characteristics of the translated text and the user environment to suggest the optimal subtitle color, size, font, position, etc. The output is the suggested subtitle style information.

[0339] Step 4:

[0340] The server performs emotion analysis using audio data. The input is the user's audio data, and the emotion analysis tool determines the emotional state. Specifically, it analyzes the user's emotions from the tone of voice and word choice, and applies emotion-based visual changes to the video as needed. For example, if joy is detected, a subtitle style with brighter colors is selected. The output is the analyzed user emotion information.

[0341] Step 5:

[0342] The terminal receives the final data sent from the server and displays it on the screen. The input consists of subtitle style information, translated text, and associated image data. The terminal uses a display mechanism to render all data based on the user's display settings. Specifically, it renders the optimal image according to the user's visual environment. The output is the image visible to the user.

[0343] (Application Example 2)

[0344] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0345] In modern visual content distribution, multilingual support and visual expression that responds to the viewer's emotions are crucial. However, there are few systems capable of real-time, high-precision audio-to-text conversion, and generating subtitles and images that take emotional impact into account. Furthermore, displaying translated text in the most appropriate format to match the audience's emotions has been challenging until now.

[0346] 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.

[0347] In this invention, the server includes data analysis means for receiving audio signals and converting them into text data in real time, conversion means for translating the text data into multiple natural languages, and subtitle suggestion means for suggesting subtitle styles that take legibility into consideration based on the translated text data. This makes it possible to provide multilingual visual information in real time that adapts to the emotions of the viewer.

[0348] "Audio signals" are data that represents sound as electrical signals and are used for communication and analysis.

[0349] "Data analysis means" refers to a device or program for analyzing audio signals and converting them into text data in real time.

[0350] "Conversion means" refers to a device or program that has the function of translating text data into a different natural language.

[0351] The "subtitle suggestion method" is a function that suggests ways to display translated text data in a format that is easy to read.

[0352] "Information display means" refers to a device or program for presenting visual information to a user.

[0353] "Image generation means" refers to a device or program for generating relevant image information based on text data and integrating it into visual information.

[0354] "Emotional analysis means" refers to a device or program that extracts emotional information from audio signals and reflects it in the display of visual information.

[0355] This invention is a system that analyzes audio signals in real time, translates them into multiple languages, and then presents them to the audience in a visually easy-to-understand format. The server receives the audio signal and converts it into text data using an audio analysis means. This process uses speech recognition technology such as the Google Cloud Speech-to-Text API.

[0356] The converted text is translated into multiple languages ​​through a translation tool. This translation process utilizes natural language processing technologies such as the Google Translate API to achieve contextually appropriate translations.

[0357] The subtitle suggestion system proposes subtitle styles in a format suitable for visual information to improve readability. This proposal selects appropriate subtitle colors, fonts, and positions based on the video content and viewer sentiment information. During this process, sentiment analysis is performed using tools such as IBM Watson Tone Analyzer to adjust the subtitle colors and display.

[0358] The image generation means generates visual information based on text data, and the information display means integrates this information. Finally, the terminal presents the video in the optimal format for the viewer's display. This allows users to enjoy rich visual content that goes beyond simple subtitles and responds to emotional context.

[0359] As a concrete example, this system can be used in live streaming of international sporting events to provide viewers with real-time subtitles in each language and colorful visuals that reflect the emotions expressed.

[0360] An example of a prompt for a generative AI model is: "Analyze the following audio data and generate translated subtitles based on the emotions you capture. In particular, display subtitles in a bright color when the emotion is joy."

[0361] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0362] Step 1:

[0363] The server receives the audio signal and converts it into text data using speech analysis tools. The input is a real-time audio signal, and the output is the converted text data. The Google Cloud Speech-to-Text API is used to convert the audio to text, and data correction is performed to improve accuracy.

[0364] Step 2:

[0365] The server receives the converted text data and performs multilingual translation using a translation tool. The input is text data, and the output is multiple translated natural language data. The Google Translate API is used to generate contextually natural translation results.

[0366] Step 3:

[0367] The server passes the translated text data to the subtitle suggestion system, which then proposes the most suitable subtitle style for the visual information. The input is the translated text data and the results of sentiment analysis, while the output is a style proposal including subtitle color, font, and position. Sentiment analysis is performed using IBM Watson Tone Analyzer to determine the proposed style, taking legibility into consideration, and this analysis is used in the subtitle suggestion.

[0368] Step 4:

[0369] The server uses the generated subtitle style to apply it to the video data via the information display device. The input is a proposed subtitle style, and the output is visual information with subtitles. The terminal renders and presents it to the viewer in the optimal format according to the display settings.

[0370] Step 5:

[0371] The server uses image generation means to generate visual aids based on text data. The input is text data and the results of sentiment analysis, and the output is customized image data according to the sentiment. This allows the system to analyze the data, render appropriate visual information, and integrate it into the video.

[0372] 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.

[0373] 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.

[0374] 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.

[0375] [Third Embodiment]

[0376] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0377] 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.

[0378] 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).

[0379] 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.

[0380] 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.

[0381] 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).

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] 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".

[0388] The system for implementing the present invention mainly includes a server, a terminal, and a user interface. The specific operation of each element is described below.

[0389] The server begins processing upon receiving audio signal data sent from the user. The received audio signal is converted into text data in real time through a speech analysis system. This speech analysis supports multiple languages ​​and uses machine learning models to enhance the recognition of local pronunciation and technical terms as needed.

[0390] Next, the server translates the text data into the target language specified by the user using a translation tool. This process employs natural language processing techniques to improve context-based translation accuracy. The translated text is synchronized within the server and can be accessed quickly as needed.

[0391] The server also uses a subtitle editing suggestion mechanism based on the translated text data to suggest a style to the user that takes into account the readability of the subtitles. The suggested style includes the subtitle's color, size, font, and position. This information is presented to the user through the user interface, allowing the user to edit and confirm the style with intuitive operations.

[0392] Furthermore, the server uses image generation means to generate image data related to the content of the subtitles. This data is used to highlight specific scenes in the video and complements the visual information. For example, if the server analyzes the word "global warming," it will suggest inserting related graphics or diagrams.

[0393] The terminal receives video data, including styles and images determined by the server, and performs final rendering. During this process, it optimizes the display according to the terminal's processing power and display settings.

[0394] Through this series of processes, users can quickly and effectively create and deliver visually appealing video content that supports multiple languages. For example, in live streaming of international conferences, multilingual subtitles can be generated and styled, and relevant images inserted in real time, ensuring effective information transmission to viewers worldwide.

[0395] The following describes the processing flow.

[0396] Step 1:

[0397] The server receives audio signal data streamed from the user. This audio data is then passed to an audio analysis unit for real-time processing.

[0398] Step 2:

[0399] The server converts the audio data received via the speech analysis unit into text data. This process applies machine learning algorithms to achieve high-precision speech recognition.

[0400] Step 3:

[0401] The server transfers the converted text data to the translation unit, which then performs the translation into the specified target language. It utilizes natural language processing techniques to provide context-aware translations.

[0402] Step 4:

[0403] Based on the translation results, the server uses a subtitle editing suggestion unit to suggest subtitle styles. This includes recommended settings for subtitle color, size, font, and position.

[0404] Step 5:

[0405] Users can review the subtitle style suggested by the server through the interface and make adjustments as needed. The user interface is designed to be simple and intuitive to use.

[0406] Step 6:

[0407] The server applies the confirmed subtitle style to the video data and generates the final video with subtitles. This video data is then sent to the terminal.

[0408] Step 7:

[0409] The server generates image data related to the subtitle text and inserts it into the video as needed. The image generation unit automatically creates visual content based on specific keywords.

[0410] Step 8:

[0411] The terminal renders the subtitled video and image data received from the server and displays them in the optimal format according to the user's display settings.

[0412] (Example 1)

[0413] 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."

[0414] Currently, in systems that convert audio signals into text data in real time and translate them into multiple languages, the challenges are reducing misrecognition and improving the accuracy of translations based on appropriate context. Furthermore, there is a need to quickly suggest highly visible subtitle styles based on the translated text and insert images that visually supplement relevant information into the content. This creates a need for a system that enables users to effectively communicate information to a wide range of language audiences.

[0415] 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.

[0416] In this invention, the server includes: an audio analysis means for receiving audio signals and converting them into text data in real time; a translation means for translating the text data into multiple languages; a subtitle editing suggestion means for proposing a subtitle style that takes legibility into consideration based on the translated text data; a display means for applying the proposed subtitle style to visual data; and an image generation means for generating visual information related to the text data and inserting it into the visual data. This enables improved accuracy in multilingual translation and the creation of highly legible video content.

[0417] A "speech analysis means" is a component that has the function of receiving a speech signal and converting it into string data in real time.

[0418] "Translation means" refers to technical components for accurately translating the aforementioned string data into multiple languages.

[0419] "Subtitle editing suggestion means" refers to components for suggesting a style that takes into account the readability of subtitles, based on translated string data.

[0420] "Display means" refers to components for applying the proposed subtitle style to visual data and outputting it visually as content.

[0421] An "image generation means" is a component that has the function of generating visual information related to string data and appropriately inserting it into the visual data.

[0422] A "generative model" is an advanced data processing technique for automatically generating relevant visual information based on prompt text.

[0423] One embodiment of this invention is a system for generating video content that supports multiple languages ​​from audio data. The specific operation is described below.

[0424] First, the user inputs audio signal data into the system through a dedicated interface. This input audio signal is received by a server. The server uses speech analysis tools to convert this audio signal into text data in real time. At this time, the server uses general speech recognition software. For example, it utilizes a widely used speech recognition service.

[0425] Next, the server translates the converted string data into the target language specified by the user. This is done using natural language processing techniques, such as translation APIs. Online translation services are particularly useful for this purpose.

[0426] Furthermore, the server suggests visually optimized subtitle styles to the user based on the translated text data. Subtitle editing software is used here, allowing the user to select the appropriate style. The suggested styles include subtitle color, size, font, and position.

[0427] Furthermore, the server uses a generative AI model to generate image data related to the string data. An example of a generation prompt is, "Create a graphic related to global warming." This image generation is intended to complement visual information, and the generated images are used to highlight specific scenes in the video.

[0428] The device receives visual data, including styles and images, sent from the server and performs the final rendering. The device optimizes the data according to the display settings and the device's own processing power to produce visually superior content.

[0429] This enables users to quickly and effectively create and distribute visually rich video content that supports multiple languages. For example, in live streaming of international conferences, multilingual subtitles are automatically generated and relevant images are added, allowing information to be effectively conveyed to viewers worldwide.

[0430] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0431] Step 1:

[0432] The user inputs audio signal data into the system through an interface. The server receives this audio signal and begins processing it. The input audio signal is analyzed using the server's audio analysis capabilities and converted into text data in real time. Specifically, speech recognition software extracts sound features and converts them into text. The output of this process is text data.

[0433] Step 2:

[0434] The server sends the string data obtained in step 1 to the translation tool, which translates it into the target language specified by the user. This translation uses natural language processing techniques to achieve high accuracy. Specifically, the translation API converts the string into a different language while analyzing the grammatical structure and considering the context. The output of this process is the translated string data.

[0435] Step 3:

[0436] The server uses the translated string data to generate a subtitle style that takes readability into consideration using a subtitle editing suggestion mechanism. Specifically, it uses a visual elements algorithm to calculate the appropriate subtitle color, size, font, and position, and provides the user with style options. The output of this step is the suggested subtitle style.

[0437] Step 4:

[0438] The server uses a generative AI model to generate images related to the translated string data. Here, a pre-defined prompt, such as "Create a graphic related to global warming," is input to the model, and visual information is generated based on it. The specific operation involves the AI ​​identifying relevant elements and generating the graphic. The output of this step is the generated image data.

[0439] Step 5:

[0440] The terminal receives visual data, including subtitle styles and image data, from the server, and renders the final video content based on that data. Specifically, the video rendering software performs optimizations according to the terminal's display settings and processing power. The output of this step is the final content with superior visual appeal.

[0441] This series of steps enables users to effectively create and distribute multilingual video content.

[0442] (Application Example 1)

[0443] 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."

[0444] In modern times, video content is consumed in many languages, and there is a demand for accurate, real-time translation of audio and presentation in a visually easy-to-understand format. However, generating and displaying multilingual subtitles is time-consuming and laborious, and effectively integrating related visual information is a difficult challenge. This invention aims to solve these problems and realize a technology that provides multilingual video content quickly and effectively.

[0445] 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.

[0446] In this invention, the server includes: an audio analysis means for receiving audio signals and converting them into encoded information in real time; a translation means for converting the encoded information into multiple languages; and a code editing suggestion means for proposing a display style that takes visibility into consideration based on the converted encoded information. This makes it possible to improve reliability and efficiency in multilingual translation and visual information presentation, and to optimize the transmission of information to the viewer.

[0447] "Speech analysis means" refers to a device or process that has the function of converting a received speech signal into encoded information in real time.

[0448] "Translation means" refers to a process or technology for converting encoded information into multiple languages.

[0449] "Code editing suggestion means" refers to an apparatus or process that has the function of suggesting a display style that takes legibility into consideration based on converted coded information.

[0450] "Presentation means" refers to an apparatus or method for applying a proposed display style to visual information.

[0451] "Image generation means" refers to a device or process that has the ability to generate image data related to encoded information and insert it into visual information.

[0452] "Material generation means" refers to a device or method that has the function of generating and presenting relevant visual materials based on encoded information.

[0453] The system for carrying out this invention mainly consists of a voice analysis means, a translation means, a code editing suggestion means, a presentation means, an image generation means, and a data generation means. The server converts the voice signal into encoded information in real time and converts this encoded information into multiple languages. Based on the converted encoded information, it proposes a display style that takes visibility into consideration and applies it to the visual information. This realizes the provision of visually effective information to the viewer.

[0454] The server uses the "speech_recognition" library for speech analysis, converting the audio signal into text data. This text data is then translated into multiple languages ​​using the "googletrans" library. Based on the translated data, it provides a visually appealing subtitle style that matches the video and generates image data using the "PIL" library to complement the relevant visual information.

[0455] The device receives this generated visual information and displays it in a way that is optimized for the device. This allows users to enjoy multilingual video content in real time.

[0456] Specific examples include live broadcasts of international conferences and film festivals, where real-time language translations and related images are provided to deliver accurate information in multiple languages ​​to viewers worldwide.

[0457] An example of a prompt for a generative AI model is: "Translate the English audio data into Spanish and display it as visually sophisticated subtitles along with the associated images."

[0458] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0459] Step 1:

[0460] The server receives an audio signal. Using this audio data as input, the server converts it into encoded information in real time using the "speech_recognition" library. As a result, the audio signal is output as text data. Specifically, the server analyzes the audio signal, recognizes the speech patterns of each language, and converts them into text.

[0461] Step 2:

[0462] The server translates the text data obtained in step 1 into the specified target language using the "googletrans" library. This translation method performs context-aware natural language processing to convert text data into multiple languages. The input is the original text data, and the output is the translated text data. Specifically, it uses a machine translation algorithm to improve translation accuracy.

[0463] Step 3:

[0464] The server uses the translated text data to propose a display style that considers readability through a code editing suggestion mechanism. The input is the translated text data, and the output is the proposed display style. This process determines visually appealing fonts, color schemes, and subtitle placement. Specifically, it performs a process to suggest the optimal style settings according to the context of the video.

[0465] Step 4:

[0466] The server uses the "PIL" library to generate image data related to the translated text. It creates visual materials related to the text, taking into account the display style obtained in step 3. The input is the translated text and related information, and the output is the generated image data. Specifically, it designs appropriate images based on the text content and prepares them for insertion into the video.

[0467] Step 5:

[0468] The terminal receives the final visual information sent from the server and displays it in the appropriate format. Based on the image data and display style generated in step 4, it optimizes the video content and provides it to the viewer. Specifically, it displays the visual information at the optimal resolution and layout according to the terminal's processing power.

[0469] Step 6:

[0470] Users utilize the delivered content while viewing generated multilingual subtitles and related images. The input is the information displayed on the device, and the output is the user's understanding and learning. Specifically, users interact with the interface to customize subtitles and access further information.

[0471] 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.

[0472] The system for carrying out the present invention comprises a server, a terminal, and a user interface. This system integrates real-time voice analysis, translation, subtitle style suggestion, sentiment analysis, and image generation functions.

[0473] The server starts operating upon receiving an audio signal provided by the user. This audio signal is converted into text data in real time by the speech analysis unit. Advanced speech recognition technology is used for speech analysis to achieve highly accurate text conversion.

[0474] The converted text data is passed to a translation unit, where it is translated into multiple specified languages ​​in a natural and contextual manner. Advanced natural language processing techniques are applied during the translation process to preserve nuances and contextual information.

[0475] The subtitle editing suggestion unit implements style suggestions to optimize subtitle readability based on the translated text. This involves considering subtitle color, size, font, and position to provide suggestions best suited to the user's viewing environment.

[0476] Furthermore, the system incorporates an emotion engine, where the server analyzes the user's emotional state from the audio data and adjusts the tone and imagery of the subtitles accordingly. By reflecting the user's emotions, deeper communication becomes possible. For example, if the server detects joy in the user's voice, it will incorporate brighter colors into the subtitles and appropriately generate and insert related images.

[0477] The device receives information from the server and renders the final video data, taking into account the user's display settings. Emotion-based visual expression provides viewers with a more sensory-driven content experience.

[0478] Through the system, users can create videos with multilingual subtitles in real time and easily add visuals that match the emotions. For example, in live broadcasts of international sporting events, it is possible to reflect emotionally rich comments in each country's language into the video, effectively conveying information to viewers worldwide while creating a sense of realism.

[0479] The following describes the processing flow.

[0480] Step 1:

[0481] The server receives audio signal data from the user. The received audio signal is immediately sent to the audio analysis unit. The audio analysis unit converts the audio into text data in real time using a specified algorithm.

[0482] Step 2:

[0483] The server passes the text data obtained from speech analysis to the translation unit. The translation unit utilizes multilingual support to translate quickly and accurately into the specified target language. The translation results are adjusted to preserve appropriate context and produce natural-sounding expressions.

[0484] Step 3:

[0485] The server analyzes text data using an emotion engine to identify the user's emotional state from their speech. The emotion engine identifies speech features associated with emotion and makes an emotion judgment based on them.

[0486] Step 4:

[0487] Based on the translated text and sentiment analysis results, the server utilizes a subtitle editing suggestion unit to propose an appropriate subtitle style to the user. This suggestion adjusts the subtitle's color, size, font, and position to match the sentiment.

[0488] Step 5:

[0489] Users can review the subtitle style suggested by the server through the user interface and make changes as needed. Sentiment-based customization options are provided during this process.

[0490] Step 6:

[0491] The server applies the user-defined subtitle style to the video data and uses an image generation unit to generate emotion-related visual content along with the translated subtitles. This includes illustrations and graphics appropriate to the scene.

[0492] Step 7:

[0493] The terminal receives the final subtitled video and generated image data from the server and renders them. The terminal takes into account the user's display settings and viewing conditions to provide the viewer with optimized video.

[0494] (Example 2)

[0495] 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."

[0496] Conventional speech analysis systems faced challenges in providing real-time multilingual support and visual representations that reflected user emotions. Furthermore, the visibility of subtitles and their integration with the visuals were often insufficient, resulting in a limited user experience.

[0497] 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.

[0498] In this invention, the server includes an analysis means for receiving audio signals and converting them into text data in real time, a conversion means for translating the text data into multiple languages, and an editing suggestion means for proposing subtitle styles that take legibility into consideration based on the translated text data. This makes it possible to provide multilingual audio translation and visually superior video expression based on emotion in real time.

[0499] "Analysis means" refers to a device that receives audio signals and converts them into text data in real time.

[0500] A "conversion device" is a device that has the function of translating text data into multiple languages.

[0501] An "editing suggestion device" is a device that has the function of suggesting a subtitle style that takes readability into consideration based on translated text data.

[0502] "Display means" refers to a device that has the function of applying the proposed subtitle style to video data.

[0503] An "emotion analysis device" is a device that analyzes the user's emotional state from audio data and adjusts the visual representation according to that emotion.

[0504] A "generation means" is a device that has the function of generating image data related to text data and inserting it into video data.

[0505] The present invention relates to a system configuration including a server, a terminal, and a user interface. This system provides the functionality to analyze audio data in real time and integrate translation, sentiment analysis, and visual representation. The software used by the server to receive audio signals, analyze them, and convert them into text data includes an audio analysis algorithm incorporating a generative AI model.

[0506] The analyzed text data is translated into multiple languages ​​by a translation unit on the server. Natural language processing techniques are applied here. Generative AI models are used in this translation process, ensuring that nuances and context are accurately preserved.

[0507] On the user terminal, a subtitle editing suggestion system automatically presents subtitle styles that take readability into consideration, based on translation data sent from the server. This allows the user to select or automatically apply the optimal style. The server also has an emotion analysis unit that analyzes the user's emotions from their voice and adjusts the visual representation accordingly. For example, if joy is detected from the user's voice, it suggests a subtitle style with bright colors and generates related positive images.

[0508] Furthermore, the generated subtitles and images are provided to the user through a display device on the terminal. This allows users to create videos with emotionally nuanced, multilingual subtitles in real time. For example, in live broadcasts of international events, it is possible to visually represent emotionally rich comments in each country's language in real time, thereby promoting a stronger understanding and engagement among viewers.

[0509] As an example of a prompt, you can give the system specific instructions such as, "Translate this audio in real time into English, Spanish, and Japanese, and suggest a sentiment-based subtitle style."

[0510] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0511] Step 1:

[0512] The server receives an audio signal from the user and sends it to the audio analysis unit. The input is the user's audio signal, which is converted into text data in real time by the analysis unit. This process uses a generative AI model that leverages deep learning to achieve highly accurate speech recognition. As output, the user's audio is converted into corresponding text data.

[0513] Step 2:

[0514] The server receives text data from the speech analysis unit and passes it to the translation unit. The input is text data, which is translated into multiple specified languages ​​using a translation mechanism. Specifically, natural language processing techniques are used to provide natural translations that preserve context. Generative AI models are again utilized in this process. The output is translated multilingual text.

[0515] Step 3:

[0516] The server provides the translated text received from the translation unit to the subtitle editing suggestion unit. The input is translated text in multiple languages, and based on this data, the editing suggestion means generates a subtitle style optimized for readability. Specifically, it considers the characteristics of the translated text and the user environment to suggest the optimal subtitle color, size, font, position, etc. The output is the suggested subtitle style information.

[0517] Step 4:

[0518] The server performs emotion analysis using audio data. The input is the user's audio data, and the emotion analysis tool determines the emotional state. Specifically, it analyzes the user's emotions from the tone of voice and word choice, and applies emotion-based visual changes to the video as needed. For example, if joy is detected, a subtitle style with brighter colors is selected. The output is the analyzed user emotion information.

[0519] Step 5:

[0520] The terminal receives the final data sent from the server and displays it on the screen. The input consists of subtitle style information, translated text, and associated image data. The terminal uses a display mechanism to render all data based on the user's display settings. Specifically, it renders the optimal image according to the user's visual environment. The output is the image visible to the user.

[0521] (Application Example 2)

[0522] 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."

[0523] In modern visual content distribution, multilingual support and visual expression that responds to the viewer's emotions are crucial. However, there are few systems capable of real-time, high-precision audio-to-text conversion, and generating subtitles and images that take emotional impact into account. Furthermore, displaying translated text in the most appropriate format to match the audience's emotions has been challenging until now.

[0524] 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.

[0525] In this invention, the server includes data analysis means for receiving audio signals and converting them into text data in real time, conversion means for translating the text data into multiple natural languages, and subtitle suggestion means for suggesting subtitle styles that take legibility into consideration based on the translated text data. This makes it possible to provide multilingual visual information in real time that adapts to the emotions of the viewer.

[0526] "Audio signals" are data that represents sound as electrical signals and are used for communication and analysis.

[0527] "Data analysis means" refers to a device or program for analyzing audio signals and converting them into text data in real time.

[0528] "Conversion means" refers to a device or program that has the function of translating text data into a different natural language.

[0529] The "subtitle suggestion method" is a function that suggests ways to display translated text data in a format that is easy to read.

[0530] "Information display means" refers to a device or program for presenting visual information to a user.

[0531] "Image generation means" refers to a device or program for generating relevant image information based on text data and integrating it into visual information.

[0532] "Emotional analysis means" refers to a device or program that extracts emotional information from audio signals and reflects it in the display of visual information.

[0533] This invention is a system that analyzes audio signals in real time, translates them into multiple languages, and then presents them to the audience in a visually easy-to-understand format. The server receives the audio signal and converts it into text data using an audio analysis means. This process uses speech recognition technology such as the Google Cloud Speech-to-Text API.

[0534] The converted text is translated into multiple languages ​​through a translation tool. This translation process utilizes natural language processing technologies such as the Google Translate API to achieve contextually appropriate translations.

[0535] The subtitle suggestion system proposes subtitle styles in a format suitable for visual information to improve readability. This proposal selects appropriate subtitle colors, fonts, and positions based on the video content and viewer sentiment information. During this process, sentiment analysis is performed using tools such as IBM Watson Tone Analyzer to adjust the subtitle colors and display.

[0536] The image generation means generates visual information based on text data, and the information display means integrates this information. Finally, the terminal presents the video in the optimal format for the viewer's display. This allows users to enjoy rich visual content that goes beyond simple subtitles and responds to emotional context.

[0537] As a concrete example, this system can be used in live streaming of international sporting events to provide viewers with real-time subtitles in each language and colorful visuals that reflect the emotions expressed.

[0538] An example of a prompt for a generative AI model is: "Analyze the following audio data and generate translated subtitles based on the emotions you capture. In particular, display subtitles in a bright color when the emotion is joy."

[0539] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0540] Step 1:

[0541] The server receives the audio signal and converts it into text data using speech analysis tools. The input is a real-time audio signal, and the output is the converted text data. The Google Cloud Speech-to-Text API is used to convert the audio to text, and data correction is performed to improve accuracy.

[0542] Step 2:

[0543] The server receives the converted text data and performs multilingual translation using a translation tool. The input is text data, and the output is multiple translated natural language data. The Google Translate API is used to generate contextually natural translation results.

[0544] Step 3:

[0545] The server passes the translated text data to the subtitle suggestion system, which then proposes the most suitable subtitle style for the visual information. The input is the translated text data and the results of sentiment analysis, while the output is a style proposal including subtitle color, font, and position. Sentiment analysis is performed using IBM Watson Tone Analyzer to determine the proposed style, taking legibility into consideration, and this analysis is used in the subtitle suggestion.

[0546] Step 4:

[0547] The server uses the generated subtitle style to apply it to the video data via the information display device. The input is a proposed subtitle style, and the output is visual information with subtitles. The terminal renders and presents it to the viewer in the optimal format according to the display settings.

[0548] Step 5:

[0549] The server uses image generation means to generate visual aids based on text data. The input is text data and the results of sentiment analysis, and the output is customized image data according to the sentiment. This allows the system to analyze the data, render appropriate visual information, and integrate it into the video.

[0550] 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.

[0551] 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.

[0552] 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.

[0553] [Fourth Embodiment]

[0554] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0555] 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.

[0556] 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).

[0557] 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.

[0558] 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.

[0559] 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).

[0560] 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.

[0561] 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.

[0562] 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.

[0563] 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.

[0564] 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.

[0565] 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.

[0566] 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".

[0567] The system for implementing the present invention mainly includes a server, a terminal, and a user interface. The specific operation of each element is described below.

[0568] The server begins processing upon receiving audio signal data sent from the user. The received audio signal is converted into text data in real time through a speech analysis system. This speech analysis supports multiple languages ​​and uses machine learning models to enhance the recognition of local pronunciation and technical terms as needed.

[0569] Next, the server translates the text data into the target language specified by the user using a translation tool. This process employs natural language processing techniques to improve context-based translation accuracy. The translated text is synchronized within the server and can be accessed quickly as needed.

[0570] The server also uses a subtitle editing suggestion mechanism based on the translated text data to suggest a style to the user that takes into account the readability of the subtitles. The suggested style includes the subtitle's color, size, font, and position. This information is presented to the user through the user interface, allowing the user to edit and confirm the style with intuitive operations.

[0571] Furthermore, the server uses image generation means to generate image data related to the content of the subtitles. This data is used to highlight specific scenes in the video and complements the visual information. For example, if the server analyzes the word "global warming," it will suggest inserting related graphics or diagrams.

[0572] The terminal receives video data, including styles and images determined by the server, and performs final rendering. During this process, it optimizes the display according to the terminal's processing power and display settings.

[0573] Through this series of processes, users can quickly and effectively create and deliver visually appealing video content that supports multiple languages. For example, in live streaming of international conferences, multilingual subtitles can be generated and styled, and relevant images inserted in real time, ensuring effective information transmission to viewers worldwide.

[0574] The following describes the processing flow.

[0575] Step 1:

[0576] The server receives audio signal data streamed from the user. This audio data is then passed to an audio analysis unit for real-time processing.

[0577] Step 2:

[0578] The server converts the audio data received via the speech analysis unit into text data. This process applies machine learning algorithms to achieve high-precision speech recognition.

[0579] Step 3:

[0580] The server transfers the converted text data to the translation unit, which then performs the translation into the specified target language. It utilizes natural language processing techniques to provide context-aware translations.

[0581] Step 4:

[0582] Based on the translation results, the server uses a subtitle editing suggestion unit to suggest subtitle styles. This includes recommended settings for subtitle color, size, font, and position.

[0583] Step 5:

[0584] Users can review the subtitle style suggested by the server through the interface and make adjustments as needed. The user interface is designed to be simple and intuitive to use.

[0585] Step 6:

[0586] The server applies the confirmed subtitle style to the video data and generates the final video with subtitles. This video data is then sent to the terminal.

[0587] Step 7:

[0588] The server generates image data related to the subtitle text and inserts it into the video as needed. The image generation unit automatically creates visual content based on specific keywords.

[0589] Step 8:

[0590] The terminal renders the subtitled video and image data received from the server and displays them in the optimal format according to the user's display settings.

[0591] (Example 1)

[0592] 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".

[0593] Currently, in systems that convert audio signals into text data in real time and translate them into multiple languages, the challenges are reducing misrecognition and improving the accuracy of translations based on appropriate context. Furthermore, there is a need to quickly suggest highly visible subtitle styles based on the translated text and insert images that visually supplement relevant information into the content. This creates a need for a system that enables users to effectively communicate information to a wide range of language audiences.

[0594] 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.

[0595] In this invention, the server includes: an audio analysis means for receiving audio signals and converting them into text data in real time; a translation means for translating the text data into multiple languages; a subtitle editing suggestion means for proposing a subtitle style that takes legibility into consideration based on the translated text data; a display means for applying the proposed subtitle style to visual data; and an image generation means for generating visual information related to the text data and inserting it into the visual data. This enables improved accuracy in multilingual translation and the creation of highly legible video content.

[0596] A "speech analysis means" is a component that has the function of receiving a speech signal and converting it into string data in real time.

[0597] "Translation means" refers to technical components for accurately translating the aforementioned string data into multiple languages.

[0598] "Subtitle editing suggestion means" refers to components for suggesting a style that takes into account the readability of subtitles, based on translated string data.

[0599] "Display means" refers to components for applying the proposed subtitle style to visual data and outputting it visually as content.

[0600] An "image generation means" is a component that has the function of generating visual information related to string data and appropriately inserting it into the visual data.

[0601] A "generative model" is an advanced data processing technique for automatically generating relevant visual information based on prompt text.

[0602] One embodiment of this invention is a system for generating video content that supports multiple languages ​​from audio data. The specific operation is described below.

[0603] First, the user inputs audio signal data into the system through a dedicated interface. This input audio signal is received by a server. The server uses speech analysis tools to convert this audio signal into text data in real time. At this time, the server uses general speech recognition software. For example, it utilizes a widely used speech recognition service.

[0604] Next, the server translates the converted string data into the target language specified by the user. This is done using natural language processing techniques, such as translation APIs. Online translation services are particularly useful for this purpose.

[0605] Furthermore, the server suggests visually optimized subtitle styles to the user based on the translated text data. Subtitle editing software is used here, allowing the user to select the appropriate style. The suggested styles include subtitle color, size, font, and position.

[0606] Furthermore, the server uses a generative AI model to generate image data related to the string data. An example of a generation prompt is, "Create a graphic related to global warming." This image generation is intended to complement visual information, and the generated images are used to highlight specific scenes in the video.

[0607] The device receives visual data, including styles and images, sent from the server and performs the final rendering. The device optimizes the data according to the display settings and the device's own processing power to produce visually superior content.

[0608] This enables users to quickly and effectively create and distribute visually rich video content that supports multiple languages. For example, in live streaming of international conferences, multilingual subtitles are automatically generated and relevant images are added, allowing information to be effectively conveyed to viewers worldwide.

[0609] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0610] Step 1:

[0611] The user inputs audio signal data into the system through an interface. The server receives this audio signal and begins processing it. The input audio signal is analyzed using the server's audio analysis capabilities and converted into text data in real time. Specifically, speech recognition software extracts sound features and converts them into text. The output of this process is text data.

[0612] Step 2:

[0613] The server sends the string data obtained in step 1 to the translation tool, which translates it into the target language specified by the user. This translation uses natural language processing techniques to achieve high accuracy. Specifically, the translation API converts the string into a different language while analyzing the grammatical structure and considering the context. The output of this process is the translated string data.

[0614] Step 3:

[0615] The server uses the translated string data to generate a subtitle style that takes readability into consideration using a subtitle editing suggestion mechanism. Specifically, it uses a visual elements algorithm to calculate the appropriate subtitle color, size, font, and position, and provides the user with style options. The output of this step is the suggested subtitle style.

[0616] Step 4:

[0617] The server uses a generative AI model to generate images related to the translated string data. Here, a pre-defined prompt, such as "Create a graphic related to global warming," is input to the model, and visual information is generated based on it. The specific operation involves the AI ​​identifying relevant elements and generating the graphic. The output of this step is the generated image data.

[0618] Step 5:

[0619] The terminal receives visual data, including subtitle styles and image data, from the server, and renders the final video content based on that data. Specifically, the video rendering software performs optimizations according to the terminal's display settings and processing power. The output of this step is the final content with superior visual appeal.

[0620] This series of steps enables users to effectively create and distribute multilingual video content.

[0621] (Application Example 1)

[0622] 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".

[0623] In modern times, video content is consumed in many languages, and there is a demand for accurate, real-time translation of audio and presentation in a visually easy-to-understand format. However, generating and displaying multilingual subtitles is time-consuming and laborious, and effectively integrating related visual information is a difficult challenge. This invention aims to solve these problems and realize a technology that provides multilingual video content quickly and effectively.

[0624] 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.

[0625] In this invention, the server includes: an audio analysis means for receiving audio signals and converting them into encoded information in real time; a translation means for converting the encoded information into multiple languages; and a code editing suggestion means for proposing a display style that takes visibility into consideration based on the converted encoded information. This makes it possible to improve reliability and efficiency in multilingual translation and visual information presentation, and to optimize the transmission of information to the viewer.

[0626] "Speech analysis means" refers to a device or process that has the function of converting a received speech signal into encoded information in real time.

[0627] "Translation means" refers to a process or technology for converting encoded information into multiple languages.

[0628] "Code editing suggestion means" refers to an apparatus or process that has the function of suggesting a display style that takes legibility into consideration based on converted coded information.

[0629] "Presentation means" refers to an apparatus or method for applying a proposed display style to visual information.

[0630] "Image generation means" refers to a device or process that has the ability to generate image data related to encoded information and insert it into visual information.

[0631] "Material generation means" refers to a device or method that has the function of generating and presenting relevant visual materials based on encoded information.

[0632] The system for carrying out this invention mainly consists of a voice analysis means, a translation means, a code editing suggestion means, a presentation means, an image generation means, and a data generation means. The server converts the voice signal into encoded information in real time and converts this encoded information into multiple languages. Based on the converted encoded information, it proposes a display style that takes visibility into consideration and applies it to the visual information. This realizes the provision of visually effective information to the viewer.

[0633] The server uses the "speech_recognition" library for speech analysis, converting the audio signal into text data. This text data is then translated into multiple languages ​​using the "googletrans" library. Based on the translated data, it provides a visually appealing subtitle style that matches the video and generates image data using the "PIL" library to complement the relevant visual information.

[0634] The device receives this generated visual information and displays it in a way that is optimized for the device. This allows users to enjoy multilingual video content in real time.

[0635] Specific examples include live broadcasts of international conferences and film festivals, where real-time language translations and related images are provided to deliver accurate information in multiple languages ​​to viewers worldwide.

[0636] An example of a prompt for a generative AI model is: "Translate the English audio data into Spanish and display it as visually sophisticated subtitles along with the associated images."

[0637] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0638] Step 1:

[0639] The server receives an audio signal. Using this audio data as input, the server converts it into encoded information in real time using the "speech_recognition" library. As a result, the audio signal is output as text data. Specifically, the server analyzes the audio signal, recognizes the speech patterns of each language, and converts them into text.

[0640] Step 2:

[0641] The server translates the text data obtained in step 1 into the specified target language using the "googletrans" library. This translation method performs context-aware natural language processing to convert text data into multiple languages. The input is the original text data, and the output is the translated text data. Specifically, it uses a machine translation algorithm to improve translation accuracy.

[0642] Step 3:

[0643] The server uses the translated text data to propose a display style that considers readability through a code editing suggestion mechanism. The input is the translated text data, and the output is the proposed display style. This process determines visually appealing fonts, color schemes, and subtitle placement. Specifically, it performs a process to suggest the optimal style settings according to the context of the video.

[0644] Step 4:

[0645] The server uses the "PIL" library to generate image data related to the translated text. It creates visual materials related to the text, taking into account the display style obtained in step 3. The input is the translated text and related information, and the output is the generated image data. Specifically, it designs appropriate images based on the text content and prepares them for insertion into the video.

[0646] Step 5:

[0647] The terminal receives the final visual information sent from the server and displays it in the appropriate format. Based on the image data and display style generated in step 4, it optimizes the video content and provides it to the viewer. Specifically, it displays the visual information at the optimal resolution and layout according to the terminal's processing power.

[0648] Step 6:

[0649] Users utilize the delivered content while viewing generated multilingual subtitles and related images. The input is the information displayed on the device, and the output is the user's understanding and learning. Specifically, users interact with the interface to customize subtitles and access further information.

[0650] 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.

[0651] The system for carrying out the present invention comprises a server, a terminal, and a user interface. This system integrates real-time voice analysis, translation, subtitle style suggestion, sentiment analysis, and image generation functions.

[0652] The server starts operating upon receiving an audio signal provided by the user. This audio signal is converted into text data in real time by the speech analysis unit. Advanced speech recognition technology is used for speech analysis to achieve highly accurate text conversion.

[0653] The converted text data is passed to a translation unit, where it is translated into multiple specified languages ​​in a natural and contextual manner. Advanced natural language processing techniques are applied during the translation process to preserve nuances and contextual information.

[0654] The subtitle editing suggestion unit implements style suggestions to optimize subtitle readability based on the translated text. This involves considering subtitle color, size, font, and position to provide suggestions best suited to the user's viewing environment.

[0655] Furthermore, the system incorporates an emotion engine, where the server analyzes the user's emotional state from the audio data and adjusts the tone and imagery of the subtitles accordingly. By reflecting the user's emotions, deeper communication becomes possible. For example, if the server detects joy in the user's voice, it will incorporate brighter colors into the subtitles and appropriately generate and insert related images.

[0656] The device receives information from the server and renders the final video data, taking into account the user's display settings. Emotion-based visual expression provides viewers with a more sensory-driven content experience.

[0657] Through the system, users can create videos with multilingual subtitles in real time and easily add visuals that match the emotions. For example, in live broadcasts of international sporting events, it is possible to reflect emotionally rich comments in each country's language into the video, effectively conveying information to viewers worldwide while creating a sense of realism.

[0658] The following describes the processing flow.

[0659] Step 1:

[0660] The server receives audio signal data from the user. The received audio signal is immediately sent to the audio analysis unit. The audio analysis unit converts the audio into text data in real time using a specified algorithm.

[0661] Step 2:

[0662] The server passes the text data obtained from speech analysis to the translation unit. The translation unit utilizes multilingual support to translate quickly and accurately into the specified target language. The translation results are adjusted to preserve appropriate context and produce natural-sounding expressions.

[0663] Step 3:

[0664] The server analyzes text data using an emotion engine to identify the user's emotional state from their speech. The emotion engine identifies speech features associated with emotion and makes an emotion judgment based on them.

[0665] Step 4:

[0666] Based on the translated text and sentiment analysis results, the server utilizes a subtitle editing suggestion unit to propose an appropriate subtitle style to the user. This suggestion adjusts the subtitle's color, size, font, and position to match the sentiment.

[0667] Step 5:

[0668] Users can review the subtitle style suggested by the server through the user interface and make changes as needed. Sentiment-based customization options are provided during this process.

[0669] Step 6:

[0670] The server applies the user-defined subtitle style to the video data and uses an image generation unit to generate emotion-related visual content along with the translated subtitles. This includes illustrations and graphics appropriate to the scene.

[0671] Step 7:

[0672] The terminal receives the final subtitled video and generated image data from the server and renders them. The terminal takes into account the user's display settings and viewing conditions to provide the viewer with optimized video.

[0673] (Example 2)

[0674] 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".

[0675] Conventional speech analysis systems faced challenges in providing real-time multilingual support and visual representations that reflected user emotions. Furthermore, the visibility of subtitles and their integration with the visuals were often insufficient, resulting in a limited user experience.

[0676] 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.

[0677] In this invention, the server includes an analysis means for receiving audio signals and converting them into text data in real time, a conversion means for translating the text data into multiple languages, and an editing suggestion means for proposing subtitle styles that take legibility into consideration based on the translated text data. This makes it possible to provide multilingual audio translation and visually superior video expression based on emotion in real time.

[0678] "Analysis means" refers to a device that receives audio signals and converts them into text data in real time.

[0679] A "conversion device" is a device that has the function of translating text data into multiple languages.

[0680] An "editing suggestion device" is a device that has the function of suggesting a subtitle style that takes readability into consideration based on translated text data.

[0681] "Display means" refers to a device that has the function of applying the proposed subtitle style to video data.

[0682] An "emotion analysis device" is a device that analyzes the user's emotional state from audio data and adjusts the visual representation according to that emotion.

[0683] A "generation means" is a device that has the function of generating image data related to text data and inserting it into video data.

[0684] The present invention relates to a system configuration including a server, a terminal, and a user interface. This system provides the functionality to analyze audio data in real time and integrate translation, sentiment analysis, and visual representation. The software used by the server to receive audio signals, analyze them, and convert them into text data includes an audio analysis algorithm incorporating a generative AI model.

[0685] The analyzed text data is translated into multiple languages ​​by a translation unit on the server. Natural language processing techniques are applied here. Generative AI models are used in this translation process, ensuring that nuances and context are accurately preserved.

[0686] On the user terminal, a subtitle editing suggestion system automatically presents subtitle styles that take readability into consideration, based on translation data sent from the server. This allows the user to select or automatically apply the optimal style. The server also has an emotion analysis unit that analyzes the user's emotions from their voice and adjusts the visual representation accordingly. For example, if joy is detected from the user's voice, it suggests a subtitle style with bright colors and generates related positive images.

[0687] Furthermore, the generated subtitles and images are provided to the user through a display device on the terminal. This allows users to create videos with emotionally nuanced, multilingual subtitles in real time. For example, in live broadcasts of international events, it is possible to visually represent emotionally rich comments in each country's language in real time, thereby promoting a stronger understanding and engagement among viewers.

[0688] As an example of a prompt, you can give the system specific instructions such as, "Translate this audio in real time into English, Spanish, and Japanese, and suggest a sentiment-based subtitle style."

[0689] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0690] Step 1:

[0691] The server receives an audio signal from the user and sends it to the audio analysis unit. The input is the user's audio signal, which is converted into text data in real time by the analysis unit. This process uses a generative AI model that leverages deep learning to achieve highly accurate speech recognition. As output, the user's audio is converted into corresponding text data.

[0692] Step 2:

[0693] The server receives text data from the speech analysis unit and passes it to the translation unit. The input is text data, which is translated into multiple specified languages ​​using a translation mechanism. Specifically, natural language processing techniques are used to provide natural translations that preserve context. Generative AI models are again utilized in this process. The output is translated multilingual text.

[0694] Step 3:

[0695] The server provides the translated text received from the translation unit to the subtitle editing suggestion unit. The input is translated text in multiple languages, and based on this data, the editing suggestion means generates a subtitle style optimized for readability. Specifically, it considers the characteristics of the translated text and the user environment to suggest the optimal subtitle color, size, font, position, etc. The output is the suggested subtitle style information.

[0696] Step 4:

[0697] The server performs emotion analysis using audio data. The input is the user's audio data, and the emotion analysis tool determines the emotional state. Specifically, it analyzes the user's emotions from the tone of voice and word choice, and applies emotion-based visual changes to the video as needed. For example, if joy is detected, a subtitle style with brighter colors is selected. The output is the analyzed user emotion information.

[0698] Step 5:

[0699] The terminal receives the final data sent from the server and displays it on the screen. The input consists of subtitle style information, translated text, and associated image data. The terminal uses a display mechanism to render all data based on the user's display settings. Specifically, it renders the optimal image according to the user's visual environment. The output is the image visible to the user.

[0700] (Application Example 2)

[0701] 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".

[0702] In modern visual content distribution, multilingual support and visual expression that responds to the viewer's emotions are crucial. However, there are few systems capable of real-time, high-precision audio-to-text conversion, and generating subtitles and images that take emotional impact into account. Furthermore, displaying translated text in the most appropriate format to match the audience's emotions has been challenging until now.

[0703] 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.

[0704] In this invention, the server includes data analysis means for receiving audio signals and converting them into text data in real time, conversion means for translating the text data into multiple natural languages, and subtitle suggestion means for suggesting subtitle styles that take legibility into consideration based on the translated text data. This makes it possible to provide multilingual visual information in real time that adapts to the emotions of the viewer.

[0705] "Audio signals" are data that represents sound as electrical signals and are used for communication and analysis.

[0706] "Data analysis means" refers to a device or program for analyzing audio signals and converting them into text data in real time.

[0707] "Conversion means" refers to a device or program that has the function of translating text data into a different natural language.

[0708] The "subtitle suggestion method" is a function that suggests ways to display translated text data in a format that is easy to read.

[0709] "Information display means" refers to a device or program for presenting visual information to a user.

[0710] "Image generation means" refers to a device or program for generating relevant image information based on text data and integrating it into visual information.

[0711] "Emotional analysis means" refers to a device or program that extracts emotional information from audio signals and reflects it in the display of visual information.

[0712] This invention is a system that analyzes audio signals in real time, translates them into multiple languages, and then presents them to the audience in a visually easy-to-understand format. The server receives the audio signal and converts it into text data using an audio analysis means. This process uses speech recognition technology such as the Google Cloud Speech-to-Text API.

[0713] The converted text is translated into multiple languages ​​through a translation tool. This translation process utilizes natural language processing technologies such as the Google Translate API to achieve contextually appropriate translations.

[0714] The subtitle suggestion system proposes subtitle styles in a format suitable for visual information to improve readability. This proposal selects appropriate subtitle colors, fonts, and positions based on the video content and viewer sentiment information. During this process, sentiment analysis is performed using tools such as IBM Watson Tone Analyzer to adjust the subtitle colors and display.

[0715] The image generation means generates visual information based on text data, and the information display means integrates this information. Finally, the terminal presents the video in the optimal format for the viewer's display. This allows users to enjoy rich visual content that goes beyond simple subtitles and responds to emotional context.

[0716] As a concrete example, this system can be used in live streaming of international sporting events to provide viewers with real-time subtitles in each language and colorful visuals that reflect the emotions expressed.

[0717] An example of a prompt for a generative AI model is: "Analyze the following audio data and generate translated subtitles based on the emotions you capture. In particular, display subtitles in a bright color when the emotion is joy."

[0718] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0719] Step 1:

[0720] The server receives the audio signal and converts it into text data using speech analysis tools. The input is a real-time audio signal, and the output is the converted text data. The Google Cloud Speech-to-Text API is used to convert the audio to text, and data correction is performed to improve accuracy.

[0721] Step 2:

[0722] The server receives the converted text data and performs multilingual translation using a translation tool. The input is text data, and the output is multiple translated natural language data. The Google Translate API is used to generate contextually natural translation results.

[0723] Step 3:

[0724] The server passes the translated text data to the subtitle suggestion system, which then proposes the most suitable subtitle style for the visual information. The input is the translated text data and the results of sentiment analysis, while the output is a style proposal including subtitle color, font, and position. Sentiment analysis is performed using IBM Watson Tone Analyzer to determine the proposed style, taking legibility into consideration, and this analysis is used in the subtitle suggestion.

[0725] Step 4:

[0726] The server uses the generated subtitle style to apply it to the video data via the information display device. The input is a proposed subtitle style, and the output is visual information with subtitles. The terminal renders and presents it to the viewer in the optimal format according to the display settings.

[0727] Step 5:

[0728] The server uses image generation means to generate visual aids based on text data. The input is text data and the results of sentiment analysis, and the output is customized image data according to the sentiment. This allows the system to analyze the data, render appropriate visual information, and integrate it into the video.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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.

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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."

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] 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.

[0749] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0750] The following is further disclosed regarding the embodiments described above.

[0751] (Claim 1)

[0752] A voice analysis means that receives an audio signal and converts it into text data in real time,

[0753] A translation means for translating the aforementioned text data into multiple languages,

[0754] A subtitle editing suggestion means that proposes a subtitle style that takes visibility into consideration based on the translated text data,

[0755] A display means for applying the proposed subtitle style to video data,

[0756] Image generation means for generating image data related to the text data and inserting it into the video data,

[0757] A system that includes this.

[0758] (Claim 2)

[0759] The system according to claim 1, wherein the voice analysis means analyzes the voice signal in real time and has a correction means for reducing misrecognition.

[0760] (Claim 3)

[0761] The system according to claim 1, wherein the subtitle editing suggestion means has the function of dynamically suggesting the position, color, and font of subtitles based on the content of the video scene.

[0762] "Example 1"

[0763] (Claim 1)

[0764] A voice analysis means that receives an audio signal and converts it into string data in real time,

[0765] A translation means for translating the aforementioned string data into multiple languages,

[0766] A subtitle editing suggestion means that proposes a subtitle style that takes visibility into consideration based on the translated string data,

[0767] A display means for applying the proposed subtitle style to visual data,

[0768] An image generation means for generating visual information related to the aforementioned string data and inserting it into the aforementioned visual data,

[0769] Means for using natural language processing technology in multilingual translation and subtitle style proposals,

[0770] Image generation means including a generative model that synthesizes relevant visual information based on prompt statements,

[0771] A system that includes this.

[0772] (Claim 2)

[0773] The system according to claim 1, wherein the voice analysis means analyzes the voice signal in real time and has a correction means for reducing misrecognition.

[0774] (Claim 3)

[0775] The system according to claim 1, wherein the subtitle editing suggestion means has the function of dynamically suggesting the position, color, and font of subtitles based on the content of the video scene.

[0776] "Application Example 1"

[0777] (Claim 1)

[0778] A voice analysis means that receives an audio signal and converts it into encoded information in real time,

[0779] Translation means for converting the encoded information into multiple languages,

[0780] A code editing proposal means that proposes a display style that takes visibility into consideration based on the converted coded information,

[0781] A presentation means for applying the proposed display style to visual information,

[0782] Image generation means for generating image data related to the encoded information and inserting it into the visual information,

[0783] A material generation means for generating and displaying related visual materials based on the aforementioned encoded information,

[0784] A system that includes this.

[0785] (Claim 2)

[0786] The system according to claim 1, wherein the voice analysis means analyzes the voice signal in real time, has a correction means for reducing misrecognition, and further has a function for displaying the generated image data.

[0787] (Claim 3)

[0788] The system according to claim 1, wherein the code editing suggestion means has the function of variably suggesting the position, color, and shape of the display based on the content of the visual information, and integrates the generated visual material into the visual information.

[0789] "Example 2 of combining an emotion engine"

[0790] (Claim 1)

[0791] An analysis means that receives an audio signal and converts it into text data in real time,

[0792] A conversion means for translating the aforementioned text data into multiple languages,

[0793] An editing suggestion means that proposes a subtitle style that takes visibility into consideration based on the translated text data,

[0794] A display means for applying the proposed subtitle style to video data,

[0795] An emotion analysis means that analyzes emotional states from audio data and adjusts visual representations according to those emotions,

[0796] A generation means for generating image data related to the text data and inserting it into the video data,

[0797] A system that includes this.

[0798] (Claim 2)

[0799] The system according to claim 1, wherein the analysis means analyzes the audio signal in real time and has a correction device that reduces misrecognition.

[0800] (Claim 3)

[0801] The system according to claim 1, wherein the editing suggestion means has the function of dynamically suggesting the position, color, and font of subtitles based on the content of the video scene.

[0802] "Application example 2 when combining with an emotional engine"

[0803] (Claim 1)

[0804] A data analysis means that receives audio signals and converts them into text data in real time,

[0805] A conversion means for translating the aforementioned text data into multiple natural languages,

[0806] A subtitle suggestion means that proposes a subtitle style that takes visibility into consideration based on the translated text data,

[0807] Information display means for applying the aforementioned subtitle style to visual information,

[0808] Image generation means for generating image information related to the aforementioned text data and inserting it into visual information,

[0809] An emotion analysis means for extracting emotional information from the aforementioned audio signal and reflecting it in the selection of subtitle colors and images,

[0810] A system that includes this.

[0811] (Claim 2)

[0812] The system according to claim 1, wherein the voice analysis means analyzes the voice signal in real time and has a correction means for reducing misrecognition.

[0813] (Claim 3)

[0814] The system according to claim 1, wherein the subtitle suggestion means has the function of dynamically suggesting the position, color, and typeface of subtitles based on the content of visual information. [Explanation of Symbols]

[0815] 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 voice analysis means that receives an audio signal and converts it into encoded information in real time, Translation means for converting the encoded information into multiple languages, A code editing proposal means that proposes a display style that takes visibility into consideration based on the converted coded information, A presentation means for applying the proposed display style to visual information, Image generation means for generating image data related to the encoded information and inserting it into the visual information, A material generation means for generating and displaying related visual materials based on the aforementioned encoded information, A system that includes this.

2. The system according to claim 1, wherein the voice analysis means analyzes the voice signal in real time, has a correction means for reducing misrecognition, and further has a function for displaying the generated image data.

3. The system according to claim 1, wherein the code editing suggestion means has the function of variably suggesting the position, color, and shape of the display based on the content of the visual information, and the generated visual material is integrated into the visual information.

Images