System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving audio information and performing real-time speech recognition; image analysis means for extracting characters from video information; generation and AI means for translating a speech recognition result and the extracted characters into a desired language; means for generating new video information including the translated speech recognition result and characters; and means for performing real-time streaming distribution of the translated video information to a viewer.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] While online education has become increasingly common due to the COVID-19 pandemic, language barriers remain, making it difficult for students and participants who speak different languages ​​to receive equal access to high-quality education. There is also a need for systems that can translate information, including text written on whiteboards and blackboards, in real time during lectures and classes, convert it into the appropriate language, and deliver it to viewers. Furthermore, it is necessary to process this information in real time and deliver it to viewers accurately and without delay. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means: a system including means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, and means for streaming the translated video data to viewers in real time. Furthermore, the system also includes a function for extracting and translating characters written on a whiteboard or blackboard in real time, and a function for allowing the user to specify the desired translation language.

[0006] "Audio data" refers to digital information captured as an audio signal, typically captured through a device such as a microphone.

[0007] "Speech recognition" is a technology that analyzes acquired voice data and converts it into text data.

[0008] "Video data" refers to digital information acquired as a video signal, typically captured through a device such as a camera.

[0009] "Extracting characters" refers to the process of identifying character information from video data and extracting it as text data.

[0010] "Image analysis" is a technology that analyzes video data and recognizes specific information (such as characters or shapes).

[0011] "Generative AI" is an artificial intelligence technology that generates new data based on specific input data (such as voice or text).

[0012] "Translation" is the process of converting text or audio in one language into text or audio in another language.

[0013] "New video data" refers to video data generated by overlaying additional information (for example, translated text) on the original video data.

[0014] "Streaming" refers to the continuous transmission of data over a network in real time, allowing recipients to consume the data at the same time.

[0015] A "viewer" is a user who can receive and view video data provided by streaming distribution. [Brief explanation of the drawings]

[0016] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0020] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0021] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[0038] Server Operation

[0039] The server processes the audio and video data received from the source of online classes and lectures. First, the audio data is acquired in real time and converted into text data using a speech recognition engine. At the same time, text written on a whiteboard or blackboard is extracted from the video data using image analysis. This allows the content of the class or lecture to be organized as text data.

[0040] Next, the acquired text data is translated using generative AI into the user's desired language. The translation results include both the content obtained through speech recognition and the characters extracted through image analysis. New video data is generated based on the translated text data, and the translation results are overlaid on this video data.

[0041] Finally, the server sends the new translated video data to the user's device for real-time streaming, allowing the user to watch the lecture or presentation in their preferred language.

[0042] Device behavior

[0043] The terminal (user device) connects to the server and receives real-time streaming data of classes and lectures. The user operates the terminal to select the desired lecture or presentation and make the necessary settings. The video data sent from the server is received in real time and the video is displayed on the terminal screen.

[0044] The device also has the ability to adjust the video quality and volume based on the user's settings, and also supports the user's choice of translation language, sending this information along with the connection request to the server.

[0045] User operations

[0046] Users can participate in online classes or lectures using a website or dedicated application. First, they access the website and select the lecture or presentation they want. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[0047] At the start of a class or lecture, the user's device connects to the server and receives real-time streaming data. The user can then view the video with the translated content overlaid. The playback speed and volume can also be adjusted as needed.

[0048] Specific examples

[0049] Example 1: Watching online lectures from a Japanese university translated into English

[0050] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[0051] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the voice data in real time and extracts the characters written on the whiteboard.

[0052] 3. The server's generation AI translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time.

[0053] 4. User A watches the lecture translated into English in real time through his / her terminal.

[0054] Example 2: Translating a Korean business seminar into Spanish and watching it

[0055] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[0056] 2. User B's device sends a connection request to the server, and the server receives the seminar streaming data. The server performs real-time speech recognition and extracts the text displayed on the slides and whiteboard.

[0057] 3. The server's generation AI translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time.

[0058] 4. User B watches the seminar translated into Spanish in real time through his terminal.

[0059] This allows users to overcome language barriers and access high-quality education and information from around the world in real time.

[0060] The processing flow will be explained below.

[0061] Server Processing

[0062] Step 1:

[0063] The server receives a connection request from a user for an online class or lecture. The request includes the user ID, the desired class / lecture ID, and the desired translation language.

[0064] Step 2:

[0065] The server receives live video and audio data of classes and lectures from the source, and converts the received data into a format that can be processed in real time.

[0066] Step 3:

[0067] The server activates an AI engine and performs real-time speech recognition on the voice data, converting the recognized content into text data.

[0068] Step 4:

[0069] The server uses image analysis to extract text written on the whiteboard or blackboard from the video data, and this text data is also saved as text.

[0070] Step 5:

[0071] The server's AI translates the speech recognition results and extracted characters into the specified language. The translation process is performed in real time, and the converted text is generated.

[0072] Step 6:

[0073] The server generates new video data using the translated text, which includes a process of overlaying the translation results onto the video.

[0074] Step 7:

[0075] The server streams the translated video data to the viewer in real time, controlling the data transmission to the user's device to minimize delays.

[0076] Terminal handling

[0077] Step 1:

[0078] The terminal (user device) sends a connection request to the server in response to a user's operation. The request includes the user ID, the class / lecture ID, and the desired translation language.

[0079] Step 2:

[0080] The device receives real-time streaming data sent from the server, which is then instantly decoded and converted into a playable format.

[0081] Step 3:

[0082] The device plays the video data and displays it for the user to view, with the translated text overlaid on the video.

[0083] Step 4:

[0084] The device has the ability to adjust video quality, volume, etc. based on user settings. Users can adjust these parameters through the settings menu.

[0085] User operations

[0086] Step 1:

[0087] Users access online classes or lectures using a website or dedicated application. Users select the lecture or lecture they want.

[0088] Step 2:

[0089] The user selects the translation language and other settings (image quality, volume, etc.) that are included in the request sent to the server.

[0090] Step 3:

[0091] Users can watch the live stream through their devices and adjust the playback speed and volume as needed while watching.

[0092] Step 4:

[0093] Users can check the translation results in the video to understand the content of the class or lecture, and can also perform other operations on the screen as needed.

[0094] At each step, the server, terminal, and user work together to create a system that provides translated video in real time.

[0095] Example 1

[0096] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0097] In modern society, online classes and lectures are becoming more and more common, creating a demand for systems that allow users to watch classes and lectures in different languages. However, existing systems often only support a limited number of languages ​​and lack real-time translation capabilities. Furthermore, few systems offer the ability to translate text information contained in videos or provide easy user settings. This presents a challenge for users, making it difficult to smoothly understand the content of classes and lectures in their own language.

[0098] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0099] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, artificial intelligence means for translating the voice recognition results and the extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, a terminal for displaying the video data reflecting the user's desired settings, and means for streaming the translated video data to viewers in real time. This allows users to view classes and lectures in their desired language in real time, making it easy to acquire education and information beyond language barriers.

[0100] "Audio data" refers to data that represents an audio signal in digital form.

[0101] "Speech recognition" refers to the technology of analyzing voice data and converting its contents into text data.

[0102] "Video data" refers to data that represents visual information in digital form.

[0103] "Image analysis" refers to a technique for extracting specific information (such as text) from video data.

[0104] "Generative AI" refers to a system that uses artificial intelligence techniques to perform a specific task (e.g., translation).

[0105] "Translation" refers to the conversion of text data written in one language into another language.

[0106] "Users" refer to people who use this system to watch online classes and lectures.

[0107] "Terminal" refers to a device used by a user (for example, a PC or smartphone).

[0108] "Streaming distribution" refers to a technology that transmits digital content over a network in real time, allowing the recipient to view it in real time.

[0109] "Whiteboard or blackboard" refers to a board-shaped writing surface used in classes or lectures.

[0110] "New video data" refers to the reprocessed video data that includes the translated speech recognition results and text.

[0111] A "receive request" refers to a user requesting a server to send data.

[0112] "Reflecting settings" refers to applying the user's desired conditions (for example, translation language and image quality settings) to the system.

[0113] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[0114] Server Operation

[0115] The server processes audio and video data from the source of online classes and lectures. First, the server acquires the audio data received from the source in real time and converts it into text data using a speech recognition engine (e.g., cloud speech recognition API). At the same time, the server extracts the text written on the slab from the video data using image analysis (e.g., image analysis library). This allows the content of the class or lecture to be organized as text data.

[0116] The server then uses a generative AI model (e.g., a generative AI engine) to translate the acquired text data into the user's desired language. The translation results include both the content obtained through speech recognition and the characters extracted through image analysis. The server then generates new video data based on the translated text data, and the translation results are overlaid on the video data.

[0117] Finally, the server sends the new translated video data to the user's device for real-time streaming, allowing the user to watch the lecture or presentation in their preferred language.

[0118] Device behavior

[0119] The terminal (user device) connects to the server and receives real-time streaming data of classes and lectures. The user operates the terminal to select the desired class or lecture and make the necessary settings. The terminal receives the video data sent from the server in real time and displays the video on the terminal screen. The terminal also has the function to adjust the video quality and volume based on the user's settings, and supports the selection of the user's preferred translation language. This information is sent along with the connection request to the server.

[0120] User operations

[0121] Users can participate in online classes or lectures using a website or dedicated application. First, users access the system and select the class or lecture they want to attend. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[0122] When a class or lecture begins, the user's device connects to the server and receives real-time streaming data. The user can then view the video with the translated content overlaid. The user can also adjust the playback speed and volume as needed.

[0123] Specific examples

[0124] Example 1: Watching online lectures from a Japanese university translated into English

[0125] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[0126] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the audio data in real time and extracts the characters written on the board.

[0127] 3. The server's generation AI translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time.

[0128] 4. User A watches the lecture translated into English in real time through his / her terminal.

[0129] Example 2: Translating a Korean business seminar into Spanish and watching it

[0130] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[0131] 2. User B's device sends a connection request to the server, and the server receives the streaming data of the seminar. The server performs real-time speech recognition and extracts the characters displayed on the slides and boards.

[0132] 3. The server's generation AI translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time.

[0133] 4. User B watches the seminar translated into Spanish in real time through his terminal.

[0134] This allows users to overcome language barriers and access high-quality education and information from around the world in real time. An example of a translation prompt is "Translate the following Japanese text into English: 'Hello, everyone. Today's math class will begin.'"

[0135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0136] Step 1:

[0137] The server receives the audio and video data.

[0138] Specifically, the server receives audio and video data in real time from the source of online classes and lectures. At this time, the audio and video data are sent in streaming format through a specific port on the server (e.g., TCP port 8000). The server receives the data using WebSocket and temporarily stores it in a buffer.

[0139] Input: Audio and video data from the source

[0140] Output: Audio and video buffers

[0141] Step 2:

[0142] The server converts the voice data into text data.

[0143] The server sends the received voice data to a cloud speech recognition API, which converts the voice data into text data in real time. The speech recognition engine analyzes the voice signal and converts the content into appropriate text.

[0144] Input: Audio data buffer

[0145] Output: Text data

[0146] Step 3:

[0147] The server extracts the text from the video data.

[0148] The server analyzes the video data using an image analysis library and extracts characters written on a board (whiteboard or blackboard). An image processing algorithm is used to detect character regions and perform character recognition. The character information extracted from the video data is then saved as text data.

[0149] Input: Video data buffer

[0150] Output: Text data of extracted characters

[0151] Step 4:

[0152] The server translates the text data.

[0153] The server uses a generative AI model (e.g., a generative AI engine) to translate text data obtained through speech recognition and image analysis into the user's desired language. The text data is translated by inputting the specified prompt into the generative AI model.

[0154] Input: Text data obtained through voice recognition and image analysis, translation language desired by the user

[0155] Output: Translated text data

[0156] Example prompt: "Translate the following Japanese text into English: 'Hello everyone. Today we will begin our math class.'"

[0157] Step 5:

[0158] The server generates the translated text as new video data.

[0159] The server overlays the translated text data onto the video data to generate new video data. To do this, the server performs text overlay processing on the video frames and performs rendering.

[0160] Input: translated text data, original video data

[0161] Output: New video data

[0162] Step 6:

[0163] The server transmits new video data to the terminal.

[0164] The server then streams the newly generated video data to the device in real time using a protocol such as RTMP (Real-Time Messaging Protocol).

[0165] Input: New video data

[0166] Output: Streaming video data

[0167] Step 7:

[0168] The terminal displays the video data.

[0169] The device receives new video data from the server and displays it in real time. The device's browser or dedicated application decodes the video and displays it on the screen.

[0170] Input: New video data in streaming format

[0171] Output: The image the user sees

[0172] Step 8:

[0173] The user performs the necessary settings and operations.

[0174] While watching a class or lecture, users can change settings and perform other operations on their devices, such as changing the playback speed, adjusting the volume, or changing the translation language. These setting changes may be resent to the server as requests.

[0175] Input: User actions

[0176] Output: Updated configuration information and its reflection

[0177] (Application example 1)

[0178] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0179] When it comes to work procedures and maintenance operations within factories, language barriers can lead to reduced efficiency and increased risk of operational errors. This issue is particularly pronounced in environments with multinational workers or when introducing new machinery. Furthermore, traditional methods lack a means to simultaneously provide real-time translation and instructions, making it difficult to improve work efficiency.

[0180] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0181] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, means for streaming the translated video data to viewers in real time, means for generating and outputting voice guidance in real time, and means for presenting the voice guidance and translation results to an automation system. This enables real-time multilingual instructions and translation within the factory, improving work efficiency and safety.

[0182] "Audio data" is data in digital or analog format that contains audio information.

[0183] "Speech recognition" is a technology in which a computer analyzes human speech and converts it into text data.

[0184] "Video data" is digital or analog data that contains visual information such as images or videos.

[0185] "Image analysis" is a technology that detects and recognizes characters and objects from video data.

[0186] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate new data and information.

[0187] "Translation" is the act of converting content expressed in one language into a different language.

[0188] "Real-time" means processing occurs immediately with little delay.

[0189] "Streaming delivery" is a technology that transmits data continuously and makes it available to the recipient immediately.

[0190] "Audio description" refers to technology that provides specific information or instructions in audio form.

[0191] An "automation system" is a configuration of equipment and software that performs a specific task or process automatically.

[0192] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[0193] Server Operation

[0194] The server is connected to the factory's automation system. First, it captures audio and video data received from microphones and cameras in real time. The audio data is converted into text data by a voice recognition engine. Image analysis software is used to detect characters and objects in the video data and extract information about them.

[0195] Next, the generative AI system translates the acquired text data and image analysis results into the user's desired language. This translation includes both the content obtained through voice recognition and the content extracted through image analysis. An audio guide is generated based on the translated text data and overlaid on the new video data.

[0196] Finally, the server streams the new translated video data and audio guide in real time using libraries such as OpenCV, Pytesseract, SpeechRecognition, Google Trans, and gTTS. The server also sends the translation results to the factory's automation systems, which output the audio guide and video.

[0197] Device behavior

[0198] The terminal (user's device) connects to the server and receives translated video data and audio guidance in real time. The user operates the terminal to select the desired work procedure or maintenance instructions and make the necessary settings. The video data and audio guidance sent from the server are received in real time and provided to the user through the terminal's screen and speaker.

[0199] The device also has the ability to adjust the video quality and volume based on the user's settings, and also supports the user's choice of translation language, sending this information along with the connection request to the server.

[0200] User operations

[0201] Users access the automated systems in factories using a website or dedicated application to receive work procedures and maintenance instructions. First, they access the system and select the desired work procedures or instructions. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[0202] At the start of the work, the user's device connects to the server and receives real-time streaming data. The user can then view the video and audio guide with the translated content overlaid in real time. The user can also adjust the playback speed and volume as needed.

[0203] Specific examples

[0204] Example 1: Translating and watching the operating procedures for a new machine in a Japanese factory

[0205] 1. User A accesses a dedicated application to learn the operating procedures for a new machine in the factory, selects the operating procedures, and selects English as the desired translation language.

[0206] 2. User A's device sends a connection request to the server, and the server receives the audio and video data in real time. The server recognizes the audio data and extracts text information from the video data.

[0207] 3. The server's generation AI translates the Japanese audio and text into English and generates new video data and audio guide. The translated data is streamed to User A's device in real time.

[0208] 4. User A can watch and listen to the operating procedures translated into English in real time through the terminal.

[0209] Prompt example

[0210] Capture Japanese audio and video, translate it into English in real time, and display it.

[0211] The most accurate translation possible

[0212] Ability to overlay text on video

[0213] Function that also provides audio output

[0214] In this way, the present invention enables real-time multilingual instructions and translation within a factory, thereby improving work efficiency and safety.

[0215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0216] Step 1:

[0217] The server captures audio and video data in real time from microphones and cameras in the factory. The audio data input includes audio instructions and work procedures in the factory, while the video data input includes images of workers and machines.

[0218] Step 2:

[0219] The server analyzes the acquired voice data using a voice recognition engine and converts it into text data. In this process, SpeechRecognition is used as the voice recognition engine, which analyzes the voice waveform data and outputs the corresponding text.

[0220] Step 3:

[0221] The server analyzes the video data using image analysis software (Pytesseract and OpenCV) and extracts text information. In this step, it detects characters and signs in the video and outputs them as text data.

[0222] Step 4:

[0223] The server converts the text data obtained from voice recognition and image analysis into the specified translation language using a generative AI system. This process uses Google Trans as the translation engine and outputs the text data translated from Japanese to the desired language, such as English.

[0224] Step 5:

[0225] The server generates new video data based on the translated text data and overlays the translated text information on the video data. It also generates an audio guide and creates audio data based on the text information. gTTS is used to generate the audio guide. The output of this step is the translated video data and audio guide.

[0226] Step 6:

[0227] The server streams the generated translated video data and audio guide in real time. The device receives this data and allows the user to view instructions for the desired work procedure or maintenance guide. The device receives the data sent from the server as input and provides the user with visual and audio information as output.

[0228] Step 7:

[0229] The user operates the device to adjust settings such as video quality, volume, and translation language. Based on the user's input, the device sends a request to the server to make the necessary adjustments. The user can then view the video with the translated content overlaid and a real-time audio guide as they work.

[0230] In this way, specific data processing and calculations are performed at each step of the server, terminal, and user, and real-time multilingual work instructions are provided.

[0231] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0232] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[0233] Server Operation

[0234] The server processes the audio and video data received from the source of online classes and lectures. First, the audio data is acquired in real time and converted into text data using a speech recognition engine. At the same time, text written on a whiteboard or blackboard is extracted from the video data using image analysis. This allows the content of the class or lecture to be organized as text data.

[0235] Next, the acquired text data is translated using generative AI into the user's desired language. The translation results include both the content obtained through speech recognition and the characters extracted through image analysis. New video data is generated based on the translated text data, and the translation results are overlaid on this video data.

[0236] Furthermore, the server uses an emotion engine to recognize the user's emotions in real time from their facial expressions, tone of voice, and other factors. Based on the recognized emotion data, the translation results are processed to adapt to the user's emotions. The server then transmits the new translated video data to the user's device for streaming in real time. This allows users to watch classes and lectures in their preferred language and receive the optimal expressions based on their emotions.

[0237] Device behavior

[0238] The terminal (user device) connects to the server and receives real-time streaming data of classes and lectures. The user operates the terminal to select the desired lecture or presentation and make the necessary settings. The video data sent from the server is received in real time and the video is displayed on the terminal screen.

[0239] The device is equipped with a camera and microphone to recognize the user's emotions, detecting the user's facial expressions and tone of voice and sending the data to the emotion engine. The emotion engine then analyzes this data and sends the recognition results to the server. The device also has the ability to adjust the image quality and volume based on the user's settings. It also supports the user's choice of translation language, and sends this information along with the connection request to the server.

[0240] User operations

[0241] Users can participate in online classes or lectures using a website or dedicated application. First, they access the website and select the lecture or presentation they want. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[0242] At the start of a class or lecture, the user's device connects to the server and receives real-time streaming data. The user can then watch the video with the translated content overlaid on it. As the user watches, the emotion engine recognizes the user's emotions, and the server adjusts the translation results and video presentation accordingly. Settings such as playback speed and volume can also be adjusted as needed.

[0243] Specific examples

[0244] Example 1: Translating online lectures from a Japanese university into English and viewing them according to your emotions

[0245] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[0246] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the audio data in real time and extracts the characters written on the whiteboard.

[0247] 3. The AI ​​translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time. The emotion engine recognizes User A's emotions and adjusts the translation results accordingly.

[0248] 4. User A watches the lecture in real time through the device, which is translated into English and presented in the most appropriate expression according to the user's emotions.

[0249] Example 2: Translating a Korean business seminar into Spanish and viewing it according to your emotions

[0250] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[0251] 2. User B's device sends a connection request to the server, and the server receives the seminar streaming data. The server performs real-time speech recognition and extracts the text displayed on the slides and whiteboard.

[0252] 3. The server's generation AI translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time. The emotion engine recognizes User B's emotions and adjusts the translation results accordingly.

[0253] 4. User B watches the seminar in real time through their device, which is translated into Spanish and presented in the most appropriate expressions according to their emotions.

[0254] This allows users to overcome language barriers and obtain high-quality education and information in real time in a way that best suits their own emotions.

[0255] The processing flow will be explained below.

[0256] Server Processing

[0257] Step 1:

[0258] The server receives a connection request from a user for an online class or lecture. The request includes the user ID, the desired class / lecture ID, and the desired translation language.

[0259] Step 2:

[0260] The server receives live video and audio data of classes and lectures from the source, and converts the received data into a format that can be processed in real time.

[0261] Step 3:

[0262] The server's speech recognition engine analyzes the received voice data and converts it into text data, which is then transcribed in real time.

[0263] Step 4:

[0264] The server's image analysis engine detects text written on the whiteboard and blackboard in the video data and converts it into text data, allowing the entire lecture content to be organized as text information.

[0265] Step 5:

[0266] The server's AI converts the voice recognition results and characters extracted through image analysis into the specified translation language. The translation results are generated in real time and saved as new text data.

[0267] Step 6:

[0268] The server's video generation engine generates new video data based on the translated text data, and the translation results are overlaid on the generated video data.

[0269] Step 7:

[0270] The server's emotion engine receives and analyzes the user's emotion data (facial expressions, tone of voice, etc.), and adjusts the way the translation results are expressed based on the emotion data.

[0271] Step 8:

[0272] The server streams the new translated and emotion-adapted video data to the device in real time, providing the data to the viewer without delay.

[0273] Terminal handling

[0274] Step 1:

[0275] The terminal (user device) sends a connection request to the server through a website or application. The request includes the user ID, the desired class / lecture ID, and the desired translation language.

[0276] Step 2:

[0277] The device receives real-time streaming data sent from the server, and the received video data is immediately decoded and converted into a playable format.

[0278] Step 3:

[0279] The device displays the video data on the screen and plays it for the user to view, with the translated text appropriately overlaid on the video.

[0280] Step 4:

[0281] The device is equipped with a camera and microphone to recognize the user's emotions in real time, and this data is sent to the emotion engine.

[0282] Step 5:

[0283] The device receives feedback from the emotion engine and adjusts the way the image is displayed and the translation results as needed.

[0284] Step 6:

[0285] The device provides the ability to adjust video quality, volume, playback speed, etc. based on user settings.

[0286] User operations

[0287] Step 1:

[0288] Users access online classes or lectures using a website or dedicated application and select the lecture or lecture they want.

[0289] Step 2:

[0290] The user selects the translation language and other settings (quality, volume, playback speed, etc.) that are included in the connection request to the server.

[0291] Step 3:

[0292] Users watch the live stream through their devices. The emotion engine recognizes the user's emotions while watching, and the server adjusts the translation results and visual expressions accordingly.

[0293] Step 4:

[0294] Users can watch the video in real time, adjust the playback speed and volume as needed, and check that the translation results are optimized for emotion.

[0295] In this way, the server, terminal, and user work together at each step to create a system that provides translated and emotion-adapted video in real time.

[0296] Example 2

[0297] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0298] Conventional online classes and lecture systems make it difficult for users who speak different languages ​​to understand the content in real time. Furthermore, they are unable to provide appropriate expressions based on the user's emotions, making it difficult to improve the user's understanding and satisfaction. Furthermore, they lack emotion recognition functionality that uses the user's facial expressions and tone of voice, making it impossible to provide information in an optimal format for each individual user. This invention solves the problem of improving the user experience by removing language barriers and providing appropriate expressions based on the user's emotions in online classes and lecture systems.

[0299] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0300] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and the extracted characters into a desired language, means for adapting the translation results based on the user's emotions, and means for streaming the translated video data to viewers in real time. This makes it possible to provide understandable information in real time to users who speak different languages ​​and to optimally express themselves based on their emotions.

[0301] "Audio data" is a digital representation of audio collected from online classes, lectures, etc.

[0302] "Speech recognition" is a technology that analyzes voice data and converts it into corresponding text data.

[0303] "Video data" is digital information representing the video stream of an online class or lecture.

[0304] "Image analysis" is a technology that identifies and extracts specific information (for example, text) from video data.

[0305] "Generative AI" is an automated artificial intelligence system that translates received voice recognition and image analysis results into a specified language.

[0306] "Translation" is the process of converting text from one language into another.

[0307] "New video data" refers to the regenerated video stream that includes the translated speech recognition results and text.

[0308] "Emotion recognition" is a technology that analyzes a user's facial expressions and tone of voice to estimate their emotional state.

[0309] "Real-time delivery" is a streaming technology that provides processed data to users almost instantly without delay.

[0310] "User" refers to an individual who uses this system to view online classes or lectures.

[0311] A "display device" is a device that displays letters and figures, such as a whiteboard or blackboard.

[0312] A "reception request" is an action in which a user requests a server to receive audio data and video data.

[0313] "Image quality" is a measure of the visual quality of video data.

[0314] "Volume" is a measure of the acoustic level (loudness) of audio data.

[0315] MODE FOR CARRYING OUT THE INVENTION

[0316] This invention is a system that translates online classes and lectures into multiple languages ​​in real time and provides them in the most appropriate expressions according to the user's feelings. The operation of this system will be explained below from the perspectives of the server, the terminal, and the user.

[0317] Server Operation

[0318] The server performs the following main processes:

[0319] 1. Speech Recognition:

[0320] The server receives audio data in real time from online classes and lectures.

[0321] Use a speech recognition engine (e.g., Google Cloud Speech-to-Text) to convert the voice data into text data.

[0322] Example: Transcribing Japanese lecture audio in real time.

[0323] 2. Image Analysis:

[0324] The server acquires the video data and extracts the text written on the whiteboard or blackboard using image analysis (e.g., Google Cloud Vision API).

[0325] For example: Reading lecture slides and what is written on the blackboard.

[0326] 3. Translation:

[0327] Using generative AI (e.g., OpenAI GPT-4), the acquired text data is translated into the user's desired language.

[0328] Example: Translating Japanese text into English in real time.

[0329] 4. Image Generation:

[0330] Based on the translated text, new video data is generated and the translation results are overlaid.

[0331] Example: Generate a lecture video with English subtitles.

[0332] 5. Emotion recognition:

[0333] Using an emotion engine (e.g., Affectiva), emotions are recognized from the user's facial expressions and tone of voice.

[0334] The recognized emotion data is used to adapt the expression of the translation results.

[0335] Example: Detect whether the user understands or is unsure and simplify the statement accordingly.

[0336] 6. Real-time streaming:

[0337] The converted video data is streamed to the user's device, and the translation result is adjusted based on the emotion data.

[0338] Example: Delivering lecture videos that are adjusted to make them easier to understand depending on the emotion.

[0339] Device behavior

[0340] The terminal performs the following main processes:

[0341] 1. Connection and setup:

[0342] The terminal connects to the server and the user selects the lecture or speech they wish to attend.

[0343] Example: A user selects a Japanese course from a list of courses and selects the English translation.

[0344] 2. Data reception and display:

[0345] It receives the video data sent from the server and displays it on the screen.

[0346] Example: Play a lecture video with English subtitles on your device.

[0347] 3. Emotional data transmission:

[0348] It uses a camera and microphone to detect the user's facial expressions and tone of voice and sends the data to an emotion engine.

[0349] Example: The user sends confused facial expressions and voice to the emotion engine and sends them to the server.

[0350] 4. Translation Language Settings:

[0351] The user selects the desired translation language and sends that information to the server.

[0352] Example: The user specifies the translation language before the lecture begins.

[0353] User operations

[0354] The user performs the following operations:

[0355] 1. Lectures and presentations:

[0356] The user selects the lecture or speech they want.

[0357] Example: Choose an online course from a Japanese university.

[0358] 2. Configure the settings:

[0359] The user can set the translation language, image quality, etc.

[0360] Example: Select English translation and high quality mode.

[0361] 3. Listening and adjusting:

[0362] Watch the video with the translated content overlaid and adjust the playback speed and volume as needed.

[0363] Example: Adjusting the volume during playback.

[0364] Specific examples

[0365] Example 1: Watching online lectures from a Japanese university translated into English

[0366] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[0367] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the audio data in real time and extracts the characters written on the whiteboard.

[0368] 3. The server translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time. The emotion engine recognizes User A's emotions and adjusts the translation results accordingly.

[0369] 4. User A watches the lecture in real time through the device, which is translated into English and presented in the most appropriate expression according to the user's emotions.

[0370] Example 2: Translating a Korean business seminar into Spanish and viewing it according to your emotions

[0371] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[0372] 2. User B's device sends a connection request to the server, and the server receives the seminar streaming data. The server performs real-time speech recognition and extracts the text displayed on the slides and whiteboard.

[0373] 3. The server translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time. The emotion engine recognizes User B's emotions and adjusts the translation results accordingly.

[0374] 4. User B watches the seminar in real time through their device, which is translated into Spanish and presented in the most appropriate expressions according to their emotions.

[0375] Prompt Sentence Examples

[0376] 1. "I would like to watch online lectures from a Japanese university with the videos translated into English."

[0377] 2. "I would like to watch a video of a Korean business seminar translated into Spanish and have it presented in a way that best suits my emotions."

[0378] This allows users to overcome language barriers and obtain high-quality education and information in real time in a way that best suits their own emotions.

[0379] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0380] Step 1: Receiving voice data and recognizing voice

[0381] Input: Audio data from online classes and lectures.

[0382] Processing: The server receives the voice data in real time using a streaming API, then converts it into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[0383] Output: Text data.

[0384] Specific operation: After the server receives the voice data, it sends the data to the voice recognition engine and immediately generates the corresponding text.

[0385] Step 2: Receiving video data and analyzing images

[0386] Input: Video data from online classes and lectures.

[0387] Processing: The server receives video data in real time using a streaming video API, and then extracts text from the whiteboard or blackboard in the video data using an image analysis tool (e.g., Google Cloud Vision API).

[0388] Output: The extracted character data.

[0389] Specific operation: The server receives the video data and sends it to the image analysis engine to extract text information.

[0390] Step 3: Translating the text data

[0391] Input: Text data of speech recognition results and extracted character data.

[0392] Processing: The server uses a generative AI (e.g., OpenAI GPT-4) to translate the acquired text data into the user's preferred language.

[0393] Output: The translated text data.

[0394] Specific operation: The server passes text data to the translation API and obtains the corresponding translation result.

[0395] Step 4: Generate new video data

[0396] Input: Translated text data.

[0397] Processing: Based on the translated text data, the server generates new video data and overlays the translation results onto the video.

[0398] Output: New video data with the translation overlaid.

[0399] What it does: The server uses a video generation engine to create a new video with the translated text overlaid on it.

[0400] Step 5: Receiving and Recognizing Emotional Data

[0401] Input: User emotion data (facial expression data and tone of voice).

[0402] Processing: The device uses the camera and microphone to capture the user's facial and voice data and sends it to the emotion recognition API. The server recognizes the emotion based on the received data.

[0403] Output: Recognized emotion data.

[0404] Specific operation: The device collects the user's emotional data, analyzes it using an emotion recognition engine, and sends the results to the server.

[0405] Step 6: Adjust translation results based on sentiment

[0406] Input: Translated text data and recognized emotion data.

[0407] Processing: The server adapts the translation results based on the emotion data.

[0408] Output: Sentiment-adapted text data.

[0409] Specific operation: The server uses an adjustment algorithm on the translation text to generate the best translation result according to the sentiment.

[0410] Step 7: Real-time delivery

[0411] Input: New video data with emotion-adapted translation results.

[0412] Processing: The server streams new video data in real time.

[0413] Output: The translated video displayed on the end user's device.

[0414] Specific operation: The server uses a streaming protocol (e.g., WebRTC) to send the generated video to the user device.

[0415] This allows users to view online classes and lectures in real time in a way that is optimal for different languages ​​and emotions.

[0416] (Application example 2)

[0417] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0418] In conventional online classes and online seminars, it has been difficult to provide accurate translations in real time to users who speak different languages. Furthermore, because translation results cannot be adapted to take the user's emotions into account, there is a risk of user understanding and satisfaction decreasing. The present invention aims to solve these problems and provide users with higher quality information by supporting multiple languages ​​and translating according to their emotions.

[0419] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0420] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, means for streaming the translated video data to viewers in real time, emotion estimation means for recognizing user emotions in real time, and means for adapting the translation results based on the recognized emotions, thereby enabling multilingual and emotion-sensitive translation.

[0421] "Audio data" refers to data for recording and transmitting audio as a digital signal.

[0422] "Speech recognition" is a technology that converts voice signals into text data.

[0423] "Video data" refers to data for recording and transmitting video as a digital signal.

[0424] "Image analysis" is the process of extracting specific information from image data.

[0425] "Generative AI" is a technology that uses artificial intelligence technology to generate new data or text based on input data.

[0426] "New video data" refers to new video data that is generated by performing specific processing or adding information to the original video data.

[0427] "Streaming distribution" is a technology that transfers and plays digital data in real time.

[0428] "Emotion estimation" is a technology that analyzes and recognizes a user's emotional state from their facial expressions and voice.

[0429] "Translation adaptation" is the process of adjusting translated text or audio based on the original content and context.

[0430] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[0431] Server Operation

[0432] The server combines multiple technologies to support communication between customers and store staff during online transactions. First, the server captures voice data in real time and converts it into text using a speech recognition engine (e.g., the speech_recognition library). At the same time, it extracts text from video data related to store product information using image analysis (e.g., the OpenCV and Pytesseract libraries). Based on this data, it translates the customer's question into the desired language using generative AI (e.g., the MarianMTModel in the Transformers library).

[0433] Furthermore, the server uses an emotion estimation engine (e.g., the deepface library) to recognize the customer's emotions in real time from their facial expressions and voice tone. Based on the recognized emotion data, the generative AI adapts the translation results and generates new video data, overlaid with a response including the translation results. This translation result is also adjusted based on the context. The generated video data is streamed to the customer's device in real time.

[0434] Device behavior

[0435] The terminal (user's device) connects to the server and receives real-time data on online commercial transactions. The user operates the terminal to select the desired commercial transaction or product information and make the necessary settings. The video and audio data sent from the server is received in real time and the video is displayed on the terminal screen. The terminal is equipped with a camera and microphone to recognize the user's emotions, and through these, the user's facial expressions and tone of voice are detected and the data is sent to the emotion estimation engine. The emotion estimation engine analyzes this data and sends the recognition results to the server. The terminal also has the function to adjust the video quality, volume, etc. based on the user's settings. It also supports the user's selection of the translation language they prefer, and sends this information along with the connection request to the server.

[0436] User operations

[0437] Users participate in online commerce in virtual stores using websites or dedicated applications. First, they access the store and select the desired products or services. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface. When a transaction begins, the user's device connects to the server and receives real-time streaming data. The user can interact in real time with the translated content overlaid on the video. While viewing, an emotion estimation engine recognizes the user's emotions, and the server adjusts the translation results and video presentation accordingly. Settings such as playback speed and volume can also be adjusted as needed.

[0438] Specific examples

[0439] Example 1: Translating a purchase on a Japanese e-commerce site into English and viewing it in a way that responds to emotions

[0440] 1. User A visits a website to purchase a high-quality Japanese home appliance, selects the product, and selects English as the desired translation language.

[0441] 2. User A's device sends a connection request to the server, and the server receives streaming data of product information. The server recognizes the voice data in real time and extracts information about the product.

[0442] 3. The generative AI translates the Japanese audio and text into English, and the translated video data is streamed in real time to User A's device. The emotion estimation engine recognizes User A's emotions and adjusts the translation results accordingly.

[0443] 4. User A receives product information in real time through their device, translated into English and presented in the most appropriate language based on their emotions.

[0444] Example 2: Translating a purchase from a Korean online fashion store into Spanish and providing emotionally relevant content

[0445] 1. User B is interested in Korean fashion and accesses a dedicated application to check products online, selects a product, and selects Spanish as the desired translation language.

[0446] 2. User B's device sends a connection request to the server, and the server receives streaming data of the product. It performs real-time voice recognition and extracts the information displayed on the product tag.

[0447] 3. The server's generation AI translates the Korean audio and text into Spanish, and the translated video data is streamed in real time to User B's device. The emotion estimation engine recognizes User B's emotions and adjusts the translation results accordingly.

[0448] 4. User B uses their device to check product information in real time, which is translated into Spanish and presented in the most appropriate language based on their emotions.

[0449] Prompt Sentence Examples

[0450] markdown

[0451] User says: "What is this product?"

[0452] Product tag information: "Product name: XYZ, Price: 2000 yen, Description: Clothing made with high-quality materials."

[0453] User Sentiment: "Excited"

[0454] Abstract

[0455] The user is asking about a product. Generate an appropriate answer by taking into account the information in the product tags and the user's sentiment. Please keep your answer in a friendly tone.

[0456] answer

[0457] Hello! This is the XYZ product, priced at 2000 yen. It's made with high-quality materials and is very popular!

[0458] The above is a detailed description of the embodiment of the present invention. Through this application example, users can overcome language barriers and receive high-quality services in real time in an optimal manner according to their own emotions.

[0459] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0460] Step 1:

[0461] The server receives voice data from the user terminal in real time. This voice data is a voice signal acquired through a microphone. This voice data is input to a voice recognition engine (for example, the speech_recognition library) and converted into text data. The output is text data of the voice recognition results.

[0462] Step 2:

[0463] The server analyzes the video data received from the device. The video data includes text written on product tags and signboards. This video data is input into an image analysis engine (e.g., OpenCV and Pytesseract libraries) to extract the text from the image. The output is the extracted text data.

[0464] Step 3:

[0465] The server inputs the speech recognition results and extracted text data into a generation AI (e.g., MarianMTModel from the transformers library), which translates the text data into the desired language. The output is the translated text data.

[0466] Step 4:

[0467] The server receives data on the user's facial expressions and tone of voice captured in real time from the device's camera and microphone. This data is input into an emotion estimation engine (e.g., the deepface library) to analyze and recognize the user's emotions. The output is the user's emotion data.

[0468] Step 5:

[0469] The server uses a generation AI to generate new video data based on the translated text data and the user's emotional data. This generation AI creates new video data based on the translation results and overlays the translation results on the new video data. The output is new video data with the translation results overlaid.

[0470] Step 6:

[0471] The server then streams the newly generated video data to the user's device in real time, allowing the user to view the video with the translated content on their device.

[0472] Step 7:

[0473] Users can ask additional questions or change settings while watching the streaming video data on their device, allowing for continuous and smooth business transactions.

[0474] Through the above steps, a system is realized in which the server, terminal, and user work together to provide multilingual support and emotional adaptation in real time.

[0475] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0476] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0477] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0478] [Second embodiment]

[0479] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0480] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0481] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0482] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0483] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0484] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0485] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0486] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0487] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0488] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0489] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0490] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0491] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[0492] Server Operation

[0493] The server processes the audio and video data received from the source of online classes and lectures. First, the audio data is acquired in real time and converted into text data using a speech recognition engine. At the same time, text written on a whiteboard or blackboard is extracted from the video data using image analysis. This allows the content of the class or lecture to be organized as text data.

[0494] Next, the acquired text data is translated using generative AI into the user's desired language. The translation results include both the content obtained through speech recognition and the characters extracted through image analysis. New video data is generated based on the translated text data, and the translation results are overlaid on this video data.

[0495] Finally, the server sends the new translated video data to the user's device for real-time streaming, allowing the user to watch the lecture or presentation in their preferred language.

[0496] Device behavior

[0497] The terminal (user device) connects to the server and receives real-time streaming data of classes and lectures. The user operates the terminal to select the desired lecture or presentation and make the necessary settings. The video data sent from the server is received in real time and the video is displayed on the terminal screen.

[0498] The device also has the ability to adjust the video quality and volume based on the user's settings, and also supports the user's choice of translation language, sending this information along with the connection request to the server.

[0499] User operations

[0500] Users can participate in online classes or lectures using a website or dedicated application. First, they access the website and select the lecture or presentation they want. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[0501] At the start of a class or lecture, the user's device connects to the server and receives real-time streaming data. The user can then view the video with the translated content overlaid. The playback speed and volume can also be adjusted as needed.

[0502] Specific examples

[0503] Example 1: Watching online lectures from a Japanese university translated into English

[0504] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[0505] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the voice data in real time and extracts the characters written on the whiteboard.

[0506] 3. The server's generation AI translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time.

[0507] 4. User A watches the lecture translated into English in real time through his / her terminal.

[0508] Example 2: Translating a Korean business seminar into Spanish and watching it

[0509] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[0510] 2. User B's device sends a connection request to the server, and the server receives the seminar streaming data. The server performs real-time speech recognition and extracts the text displayed on the slides and whiteboard.

[0511] 3. The server's generation AI translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time.

[0512] 4. User B watches the seminar translated into Spanish in real time through his terminal.

[0513] This allows users to overcome language barriers and access high-quality education and information from around the world in real time.

[0514] The processing flow will be explained below.

[0515] Server Processing

[0516] Step 1:

[0517] The server receives a connection request from a user for an online class or lecture. The request includes the user ID, the desired class / lecture ID, and the desired translation language.

[0518] Step 2:

[0519] The server receives live video and audio data of classes and lectures from the source, and converts the received data into a format that can be processed in real time.

[0520] Step 3:

[0521] The server activates an AI engine and performs real-time speech recognition on the voice data, converting the recognized content into text data.

[0522] Step 4:

[0523] The server uses image analysis to extract text written on the whiteboard or blackboard from the video data, and this text data is also saved as text.

[0524] Step 5:

[0525] The server's AI translates the speech recognition results and extracted characters into the specified language. The translation process is performed in real time, and the converted text is generated.

[0526] Step 6:

[0527] The server generates new video data using the translated text, which includes a process of overlaying the translation results onto the video.

[0528] Step 7:

[0529] The server streams the translated video data to the viewer in real time, controlling the data transmission to the user's device to minimize delays.

[0530] Terminal handling

[0531] Step 1:

[0532] The terminal (user device) sends a connection request to the server in response to a user's operation. The request includes the user ID, the class / lecture ID, and the desired translation language.

[0533] Step 2:

[0534] The device receives real-time streaming data sent from the server, which is then instantly decoded and converted into a playable format.

[0535] Step 3:

[0536] The device plays the video data and displays it for the user to view, with the translated text overlaid on the video.

[0537] Step 4:

[0538] The device has the ability to adjust video quality, volume, etc. based on user settings. Users can adjust these parameters through the settings menu.

[0539] User operations

[0540] Step 1:

[0541] Users access online classes or lectures using a website or dedicated application. Users select the lecture or lecture they want.

[0542] Step 2:

[0543] The user selects the translation language and other settings (image quality, volume, etc.) that are included in the request sent to the server.

[0544] Step 3:

[0545] Users can watch the live stream through their devices and adjust the playback speed and volume as needed while watching.

[0546] Step 4:

[0547] Users can check the translation results in the video to understand the content of the class or lecture, and can also perform other operations on the screen as needed.

[0548] At each step, the server, terminal, and user work together to create a system that provides translated video in real time.

[0549] Example 1

[0550] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0551] In modern society, online classes and lectures are becoming more and more common, creating a demand for systems that allow users to watch classes and lectures in different languages. However, existing systems often only support a limited number of languages ​​and lack real-time translation capabilities. Furthermore, few systems offer the ability to translate text information contained in videos or provide easy user settings. This presents a challenge for users, making it difficult to smoothly understand the content of classes and lectures in their own language.

[0552] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0553] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, artificial intelligence means for translating the voice recognition results and the extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, a terminal for displaying the video data reflecting the user's desired settings, and means for streaming the translated video data to viewers in real time. This allows users to view classes and lectures in their desired language in real time, making it easy to acquire education and information beyond language barriers.

[0554] "Audio data" refers to data that represents an audio signal in digital form.

[0555] "Speech recognition" refers to the technology of analyzing voice data and converting its contents into text data.

[0556] "Video data" refers to data that represents visual information in digital form.

[0557] "Image analysis" refers to a technique for extracting specific information (such as text) from video data.

[0558] "Generative AI" refers to a system that uses artificial intelligence techniques to perform a specific task (e.g., translation).

[0559] "Translation" refers to the conversion of text data written in one language into another language.

[0560] "Users" refer to people who use this system to watch online classes and lectures.

[0561] "Terminal" refers to a device used by a user (for example, a PC or smartphone).

[0562] "Streaming distribution" refers to a technology that transmits digital content over a network in real time, allowing the recipient to view it in real time.

[0563] "Whiteboard or blackboard" refers to a board-shaped writing surface used in classes or lectures.

[0564] "New video data" refers to the reprocessed video data that includes the translated speech recognition results and text.

[0565] A "receive request" refers to a user requesting a server to send data.

[0566] "Reflecting settings" refers to applying the user's desired conditions (for example, translation language and image quality settings) to the system.

[0567] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[0568] Server Operation

[0569] The server processes audio and video data from the source of online classes and lectures. First, the server acquires the audio data received from the source in real time and converts it into text data using a speech recognition engine (e.g., cloud speech recognition API). At the same time, the server extracts the text written on the slab from the video data using image analysis (e.g., image analysis library). This allows the content of the class or lecture to be organized as text data.

[0570] The server then uses a generative AI model (e.g., a generative AI engine) to translate the acquired text data into the user's desired language. The translation results include both the content obtained through speech recognition and the characters extracted through image analysis. The server then generates new video data based on the translated text data, and the translation results are overlaid on the video data.

[0571] Finally, the server sends the new translated video data to the user's device for real-time streaming, allowing the user to watch the lecture or presentation in their preferred language.

[0572] Device behavior

[0573] The terminal (user device) connects to the server and receives real-time streaming data of classes and lectures. The user operates the terminal to select the desired class or lecture and make the necessary settings. The terminal receives the video data sent from the server in real time and displays the video on the terminal screen. The terminal also has the function to adjust the video quality and volume based on the user's settings, and supports the selection of the user's preferred translation language. This information is sent along with the connection request to the server.

[0574] User operations

[0575] Users can participate in online classes or lectures using a website or dedicated application. First, users access the system and select the class or lecture they want to attend. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[0576] When a class or lecture begins, the user's device connects to the server and receives real-time streaming data. The user can then view the video with the translated content overlaid. The user can also adjust the playback speed and volume as needed.

[0577] Specific examples

[0578] Example 1: Watching online lectures from a Japanese university translated into English

[0579] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[0580] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the audio data in real time and extracts the characters written on the board.

[0581] 3. The server's generation AI translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time.

[0582] 4. User A watches the lecture translated into English in real time through his / her terminal.

[0583] Example 2: Translating a Korean business seminar into Spanish and watching it

[0584] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[0585] 2. User B's device sends a connection request to the server, and the server receives the streaming data of the seminar. The server performs real-time speech recognition and extracts the characters displayed on the slides and boards.

[0586] 3. The server's generation AI translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time.

[0587] 4. User B watches the seminar translated into Spanish in real time through his terminal.

[0588] This allows users to overcome language barriers and access high-quality education and information from around the world in real time. An example of a translation prompt is "Translate the following Japanese text into English: 'Hello, everyone. Today's math class will begin.'"

[0589] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0590] Step 1:

[0591] The server receives the audio and video data.

[0592] Specifically, the server receives audio and video data in real time from the source of online classes and lectures. At this time, the audio and video data are sent in streaming format through a specific port on the server (e.g., TCP port 8000). The server receives the data using WebSocket and temporarily stores it in a buffer.

[0593] Input: Audio and video data from the source

[0594] Output: Audio and video buffers

[0595] Step 2:

[0596] The server converts the voice data into text data.

[0597] The server sends the received voice data to a cloud speech recognition API, which converts the voice data into text data in real time. The speech recognition engine analyzes the voice signal and converts the content into appropriate text.

[0598] Input: Audio data buffer

[0599] Output: Text data

[0600] Step 3:

[0601] The server extracts the text from the video data.

[0602] The server analyzes the video data using an image analysis library and extracts characters written on a board (whiteboard or blackboard). An image processing algorithm is used to detect character regions and perform character recognition. The character information extracted from the video data is then saved as text data.

[0603] Input: Video data buffer

[0604] Output: Text data of extracted characters

[0605] Step 4:

[0606] The server translates the text data.

[0607] The server uses a generative AI model (e.g., a generative AI engine) to translate text data obtained through speech recognition and image analysis into the user's desired language. The text data is translated by inputting the specified prompt into the generative AI model.

[0608] Input: Text data obtained through voice recognition and image analysis, translation language desired by the user

[0609] Output: Translated text data

[0610] Example prompt: "Translate the following Japanese text into English: 'Hello everyone. Today we will begin our math class.'"

[0611] Step 5:

[0612] The server generates the translated text as new video data.

[0613] The server overlays the translated text data onto the video data to generate new video data. To do this, the server performs text overlay processing on the video frames and performs rendering.

[0614] Input: translated text data, original video data

[0615] Output: New video data

[0616] Step 6:

[0617] The server transmits new video data to the terminal.

[0618] The server then streams the newly generated video data to the device in real time using a protocol such as RTMP (Real-Time Messaging Protocol).

[0619] Input: New video data

[0620] Output: Streaming video data

[0621] Step 7:

[0622] The terminal displays the video data.

[0623] The device receives new video data from the server and displays it in real time. The device's browser or dedicated application decodes the video and displays it on the screen.

[0624] Input: New video data in streaming format

[0625] Output: The image the user sees

[0626] Step 8:

[0627] The user performs the necessary settings and operations.

[0628] While watching a class or lecture, users can change settings and perform other operations on their devices, such as changing the playback speed, adjusting the volume, or changing the translation language. These setting changes may be resent to the server as requests.

[0629] Input: User actions

[0630] Output: Updated configuration information and its reflection

[0631] (Application example 1)

[0632] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0633] When it comes to work procedures and maintenance operations within factories, language barriers can lead to reduced efficiency and increased risk of operational errors. This issue is particularly pronounced in environments with multinational workers or when introducing new machinery. Furthermore, traditional methods lack a means to simultaneously provide real-time translation and instructions, making it difficult to improve work efficiency.

[0634] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0635] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, means for streaming the translated video data to viewers in real time, means for generating and outputting voice guidance in real time, and means for presenting the voice guidance and translation results to an automation system. This enables real-time multilingual instructions and translation within the factory, improving work efficiency and safety.

[0636] "Audio data" is data in digital or analog format that contains audio information.

[0637] "Speech recognition" is a technology in which a computer analyzes human speech and converts it into text data.

[0638] "Video data" is digital or analog data that contains visual information such as images or videos.

[0639] "Image analysis" is a technology that detects and recognizes characters and objects from video data.

[0640] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate new data and information.

[0641] "Translation" is the act of converting content expressed in one language into a different language.

[0642] "Real-time" means processing occurs immediately with little delay.

[0643] "Streaming delivery" is a technology that transmits data continuously and makes it available to the recipient immediately.

[0644] "Audio description" refers to technology that provides specific information or instructions in audio form.

[0645] An "automation system" is a configuration of equipment and software that performs a specific task or process automatically.

[0646] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[0647] Server Operation

[0648] The server is connected to the factory's automation system. First, it captures audio and video data received from microphones and cameras in real time. The audio data is converted into text data by a voice recognition engine. Image analysis software is used to detect characters and objects in the video data and extract information about them.

[0649] Next, the generative AI system translates the acquired text data and image analysis results into the user's desired language. This translation includes both the content obtained through voice recognition and the content extracted through image analysis. An audio guide is generated based on the translated text data and overlaid on the new video data.

[0650] Finally, the server streams the new translated video data and audio guide in real time using libraries such as OpenCV, Pytesseract, SpeechRecognition, Google Trans, and gTTS. The server also sends the translation results to the factory's automation systems, which output the audio guide and video.

[0651] Device behavior

[0652] The terminal (user's device) connects to the server and receives translated video data and audio guidance in real time. The user operates the terminal to select the desired work procedure or maintenance instructions and make the necessary settings. The video data and audio guidance sent from the server are received in real time and provided to the user through the terminal's screen and speaker.

[0653] The device also has the ability to adjust the video quality and volume based on the user's settings, and also supports the user's choice of translation language, sending this information along with the connection request to the server.

[0654] User operations

[0655] Users access the automated systems in factories using a website or dedicated application to receive work procedures and maintenance instructions. First, they access the system and select the desired work procedures or instructions. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[0656] At the start of the work, the user's device connects to the server and receives real-time streaming data. The user can then view the video and audio guide with the translated content overlaid in real time. The user can also adjust the playback speed and volume as needed.

[0657] Specific examples

[0658] Example 1: Translating and watching the operating procedures for a new machine in a Japanese factory

[0659] 1. User A accesses a dedicated application to learn the operating procedures for a new machine in the factory, selects the operating procedures, and selects English as the desired translation language.

[0660] 2. User A's device sends a connection request to the server, and the server receives the audio and video data in real time. The server recognizes the audio data and extracts text information from the video data.

[0661] 3. The server's generation AI translates the Japanese audio and text into English and generates new video data and audio guide. The translated data is streamed to User A's device in real time.

[0662] 4. User A can watch and listen to the operating procedures translated into English in real time through the terminal.

[0663] Prompt example

[0664] Capture Japanese audio and video, translate it into English in real time, and display it.

[0665] The most accurate translation possible

[0666] Ability to overlay text on video

[0667] Function that also provides audio output

[0668] In this way, the present invention enables real-time multilingual instructions and translation within a factory, thereby improving work efficiency and safety.

[0669] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0670] Step 1:

[0671] The server captures audio and video data in real time from microphones and cameras in the factory. The audio data input includes audio instructions and work procedures in the factory, while the video data input includes images of workers and machines.

[0672] Step 2:

[0673] The server analyzes the acquired voice data using a voice recognition engine and converts it into text data. In this process, SpeechRecognition is used as the voice recognition engine, which analyzes the voice waveform data and outputs the corresponding text.

[0674] Step 3:

[0675] The server analyzes the video data using image analysis software (Pytesseract and OpenCV) and extracts text information. In this step, it detects characters and signs in the video and outputs them as text data.

[0676] Step 4:

[0677] The server converts the text data obtained from voice recognition and image analysis into the specified translation language using a generative AI system. This process uses Google Trans as the translation engine and outputs the text data translated from Japanese to the desired language, such as English.

[0678] Step 5:

[0679] The server generates new video data based on the translated text data and overlays the translated text information on the video data. It also generates an audio guide and creates audio data based on the text information. gTTS is used to generate the audio guide. The output of this step is the translated video data and audio guide.

[0680] Step 6:

[0681] The server streams the generated translated video data and audio guide in real time. The device receives this data and allows the user to view instructions for the desired work procedure or maintenance guide. The device receives the data sent from the server as input and provides the user with visual and audio information as output.

[0682] Step 7:

[0683] The user operates the device to adjust settings such as video quality, volume, and translation language. Based on the user's input, the device sends a request to the server to make the necessary adjustments. The user can then view the video with the translated content overlaid and a real-time audio guide as they work.

[0684] In this way, specific data processing and calculations are performed at each step of the server, terminal, and user, and real-time multilingual work instructions are provided.

[0685] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0686] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[0687] Server Operation

[0688] The server processes the audio and video data received from the source of online classes and lectures. First, the audio data is acquired in real time and converted into text data using a speech recognition engine. At the same time, text written on a whiteboard or blackboard is extracted from the video data using image analysis. This allows the content of the class or lecture to be organized as text data.

[0689] Next, the acquired text data is translated using generative AI into the user's desired language. The translation results include both the content obtained through speech recognition and the characters extracted through image analysis. New video data is generated based on the translated text data, and the translation results are overlaid on this video data.

[0690] Furthermore, the server uses an emotion engine to recognize the user's emotions in real time from their facial expressions, tone of voice, and other factors. Based on the recognized emotion data, the translation results are processed to adapt to the user's emotions. The server then transmits the new translated video data to the user's device for streaming in real time. This allows users to watch classes and lectures in their preferred language and receive the optimal expressions based on their emotions.

[0691] Device behavior

[0692] The terminal (user device) connects to the server and receives real-time streaming data of classes and lectures. The user operates the terminal to select the desired lecture or presentation and make the necessary settings. The video data sent from the server is received in real time and the video is displayed on the terminal screen.

[0693] The device is equipped with a camera and microphone to recognize the user's emotions, detecting the user's facial expressions and tone of voice and sending the data to the emotion engine. The emotion engine then analyzes this data and sends the recognition results to the server. The device also has the ability to adjust the image quality and volume based on the user's settings. It also supports the user's choice of translation language, and sends this information along with the connection request to the server.

[0694] User operations

[0695] Users can participate in online classes or lectures using a website or dedicated application. First, they access the website and select the lecture or presentation they want. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[0696] At the start of a class or lecture, the user's device connects to the server and receives real-time streaming data. The user can then watch the video with the translated content overlaid on it. As the user watches, the emotion engine recognizes the user's emotions, and the server adjusts the translation results and video presentation accordingly. Settings such as playback speed and volume can also be adjusted as needed.

[0697] Specific examples

[0698] Example 1: Translating online lectures from a Japanese university into English and viewing them according to your emotions

[0699] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[0700] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the audio data in real time and extracts the characters written on the whiteboard.

[0701] 3. The AI ​​translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time. The emotion engine recognizes User A's emotions and adjusts the translation results accordingly.

[0702] 4. User A watches the lecture in real time through the device, which is translated into English and presented in the most appropriate expression according to the user's emotions.

[0703] Example 2: Translating a Korean business seminar into Spanish and viewing it according to your emotions

[0704] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[0705] 2. User B's device sends a connection request to the server, and the server receives the seminar streaming data. The server performs real-time speech recognition and extracts the text displayed on the slides and whiteboard.

[0706] 3. The server's generation AI translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time. The emotion engine recognizes User B's emotions and adjusts the translation results accordingly.

[0707] 4. User B watches the seminar in real time through their device, which is translated into Spanish and presented in the most appropriate expressions according to their emotions.

[0708] This allows users to overcome language barriers and obtain high-quality education and information in real time in a way that best suits their own emotions.

[0709] The processing flow will be explained below.

[0710] Server Processing

[0711] Step 1:

[0712] The server receives a connection request from a user for an online class or lecture. The request includes the user ID, the desired class / lecture ID, and the desired translation language.

[0713] Step 2:

[0714] The server receives live video and audio data of classes and lectures from the source, and converts the received data into a format that can be processed in real time.

[0715] Step 3:

[0716] The server's speech recognition engine analyzes the received voice data and converts it into text data, which is then transcribed in real time.

[0717] Step 4:

[0718] The server's image analysis engine detects text written on the whiteboard and blackboard in the video data and converts it into text data, allowing the entire lecture content to be organized as text information.

[0719] Step 5:

[0720] The server's AI converts the voice recognition results and characters extracted through image analysis into the specified translation language. The translation results are generated in real time and saved as new text data.

[0721] Step 6:

[0722] The server's video generation engine generates new video data based on the translated text data, and the translation results are overlaid on the generated video data.

[0723] Step 7:

[0724] The server's emotion engine receives and analyzes the user's emotion data (facial expressions, tone of voice, etc.), and adjusts the way the translation results are expressed based on the emotion data.

[0725] Step 8:

[0726] The server streams the new translated and emotion-adapted video data to the device in real time, providing the data to the viewer without delay.

[0727] Terminal handling

[0728] Step 1:

[0729] The terminal (user device) sends a connection request to the server through a website or application. The request includes the user ID, the desired class / lecture ID, and the desired translation language.

[0730] Step 2:

[0731] The device receives real-time streaming data sent from the server, and the received video data is immediately decoded and converted into a playable format.

[0732] Step 3:

[0733] The device displays the video data on the screen and plays it for the user to view, with the translated text appropriately overlaid on the video.

[0734] Step 4:

[0735] The device is equipped with a camera and microphone to recognize the user's emotions in real time, and this data is sent to the emotion engine.

[0736] Step 5:

[0737] The device receives feedback from the emotion engine and adjusts the way the image is displayed and the translation results as needed.

[0738] Step 6:

[0739] The device provides the ability to adjust video quality, volume, playback speed, etc. based on user settings.

[0740] User operations

[0741] Step 1:

[0742] Users access online classes or lectures using a website or dedicated application and select the lecture or lecture they want.

[0743] Step 2:

[0744] The user selects the translation language and other settings (quality, volume, playback speed, etc.) that are included in the connection request to the server.

[0745] Step 3:

[0746] Users watch the live stream through their devices. The emotion engine recognizes the user's emotions while watching, and the server adjusts the translation results and visual expressions accordingly.

[0747] Step 4:

[0748] Users can watch the video in real time, adjust the playback speed and volume as needed, and check that the translation results are optimized for emotion.

[0749] In this way, the server, terminal, and user work together at each step to create a system that provides translated and emotion-adapted video in real time.

[0750] Example 2

[0751] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0752] Conventional online classes and lecture systems make it difficult for users who speak different languages ​​to understand the content in real time. Furthermore, they are unable to provide appropriate expressions based on the user's emotions, making it difficult to improve the user's understanding and satisfaction. Furthermore, they lack emotion recognition functionality that uses the user's facial expressions and tone of voice, making it impossible to provide information in an optimal format for each individual user. This invention solves the problem of improving the user experience by removing language barriers and providing appropriate expressions based on the user's emotions in online classes and lecture systems.

[0753] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0754] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and the extracted characters into a desired language, means for adapting the translation results based on the user's emotions, and means for streaming the translated video data to viewers in real time. This makes it possible to provide understandable information in real time to users who speak different languages ​​and to optimally express themselves based on their emotions.

[0755] "Audio data" is a digital representation of audio collected from online classes, lectures, etc.

[0756] "Speech recognition" is a technology that analyzes voice data and converts it into corresponding text data.

[0757] "Video data" is digital information representing the video stream of an online class or lecture.

[0758] "Image analysis" is a technology that identifies and extracts specific information (for example, text) from video data.

[0759] "Generative AI" is an automated artificial intelligence system that translates received voice recognition and image analysis results into a specified language.

[0760] "Translation" is the process of converting text from one language into another.

[0761] "New video data" refers to the regenerated video stream that includes the translated speech recognition results and text.

[0762] "Emotion recognition" is a technology that analyzes a user's facial expressions and tone of voice to estimate their emotional state.

[0763] "Real-time delivery" is a streaming technology that provides processed data to users almost instantly without delay.

[0764] "User" refers to an individual who uses this system to view online classes or lectures.

[0765] A "display device" is a device that displays letters and figures, such as a whiteboard or blackboard.

[0766] A "reception request" is an action in which a user requests a server to receive audio data and video data.

[0767] "Image quality" is a measure of the visual quality of video data.

[0768] "Volume" is a measure of the acoustic level (loudness) of audio data.

[0769] MODE FOR CARRYING OUT THE INVENTION

[0770] This invention is a system that translates online classes and lectures into multiple languages ​​in real time and provides them in the most appropriate expressions according to the user's feelings. The operation of this system will be explained below from the perspectives of the server, the terminal, and the user.

[0771] Server Operation

[0772] The server performs the following main processes:

[0773] 1. Speech Recognition:

[0774] The server receives audio data in real time from online classes and lectures.

[0775] Use a speech recognition engine (e.g., Google Cloud Speech-to-Text) to convert the voice data into text data.

[0776] Example: Transcribing Japanese lecture audio in real time.

[0777] 2. Image Analysis:

[0778] The server acquires the video data and extracts the text written on the whiteboard or blackboard using image analysis (e.g., Google Cloud Vision API).

[0779] For example: Reading lecture slides and what is written on the blackboard.

[0780] 3. Translation:

[0781] Using generative AI (e.g., OpenAI GPT-4), the acquired text data is translated into the user's desired language.

[0782] Example: Translating Japanese text into English in real time.

[0783] 4. Image Generation:

[0784] Based on the translated text, new video data is generated and the translation results are overlaid.

[0785] Example: Generate a lecture video with English subtitles.

[0786] 5. Emotion recognition:

[0787] Using an emotion engine (e.g., Affectiva), emotions are recognized from the user's facial expressions and tone of voice.

[0788] The recognized emotion data is used to adapt the expression of the translation results.

[0789] Example: Detect whether the user understands or is unsure and simplify the statement accordingly.

[0790] 6. Real-time streaming:

[0791] The converted video data is streamed to the user's device, and the translation result is adjusted based on the emotion data.

[0792] Example: Delivering lecture videos that are adjusted to make them easier to understand depending on the emotion.

[0793] Device behavior

[0794] The terminal performs the following main processes:

[0795] 1. Connection and setup:

[0796] The terminal connects to the server and the user selects the lecture or speech they wish to attend.

[0797] Example: A user selects a Japanese course from a list of courses and selects the English translation.

[0798] 2. Data reception and display:

[0799] It receives the video data sent from the server and displays it on the screen.

[0800] Example: Play a lecture video with English subtitles on your device.

[0801] 3. Emotional data transmission:

[0802] It uses a camera and microphone to detect the user's facial expressions and tone of voice and sends the data to an emotion engine.

[0803] Example: The user sends confused facial expressions and voice to the emotion engine and sends them to the server.

[0804] 4. Translation Language Settings:

[0805] The user selects the desired translation language and sends that information to the server.

[0806] Example: The user specifies the translation language before the lecture begins.

[0807] User operations

[0808] The user performs the following operations:

[0809] 1. Lectures and presentations:

[0810] The user selects the lecture or speech they want.

[0811] Example: Choose an online course from a Japanese university.

[0812] 2. Configure the settings:

[0813] The user can set the translation language, image quality, etc.

[0814] Example: Select English translation and high quality mode.

[0815] 3. Listening and adjusting:

[0816] Watch the video with the translated content overlaid and adjust the playback speed and volume as needed.

[0817] Example: Adjusting the volume during playback.

[0818] Specific examples

[0819] Example 1: Watching online lectures from a Japanese university translated into English

[0820] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[0821] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the audio data in real time and extracts the characters written on the whiteboard.

[0822] 3. The server translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time. The emotion engine recognizes User A's emotions and adjusts the translation results accordingly.

[0823] 4. User A watches the lecture in real time through the device, which is translated into English and presented in the most appropriate expression according to the user's emotions.

[0824] Example 2: Translating a Korean business seminar into Spanish and viewing it according to your emotions

[0825] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[0826] 2. User B's device sends a connection request to the server, and the server receives the seminar streaming data. The server performs real-time speech recognition and extracts the text displayed on the slides and whiteboard.

[0827] 3. The server translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time. The emotion engine recognizes User B's emotions and adjusts the translation results accordingly.

[0828] 4. User B watches the seminar in real time through their device, which is translated into Spanish and presented in the most appropriate expressions according to their emotions.

[0829] Prompt Sentence Examples

[0830] 1. "I would like to watch online lectures from a Japanese university with the videos translated into English."

[0831] 2. "I would like to watch a video of a Korean business seminar translated into Spanish and have it presented in a way that best suits my emotions."

[0832] This allows users to overcome language barriers and obtain high-quality education and information in real time in a way that best suits their own emotions.

[0833] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0834] Step 1: Receiving voice data and recognizing voice

[0835] Input: Audio data from online classes and lectures.

[0836] Processing: The server receives the voice data in real time using a streaming API, then converts it into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[0837] Output: Text data.

[0838] Specific operation: After the server receives the voice data, it sends the data to the voice recognition engine and immediately generates the corresponding text.

[0839] Step 2: Receiving video data and analyzing images

[0840] Input: Video data from online classes and lectures.

[0841] Processing: The server receives video data in real time using a streaming video API, and then extracts text from the whiteboard or blackboard in the video data using an image analysis tool (e.g., Google Cloud Vision API).

[0842] Output: The extracted character data.

[0843] Specific operation: The server receives the video data and sends it to the image analysis engine to extract text information.

[0844] Step 3: Translating the text data

[0845] Input: Text data of speech recognition results and extracted character data.

[0846] Processing: The server uses a generative AI (e.g., OpenAI GPT-4) to translate the acquired text data into the user's preferred language.

[0847] Output: The translated text data.

[0848] Specific operation: The server passes text data to the translation API and obtains the corresponding translation result.

[0849] Step 4: Generate new video data

[0850] Input: Translated text data.

[0851] Processing: Based on the translated text data, the server generates new video data and overlays the translation results onto the video.

[0852] Output: New video data with the translation overlaid.

[0853] What it does: The server uses a video generation engine to create a new video with the translated text overlaid on it.

[0854] Step 5: Receiving and Recognizing Emotional Data

[0855] Input: User emotion data (facial expression data and tone of voice).

[0856] Processing: The device uses the camera and microphone to capture the user's facial and voice data and sends it to the emotion recognition API. The server recognizes the emotion based on the received data.

[0857] Output: Recognized emotion data.

[0858] Specific operation: The device collects the user's emotional data, analyzes it using an emotion recognition engine, and sends the results to the server.

[0859] Step 6: Adjust translation results based on sentiment

[0860] Input: Translated text data and recognized emotion data.

[0861] Processing: The server adapts the translation results based on the emotion data.

[0862] Output: Sentiment-adapted text data.

[0863] Specific operation: The server uses an adjustment algorithm on the translation text to generate the best translation result according to the sentiment.

[0864] Step 7: Real-time delivery

[0865] Input: New video data with emotion-adapted translation results.

[0866] Processing: The server streams new video data in real time.

[0867] Output: The translated video displayed on the end user's device.

[0868] Specific operation: The server uses a streaming protocol (e.g., WebRTC) to send the generated video to the user device.

[0869] This allows users to view online classes and lectures in real time in a way that is optimal for different languages ​​and emotions.

[0870] (Application example 2)

[0871] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0872] In conventional online classes and online seminars, it has been difficult to provide accurate translations in real time to users who speak different languages. Furthermore, because translation results cannot be adapted to take the user's emotions into account, there is a risk of user understanding and satisfaction decreasing. The present invention aims to solve these problems and provide users with higher quality information by supporting multiple languages ​​and translating according to their emotions.

[0873] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0874] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, means for streaming the translated video data to viewers in real time, emotion estimation means for recognizing user emotions in real time, and means for adapting the translation results based on the recognized emotions, thereby enabling multilingual and emotion-sensitive translation.

[0875] "Audio data" refers to data for recording and transmitting audio as a digital signal.

[0876] "Speech recognition" is a technology that converts voice signals into text data.

[0877] "Video data" refers to data for recording and transmitting video as a digital signal.

[0878] "Image analysis" is the process of extracting specific information from image data.

[0879] "Generative AI" is a technology that uses artificial intelligence technology to generate new data or text based on input data.

[0880] "New video data" refers to new video data that is generated by performing specific processing or adding information to the original video data.

[0881] "Streaming distribution" is a technology that transfers and plays digital data in real time.

[0882] "Emotion estimation" is a technology that analyzes and recognizes a user's emotional state from their facial expressions and voice.

[0883] "Translation adaptation" is the process of adjusting translated text or audio based on the original content and context.

[0884] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[0885] Server Operation

[0886] The server combines multiple technologies to support communication between customers and store staff during online transactions. First, the server captures voice data in real time and converts it into text using a speech recognition engine (e.g., the speech_recognition library). At the same time, it extracts text from video data related to store product information using image analysis (e.g., the OpenCV and Pytesseract libraries). Based on this data, it translates the customer's question into the desired language using generative AI (e.g., the MarianMTModel in the Transformers library).

[0887] Furthermore, the server uses an emotion estimation engine (e.g., the deepface library) to recognize the customer's emotions in real time from their facial expressions and voice tone. Based on the recognized emotion data, the generative AI adapts the translation results and generates new video data, overlaid with a response including the translation results. This translation result is also adjusted based on the context. The generated video data is streamed to the customer's device in real time.

[0888] Device behavior

[0889] The terminal (user's device) connects to the server and receives real-time data on online commercial transactions. The user operates the terminal to select the desired commercial transaction or product information and make the necessary settings. The video and audio data sent from the server is received in real time and the video is displayed on the terminal screen. The terminal is equipped with a camera and microphone to recognize the user's emotions, and through these, the user's facial expressions and tone of voice are detected and the data is sent to the emotion estimation engine. The emotion estimation engine analyzes this data and sends the recognition results to the server. The terminal also has the function to adjust the video quality, volume, etc. based on the user's settings. It also supports the user's selection of the translation language they prefer, and sends this information along with the connection request to the server.

[0890] User operations

[0891] Users participate in online commerce in virtual stores using websites or dedicated applications. First, they access the store and select the desired products or services. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface. When a transaction begins, the user's device connects to the server and receives real-time streaming data. The user can interact in real time with the translated content overlaid on the video. While viewing, an emotion estimation engine recognizes the user's emotions, and the server adjusts the translation results and video presentation accordingly. Settings such as playback speed and volume can also be adjusted as needed.

[0892] Specific examples

[0893] Example 1: Translating a purchase on a Japanese e-commerce site into English and viewing it in a way that responds to emotions

[0894] 1. User A visits a website to purchase a high-quality Japanese home appliance, selects the product, and selects English as the desired translation language.

[0895] 2. User A's device sends a connection request to the server, and the server receives streaming data of product information. The server recognizes the voice data in real time and extracts information about the product.

[0896] 3. The generative AI translates the Japanese audio and text into English, and the translated video data is streamed in real time to User A's device. The emotion estimation engine recognizes User A's emotions and adjusts the translation results accordingly.

[0897] 4. User A receives product information in real time through their device, translated into English and presented in the most appropriate language based on their emotions.

[0898] Example 2: Translating a purchase from a Korean online fashion store into Spanish and providing emotionally relevant content

[0899] 1. User B is interested in Korean fashion and accesses a dedicated application to check products online, selects a product, and selects Spanish as the desired translation language.

[0900] 2. User B's device sends a connection request to the server, and the server receives streaming data of the product. It performs real-time voice recognition and extracts the information displayed on the product tag.

[0901] 3. The server's generation AI translates the Korean audio and text into Spanish, and the translated video data is streamed in real time to User B's device. The emotion estimation engine recognizes User B's emotions and adjusts the translation results accordingly.

[0902] 4. User B uses their device to check product information in real time, which is translated into Spanish and presented in the most appropriate language based on their emotions.

[0903] Prompt Sentence Examples

[0904] markdown

[0905] User says: "What is this product?"

[0906] Product tag information: "Product name: XYZ, Price: 2000 yen, Description: Clothing made with high-quality materials."

[0907] User Sentiment: "Excited"

[0908] Abstract

[0909] The user is asking about a product. Generate an appropriate answer by taking into account the information in the product tags and the user's sentiment. Please keep your answer in a friendly tone.

[0910] answer

[0911] Hello! This is the XYZ product, priced at 2000 yen. It's made with high-quality materials and is very popular!

[0912] The above is a detailed description of the embodiment of the present invention. Through this application example, users can overcome language barriers and receive high-quality services in real time in an optimal manner according to their own emotions.

[0913] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0914] Step 1:

[0915] The server receives voice data from the user terminal in real time. This voice data is a voice signal acquired through a microphone. This voice data is input to a voice recognition engine (for example, the speech_recognition library) and converted into text data. The output is text data of the voice recognition results.

[0916] Step 2:

[0917] The server analyzes the video data received from the device. The video data includes text written on product tags and signboards. This video data is input into an image analysis engine (e.g., OpenCV and Pytesseract libraries) to extract the text from the image. The output is the extracted text data.

[0918] Step 3:

[0919] The server inputs the speech recognition results and extracted text data into a generation AI (e.g., MarianMTModel from the transformers library), which translates the text data into the desired language. The output is the translated text data.

[0920] Step 4:

[0921] The server receives data on the user's facial expressions and tone of voice captured in real time from the device's camera and microphone. This data is input into an emotion estimation engine (e.g., the deepface library) to analyze and recognize the user's emotions. The output is the user's emotion data.

[0922] Step 5:

[0923] The server uses a generation AI to generate new video data based on the translated text data and the user's emotional data. This generation AI creates new video data based on the translation results and overlays the translation results on the new video data. The output is new video data with the translation results overlaid.

[0924] Step 6:

[0925] The server then streams the newly generated video data to the user's device in real time, allowing the user to view the video with the translated content on their device.

[0926] Step 7:

[0927] Users can ask additional questions or change settings while watching the streaming video data on their device, allowing for continuous and smooth business transactions.

[0928] Through the above steps, a system is realized in which the server, terminal, and user work together to provide multilingual support and emotional adaptation in real time.

[0929] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0930] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0931] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0932] [Third embodiment]

[0933] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0934] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0935] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0936] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0937] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0938] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0939] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0940] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0941] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0942] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0943] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0944] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0945] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[0946] Server Operation

[0947] The server processes the audio and video data received from the source of online classes and lectures. First, the audio data is acquired in real time and converted into text data using a speech recognition engine. At the same time, text written on a whiteboard or blackboard is extracted from the video data using image analysis. This allows the content of the class or lecture to be organized as text data.

[0948] Next, the acquired text data is translated using generative AI into the user's desired language. The translation results include both the content obtained through speech recognition and the characters extracted through image analysis. New video data is generated based on the translated text data, and the translation results are overlaid on this video data.

[0949] Finally, the server sends the new translated video data to the user's device for real-time streaming, allowing the user to watch the lecture or presentation in their preferred language.

[0950] Device behavior

[0951] The terminal (user device) connects to the server and receives real-time streaming data of classes and lectures. The user operates the terminal to select the desired lecture or presentation and make the necessary settings. The video data sent from the server is received in real time and the video is displayed on the terminal screen.

[0952] The device also has the ability to adjust the video quality and volume based on the user's settings, and also supports the user's choice of translation language, sending this information along with the connection request to the server.

[0953] User operations

[0954] Users can participate in online classes or lectures using a website or dedicated application. First, they access the website and select the lecture or presentation they want. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[0955] At the start of a class or lecture, the user's device connects to the server and receives real-time streaming data. The user can then view the video with the translated content overlaid. The playback speed and volume can also be adjusted as needed.

[0956] Specific examples

[0957] Example 1: Watching online lectures from a Japanese university translated into English

[0958] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[0959] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the voice data in real time and extracts the characters written on the whiteboard.

[0960] 3. The server's generation AI translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time.

[0961] 4. User A watches the lecture translated into English in real time through his / her terminal.

[0962] Example 2: Translating a Korean business seminar into Spanish and watching it

[0963] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[0964] 2. User B's device sends a connection request to the server, and the server receives the seminar streaming data. The server performs real-time speech recognition and extracts the text displayed on the slides and whiteboard.

[0965] 3. The server's generation AI translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time.

[0966] 4. User B watches the seminar translated into Spanish in real time through his terminal.

[0967] This allows users to overcome language barriers and access high-quality education and information from around the world in real time.

[0968] The processing flow will be explained below.

[0969] Server Processing

[0970] Step 1:

[0971] The server receives a connection request from a user for an online class or lecture. The request includes the user ID, the desired class / lecture ID, and the desired translation language.

[0972] Step 2:

[0973] The server receives live video and audio data of classes and lectures from the source, and converts the received data into a format that can be processed in real time.

[0974] Step 3:

[0975] The server activates an AI engine and performs real-time speech recognition on the voice data, converting the recognized content into text data.

[0976] Step 4:

[0977] The server uses image analysis to extract text written on the whiteboard or blackboard from the video data, and this text data is also saved as text.

[0978] Step 5:

[0979] The server's AI translates the speech recognition results and extracted characters into the specified language. The translation process is performed in real time, and the converted text is generated.

[0980] Step 6:

[0981] The server generates new video data using the translated text, which includes a process of overlaying the translation results onto the video.

[0982] Step 7:

[0983] The server streams the translated video data to the viewer in real time, controlling the data transmission to the user's device to minimize delays.

[0984] Terminal handling

[0985] Step 1:

[0986] The terminal (user device) sends a connection request to the server in response to a user's operation. The request includes the user ID, the class / lecture ID, and the desired translation language.

[0987] Step 2:

[0988] The device receives real-time streaming data sent from the server, which is then instantly decoded and converted into a playable format.

[0989] Step 3:

[0990] The device plays the video data and displays it for the user to view, with the translated text overlaid on the video.

[0991] Step 4:

[0992] The device has the ability to adjust video quality, volume, etc. based on user settings. Users can adjust these parameters through the settings menu.

[0993] User operations

[0994] Step 1:

[0995] Users access online classes or lectures using a website or dedicated application. Users select the lecture or lecture they want.

[0996] Step 2:

[0997] The user selects the translation language and other settings (image quality, volume, etc.) that are included in the request sent to the server.

[0998] Step 3:

[0999] Users can watch the live stream through their devices and adjust the playback speed and volume as needed while watching.

[1000] Step 4:

[1001] Users can check the translation results in the video to understand the content of the class or lecture, and can also perform other operations on the screen as needed.

[1002] At each step, the server, terminal, and user work together to create a system that provides translated video in real time.

[1003] Example 1

[1004] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1005] In modern society, online classes and lectures are becoming more and more common, creating a demand for systems that allow users to watch classes and lectures in different languages. However, existing systems often only support a limited number of languages ​​and lack real-time translation capabilities. Furthermore, few systems offer the ability to translate text information contained in videos or provide easy user settings. This presents a challenge for users, making it difficult to smoothly understand the content of classes and lectures in their own language.

[1006] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1007] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, artificial intelligence means for translating the voice recognition results and the extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, a terminal for displaying the video data reflecting the user's desired settings, and means for streaming the translated video data to viewers in real time. This allows users to view classes and lectures in their desired language in real time, making it easy to acquire education and information beyond language barriers.

[1008] "Audio data" refers to data that represents an audio signal in digital form.

[1009] "Speech recognition" refers to the technology of analyzing voice data and converting its contents into text data.

[1010] "Video data" refers to data that represents visual information in digital form.

[1011] "Image analysis" refers to a technique for extracting specific information (such as text) from video data.

[1012] "Generative AI" refers to a system that uses artificial intelligence techniques to perform a specific task (e.g., translation).

[1013] "Translation" refers to the conversion of text data written in one language into another language.

[1014] "Users" refer to people who use this system to watch online classes and lectures.

[1015] "Terminal" refers to a device used by a user (for example, a PC or smartphone).

[1016] "Streaming distribution" refers to a technology that transmits digital content over a network in real time, allowing the recipient to view it in real time.

[1017] "Whiteboard or blackboard" refers to a board-shaped writing surface used in classes or lectures.

[1018] "New video data" refers to the reprocessed video data that includes the translated speech recognition results and text.

[1019] A "receive request" refers to a user requesting a server to send data.

[1020] "Reflecting settings" refers to applying the user's desired conditions (for example, translation language and image quality settings) to the system.

[1021] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[1022] Server Operation

[1023] The server processes audio and video data from the source of online classes and lectures. First, the server acquires the audio data received from the source in real time and converts it into text data using a speech recognition engine (e.g., cloud speech recognition API). At the same time, the server extracts the text written on the slab from the video data using image analysis (e.g., image analysis library). This allows the content of the class or lecture to be organized as text data.

[1024] The server then uses a generative AI model (e.g., a generative AI engine) to translate the acquired text data into the user's desired language. The translation results include both the content obtained through speech recognition and the characters extracted through image analysis. The server then generates new video data based on the translated text data, and the translation results are overlaid on the video data.

[1025] Finally, the server sends the new translated video data to the user's device for real-time streaming, allowing the user to watch the lecture or presentation in their preferred language.

[1026] Device behavior

[1027] The terminal (user device) connects to the server and receives real-time streaming data of classes and lectures. The user operates the terminal to select the desired class or lecture and make the necessary settings. The terminal receives the video data sent from the server in real time and displays the video on the terminal screen. The terminal also has the function to adjust the video quality and volume based on the user's settings, and supports the selection of the user's preferred translation language. This information is sent along with the connection request to the server.

[1028] User operations

[1029] Users can participate in online classes or lectures using a website or dedicated application. First, users access the system and select the class or lecture they want to attend. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[1030] When a class or lecture begins, the user's device connects to the server and receives real-time streaming data. The user can then view the video with the translated content overlaid. The user can also adjust the playback speed and volume as needed.

[1031] Specific examples

[1032] Example 1: Watching online lectures from a Japanese university translated into English

[1033] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[1034] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the audio data in real time and extracts the characters written on the board.

[1035] 3. The server's generation AI translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time.

[1036] 4. User A watches the lecture translated into English in real time through his / her terminal.

[1037] Example 2: Translating a Korean business seminar into Spanish and watching it

[1038] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[1039] 2. User B's device sends a connection request to the server, and the server receives the streaming data of the seminar. The server performs real-time speech recognition and extracts the characters displayed on the slides and boards.

[1040] 3. The server's generation AI translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time.

[1041] 4. User B watches the seminar translated into Spanish in real time through his terminal.

[1042] This allows users to overcome language barriers and access high-quality education and information from around the world in real time. An example of a translation prompt is "Translate the following Japanese text into English: 'Hello, everyone. Today's math class will begin.'"

[1043] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1044] Step 1:

[1045] The server receives the audio and video data.

[1046] Specifically, the server receives audio and video data in real time from the source of online classes and lectures. At this time, the audio and video data are sent in streaming format through a specific port on the server (e.g., TCP port 8000). The server receives the data using WebSocket and temporarily stores it in a buffer.

[1047] Input: Audio and video data from the source

[1048] Output: Audio and video buffers

[1049] Step 2:

[1050] The server converts the voice data into text data.

[1051] The server sends the received voice data to a cloud speech recognition API, which converts the voice data into text data in real time. The speech recognition engine analyzes the voice signal and converts the content into appropriate text.

[1052] Input: Audio data buffer

[1053] Output: Text data

[1054] Step 3:

[1055] The server extracts the text from the video data.

[1056] The server analyzes the video data using an image analysis library and extracts characters written on a board (whiteboard or blackboard). An image processing algorithm is used to detect character regions and perform character recognition. The character information extracted from the video data is then saved as text data.

[1057] Input: Video data buffer

[1058] Output: Text data of extracted characters

[1059] Step 4:

[1060] The server translates the text data.

[1061] The server uses a generative AI model (e.g., a generative AI engine) to translate text data obtained through speech recognition and image analysis into the user's desired language. The text data is translated by inputting the specified prompt into the generative AI model.

[1062] Input: Text data obtained through voice recognition and image analysis, translation language desired by the user

[1063] Output: Translated text data

[1064] Example prompt: "Translate the following Japanese text into English: 'Hello everyone. Today we will begin our math class.'"

[1065] Step 5:

[1066] The server generates the translated text as new video data.

[1067] The server overlays the translated text data onto the video data to generate new video data. To do this, the server performs text overlay processing on the video frames and performs rendering.

[1068] Input: translated text data, original video data

[1069] Output: New video data

[1070] Step 6:

[1071] The server transmits new video data to the terminal.

[1072] The server then streams the newly generated video data to the device in real time using a protocol such as RTMP (Real-Time Messaging Protocol).

[1073] Input: New video data

[1074] Output: Streaming video data

[1075] Step 7:

[1076] The terminal displays the video data.

[1077] The device receives new video data from the server and displays it in real time. The device's browser or dedicated application decodes the video and displays it on the screen.

[1078] Input: New video data in streaming format

[1079] Output: The image the user sees

[1080] Step 8:

[1081] The user performs the necessary settings and operations.

[1082] While watching a class or lecture, users can change settings and perform other operations on their devices, such as changing the playback speed, adjusting the volume, or changing the translation language. These setting changes may be resent to the server as requests.

[1083] Input: User actions

[1084] Output: Updated configuration information and its reflection

[1085] (Application example 1)

[1086] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1087] When it comes to work procedures and maintenance operations within factories, language barriers can lead to reduced efficiency and increased risk of operational errors. This issue is particularly pronounced in environments with multinational workers or when introducing new machinery. Furthermore, traditional methods lack a means to simultaneously provide real-time translation and instructions, making it difficult to improve work efficiency.

[1088] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1089] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, means for streaming the translated video data to viewers in real time, means for generating and outputting voice guidance in real time, and means for presenting the voice guidance and translation results to an automation system. This enables real-time multilingual instructions and translation within the factory, improving work efficiency and safety.

[1090] "Audio data" is data in digital or analog format that contains audio information.

[1091] "Speech recognition" is a technology in which a computer analyzes human speech and converts it into text data.

[1092] "Video data" is digital or analog data that contains visual information such as images or videos.

[1093] "Image analysis" is a technology that detects and recognizes characters and objects from video data.

[1094] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate new data and information.

[1095] "Translation" is the act of converting content expressed in one language into a different language.

[1096] "Real-time" means processing occurs immediately with little delay.

[1097] "Streaming delivery" is a technology that transmits data continuously and makes it available to the recipient immediately.

[1098] "Audio description" refers to technology that provides specific information or instructions in audio form.

[1099] An "automation system" is a configuration of equipment and software that performs a specific task or process automatically.

[1100] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[1101] Server Operation

[1102] The server is connected to the factory's automation system. First, it captures audio and video data received from microphones and cameras in real time. The audio data is converted into text data by a voice recognition engine. Image analysis software is used to detect characters and objects in the video data and extract information about them.

[1103] Next, the generative AI system translates the acquired text data and image analysis results into the user's desired language. This translation includes both the content obtained through voice recognition and the content extracted through image analysis. An audio guide is generated based on the translated text data and overlaid on the new video data.

[1104] Finally, the server streams the new translated video data and audio guide in real time using libraries such as OpenCV, Pytesseract, SpeechRecognition, Google Trans, and gTTS. The server also sends the translation results to the factory's automation systems, which output the audio guide and video.

[1105] Device behavior

[1106] The terminal (user's device) connects to the server and receives translated video data and audio guidance in real time. The user operates the terminal to select the desired work procedure or maintenance instructions and make the necessary settings. The video data and audio guidance sent from the server are received in real time and provided to the user through the terminal's screen and speaker.

[1107] The device also has the ability to adjust the video quality and volume based on the user's settings, and also supports the user's choice of translation language, sending this information along with the connection request to the server.

[1108] User operations

[1109] Users access the automated systems in factories using a website or dedicated application to receive work procedures and maintenance instructions. First, they access the system and select the desired work procedures or instructions. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[1110] At the start of the work, the user's device connects to the server and receives real-time streaming data. The user can then view the video and audio guide with the translated content overlaid in real time. The user can also adjust the playback speed and volume as needed.

[1111] Specific examples

[1112] Example 1: Translating and watching the operating procedures for a new machine in a Japanese factory

[1113] 1. User A accesses a dedicated application to learn the operating procedures for a new machine in the factory, selects the operating procedures, and selects English as the desired translation language.

[1114] 2. User A's device sends a connection request to the server, and the server receives the audio and video data in real time. The server recognizes the audio data and extracts text information from the video data.

[1115] 3. The server's generation AI translates the Japanese audio and text into English and generates new video data and audio guide. The translated data is streamed to User A's device in real time.

[1116] 4. User A can watch and listen to the operating procedures translated into English in real time through the terminal.

[1117] Prompt example

[1118] Capture Japanese audio and video, translate it into English in real time, and display it.

[1119] The most accurate translation possible

[1120] Ability to overlay text on video

[1121] Function that also provides audio output

[1122] In this way, the present invention enables real-time multilingual instructions and translation within a factory, thereby improving work efficiency and safety.

[1123] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1124] Step 1:

[1125] The server captures audio and video data in real time from microphones and cameras in the factory. The audio data input includes audio instructions and work procedures in the factory, while the video data input includes images of workers and machines.

[1126] Step 2:

[1127] The server analyzes the acquired voice data using a voice recognition engine and converts it into text data. In this process, SpeechRecognition is used as the voice recognition engine, which analyzes the voice waveform data and outputs the corresponding text.

[1128] Step 3:

[1129] The server analyzes the video data using image analysis software (Pytesseract and OpenCV) and extracts text information. In this step, it detects characters and signs in the video and outputs them as text data.

[1130] Step 4:

[1131] The server converts the text data obtained from voice recognition and image analysis into the specified translation language using a generative AI system. This process uses Google Trans as the translation engine and outputs the text data translated from Japanese to the desired language, such as English.

[1132] Step 5:

[1133] The server generates new video data based on the translated text data and overlays the translated text information on the video data. It also generates an audio guide and creates audio data based on the text information. gTTS is used to generate the audio guide. The output of this step is the translated video data and audio guide.

[1134] Step 6:

[1135] The server streams the generated translated video data and audio guide in real time. The device receives this data and allows the user to view instructions for the desired work procedure or maintenance guide. The device receives the data sent from the server as input and provides the user with visual and audio information as output.

[1136] Step 7:

[1137] The user operates the device to adjust settings such as video quality, volume, and translation language. Based on the user's input, the device sends a request to the server to make the necessary adjustments. The user can then view the video with the translated content overlaid and a real-time audio guide as they work.

[1138] In this way, specific data processing and calculations are performed at each step of the server, terminal, and user, and real-time multilingual work instructions are provided.

[1139] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1140] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[1141] Server Operation

[1142] The server processes the audio and video data received from the source of online classes and lectures. First, the audio data is acquired in real time and converted into text data using a speech recognition engine. At the same time, text written on a whiteboard or blackboard is extracted from the video data using image analysis. This allows the content of the class or lecture to be organized as text data.

[1143] Next, the acquired text data is translated using generative AI into the user's desired language. The translation results include both the content obtained through speech recognition and the characters extracted through image analysis. New video data is generated based on the translated text data, and the translation results are overlaid on this video data.

[1144] Furthermore, the server uses an emotion engine to recognize the user's emotions in real time from their facial expressions, tone of voice, and other factors. Based on the recognized emotion data, the translation results are processed to adapt to the user's emotions. The server then transmits the new translated video data to the user's device for streaming in real time. This allows users to watch classes and lectures in their preferred language and receive the optimal expressions based on their emotions.

[1145] Device behavior

[1146] The terminal (user device) connects to the server and receives real-time streaming data of classes and lectures. The user operates the terminal to select the desired lecture or presentation and make the necessary settings. The video data sent from the server is received in real time and the video is displayed on the terminal screen.

[1147] The device is equipped with a camera and microphone to recognize the user's emotions, detecting the user's facial expressions and tone of voice and sending the data to the emotion engine. The emotion engine then analyzes this data and sends the recognition results to the server. The device also has the ability to adjust the image quality and volume based on the user's settings. It also supports the user's choice of translation language, and sends this information along with the connection request to the server.

[1148] User operations

[1149] Users can participate in online classes or lectures using a website or dedicated application. First, they access the website and select the lecture or presentation they want. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[1150] At the start of a class or lecture, the user's device connects to the server and receives real-time streaming data. The user can then watch the video with the translated content overlaid on it. As the user watches, the emotion engine recognizes the user's emotions, and the server adjusts the translation results and video presentation accordingly. Settings such as playback speed and volume can also be adjusted as needed.

[1151] Specific examples

[1152] Example 1: Translating online lectures from a Japanese university into English and viewing them according to your emotions

[1153] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[1154] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the audio data in real time and extracts the characters written on the whiteboard.

[1155] 3. The AI ​​translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time. The emotion engine recognizes User A's emotions and adjusts the translation results accordingly.

[1156] 4. User A watches the lecture in real time through the device, which is translated into English and presented in the most appropriate expression according to the user's emotions.

[1157] Example 2: Translating a Korean business seminar into Spanish and viewing it according to your emotions

[1158] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[1159] 2. User B's device sends a connection request to the server, and the server receives the seminar streaming data. The server performs real-time speech recognition and extracts the text displayed on the slides and whiteboard.

[1160] 3. The server's generation AI translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time. The emotion engine recognizes User B's emotions and adjusts the translation results accordingly.

[1161] 4. User B watches the seminar in real time through their device, which is translated into Spanish and presented in the most appropriate expressions according to their emotions.

[1162] This allows users to overcome language barriers and obtain high-quality education and information in real time in a way that best suits their own emotions.

[1163] The processing flow will be explained below.

[1164] Server Processing

[1165] Step 1:

[1166] The server receives a connection request from a user for an online class or lecture. The request includes the user ID, the desired class / lecture ID, and the desired translation language.

[1167] Step 2:

[1168] The server receives live video and audio data of classes and lectures from the source, and converts the received data into a format that can be processed in real time.

[1169] Step 3:

[1170] The server's speech recognition engine analyzes the received voice data and converts it into text data, which is then transcribed in real time.

[1171] Step 4:

[1172] The server's image analysis engine detects text written on the whiteboard and blackboard in the video data and converts it into text data, allowing the entire lecture content to be organized as text information.

[1173] Step 5:

[1174] The server's AI converts the voice recognition results and characters extracted through image analysis into the specified translation language. The translation results are generated in real time and saved as new text data.

[1175] Step 6:

[1176] The server's video generation engine generates new video data based on the translated text data, and the translation results are overlaid on the generated video data.

[1177] Step 7:

[1178] The server's emotion engine receives and analyzes the user's emotion data (facial expressions, tone of voice, etc.), and adjusts the way the translation results are expressed based on the emotion data.

[1179] Step 8:

[1180] The server streams the new translated and emotion-adapted video data to the device in real time, providing the data to the viewer without delay.

[1181] Terminal handling

[1182] Step 1:

[1183] The terminal (user device) sends a connection request to the server through a website or application. The request includes the user ID, the desired class / lecture ID, and the desired translation language.

[1184] Step 2:

[1185] The device receives real-time streaming data sent from the server, and the received video data is immediately decoded and converted into a playable format.

[1186] Step 3:

[1187] The device displays the video data on the screen and plays it for the user to view, with the translated text appropriately overlaid on the video.

[1188] Step 4:

[1189] The device is equipped with a camera and microphone to recognize the user's emotions in real time, and this data is sent to the emotion engine.

[1190] Step 5:

[1191] The device receives feedback from the emotion engine and adjusts the way the image is displayed and the translation results as needed.

[1192] Step 6:

[1193] The device provides the ability to adjust video quality, volume, playback speed, etc. based on user settings.

[1194] User operations

[1195] Step 1:

[1196] Users access online classes or lectures using a website or dedicated application and select the lecture or lecture they want.

[1197] Step 2:

[1198] The user selects the translation language and other settings (quality, volume, playback speed, etc.) that are included in the connection request to the server.

[1199] Step 3:

[1200] Users watch the live stream through their devices. The emotion engine recognizes the user's emotions while watching, and the server adjusts the translation results and visual expressions accordingly.

[1201] Step 4:

[1202] Users can watch the video in real time, adjust the playback speed and volume as needed, and check that the translation results are optimized for emotion.

[1203] In this way, the server, terminal, and user work together at each step to create a system that provides translated and emotion-adapted video in real time.

[1204] Example 2

[1205] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1206] Conventional online classes and lecture systems make it difficult for users who speak different languages ​​to understand the content in real time. Furthermore, they are unable to provide appropriate expressions based on the user's emotions, making it difficult to improve the user's understanding and satisfaction. Furthermore, they lack emotion recognition functionality that uses the user's facial expressions and tone of voice, making it impossible to provide information in an optimal format for each individual user. This invention solves the problem of improving the user experience by removing language barriers and providing appropriate expressions based on the user's emotions in online classes and lecture systems.

[1207] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1208] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and the extracted characters into a desired language, means for adapting the translation results based on the user's emotions, and means for streaming the translated video data to viewers in real time. This makes it possible to provide understandable information in real time to users who speak different languages ​​and to optimally express themselves based on their emotions.

[1209] "Audio data" is a digital representation of audio collected from online classes, lectures, etc.

[1210] "Speech recognition" is a technology that analyzes voice data and converts it into corresponding text data.

[1211] "Video data" is digital information representing the video stream of an online class or lecture.

[1212] "Image analysis" is a technology that identifies and extracts specific information (for example, text) from video data.

[1213] "Generative AI" is an automated artificial intelligence system that translates received voice recognition and image analysis results into a specified language.

[1214] "Translation" is the process of converting text from one language into another.

[1215] "New video data" refers to the regenerated video stream that includes the translated speech recognition results and text.

[1216] "Emotion recognition" is a technology that analyzes a user's facial expressions and tone of voice to estimate their emotional state.

[1217] "Real-time delivery" is a streaming technology that provides processed data to users almost instantly without delay.

[1218] "User" refers to an individual who uses this system to view online classes or lectures.

[1219] A "display device" is a device that displays letters and figures, such as a whiteboard or blackboard.

[1220] A "reception request" is an action in which a user requests a server to receive audio data and video data.

[1221] "Image quality" is a measure of the visual quality of video data.

[1222] "Volume" is a measure of the acoustic level (loudness) of audio data.

[1223] MODE FOR CARRYING OUT THE INVENTION

[1224] This invention is a system that translates online classes and lectures into multiple languages ​​in real time and provides them in the most appropriate expressions according to the user's feelings. The operation of this system will be explained below from the perspectives of the server, the terminal, and the user.

[1225] Server Operation

[1226] The server performs the following main processes:

[1227] 1. Speech Recognition:

[1228] The server receives audio data in real time from online classes and lectures.

[1229] Use a speech recognition engine (e.g., Google Cloud Speech-to-Text) to convert the voice data into text data.

[1230] Example: Transcribing Japanese lecture audio in real time.

[1231] 2. Image Analysis:

[1232] The server acquires the video data and extracts the text written on the whiteboard or blackboard using image analysis (e.g., Google Cloud Vision API).

[1233] For example: Reading lecture slides and what is written on the blackboard.

[1234] 3. Translation:

[1235] Using generative AI (e.g., OpenAI GPT-4), the acquired text data is translated into the user's desired language.

[1236] Example: Translating Japanese text into English in real time.

[1237] 4. Image Generation:

[1238] Based on the translated text, new video data is generated and the translation results are overlaid.

[1239] Example: Generate a lecture video with English subtitles.

[1240] 5. Emotion recognition:

[1241] Using an emotion engine (e.g., Affectiva), emotions are recognized from the user's facial expressions and tone of voice.

[1242] The recognized emotion data is used to adapt the expression of the translation results.

[1243] Example: Detect whether the user understands or is unsure and simplify the statement accordingly.

[1244] 6. Real-time streaming:

[1245] The converted video data is streamed to the user's device, and the translation result is adjusted based on the emotion data.

[1246] Example: Delivering lecture videos that are adjusted to make them easier to understand depending on the emotion.

[1247] Device behavior

[1248] The terminal performs the following main processes:

[1249] 1. Connection and setup:

[1250] The terminal connects to the server and the user selects the lecture or speech they wish to attend.

[1251] Example: A user selects a Japanese course from a list of courses and selects the English translation.

[1252] 2. Data reception and display:

[1253] It receives the video data sent from the server and displays it on the screen.

[1254] Example: Play a lecture video with English subtitles on your device.

[1255] 3. Emotional data transmission:

[1256] It uses a camera and microphone to detect the user's facial expressions and tone of voice and sends the data to an emotion engine.

[1257] Example: The user sends confused facial expressions and voice to the emotion engine and sends them to the server.

[1258] 4. Translation Language Settings:

[1259] The user selects the desired translation language and sends that information to the server.

[1260] Example: The user specifies the translation language before the lecture begins.

[1261] User operations

[1262] The user performs the following operations:

[1263] 1. Lectures and presentations:

[1264] The user selects the lecture or speech they want.

[1265] Example: Choose an online course from a Japanese university.

[1266] 2. Configure the settings:

[1267] The user can set the translation language, image quality, etc.

[1268] Example: Select English translation and high quality mode.

[1269] 3. Listening and adjusting:

[1270] Watch the video with the translated content overlaid and adjust the playback speed and volume as needed.

[1271] Example: Adjusting the volume during playback.

[1272] Specific examples

[1273] Example 1: Watching online lectures from a Japanese university translated into English

[1274] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[1275] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the audio data in real time and extracts the characters written on the whiteboard.

[1276] 3. The server translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time. The emotion engine recognizes User A's emotions and adjusts the translation results accordingly.

[1277] 4. User A watches the lecture in real time through the device, which is translated into English and presented in the most appropriate expression according to the user's emotions.

[1278] Example 2: Translating a Korean business seminar into Spanish and viewing it according to your emotions

[1279] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[1280] 2. User B's device sends a connection request to the server, and the server receives the seminar streaming data. The server performs real-time speech recognition and extracts the text displayed on the slides and whiteboard.

[1281] 3. The server translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time. The emotion engine recognizes User B's emotions and adjusts the translation results accordingly.

[1282] 4. User B watches the seminar in real time through their device, which is translated into Spanish and presented in the most appropriate expressions according to their emotions.

[1283] Prompt Sentence Examples

[1284] 1. "I would like to watch online lectures from a Japanese university with the videos translated into English."

[1285] 2. "I would like to watch a video of a Korean business seminar translated into Spanish and have it presented in a way that best suits my emotions."

[1286] This allows users to overcome language barriers and obtain high-quality education and information in real time in a way that best suits their own emotions.

[1287] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1288] Step 1: Receiving voice data and recognizing voice

[1289] Input: Audio data from online classes and lectures.

[1290] Processing: The server receives the voice data in real time using a streaming API, then converts it into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[1291] Output: Text data.

[1292] Specific operation: After the server receives the voice data, it sends the data to the voice recognition engine and immediately generates the corresponding text.

[1293] Step 2: Receiving video data and analyzing images

[1294] Input: Video data from online classes and lectures.

[1295] Processing: The server receives video data in real time using a streaming video API, and then extracts text from the whiteboard or blackboard in the video data using an image analysis tool (e.g., Google Cloud Vision API).

[1296] Output: The extracted character data.

[1297] Specific operation: The server receives the video data and sends it to the image analysis engine to extract text information.

[1298] Step 3: Translating the text data

[1299] Input: Text data of speech recognition results and extracted character data.

[1300] Processing: The server uses a generative AI (e.g., OpenAI GPT-4) to translate the acquired text data into the user's preferred language.

[1301] Output: The translated text data.

[1302] Specific operation: The server passes text data to the translation API and obtains the corresponding translation result.

[1303] Step 4: Generate new video data

[1304] Input: Translated text data.

[1305] Processing: Based on the translated text data, the server generates new video data and overlays the translation results onto the video.

[1306] Output: New video data with the translation overlaid.

[1307] What it does: The server uses a video generation engine to create a new video with the translated text overlaid on it.

[1308] Step 5: Receiving and Recognizing Emotional Data

[1309] Input: User emotion data (facial expression data and tone of voice).

[1310] Processing: The device uses the camera and microphone to capture the user's facial and voice data and sends it to the emotion recognition API. The server recognizes the emotion based on the received data.

[1311] Output: Recognized emotion data.

[1312] Specific operation: The device collects the user's emotional data, analyzes it using an emotion recognition engine, and sends the results to the server.

[1313] Step 6: Adjust translation results based on sentiment

[1314] Input: Translated text data and recognized emotion data.

[1315] Processing: The server adapts the translation results based on the emotion data.

[1316] Output: Sentiment-adapted text data.

[1317] Specific operation: The server uses an adjustment algorithm on the translation text to generate the best translation result according to the sentiment.

[1318] Step 7: Real-time delivery

[1319] Input: New video data with emotion-adapted translation results.

[1320] Processing: The server streams new video data in real time.

[1321] Output: The translated video displayed on the end user's device.

[1322] Specific operation: The server uses a streaming protocol (e.g., WebRTC) to send the generated video to the user device.

[1323] This allows users to view online classes and lectures in real time in a way that is optimal for different languages ​​and emotions.

[1324] (Application example 2)

[1325] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1326] In conventional online classes and online seminars, it has been difficult to provide accurate translations in real time to users who speak different languages. Furthermore, because translation results cannot be adapted to take the user's emotions into account, there is a risk of user understanding and satisfaction decreasing. The present invention aims to solve these problems and provide users with higher quality information by supporting multiple languages ​​and translating according to their emotions.

[1327] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1328] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, means for streaming the translated video data to viewers in real time, emotion estimation means for recognizing user emotions in real time, and means for adapting the translation results based on the recognized emotions, thereby enabling multilingual and emotion-sensitive translation.

[1329] "Audio data" refers to data for recording and transmitting audio as a digital signal.

[1330] "Speech recognition" is a technology that converts voice signals into text data.

[1331] "Video data" refers to data for recording and transmitting video as a digital signal.

[1332] "Image analysis" is the process of extracting specific information from image data.

[1333] "Generative AI" is a technology that uses artificial intelligence technology to generate new data or text based on input data.

[1334] "New video data" refers to new video data that is generated by performing specific processing or adding information to the original video data.

[1335] "Streaming distribution" is a technology that transfers and plays digital data in real time.

[1336] "Emotion estimation" is a technology that analyzes and recognizes a user's emotional state from their facial expressions and voice.

[1337] "Translation adaptation" is the process of adjusting translated text or audio based on the original content and context.

[1338] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[1339] Server Operation

[1340] The server combines multiple technologies to support communication between customers and store staff during online transactions. First, the server captures voice data in real time and converts it into text using a speech recognition engine (e.g., the speech_recognition library). At the same time, it extracts text from video data related to store product information using image analysis (e.g., the OpenCV and Pytesseract libraries). Based on this data, it translates the customer's question into the desired language using generative AI (e.g., the MarianMTModel in the Transformers library).

[1341] Furthermore, the server uses an emotion estimation engine (e.g., the deepface library) to recognize the customer's emotions in real time from their facial expressions and voice tone. Based on the recognized emotion data, the generative AI adapts the translation results and generates new video data, overlaid with a response including the translation results. This translation result is also adjusted based on the context. The generated video data is streamed to the customer's device in real time.

[1342] Device behavior

[1343] The terminal (user's device) connects to the server and receives real-time data on online commercial transactions. The user operates the terminal to select the desired commercial transaction or product information and make the necessary settings. The video and audio data sent from the server is received in real time and the video is displayed on the terminal screen. The terminal is equipped with a camera and microphone to recognize the user's emotions, and through these, the user's facial expressions and tone of voice are detected and the data is sent to the emotion estimation engine. The emotion estimation engine analyzes this data and sends the recognition results to the server. The terminal also has the function to adjust the video quality, volume, etc. based on the user's settings. It also supports the user's selection of the translation language they prefer, and sends this information along with the connection request to the server.

[1344] User operations

[1345] Users participate in online commerce in virtual stores using websites or dedicated applications. First, they access the store and select the desired products or services. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface. When a transaction begins, the user's device connects to the server and receives real-time streaming data. The user can interact in real time with the translated content overlaid on the video. While viewing, an emotion estimation engine recognizes the user's emotions, and the server adjusts the translation results and video presentation accordingly. Settings such as playback speed and volume can also be adjusted as needed.

[1346] Specific examples

[1347] Example 1: Translating a purchase on a Japanese e-commerce site into English and viewing it in a way that responds to emotions

[1348] 1. User A visits a website to purchase a high-quality Japanese home appliance, selects the product, and selects English as the desired translation language.

[1349] 2. User A's device sends a connection request to the server, and the server receives streaming data of product information. The server recognizes the voice data in real time and extracts information about the product.

[1350] 3. The generative AI translates the Japanese audio and text into English, and the translated video data is streamed in real time to User A's device. The emotion estimation engine recognizes User A's emotions and adjusts the translation results accordingly.

[1351] 4. User A receives product information in real time through their device, translated into English and presented in the most appropriate language based on their emotions.

[1352] Example 2: Translating a purchase from a Korean online fashion store into Spanish and providing emotionally relevant content

[1353] 1. User B is interested in Korean fashion and accesses a dedicated application to check products online, selects a product, and selects Spanish as the desired translation language.

[1354] 2. User B's device sends a connection request to the server, and the server receives streaming data of the product. It performs real-time voice recognition and extracts the information displayed on the product tag.

[1355] 3. The server's generation AI translates the Korean audio and text into Spanish, and the translated video data is streamed in real time to User B's device. The emotion estimation engine recognizes User B's emotions and adjusts the translation results accordingly.

[1356] 4. User B uses their device to check product information in real time, which is translated into Spanish and presented in the most appropriate language based on their emotions.

[1357] Prompt Sentence Examples

[1358] markdown

[1359] User says: "What is this product?"

[1360] Product tag information: "Product name: XYZ, Price: 2000 yen, Description: Clothing made with high-quality materials."

[1361] User Sentiment: "Excited"

[1362] Abstract

[1363] The user is asking about a product. Generate an appropriate answer by taking into account the information in the product tags and the user's sentiment. Please keep your answer in a friendly tone.

[1364] answer

[1365] Hello! This is the XYZ product, priced at 2000 yen. It's made with high-quality materials and is very popular!

[1366] The above is a detailed description of the embodiment of the present invention. Through this application example, users can overcome language barriers and receive high-quality services in real time in an optimal manner according to their own emotions.

[1367] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1368] Step 1:

[1369] The server receives voice data from the user terminal in real time. This voice data is a voice signal acquired through a microphone. This voice data is input to a voice recognition engine (for example, the speech_recognition library) and converted into text data. The output is text data of the voice recognition results.

[1370] Step 2:

[1371] The server analyzes the video data received from the device. The video data includes text written on product tags and signboards. This video data is input into an image analysis engine (e.g., OpenCV and Pytesseract libraries) to extract the text from the image. The output is the extracted text data.

[1372] Step 3:

[1373] The server inputs the speech recognition results and extracted text data into a generation AI (e.g., MarianMTModel from the transformers library), which translates the text data into the desired language. The output is the translated text data.

[1374] Step 4:

[1375] The server receives data on the user's facial expressions and tone of voice captured in real time from the device's camera and microphone. This data is input into an emotion estimation engine (e.g., the deepface library) to analyze and recognize the user's emotions. The output is the user's emotion data.

[1376] Step 5:

[1377] The server uses a generation AI to generate new video data based on the translated text data and the user's emotional data. This generation AI creates new video data based on the translation results and overlays the translation results on the new video data. The output is new video data with the translation results overlaid.

[1378] Step 6:

[1379] The server then streams the newly generated video data to the user's device in real time, allowing the user to view the video with the translated content on their device.

[1380] Step 7:

[1381] Users can ask additional questions or change settings while watching the streaming video data on their device, allowing for continuous and smooth business transactions.

[1382] Through the above steps, a system is realized in which the server, terminal, and user work together to provide multilingual support and emotional adaptation in real time.

[1383] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1384] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1385] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1386] [Fourth embodiment]

[1387] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1388] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1389] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1390] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1391] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1392] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1393] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1394] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1395] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1396] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1397] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1398] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1399] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1400] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[1401] Server Operation

[1402] The server processes the audio and video data received from the source of online classes and lectures. First, the audio data is acquired in real time and converted into text data using a speech recognition engine. At the same time, text written on a whiteboard or blackboard is extracted from the video data using image analysis. This allows the content of the class or lecture to be organized as text data.

[1403] Next, the acquired text data is translated using generative AI into the user's desired language. The translation results include both the content obtained through speech recognition and the characters extracted through image analysis. New video data is generated based on the translated text data, and the translation results are overlaid on this video data.

[1404] Finally, the server sends the new translated video data to the user's device for real-time streaming, allowing the user to watch the lecture or presentation in their preferred language.

[1405] Device behavior

[1406] The terminal (user device) connects to the server and receives real-time streaming data of classes and lectures. The user operates the terminal to select the desired lecture or presentation and make the necessary settings. The video data sent from the server is received in real time and the video is displayed on the terminal screen.

[1407] The device also has the ability to adjust the video quality and volume based on the user's settings, and also supports the user's choice of translation language, sending this information along with the connection request to the server.

[1408] User operations

[1409] Users can participate in online classes or lectures using a website or dedicated application. First, they access the website and select the lecture or presentation they want. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[1410] At the start of a class or lecture, the user's device connects to the server and receives real-time streaming data. The user can then view the video with the translated content overlaid. The playback speed and volume can also be adjusted as needed.

[1411] Specific examples

[1412] Example 1: Watching online lectures from a Japanese university translated into English

[1413] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[1414] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the voice data in real time and extracts the characters written on the whiteboard.

[1415] 3. The server's generation AI translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time.

[1416] 4. User A watches the lecture translated into English in real time through his / her terminal.

[1417] Example 2: Translating a Korean business seminar into Spanish and watching it

[1418] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[1419] 2. User B's device sends a connection request to the server, and the server receives the seminar streaming data. The server performs real-time speech recognition and extracts the text displayed on the slides and whiteboard.

[1420] 3. The server's generation AI translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time.

[1421] 4. User B watches the seminar translated into Spanish in real time through his terminal.

[1422] This allows users to overcome language barriers and access high-quality education and information from around the world in real time.

[1423] The processing flow will be explained below.

[1424] Server Processing

[1425] Step 1:

[1426] The server receives a connection request from a user for an online class or lecture. The request includes the user ID, the desired class / lecture ID, and the desired translation language.

[1427] Step 2:

[1428] The server receives live video and audio data of classes and lectures from the source, and converts the received data into a format that can be processed in real time.

[1429] Step 3:

[1430] The server activates an AI engine and performs real-time speech recognition on the voice data, converting the recognized content into text data.

[1431] Step 4:

[1432] The server uses image analysis to extract text written on the whiteboard or blackboard from the video data, and this text data is also saved as text.

[1433] Step 5:

[1434] The server's AI translates the speech recognition results and extracted characters into the specified language. The translation process is performed in real time, and the converted text is generated.

[1435] Step 6:

[1436] The server generates new video data using the translated text, which includes a process of overlaying the translation results onto the video.

[1437] Step 7:

[1438] The server streams the translated video data to the viewer in real time, controlling the data transmission to the user's device to minimize delays.

[1439] Terminal handling

[1440] Step 1:

[1441] The terminal (user device) sends a connection request to the server in response to a user's operation. The request includes the user ID, the class / lecture ID, and the desired translation language.

[1442] Step 2:

[1443] The device receives real-time streaming data sent from the server, which is then instantly decoded and converted into a playable format.

[1444] Step 3:

[1445] The device plays the video data and displays it for the user to view, with the translated text overlaid on the video.

[1446] Step 4:

[1447] The device has the ability to adjust video quality, volume, etc. based on user settings. Users can adjust these parameters through the settings menu.

[1448] User operations

[1449] Step 1:

[1450] Users access online classes or lectures using a website or dedicated application. Users select the lecture or lecture they want.

[1451] Step 2:

[1452] The user selects the translation language and other settings (image quality, volume, etc.) that are included in the request sent to the server.

[1453] Step 3:

[1454] Users can watch the live stream through their devices and adjust the playback speed and volume as needed while watching.

[1455] Step 4:

[1456] Users can check the translation results in the video to understand the content of the class or lecture, and can also perform other operations on the screen as needed.

[1457] At each step, the server, terminal, and user work together to create a system that provides translated video in real time.

[1458] Example 1

[1459] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1460] In modern society, online classes and lectures are becoming more and more common, creating a demand for systems that allow users to watch classes and lectures in different languages. However, existing systems often only support a limited number of languages ​​and lack real-time translation capabilities. Furthermore, few systems offer the ability to translate text information contained in videos or provide easy user settings. This presents a challenge for users, making it difficult to smoothly understand the content of classes and lectures in their own language.

[1461] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1462] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, artificial intelligence means for translating the voice recognition results and the extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, a terminal for displaying the video data reflecting the user's desired settings, and means for streaming the translated video data to viewers in real time. This allows users to view classes and lectures in their desired language in real time, making it easy to acquire education and information beyond language barriers.

[1463] "Audio data" refers to data that represents an audio signal in digital form.

[1464] "Speech recognition" refers to the technology of analyzing voice data and converting its contents into text data.

[1465] "Video data" refers to data that represents visual information in digital form.

[1466] "Image analysis" refers to a technique for extracting specific information (such as text) from video data.

[1467] "Generative AI" refers to a system that uses artificial intelligence techniques to perform a specific task (e.g., translation).

[1468] "Translation" refers to the conversion of text data written in one language into another language.

[1469] "Users" refer to people who use this system to watch online classes and lectures.

[1470] "Terminal" refers to a device used by a user (for example, a PC or smartphone).

[1471] "Streaming distribution" refers to a technology that transmits digital content over a network in real time, allowing the recipient to view it in real time.

[1472] "Whiteboard or blackboard" refers to a board-shaped writing surface used in classes or lectures.

[1473] "New video data" refers to the reprocessed video data that includes the translated speech recognition results and text.

[1474] A "receive request" refers to a user requesting a server to send data.

[1475] "Reflecting settings" refers to applying the user's desired conditions (for example, translation language and image quality settings) to the system.

[1476] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[1477] Server Operation

[1478] The server processes audio and video data from the source of online classes and lectures. First, the server acquires the audio data received from the source in real time and converts it into text data using a speech recognition engine (e.g., cloud speech recognition API). At the same time, the server extracts the text written on the slab from the video data using image analysis (e.g., image analysis library). This allows the content of the class or lecture to be organized as text data.

[1479] The server then uses a generative AI model (e.g., a generative AI engine) to translate the acquired text data into the user's desired language. The translation results include both the content obtained through speech recognition and the characters extracted through image analysis. The server then generates new video data based on the translated text data, and the translation results are overlaid on the video data.

[1480] Finally, the server sends the new translated video data to the user's device for real-time streaming, allowing the user to watch the lecture or presentation in their preferred language.

[1481] Device behavior

[1482] The terminal (user device) connects to the server and receives real-time streaming data of classes and lectures. The user operates the terminal to select the desired class or lecture and make the necessary settings. The terminal receives the video data sent from the server in real time and displays the video on the terminal screen. The terminal also has the function to adjust the video quality and volume based on the user's settings, and supports the selection of the user's preferred translation language. This information is sent along with the connection request to the server.

[1483] User operations

[1484] Users can participate in online classes or lectures using a website or dedicated application. First, users access the system and select the class or lecture they want to attend. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[1485] When a class or lecture begins, the user's device connects to the server and receives real-time streaming data. The user can then view the video with the translated content overlaid. The user can also adjust the playback speed and volume as needed.

[1486] Specific examples

[1487] Example 1: Watching online lectures from a Japanese university translated into English

[1488] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[1489] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the audio data in real time and extracts the characters written on the board.

[1490] 3. The server's generation AI translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time.

[1491] 4. User A watches the lecture translated into English in real time through his / her terminal.

[1492] Example 2: Translating a Korean business seminar into Spanish and watching it

[1493] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[1494] 2. User B's device sends a connection request to the server, and the server receives the streaming data of the seminar. The server performs real-time speech recognition and extracts the characters displayed on the slides and boards.

[1495] 3. The server's generation AI translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time.

[1496] 4. User B watches the seminar translated into Spanish in real time through his terminal.

[1497] This allows users to overcome language barriers and access high-quality education and information from around the world in real time. An example of a translation prompt is "Translate the following Japanese text into English: 'Hello, everyone. Today's math class will begin.'"

[1498] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1499] Step 1:

[1500] The server receives the audio and video data.

[1501] Specifically, the server receives audio and video data in real time from the source of online classes and lectures. At this time, the audio and video data are sent in streaming format through a specific port on the server (e.g., TCP port 8000). The server receives the data using WebSocket and temporarily stores it in a buffer.

[1502] Input: Audio and video data from the source

[1503] Output: Audio and video buffers

[1504] Step 2:

[1505] The server converts the voice data into text data.

[1506] The server sends the received voice data to a cloud speech recognition API, which converts the voice data into text data in real time. The speech recognition engine analyzes the voice signal and converts the content into appropriate text.

[1507] Input: Audio data buffer

[1508] Output: Text data

[1509] Step 3:

[1510] The server extracts the text from the video data.

[1511] The server analyzes the video data using an image analysis library and extracts characters written on a board (whiteboard or blackboard). An image processing algorithm is used to detect character regions and perform character recognition. The character information extracted from the video data is then saved as text data.

[1512] Input: Video data buffer

[1513] Output: Text data of extracted characters

[1514] Step 4:

[1515] The server translates the text data.

[1516] The server uses a generative AI model (e.g., a generative AI engine) to translate text data obtained through speech recognition and image analysis into the user's desired language. The text data is translated by inputting the specified prompt into the generative AI model.

[1517] Input: Text data obtained through voice recognition and image analysis, translation language desired by the user

[1518] Output: Translated text data

[1519] Example prompt: "Translate the following Japanese text into English: 'Hello everyone. Today we will begin our math class.'"

[1520] Step 5:

[1521] The server generates the translated text as new video data.

[1522] The server overlays the translated text data onto the video data to generate new video data. To do this, the server performs text overlay processing on the video frames and performs rendering.

[1523] Input: translated text data, original video data

[1524] Output: New video data

[1525] Step 6:

[1526] The server transmits new video data to the terminal.

[1527] The server then streams the newly generated video data to the device in real time using a protocol such as RTMP (Real-Time Messaging Protocol).

[1528] Input: New video data

[1529] Output: Streaming video data

[1530] Step 7:

[1531] The terminal displays the video data.

[1532] The device receives new video data from the server and displays it in real time. The device's browser or dedicated application decodes the video and displays it on the screen.

[1533] Input: New video data in streaming format

[1534] Output: The image the user sees

[1535] Step 8:

[1536] The user performs the necessary settings and operations.

[1537] While watching a class or lecture, users can change settings and perform other operations on their devices, such as changing the playback speed, adjusting the volume, or changing the translation language. These setting changes may be resent to the server as requests.

[1538] Input: User actions

[1539] Output: Updated configuration information and its reflection

[1540] (Application example 1)

[1541] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1542] When it comes to work procedures and maintenance operations within factories, language barriers can lead to reduced efficiency and increased risk of operational errors. This issue is particularly pronounced in environments with multinational workers or when introducing new machinery. Furthermore, traditional methods lack a means to simultaneously provide real-time translation and instructions, making it difficult to improve work efficiency.

[1543] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1544] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, means for streaming the translated video data to viewers in real time, means for generating and outputting voice guidance in real time, and means for presenting the voice guidance and translation results to an automation system. This enables real-time multilingual instructions and translation within the factory, improving work efficiency and safety.

[1545] "Audio data" is data in digital or analog format that contains audio information.

[1546] "Speech recognition" is a technology in which a computer analyzes human speech and converts it into text data.

[1547] "Video data" is digital or analog data that contains visual information such as images or videos.

[1548] "Image analysis" is a technology that detects and recognizes characters and objects from video data.

[1549] "Generative AI" is a system that uses artificial intelligence technology to analyze data and generate new data and information.

[1550] "Translation" is the act of converting content expressed in one language into a different language.

[1551] "Real-time" means processing occurs immediately with little delay.

[1552] "Streaming delivery" is a technology that transmits data continuously and makes it available to the recipient immediately.

[1553] "Audio description" refers to technology that provides specific information or instructions in audio form.

[1554] An "automation system" is a configuration of equipment and software that performs a specific task or process automatically.

[1555] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[1556] Server Operation

[1557] The server is connected to the factory's automation system. First, it captures audio and video data received from microphones and cameras in real time. The audio data is converted into text data by a voice recognition engine. Image analysis software is used to detect characters and objects in the video data and extract information about them.

[1558] Next, the generative AI system translates the acquired text data and image analysis results into the user's desired language. This translation includes both the content obtained through voice recognition and the content extracted through image analysis. An audio guide is generated based on the translated text data and overlaid on the new video data.

[1559] Finally, the server streams the new translated video data and audio guide in real time using libraries such as OpenCV, Pytesseract, SpeechRecognition, Google Trans, and gTTS. The server also sends the translation results to the factory's automation systems, which output the audio guide and video.

[1560] Device behavior

[1561] The terminal (user's device) connects to the server and receives translated video data and audio guidance in real time. The user operates the terminal to select the desired work procedure or maintenance instructions and make the necessary settings. The video data and audio guidance sent from the server are received in real time and provided to the user through the terminal's screen and speaker.

[1562] The device also has the ability to adjust the video quality and volume based on the user's settings, and also supports the user's choice of translation language, sending this information along with the connection request to the server.

[1563] User operations

[1564] Users access the automated systems in factories using a website or dedicated application to receive work procedures and maintenance instructions. First, they access the system and select the desired work procedures or instructions. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[1565] At the start of the work, the user's device connects to the server and receives real-time streaming data. The user can then view the video and audio guide with the translated content overlaid in real time. The user can also adjust the playback speed and volume as needed.

[1566] Specific examples

[1567] Example 1: Translating and watching the operating procedures for a new machine in a Japanese factory

[1568] 1. User A accesses a dedicated application to learn the operating procedures for a new machine in the factory, selects the operating procedures, and selects English as the desired translation language.

[1569] 2. User A's device sends a connection request to the server, and the server receives the audio and video data in real time. The server recognizes the audio data and extracts text information from the video data.

[1570] 3. The server's generation AI translates the Japanese audio and text into English and generates new video data and audio guide. The translated data is streamed to User A's device in real time.

[1571] 4. User A can watch and listen to the operating procedures translated into English in real time through the terminal.

[1572] Prompt example

[1573] Capture Japanese audio and video, translate it into English in real time, and display it.

[1574] The most accurate translation possible

[1575] Ability to overlay text on video

[1576] Function that also provides audio output

[1577] In this way, the present invention enables real-time multilingual instructions and translation within a factory, thereby improving work efficiency and safety.

[1578] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1579] Step 1:

[1580] The server captures audio and video data in real time from microphones and cameras in the factory. The audio data input includes audio instructions and work procedures in the factory, while the video data input includes images of workers and machines.

[1581] Step 2:

[1582] The server analyzes the acquired voice data using a voice recognition engine and converts it into text data. In this process, SpeechRecognition is used as the voice recognition engine, which analyzes the voice waveform data and outputs the corresponding text.

[1583] Step 3:

[1584] The server analyzes the video data using image analysis software (Pytesseract and OpenCV) and extracts text information. In this step, it detects characters and signs in the video and outputs them as text data.

[1585] Step 4:

[1586] The server converts the text data obtained from voice recognition and image analysis into the specified translation language using a generative AI system. This process uses Google Trans as the translation engine and outputs the text data translated from Japanese to the desired language, such as English.

[1587] Step 5:

[1588] The server generates new video data based on the translated text data and overlays the translated text information on the video data. It also generates an audio guide and creates audio data based on the text information. gTTS is used to generate the audio guide. The output of this step is the translated video data and audio guide.

[1589] Step 6:

[1590] The server streams the generated translated video data and audio guide in real time. The device receives this data and allows the user to view instructions for the desired work procedure or maintenance guide. The device receives the data sent from the server as input and provides the user with visual and audio information as output.

[1591] Step 7:

[1592] The user operates the device to adjust settings such as video quality, volume, and translation language. Based on the user's input, the device sends a request to the server to make the necessary adjustments. The user can then view the video with the translated content overlaid and a real-time audio guide as they work.

[1593] In this way, specific data processing and calculations are performed at each step of the server, terminal, and user, and real-time multilingual work instructions are provided.

[1594] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1595] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[1596] Server Operation

[1597] The server processes the audio and video data received from the source of online classes and lectures. First, the audio data is acquired in real time and converted into text data using a speech recognition engine. At the same time, text written on a whiteboard or blackboard is extracted from the video data using image analysis. This allows the content of the class or lecture to be organized as text data.

[1598] Next, the acquired text data is translated using generative AI into the user's desired language. The translation results include both the content obtained through speech recognition and the characters extracted through image analysis. New video data is generated based on the translated text data, and the translation results are overlaid on this video data.

[1599] Furthermore, the server uses an emotion engine to recognize the user's emotions in real time from their facial expressions, tone of voice, and other factors. Based on the recognized emotion data, the translation results are processed to adapt to the user's emotions. The server then transmits the new translated video data to the user's device for streaming in real time. This allows users to watch classes and lectures in their preferred language and receive the optimal expressions based on their emotions.

[1600] Device behavior

[1601] The terminal (user device) connects to the server and receives real-time streaming data of classes and lectures. The user operates the terminal to select the desired lecture or presentation and make the necessary settings. The video data sent from the server is received in real time and the video is displayed on the terminal screen.

[1602] The device is equipped with a camera and microphone to recognize the user's emotions, detecting the user's facial expressions and tone of voice and sending the data to the emotion engine. The emotion engine then analyzes this data and sends the recognition results to the server. The device also has the ability to adjust the image quality and volume based on the user's settings. It also supports the user's choice of translation language, and sends this information along with the connection request to the server.

[1603] User operations

[1604] Users can participate in online classes or lectures using a website or dedicated application. First, they access the website and select the lecture or presentation they want. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface.

[1605] At the start of a class or lecture, the user's device connects to the server and receives real-time streaming data. The user can then watch the video with the translated content overlaid on it. As the user watches, the emotion engine recognizes the user's emotions, and the server adjusts the translation results and video presentation accordingly. Settings such as playback speed and volume can also be adjusted as needed.

[1606] Specific examples

[1607] Example 1: Translating online lectures from a Japanese university into English and viewing them according to your emotions

[1608] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[1609] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the audio data in real time and extracts the characters written on the whiteboard.

[1610] 3. The AI ​​translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time. The emotion engine recognizes User A's emotions and adjusts the translation results accordingly.

[1611] 4. User A watches the lecture in real time through the device, which is translated into English and presented in the most appropriate expression according to the user's emotions.

[1612] Example 2: Translating a Korean business seminar into Spanish and viewing it according to your emotions

[1613] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[1614] 2. User B's device sends a connection request to the server, and the server receives the seminar streaming data. The server performs real-time speech recognition and extracts the text displayed on the slides and whiteboard.

[1615] 3. The server's generation AI translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time. The emotion engine recognizes User B's emotions and adjusts the translation results accordingly.

[1616] 4. User B watches the seminar in real time through their device, which is translated into Spanish and presented in the most appropriate expressions according to their emotions.

[1617] This allows users to overcome language barriers and obtain high-quality education and information in real time in a way that best suits their own emotions.

[1618] The processing flow will be explained below.

[1619] Server Processing

[1620] Step 1:

[1621] The server receives a connection request from a user for an online class or lecture. The request includes the user ID, the desired class / lecture ID, and the desired translation language.

[1622] Step 2:

[1623] The server receives live video and audio data of classes and lectures from the source, and converts the received data into a format that can be processed in real time.

[1624] Step 3:

[1625] The server's speech recognition engine analyzes the received voice data and converts it into text data, which is then transcribed in real time.

[1626] Step 4:

[1627] The server's image analysis engine detects text written on the whiteboard and blackboard in the video data and converts it into text data, allowing the entire lecture content to be organized as text information.

[1628] Step 5:

[1629] The server's AI converts the voice recognition results and characters extracted through image analysis into the specified translation language. The translation results are generated in real time and saved as new text data.

[1630] Step 6:

[1631] The server's video generation engine generates new video data based on the translated text data, and the translation results are overlaid on the generated video data.

[1632] Step 7:

[1633] The server's emotion engine receives and analyzes the user's emotion data (facial expressions, tone of voice, etc.), and adjusts the way the translation results are expressed based on the emotion data.

[1634] Step 8:

[1635] The server streams the new translated and emotion-adapted video data to the device in real time, providing the data to the viewer without delay.

[1636] Terminal handling

[1637] Step 1:

[1638] The terminal (user device) sends a connection request to the server through a website or application. The request includes the user ID, the desired class / lecture ID, and the desired translation language.

[1639] Step 2:

[1640] The device receives real-time streaming data sent from the server, and the received video data is immediately decoded and converted into a playable format.

[1641] Step 3:

[1642] The device displays the video data on the screen and plays it for the user to view, with the translated text appropriately overlaid on the video.

[1643] Step 4:

[1644] The device is equipped with a camera and microphone to recognize the user's emotions in real time, and this data is sent to the emotion engine.

[1645] Step 5:

[1646] The device receives feedback from the emotion engine and adjusts the way the image is displayed and the translation results as needed.

[1647] Step 6:

[1648] The device provides the ability to adjust video quality, volume, playback speed, etc. based on user settings.

[1649] User operations

[1650] Step 1:

[1651] Users access online classes or lectures using a website or dedicated application and select the lecture or lecture they want.

[1652] Step 2:

[1653] The user selects the translation language and other settings (quality, volume, playback speed, etc.) that are included in the connection request to the server.

[1654] Step 3:

[1655] Users watch the live stream through their devices. The emotion engine recognizes the user's emotions while watching, and the server adjusts the translation results and visual expressions accordingly.

[1656] Step 4:

[1657] Users can watch the video in real time, adjust the playback speed and volume as needed, and check that the translation results are optimized for emotion.

[1658] In this way, the server, terminal, and user work together at each step to create a system that provides translated and emotion-adapted video in real time.

[1659] Example 2

[1660] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1661] Conventional online classes and lecture systems make it difficult for users who speak different languages ​​to understand the content in real time. Furthermore, they are unable to provide appropriate expressions based on the user's emotions, making it difficult to improve the user's understanding and satisfaction. Furthermore, they lack emotion recognition functionality that uses the user's facial expressions and tone of voice, making it impossible to provide information in an optimal format for each individual user. This invention solves the problem of improving the user experience by removing language barriers and providing appropriate expressions based on the user's emotions in online classes and lecture systems.

[1662] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1663] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and the extracted characters into a desired language, means for adapting the translation results based on the user's emotions, and means for streaming the translated video data to viewers in real time. This makes it possible to provide understandable information in real time to users who speak different languages ​​and to optimally express themselves based on their emotions.

[1664] "Audio data" is a digital representation of audio collected from online classes, lectures, etc.

[1665] "Speech recognition" is a technology that analyzes voice data and converts it into corresponding text data.

[1666] "Video data" is digital information representing the video stream of an online class or lecture.

[1667] "Image analysis" is a technology that identifies and extracts specific information (for example, text) from video data.

[1668] "Generative AI" is an automated artificial intelligence system that translates received voice recognition and image analysis results into a specified language.

[1669] "Translation" is the process of converting text from one language into another.

[1670] "New video data" refers to the regenerated video stream that includes the translated speech recognition results and text.

[1671] "Emotion recognition" is a technology that analyzes a user's facial expressions and tone of voice to estimate their emotional state.

[1672] "Real-time delivery" is a streaming technology that provides processed data to users almost instantly without delay.

[1673] "User" refers to an individual who uses this system to view online classes or lectures.

[1674] A "display device" is a device that displays letters and figures, such as a whiteboard or blackboard.

[1675] A "reception request" is an action in which a user requests a server to receive audio data and video data.

[1676] "Image quality" is a measure of the visual quality of video data.

[1677] "Volume" is a measure of the acoustic level (loudness) of audio data.

[1678] MODE FOR CARRYING OUT THE INVENTION

[1679] This invention is a system that translates online classes and lectures into multiple languages ​​in real time and provides them in the most appropriate expressions according to the user's feelings. The operation of this system will be explained below from the perspectives of the server, the terminal, and the user.

[1680] Server Operation

[1681] The server performs the following main processes:

[1682] 1. Speech Recognition:

[1683] The server receives audio data in real time from online classes and lectures.

[1684] Use a speech recognition engine (e.g., Google Cloud Speech-to-Text) to convert the voice data into text data.

[1685] Example: Transcribing Japanese lecture audio in real time.

[1686] 2. Image Analysis:

[1687] The server acquires the video data and extracts the text written on the whiteboard or blackboard using image analysis (e.g., Google Cloud Vision API).

[1688] For example: Reading lecture slides and what is written on the blackboard.

[1689] 3. Translation:

[1690] Using generative AI (e.g., OpenAI GPT-4), the acquired text data is translated into the user's desired language.

[1691] Example: Translating Japanese text into English in real time.

[1692] 4. Image Generation:

[1693] Based on the translated text, new video data is generated and the translation results are overlaid.

[1694] Example: Generate a lecture video with English subtitles.

[1695] 5. Emotion recognition:

[1696] Using an emotion engine (e.g., Affectiva), emotions are recognized from the user's facial expressions and tone of voice.

[1697] The recognized emotion data is used to adapt the expression of the translation results.

[1698] Example: Detect whether the user understands or is unsure and simplify the statement accordingly.

[1699] 6. Real-time streaming:

[1700] The converted video data is streamed to the user's device, and the translation result is adjusted based on the emotion data.

[1701] Example: Delivering lecture videos that are adjusted to make them easier to understand depending on the emotion.

[1702] Device behavior

[1703] The terminal performs the following main processes:

[1704] 1. Connection and setup:

[1705] The terminal connects to the server and the user selects the lecture or speech they wish to attend.

[1706] Example: A user selects a Japanese course from a list of courses and selects the English translation.

[1707] 2. Data reception and display:

[1708] It receives the video data sent from the server and displays it on the screen.

[1709] Example: Play a lecture video with English subtitles on your device.

[1710] 3. Emotional data transmission:

[1711] It uses a camera and microphone to detect the user's facial expressions and tone of voice and sends the data to an emotion engine.

[1712] Example: The user sends confused facial expressions and voice to the emotion engine and sends them to the server.

[1713] 4. Translation Language Settings:

[1714] The user selects the desired translation language and sends that information to the server.

[1715] Example: The user specifies the translation language before the lecture begins.

[1716] User operations

[1717] The user performs the following operations:

[1718] 1. Lectures and presentations:

[1719] The user selects the lecture or speech they want.

[1720] Example: Choose an online course from a Japanese university.

[1721] 2. Configure the settings:

[1722] The user can set the translation language, image quality, etc.

[1723] Example: Select English translation and high quality mode.

[1724] 3. Listening and adjusting:

[1725] Watch the video with the translated content overlaid and adjust the playback speed and volume as needed.

[1726] Example: Adjusting the volume during playback.

[1727] Specific examples

[1728] Example 1: Watching online lectures from a Japanese university translated into English

[1729] 1. User A accesses a website to participate in an online lecture at a Japanese university, selects the lecture, and selects English as the desired translation language.

[1730] 2. User A's device sends a connection request to the server, and the server receives the streaming data of the lecture. The server recognizes the audio data in real time and extracts the characters written on the whiteboard.

[1731] 3. The server translates the Japanese audio and text into English and generates new video data. The translated video data is streamed to User A's device in real time. The emotion engine recognizes User A's emotions and adjusts the translation results accordingly.

[1732] 4. User A watches the lecture in real time through the device, which is translated into English and presented in the most appropriate expression according to the user's emotions.

[1733] Example 2: Translating a Korean business seminar into Spanish and viewing it according to your emotions

[1734] 1. User B accesses the dedicated application to select a seminar to participate in an online business seminar in Korea, and selects Spanish as the desired translation language.

[1735] 2. User B's device sends a connection request to the server, and the server receives the seminar streaming data. The server performs real-time speech recognition and extracts the text displayed on the slides and whiteboard.

[1736] 3. The server translates the Korean audio and text into Spanish and generates new video data. The translated video data is streamed to User B's device in real time. The emotion engine recognizes User B's emotions and adjusts the translation results accordingly.

[1737] 4. User B watches the seminar in real time through their device, which is translated into Spanish and presented in the most appropriate expressions according to their emotions.

[1738] Prompt Sentence Examples

[1739] 1. "I would like to watch online lectures from a Japanese university with the videos translated into English."

[1740] 2. "I would like to watch a video of a Korean business seminar translated into Spanish and have it presented in a way that best suits my emotions."

[1741] This allows users to overcome language barriers and obtain high-quality education and information in real time in a way that best suits their own emotions.

[1742] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1743] Step 1: Receiving voice data and recognizing voice

[1744] Input: Audio data from online classes and lectures.

[1745] Processing: The server receives the voice data in real time using a streaming API, then converts it into text using a speech recognition engine (e.g., Google Cloud Speech-to-Text).

[1746] Output: Text data.

[1747] Specific operation: After the server receives the voice data, it sends the data to the voice recognition engine and immediately generates the corresponding text.

[1748] Step 2: Receiving video data and analyzing images

[1749] Input: Video data from online classes and lectures.

[1750] Processing: The server receives video data in real time using a streaming video API, and then extracts text from the whiteboard or blackboard in the video data using an image analysis tool (e.g., Google Cloud Vision API).

[1751] Output: The extracted character data.

[1752] Specific operation: The server receives the video data and sends it to the image analysis engine to extract text information.

[1753] Step 3: Translating the text data

[1754] Input: Text data of speech recognition results and extracted character data.

[1755] Processing: The server uses a generative AI (e.g., OpenAI GPT-4) to translate the acquired text data into the user's preferred language.

[1756] Output: The translated text data.

[1757] Specific operation: The server passes text data to the translation API and obtains the corresponding translation result.

[1758] Step 4: Generate new video data

[1759] Input: Translated text data.

[1760] Processing: Based on the translated text data, the server generates new video data and overlays the translation results onto the video.

[1761] Output: New video data with the translation overlaid.

[1762] What it does: The server uses a video generation engine to create a new video with the translated text overlaid on it.

[1763] Step 5: Receiving and Recognizing Emotional Data

[1764] Input: User emotion data (facial expression data and tone of voice).

[1765] Processing: The device uses the camera and microphone to capture the user's facial and voice data and sends it to the emotion recognition API. The server recognizes the emotion based on the received data.

[1766] Output: Recognized emotion data.

[1767] Specific operation: The device collects the user's emotional data, analyzes it using an emotion recognition engine, and sends the results to the server.

[1768] Step 6: Adjust translation results based on sentiment

[1769] Input: Translated text data and recognized emotion data.

[1770] Processing: The server adapts the translation results based on the emotion data.

[1771] Output: Sentiment-adapted text data.

[1772] Specific operation: The server uses an adjustment algorithm on the translation text to generate the best translation result according to the sentiment.

[1773] Step 7: Real-time delivery

[1774] Input: New video data with emotion-adapted translation results.

[1775] Processing: The server streams new video data in real time.

[1776] Output: The translated video displayed on the end user's device.

[1777] Specific operation: The server uses a streaming protocol (e.g., WebRTC) to send the generated video to the user device.

[1778] This allows users to view online classes and lectures in real time in a way that is optimal for different languages ​​and emotions.

[1779] (Application example 2)

[1780] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1781] In conventional online classes and online seminars, it has been difficult to provide accurate translations in real time to users who speak different languages. Furthermore, because translation results cannot be adapted to take the user's emotions into account, there is a risk of user understanding and satisfaction decreasing. The present invention aims to solve these problems and provide users with higher quality information by supporting multiple languages ​​and translating according to their emotions.

[1782] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1783] In this invention, the server includes means for receiving voice data and performing voice recognition in real time, image analysis means for extracting characters from video data, generation AI means for translating the voice recognition results and extracted characters into a desired language, means for generating new video data including the translated voice recognition results and characters, means for streaming the translated video data to viewers in real time, emotion estimation means for recognizing user emotions in real time, and means for adapting the translation results based on the recognized emotions, thereby enabling multilingual and emotion-sensitive translation.

[1784] "Audio data" refers to data for recording and transmitting audio as a digital signal.

[1785] "Speech recognition" is a technology that converts voice signals into text data.

[1786] "Video data" refers to data for recording and transmitting video as a digital signal.

[1787] "Image analysis" is the process of extracting specific information from image data.

[1788] "Generative AI" is a technology that uses artificial intelligence technology to generate new data or text based on input data.

[1789] "New video data" refers to new video data that is generated by performing specific processing or adding information to the original video data.

[1790] "Streaming distribution" is a technology that transfers and plays digital data in real time.

[1791] "Emotion estimation" is a technology that analyzes and recognizes a user's emotional state from their facial expressions and voice.

[1792] "Translation adaptation" is the process of adjusting translated text or audio based on the original content and context.

[1793] The following describes an embodiment of the present invention, which will be explained mainly from the viewpoints of the server, the terminal, and the user.

[1794] Server Operation

[1795] The server combines multiple technologies to support communication between customers and store staff during online transactions. First, the server captures voice data in real time and converts it into text using a speech recognition engine (e.g., the speech_recognition library). At the same time, it extracts text from video data related to store product information using image analysis (e.g., the OpenCV and Pytesseract libraries). Based on this data, it translates the customer's question into the desired language using generative AI (e.g., the MarianMTModel in the Transformers library).

[1796] Furthermore, the server uses an emotion estimation engine (e.g., the deepface library) to recognize the customer's emotions in real time from their facial expressions and voice tone. Based on the recognized emotion data, the generative AI adapts the translation results and generates new video data, overlaid with a response including the translation results. This translation result is also adjusted based on the context. The generated video data is streamed to the customer's device in real time.

[1797] Device behavior

[1798] The terminal (user's device) connects to the server and receives real-time data on online commercial transactions. The user operates the terminal to select the desired commercial transaction or product information and make the necessary settings. The video and audio data sent from the server is received in real time and the video is displayed on the terminal screen. The terminal is equipped with a camera and microphone to recognize the user's emotions, and through these, the user's facial expressions and tone of voice are detected and the data is sent to the emotion estimation engine. The emotion estimation engine analyzes this data and sends the recognition results to the server. The terminal also has the function to adjust the video quality, volume, etc. based on the user's settings. It also supports the user's selection of the translation language they prefer, and sends this information along with the connection request to the server.

[1799] User operations

[1800] Users participate in online commerce in virtual stores using websites or dedicated applications. First, they access the store and select the desired products or services. Other settings (e.g., translation language, image quality settings, etc.) are also configured through the user interface. When a transaction begins, the user's device connects to the server and receives real-time streaming data. The user can interact in real time with the translated content overlaid on the video. While viewing, an emotion estimation engine recognizes the user's emotions, and the server adjusts the translation results and video presentation accordingly. Settings such as playback speed and volume can also be adjusted as needed.

[1801] Specific examples

[1802] Example 1: Translating a purchase on a Japanese e-commerce site into English and viewing it in a way that responds to emotions

[1803] 1. User A visits a website to purchase a high-quality Japanese home appliance, selects the product, and selects English as the desired translation language.

[1804] 2. User A's device sends a connection request to the server, and the server receives streaming data of product information. The server recognizes the voice data in real time and extracts information about the product.

[1805] 3. The generative AI translates the Japanese audio and text into English, and the translated video data is streamed in real time to User A's device. The emotion estimation engine recognizes User A's emotions and adjusts the translation results accordingly.

[1806] 4. User A receives product information in real time through their device, translated into English and presented in the most appropriate language based on their emotions.

[1807] Example 2: Translating a purchase from a Korean online fashion store into Spanish and providing emotionally relevant content

[1808] 1. User B is interested in Korean fashion and accesses a dedicated application to check products online, selects a product, and selects Spanish as the desired translation language.

[1809] 2. User B's device sends a connection request to the server, and the server receives streaming data of the product. It performs real-time voice recognition and extracts the information displayed on the product tag.

[1810] 3. The server's generation AI translates the Korean audio and text into Spanish, and the translated video data is streamed in real time to User B's device. The emotion estimation engine recognizes User B's emotions and adjusts the translation results accordingly.

[1811] 4. User B uses their device to check product information in real time, which is translated into Spanish and presented in the most appropriate language based on their emotions.

[1812] Prompt Sentence Examples

[1813] markdown

[1814] User says: "What is this product?"

[1815] Product tag information: "Product name: XYZ, Price: 2000 yen, Description: Clothing made with high-quality materials."

[1816] User Sentiment: "Excited"

[1817] Abstract

[1818] The user is asking about a product. Generate an appropriate answer by taking into account the information in the product tags and the user's sentiment. Please keep your answer in a friendly tone.

[1819] answer

[1820] Hello! This is the XYZ product, priced at 2000 yen. It's made with high-quality materials and is very popular!

[1821] The above is a detailed description of the embodiment of the present invention. Through this application example, users can overcome language barriers and receive high-quality services in real time in an optimal manner according to their own emotions.

[1822] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1823] Step 1:

[1824] The server receives voice data from the user terminal in real time. This voice data is a voice signal acquired through a microphone. This voice data is input to a voice recognition engine (for example, the speech_recognition library) and converted into text data. The output is text data of the voice recognition results.

[1825] Step 2:

[1826] The server analyzes the video data received from the device. The video data includes text written on product tags and signboards. This video data is input into an image analysis engine (e.g., OpenCV and Pytesseract libraries) to extract the text from the image. The output is the extracted text data.

[1827] Step 3:

[1828] The server inputs the speech recognition results and extracted text data into a generation AI (e.g., MarianMTModel from the transformers library), which translates the text data into the desired language. The output is the translated text data.

[1829] Step 4:

[1830] The server receives data on the user's facial expressions and tone of voice captured in real time from the device's camera and microphone. This data is input into an emotion estimation engine (e.g., the deepface library) to analyze and recognize the user's emotions. The output is the user's emotion data.

[1831] Step 5:

[1832] The server uses a generation AI to generate new video data based on the translated text data and the user's emotional data. This generation AI creates new video data based on the translation results and overlays the translation results on the new video data. The output is new video data with the translation results overlaid.

[1833] Step 6:

[1834] The server then streams the newly generated video data to the user's device in real time, allowing the user to view the video with the translated content on their device.

[1835] Step 7:

[1836] Users can ask additional questions or change settings while watching the streaming video data on their device, allowing for continuous and smooth business transactions.

[1837] Through the above steps, a system is realized in which the server, terminal, and user work together to provide multilingual support and emotional adaptation in real time.

[1838] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1839] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1840] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1841] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1842] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1843] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1844] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1845] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1846] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1847] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1848] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1849] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1850] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1851] 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.

[1852] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1853] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1854] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1855] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1856] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1857] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1858] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1859] The following is further disclosed regarding the above embodiment.

[1860] (Claim 1)

[1861] means for receiving voice data and performing real-time voice recognition;

[1862] image analysis means for extracting characters from video data;

[1863] A generating AI means for translating the speech recognition results and extracted characters into a desired language;

[1864] means for generating new video data including the translated speech recognition result and characters;

[1865] A means of streaming the translated video data to viewers in real time;

[1866] A system including:

[1867] (Claim 2)

[1868] 2. The system of claim 1, wherein the extracted characters are characters written on a whiteboard or a blackboard.

[1869] (Claim 3)

[1870] 2. The system according to claim 1, further comprising: means for accepting a request to receive audio data and video data; and means for allowing a user to specify a desired translation language.

[1871] "Example 1"

[1872] (Claim 1)

[1873] means for receiving voice data and performing real-time voice recognition;

[1874] image analysis means for extracting characters from video data;

[1875] A generating artificial intelligence means for translating the speech recognition result and extracted characters into a desired language;

[1876] means for generating new video data including the translated speech recognition result and characters;

[1877] a terminal that displays video data reflecting settings desired by a user;

[1878] A means of streaming the translated video data to viewers in real time;

[1879] A system including:

[1880] (Claim 2)

[1881] 2. The system according to claim 1, wherein the extracted characters are characters written on a plate-like object.

[1882] (Claim 3)

[1883] 2. The system according to claim 1, further comprising: means for accepting a request to receive audio data and video data; means for allowing a user to specify a desired translation language; and means for allowing a user to make settings.

[1884] "Application Example 1"

[1885] (Claim 1)

[1886] means for receiving voice data and performing real-time voice recognition;

[1887] image analysis means for extracting characters from video data;

[1888] A generating AI means for translating the speech recognition results and extracted characters into a desired language;

[1889] means for generating new video data including the translated speech recognition result and characters;

[1890] A means of streaming the translated video data to viewers in real time;

[1891] means for generating and outputting audio description in real time;

[1892] means for presenting audio prompts and translation results to an automated system;

[1893] A system including:

[1894] (Claim 2)

[1895] 2. The system according to claim 1, wherein the extracted characters are characters written on an information display medium.

[1896] (Claim 3)

[1897] 2. The system according to claim 1, further comprising: means for accepting a request to receive audio data and video data; and means for allowing a user to specify a desired translation language.

[1898] "Example 2: Combining Emotion Engines"

[1899] (Claim 1)

[1900] means for receiving voice data and performing real-time voice recognition;

[1901] image analysis means for extracting characters from video data;

[1902] A generating AI means for translating the speech recognition results and extracted characters into a desired language;

[1903] means for generating new video data ...

Claims

1. means for receiving voice data and performing real-time voice recognition; image analysis means for extracting characters from video data; A generating AI means for translating the speech recognition results and extracted characters into a desired language; means for generating new video data including the translated speech recognition result and characters; A means of streaming the translated video data to viewers in real time; A system including:

2. 2. The system of claim 1, wherein the extracted characters are characters written on a whiteboard or a blackboard.

3. 2. The system according to claim 1, further comprising: means for accepting a request to receive audio data and video data; and means for allowing a user to specify a desired translation language.

Images