system

The system addresses language barriers in video content by translating and overlaying subtitles and audio in real-time, ensuring smooth communication and understanding across different languages.

JP2026099316APending Publication Date: 2026-06-18SOFTBANK GROUP CORP

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
SOFTBANK GROUP CORP
Filing Date
2024-12-06
Publication Date
2026-06-18

Smart Images

  • Figure 2026099316000001_ABST
    Figure 2026099316000001_ABST
Patent Text Reader

Abstract

We provide the system. [Solution] A method for recognizing text from video data, A means for translating the recognized characters into a different language, A means for overlaying and displaying the translated text on the video data, A means of recognizing and converting audio data into text, A means of translating transcribed audio data into different languages, A means of displaying subtitles by synchronizing translated audio data with video data, A system that includes this.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] An object of the present invention is to remove the language barrier and enable smoother communication when people speaking different languages watch video contents such as classes and lectures in real time. In particular, it is an object of the present invention to provide technical means for immediately recognizing not only voice but also character information included in video and efficiently providing the translated result to viewers.

Means for Solving the Problems

[0005] This invention solves the problem by providing means for recognizing characters from video data, means for translating the recognized characters into different languages, and means for overlaying and displaying the translated characters on the video data. Furthermore, by including means for recognizing and converting audio data into text, means for translating the converted audio data into different languages, and means for displaying the translated audio data as subtitles synchronized with the video data, it achieves real-time multilingual support for both audio and video.

[0006] "Video data" refers to digital information that includes visual information obtained by cameras or other means of acquiring images.

[0007] "Character recognition" is a technology that identifies textual information in video data and converts it into digital text data.

[0008] "Translation" is the process of converting text written in one language into a specified different language.

[0009] "Overlay" is a technique that displays additional information, such as text or images, superimposed on video data.

[0010] "Audio data" refers to a digital representation of acoustic information obtained through a microphone or other means of sound acquisition.

[0011] "Speech recognition" is a technology that analyzes audio data and converts it into text format.

[0012] "Subtitle display" is a technology that displays text on the screen as supplementary information when watching a video. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

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

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

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

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

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

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

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

[0021] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0034] This invention provides a multilingual system that enables speakers of different languages ​​to view lecture and presentation content in real time. This system primarily functions through three entities: a server, a terminal, and a user.

[0035] First, the user accesses online classes or lectures using their device. The device acquires audio and video data in real time and sends it to the server. The server performs speech recognition on the received data and converts the audio data into text. Then, it uses a translation API to translate this text into the specified language.

[0036] Next, regarding video data, the terminal transfers the video it captures or records to the server. The server uses optical character recognition (OCR) to extract text information from the video. This text information is also translated into different languages ​​as needed.

[0037] The translated audio and video text are integrated by the server and provided to the user as subtitles and video overlays. The device receives this and displays it on the user's screen in real time. This allows users to understand the content of lectures and presentations in their native language.

[0038] As a concrete example, when an English-speaking user watches a lecture delivered in Japanese, the device acquires Japanese audio and video and sends them to the server. The server translates the Japanese audio into English and displays it as subtitles. In addition, the Japanese text displayed on the slides is recognized by OCR, translated into English, and provided to the user. This process enables smooth content reception that transcends language barriers.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user accesses the online platform using their device and begins the class or lecture they wish to watch. The device acquires video and audio data in real time and prepares to stream this data to the server.

[0042] Step 2:

[0043] The terminal sends the streamed audio data to the server at regular intervals. The server performs speech recognition processing on the received audio data, converting the speech into text. A speech recognition algorithm is used for this conversion.

[0044] Step 3:

[0045] The server sends the text obtained through speech recognition to a translation API, which then translates it into the specified target language. The translation result is formatted as subtitle data and timestamped.

[0046] Step 4:

[0047] Simultaneously, the terminal continuously streams video data to the server. The server uses OCR (Optical Character Recognition) to detect text information from each frame of the video.

[0048] Step 5:

[0049] The text information extracted by OCR is also translated into the target language using a translation API. The server overlays the translated text onto the video frame, generating a video stream that can be viewed by the user along with subtitles.

[0050] Step 6:

[0051] The server encodes the translated subtitles and overlaid video in real time and delivers them to the device. The device receives this stream and displays it visually on the user's display.

[0052] Step 7:

[0053] Users will be able to understand the content of lectures and presentations in real time through translated videos and subtitles displayed on their devices.

[0054] (Example 1)

[0055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0056] When speakers of different languages ​​watch lectures or presentations in real time, a language barrier presents a challenge. This challenge arises from the lack of efficient systems that can translate and display different languages ​​within a realistic timeframe.

[0057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0058] In this invention, the server includes means for compressing and transmitting audio and video data received from the viewer's terminal, means for converting the received audio data into text information, and means for translating the text information into multiple languages. This makes it possible to view and understand information in different languages ​​in real time.

[0059] "Audio data received from the viewer's device" refers to information that represents the waveform of sound transmitted from the device used by the user in digital format.

[0060] "Means for compressing and transmitting video data" refers to technologies that reduce the amount of data in order to efficiently transmit video information.

[0061] "Methods for converting acoustic data into textual information" refers to technologies that analyze sound waveforms and convert them into corresponding strings of characters.

[0062] "Means of translating textual information into multiple languages" refers to the function of software that converts text written in one language into another language.

[0063] "Methods for overlaying information onto video data" refers to techniques that visually display additional information by overlaying it onto specific parts of a video.

[0064] "A means of acquiring and translating textual information from video data using optical technology" refers to a technology that recognizes text within an image and translates it into another language.

[0065] "A means of displaying translated text information in conjunction with video data" refers to a technology that displays translated text information on the screen at a timing corresponding to the content of the video.

[0066] This invention is a real-time lecture and presentation viewing system that supports multiple languages. The system mainly consists of three components: a server, a terminal, and a user.

[0067] Users access online classes and lectures using their devices. These devices include smartphones, tablets, or computers, and they utilize online meeting tools via an internet connection. An example of such a meeting tool is the general term "online meeting system."

[0068] The device uses a microphone and camera to acquire real-time audio and video data and sends this data to a server. The server converts the audio data into text information using a speech recognition algorithm. Specifically, a "speech recognition system" is used for this process. The converted text information is then translated into the desired language using a translation API.

[0069] Regarding video data, the server uses optical technology to extract text information from the video. An example of this optical technology is an "OCR system." This text information is then translated using a translation API.

[0070] The server overlays the translated text onto the video data in real time. The receiving terminal then displays this result as subtitles on the user's screen. This allows users to understand the content of lectures and presentations in their own language.

[0071] As a concrete example, consider a scenario where an English-speaking user is watching a lecture conducted in Japanese. The device acquires Japanese audio and video and sends them to the server. On the server, the audio data is translated into English text and displayed as subtitles. Similarly, the text within the video is translated into English and provided to the user. In this way, content can be received smoothly, transcending language barriers.

[0072] Example of a prompt for a generative AI model: "Please describe in detail the programmatic processing flow for viewing an online lecture in Japanese with real-time English subtitles."

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] The user accesses online classes and lectures using their device. The device, via its internet connection, launches the online conferencing system and acquires audio and video data of the lecture in real time. In this step, the video and audio data of the online lecture are used as input, and this data is passed directly to the next step as output.

[0076] Step 2:

[0077] The terminal sends the acquired audio and video data to the server. The data is compressed before transmission and optimized for faster processing on the server. The input for this step is the raw audio and video data acquired by the terminal, and the output is the compressed data sent to the server.

[0078] Step 3:

[0079] The server receives compressed audio data and converts it into text information using a speech recognition system. In this conversion, the audio waveform data is used as input, and the corresponding text data is generated as output. Specifically, the server performs calculations such as noise reduction and speech segmentation.

[0080] Step 4:

[0081] The server translates the generated text information into multiple languages ​​using a translation API. The input is text information converted from speech, and the output is text translated into the user's desired language. The server performs contextual analysis and other processes to maintain translation accuracy throughout this process.

[0082] Step 5:

[0083] The server acquires text information from video data using optical technology. Here, an OCR system analyzes video frames and extracts text. The input is compressed video data, and the output is text information within the video. The server filters the data according to the characteristics of the video.

[0084] Step 6:

[0085] The system translates text information obtained using OCR technology into the language specified by the translation API. The input is raw text information from the OCR, and the output is translated text information. The server maintains the translation results in a consistent format.

[0086] Step 7:

[0087] The server integrates translated text and audio-text information and generates subtitles by overlaying them onto the video data. The input is translated text information, and the output is video data with the overlay. The server uses a video synchronization function to adjust the timing of the subtitle display.

[0088] Step 8:

[0089] The terminal receives video data with overlays sent from the server and displays it on the user's screen in real time. The input is video data with overlay information, and the output provides video that contributes to the user's viewing experience. The terminal optimizes the video display using playback software.

[0090] (Application Example 1)

[0091] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] Currently, there is a challenge in smooth communication among family members who speak different languages. In particular, important conversations in daily life can be hindered by language barriers. This can impede the sharing of emotions and the transmission of intentions, potentially weakening family ties.

[0093] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0094] In this invention, the server includes processing means for recognizing linguistic expressions from video information, processing means for translating the recognized linguistic expressions into a different language, and processing means for overlaying and displaying the translated linguistic expressions on the video information. This enables smooth, real-time communication between members of a household who speak different languages, and reduces communication barriers caused by language differences.

[0095] "Visual information" refers to visual data, specifically information related to vision acquired through video equipment.

[0096] "Linguistic expression" refers to texts or symbols that concretely represent content or information conveyed through language.

[0097] "Recognition processing means" refers to technologies and methods for analyzing input data and identifying its content.

[0098] A "translation processing method" refers to a technology or system for converting information expressed in one language into another language.

[0099] "Processing methods for overlaying information" refer to technologies and techniques for visually presenting new information by overlaying it on top of existing video information.

[0100] "Auditory information" refers to data related to sounds that can be received aurally.

[0101] "Documentation processing means" refers to technologies and systems for converting acquired audio information into text format.

[0102] "Subtitle display processing means" refers to technologies and methods for adding linguistic information to video and presenting it visually.

[0103] To implement this invention, a server plays a central role. The server receives audio and video information transmitted from a home communication robot. The server documents the audio information and utilizes Amazon Transcribe and Google Translate API to translate its contents into different languages. In addition, the server recognizes linguistic expressions contained in the video information using Tesseract OCR and similarly translates them into different languages.

[0104] The converted language expressions and texts are processed on the server into data structures appropriate for each display format. This allows home robots to overlay translated subtitles onto video information or play translated audio.

[0105] The device, in this case a home robot, provides the user with translated information in visual or audio format. This allows the user to communicate in real time with family members who speak different languages.

[0106] For example, if a parent says "What do you want for lunch?" in Japanese, the robot will display the subtitle "What do you want for lunch?" to the child. Sometimes, a translated voice message will also play simultaneously. An example of a prompt message is, "Please translate the Japanese voice input into English in real time."

[0107] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0108] Step 1:

[0109] The device (a home robot) captures conversations within the home as voice input via its microphone. This input is sent to the server in stream format. The server then converts this voice data into text using Amazon Transcribe. This process results in the creation of a documented voice.

[0110] Step 2:

[0111] The server uses the Google Translate API to convert transcribed speech information into a different language specified by the user. The input is transcribed Japanese data, and the output is translated English text. The translation results are stored in a database and used in subsequent processes.

[0112] Step 3:

[0113] The device uses its camera to capture video information from within the home. This video data is transferred to a server, which uses Tesseract OCR to extract text information from the video. The input is a still image or a video frame, and the output is the extracted Japanese text.

[0114] Step 4:

[0115] The server also translates the text information extracted by OCR into the specified language using the Google Translate API. The input is the extracted Japanese text information, and the output is the translated English text information.

[0116] Step 5:

[0117] The server integrates the translated audio and video text and prepares it for display on the home robot's screen. The user will see English subtitles overlaid on the video data. This step includes video synchronization and subtitle formatting adjustments.

[0118] Step 6:

[0119] The device receives integrated data and provides it to the user. The user can then understand domestic conversations in other languages ​​through voice guidance and subtitles.

[0120] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0121] This invention is a multilingual system that allows users to view lessons and lectures in different languages ​​in real time, and further incorporates an emotion engine that recognizes the user's emotions in real time and provides information accordingly. This system mainly consists of three components: a server, a terminal, and a user.

[0122] Users connect to an online platform using their devices to view lectures and presentations in real time. The devices have the capability to acquire audio and video data from users and transmit it to a server. The server applies speech recognition to the acquired audio data and converts it to text. It also has the functionality to translate the textualized audio data into a language specified by the user.

[0123] Simultaneously, the server uses optical character recognition (OCR) to detect text information from the video data and translates the recognized text information into different languages ​​as needed. The translated text and audio text are then overlaid and provided to the user as subtitles.

[0124] A distinctive feature of this invention is the incorporation of an emotion engine. The emotion engine analyzes the user's voice tone, speed, and facial expression data to evaluate the user's emotional state in real time. The terminal acquires necessary data through its camera and microphone, and the server analyzes this data using the emotion engine. The obtained emotional information is used to optimize the user experience. For example, if the emotion engine detects that the user is confused, the system can provide additional explanations.

[0125] As a concrete example, when an English-speaking user watches a lecture conducted in Japanese, the device acquires Japanese audio and video, and the server translates this data into English and provides it. Furthermore, if the user expresses surprise or confusion, the system automatically provides corresponding content to support the user's understanding. This provides a rich learning experience that transcends language and emotional barriers.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The user accesses the online platform via their device and begins the class or lecture they wish to watch. The device acquires video data through its camera and collects audio data through its microphone. This data is then prepared for streaming to the server.

[0129] Step 2:

[0130] The terminal sends audio data to the server at specific time intervals. The server processes the received audio data using speech recognition and converts the audio content into text format. This conversion is performed using a speech recognition algorithm.

[0131] Step 3:

[0132] The server sends the text data obtained through speech recognition to a translation API, which translates it into the target language specified in the assignment. The translated text data is then formatted in a user-friendly format.

[0133] Step 4:

[0134] The terminal continuously streams video data in real time, and the server analyzes each frame of the video. The server uses optical character recognition (OCR) to extract text information from the video and generates digital text data.

[0135] Step 5:

[0136] The text data obtained by OCR is also translated into the target language using a translation API. The server overlays the translated text data onto the video, preparing it for display on the user's screen.

[0137] Step 6:

[0138] The emotion engine is activated, and the server analyzes the user's facial expression and voice data transmitted from the terminal. It recognizes the emotional signs the user is showing and evaluates those emotions in real time.

[0139] Step 7:

[0140] Based on the emotion recognition results, the server takes actions that correspond to the user's emotions. For example, if the server determines that the user is confused, it automatically provides additional explanations or hints. This helps users achieve better understanding despite language barriers.

[0141] (Example 2)

[0142] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0143] Understanding lectures and presentations in different languages ​​in real time is difficult for many users. Furthermore, the inability to receive appropriate emotional responses to the content of lectures and presentations limits the user experience. To solve these problems, real-time language translation and information delivery that responds to the user's emotions are necessary.

[0144] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0145] In this invention, the server includes means for recognizing text from video information, means for recognizing and documenting audio information, and means for collecting and evaluating the user's voice and facial expression information in real time in order to analyze their emotional state. This enables the user to understand content in different languages ​​in real time and to receive information tailored to their individual emotional state.

[0146] "Visual information" refers to visual data acquired through cameras and digital devices, enabling a visual understanding of the content.

[0147] "Notation" refers to the characters and symbols contained within video information, and these should be recognized in order to convert that information into a format that users can understand.

[0148] "Acoustic information" refers to audio data acquired through microphones or other means, which conveys auditory content or information.

[0149] "Documentation" refers to the process of recognizing acoustic information and converting it into text, with the aim of transforming collected data into a clear and searchable format.

[0150] "Emotional state" refers to the mental and emotional state of a user, evaluated by analyzing user behavior indicators such as voice tone and facial expression data.

[0151] "Evaluating in real time" refers to a process where data is acquired and analyzed simultaneously, so that the information is immediately reflected in the data.

[0152] This invention is a system that enables real-time viewing of multilingual lessons and lectures, and further provides information tailored to the user's emotional state. The system mainly consists of three components: a server, a terminal, and the user.

[0153] First, users connect to an online platform using their device and watch classes or lectures in real time. The device then uses its built-in camera and microphone to acquire video and audio information.

[0154] After the server receives the data sent from the terminal, the following processes take place: The server applies speech recognition technology to the audio information and documents the speech as text. This process uses speech recognition modules such as speech recognition software APIs. Furthermore, this text information is translated into a language that the user can understand by a multilingual translation system. In this step, for example, the use of a translation API can be considered.

[0155] Regarding video information, the server uses optical character recognition technology to analyze the text within the video and extract the text information. This text information is also translated into different languages ​​and displayed overlaid on the video information, enabling real-time subtitle generation.

[0156] Furthermore, to analyze the user's emotional state, the device transmits voice tone and facial expression information to the server. The server evaluates this in real time using emotion analysis technology and provides additional information tailored to the user's level of understanding and emotions. This allows users to understand the content of lectures and classes more effectively.

[0157] As a concrete example, when an English-speaking user watches a lecture delivered in Japanese, the device acquires the Japanese audio and video, and the server translates it into English and displays subtitles in real time. In this case, if the user appears confused, the system can automatically provide additional English annotations or explanations.

[0158] An example of a prompt to input into a generative AI model would be: "Translate the audio and text of a lecture given in Japanese into English and display them as subtitles in real time. Also, provide additional explanations if the user becomes confused." This allows users to enjoy a learning experience that transcends language and emotional barriers.

[0159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0160] Step 1:

[0161] The user connects to the online platform using their device. Based on the user's actions, the device opens a web browser or dedicated application and accesses a URL or address that streams real-time classes or lectures. The platform then begins streaming the video and audio data of the classes or lectures to the device.

[0162] Input: User connection request

[0163] Output: Real-time video and audio data

[0164] Step 2:

[0165] The device uses its camera and microphone to send acquired video and audio information to the server. In this process, video data is sent to the server in video stream format (e.g., H.264), and audio data is sent in audio stream format (e.g., AAC).

[0166] Input: Real-time video and audio data

[0167] Output: Streaming data to the server

[0168] Step 3:

[0169] The server converts the received acoustic information into text information using speech recognition technology. The speech recognition module (e.g., speech recognition software API) analyzes the acoustic signal, statistically evaluates the extracted phonemes, and generates the corresponding string.

[0170] Input: Streamed audio data

[0171] Output: Text information (text-converted audio data)

[0172] Step 4:

[0173] The server translates text information into the specified language using a multilingual translation system. A multilingual translation module (e.g., a translation API) takes text data as input and applies a translation algorithm to generate text data corresponding to a specific target language.

[0174] Input: Transcribed audio data

[0175] Output: Translated text information

[0176] Step 5:

[0177] The server applies optical character recognition (OCR) technology to the video information, analyzing the text within the video to extract character information. The OCR system identifies text areas from the video frame, analyzes the font, character shape, color, etc. used within them, and generates corresponding text data.

[0178] Input: Streamed video data

[0179] Output: Analyzed text information (text in the video)

[0180] Step 6:

[0181] The server translates the text information acquired by OCR into different languages ​​and converts it into a format that can be overlaid on the video information. The translated text is generated as a subtitle file for visualization and is composited into the streaming video.

[0182] Input: OCR result text information

[0183] Output: Translated subtitle text

[0184] Step 7:

[0185] The device's camera and microphone collect the user's voice tone and facial expression information in real time and send it to the server. The server analyzes this data using an emotion analysis module and evaluates the user's emotional state in real time.

[0186] Input: User's voice tone and facial expression data

[0187] Output: Real-time sentiment evaluation results

[0188] Step 8:

[0189] Based on the sentiment analysis results, the server determines and sends additional information necessary to optimize the user experience. This process selects emotionally relevant hints and supplementary explanations, presenting them in a user-friendly format.

[0190] Input: Sentiment evaluation result

[0191] Output: Additional information provided to the user

[0192] (Application Example 2)

[0193] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0194] When viewing lectures or classes delivered in different languages ​​in real time, there is a need to eliminate the delays and confusion caused by language differences and to provide personalized information that responds to the viewer's emotions. However, conventional technologies have lacked the ability to provide information based on the viewer's emotions, making it difficult to optimize the viewer experience. Therefore, new technologies are needed to effectively solve these problems.

[0195] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0196] In this invention, the server includes means for recognizing characters from a video signal, means for translating the recognized characters into a different language, means for overlaying and displaying the translated characters on the video signal, and means for recognizing an audio signal and converting it into text. This enables real-time analysis of the viewer's emotional state while viewing content in different languages, facilitating understanding and providing personalized information tailored to their emotions.

[0197] A "video signal" is a signal obtained by converting changes in light into an electrical signal, and it is a medium for transmitting visual information.

[0198] "Means of recognizing characters" refers to technology that extracts character information from video signals in digital format, thereby enabling automated character reading.

[0199] "Means of translation into different languages" refers to technologies that convert text or sound from one language to another, facilitating communication between multiple languages.

[0200] "Methods of overlaying" refer to techniques that visually display additional information on top of the original image, providing viewers with extra information.

[0201] An "audio signal" is a signal obtained by converting fluctuations in sound into an electrical signal, and it is a medium for transmitting auditory information.

[0202] "Means of recognizing speech and converting it into text" refers to technology that interprets speech signals and converts them into textual information, and is a means of visualizing speech.

[0203] "Methods for analyzing emotions in real time" refer to technologies that immediately evaluate a user's emotional state based on audio and video data, making it possible to grasp their emotions at that moment.

[0204] "Personalized information delivery" refers to providing information optimized according to the user's specific needs and circumstances, thereby offering a more effective experience.

[0205] This invention is a system that enables real-time viewing of lectures and classes delivered in different languages, and provides personalized information tailored to the viewer's emotions. The system mainly consists of three components: a server, a terminal, and a user.

[0206] The device is equipped with a camera and microphone to acquire audio and video signals. This data is sent to a server. The server uses a speech recognition algorithm to convert the audio signals into text and translate them into different languages. The translated audio text is displayed as visual information, overlaid on the video signal.

[0207] The server also uses optical character recognition (OCR) technology to recognize characters within the video signal. The recognized characters are translated into a specified language and overlaid on the video signal for the user to see.

[0208] Furthermore, the server uses a generative AI model to analyze the user's voice tone and speed, as well as video data, to evaluate the user's emotional state in real time. This allows it to detect emotions such as surprise or confusion and provide additional information corresponding to those emotions. For example, if a user expresses surprise during a lecture, relevant background information is presented to clarify the meaning of this emotion.

[0209] As a concrete example, when a user watches a history lecture delivered in Japanese but in English, the system displays subtitles with real-time translation and provides additional information about the historical context when the user expresses surprise or questions. An example of a prompt to the generative AI model in such a system might be, "Surprised user detected from user emotion data. Please provide background information related to the content being viewed."

[0210] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0211] Step 1:

[0212] The terminal uses the user's camera and microphone to acquire video and audio signals. The input consists of real-time visual and audio data, which are then transmitted to the server in digital format.

[0213] Step 2:

[0214] The server applies a speech recognition algorithm to the received audio signal. The input is an audio signal, and this data is output as text data. This process converts the audio content into text.

[0215] Step 3:

[0216] The server translates text data obtained through speech recognition into different languages. The input is text data, and the translation engine outputs the translated text in the specified language. This translation result is then used in the next step.

[0217] Step 4:

[0218] The server uses optical character recognition (OCR) technology to recognize characters from video signals. The input is a video signal, and the extracted character information is output as text data. This data is used in a later translation step.

[0219] Step 5:

[0220] The server translates the characters recognized in the video into a different language. The input is character information detected by OCR, and this is output as text in the specified language.

[0221] Step 6:

[0222] The server overlays translated text and audio data onto the video signal. The input is the translated text and video signal, and the output is a subtitled video presented to the user. This subtitle information visually supplements the user's understanding.

[0223] Step 7:

[0224] The server uses a generative AI model to analyze the user's voice tone and facial expressions from the video, and evaluates their emotions. The input is audio and video data, and the output is the user's emotion evaluation result.

[0225] Step 8:

[0226] Based on the sentiment evaluation results, the server provides additional information tailored to the user's state. The input consists of the sentiment evaluation results and information about the content being viewed, while the output is additional information to aid user understanding. This makes it easier for users to gain a deeper understanding of the content's context.

[0227] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0228] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0229] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0233] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0234] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0235] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0236] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0237] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0238] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0239] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0240] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0241] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0242] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0243] This invention provides a multilingual system that enables speakers of different languages ​​to view lecture and presentation content in real time. This system primarily functions through three entities: a server, a terminal, and a user.

[0244] First, the user accesses online classes or lectures using their device. The device acquires audio and video data in real time and sends it to the server. The server performs speech recognition on the received data and converts the audio data into text. Then, it uses a translation API to translate this text into the specified language.

[0245] Next, regarding video data, the terminal transfers the video it captures or records to the server. The server uses optical character recognition (OCR) to extract text information from the video. This text information is also translated into different languages ​​as needed.

[0246] The translated audio and video text are integrated by the server and provided to the user as subtitles and video overlays. The device receives this and displays it on the user's screen in real time. This allows users to understand the content of lectures and presentations in their native language.

[0247] As a concrete example, when an English-speaking user watches a lecture delivered in Japanese, the device acquires Japanese audio and video and sends them to the server. The server translates the Japanese audio into English and displays it as subtitles. In addition, the Japanese text displayed on the slides is recognized by OCR, translated into English, and provided to the user. This process enables smooth content reception that transcends language barriers.

[0248] The following describes the processing flow.

[0249] Step 1:

[0250] The user accesses the online platform using their device and begins the class or lecture they wish to watch. The device acquires video and audio data in real time and prepares to stream this data to the server.

[0251] Step 2:

[0252] The terminal sends the streamed audio data to the server at regular intervals. The server performs speech recognition processing on the received audio data, converting the speech into text. A speech recognition algorithm is used for this conversion.

[0253] Step 3:

[0254] The server sends the text obtained through speech recognition to a translation API, which then translates it into the specified target language. The translation result is formatted as subtitle data and timestamped.

[0255] Step 4:

[0256] Simultaneously, the terminal continuously streams video data to the server. The server uses OCR (Optical Character Recognition) to detect text information from each frame of the video.

[0257] Step 5:

[0258] The text information extracted by OCR is also translated into the target language using a translation API. The server overlays the translated text onto the video frame, generating a video stream that can be viewed by the user along with subtitles.

[0259] Step 6:

[0260] The server encodes the translated subtitles and overlaid video in real time and delivers them to the device. The device receives this stream and displays it visually on the user's display.

[0261] Step 7:

[0262] Users will be able to understand the content of lectures and presentations in real time through translated videos and subtitles displayed on their devices.

[0263] (Example 1)

[0264] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0265] When speakers of different languages ​​watch lectures or presentations in real time, a language barrier presents a challenge. This challenge arises from the lack of efficient systems that can translate and display different languages ​​within a realistic timeframe.

[0266] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0267] In this invention, the server includes means for compressing and transmitting audio and video data received from the viewer's terminal, means for converting the received audio data into text information, and means for translating the text information into multiple languages. This makes it possible to view and understand information in different languages ​​in real time.

[0268] "Audio data received from the viewer's device" refers to information that represents the waveform of sound transmitted from the device used by the user in digital format.

[0269] "Means for compressing and transmitting video data" refers to technologies that reduce the amount of data in order to efficiently transmit video information.

[0270] "Methods for converting acoustic data into textual information" refers to technologies that analyze sound waveforms and convert them into corresponding strings of characters.

[0271] "Means of translating textual information into multiple languages" refers to the function of software that converts text written in one language into another language.

[0272] "Methods for overlaying information onto video data" refers to techniques that visually display additional information by overlaying it onto specific parts of a video.

[0273] "A means of acquiring and translating textual information from video data using optical technology" refers to a technology that recognizes text within an image and translates it into another language.

[0274] "A means of displaying translated text information in conjunction with video data" refers to a technology that displays translated text information on the screen at a timing corresponding to the content of the video.

[0275] This invention is a real-time lecture and presentation viewing system that supports multiple languages. The system mainly consists of three components: a server, a terminal, and a user.

[0276] Users access online classes and lectures using their devices. These devices include smartphones, tablets, or computers, and they utilize online meeting tools via an internet connection. An example of such a meeting tool is the general term "online meeting system."

[0277] The device uses a microphone and camera to acquire real-time audio and video data and sends this data to a server. The server converts the audio data into text information using a speech recognition algorithm. Specifically, a "speech recognition system" is used for this process. The converted text information is then translated into the desired language using a translation API.

[0278] Regarding video data, the server uses optical technology to extract text information from the video. An example of this optical technology is an "OCR system." This text information is then translated using a translation API.

[0279] The server overlays the translated text onto the video data in real time. The receiving terminal then displays this result as subtitles on the user's screen. This allows users to understand the content of lectures and presentations in their own language.

[0280] As a specific example, consider the case where a lecture conducted in Japanese is viewed by a user who speaks English. The terminal acquires the Japanese audio and video and transmits them to the server. At the server, the audio data is translated into English character information and displayed as subtitles. Also, the character information within the video is translated into English and provided to the user. In this way, it becomes possible to smoothly receive the content across language differences.

[0281] Example of a prompt sentence for the generative AI model: "Please specifically explain the program processing flow for viewing a Japanese online lecture with real-time English subtitles."

[0282] The flow of the specific processing in Example 1 will be described using FIG. 11.

[0283] Step 1:

[0284] The user accesses an online class or lecture using the terminal. The terminal activates an online meeting system via an Internet connection and acquires the acoustic data and video data of the lecture in real time. In this step, the video and acoustic data of the online lecture are used as input, and these data are directly passed to the next step as output.

[0285] Step 2:

[0286] The terminal transmits the acquired acoustic data and video data to the server. The data is compressed and transmitted, optimized for rapid processing at the server. The input for this step is the raw acoustic data and video data acquired by the terminal, and the output is the compressed data sent to the server.

[0287] Step 3:

[0288] The server receives compressed audio data and converts it into text information using a speech recognition system. In this conversion, the audio waveform data is used as input, and the corresponding text data is generated as output. Specifically, the server performs calculations such as noise reduction and speech segmentation.

[0289] Step 4:

[0290] The server translates the generated text information into multiple languages ​​using a translation API. The input is text information converted from speech, and the output is text translated into the user's desired language. The server performs contextual analysis and other processes to maintain translation accuracy throughout this process.

[0291] Step 5:

[0292] The server acquires text information from video data using optical technology. Here, an OCR system analyzes video frames and extracts text. The input is compressed video data, and the output is text information within the video. The server filters the data according to the characteristics of the video.

[0293] Step 6:

[0294] The system translates text information obtained using OCR technology into the language specified by the translation API. The input is raw text information from the OCR, and the output is translated text information. The server maintains the translation results in a consistent format.

[0295] Step 7:

[0296] The server integrates translated text and audio-text information and generates subtitles by overlaying them onto the video data. The input is translated text information, and the output is video data with the overlay. The server uses a video synchronization function to adjust the timing of the subtitle display.

[0297] Step 8:

[0298] The terminal receives video data with overlays sent from the server and displays it on the user's screen in real time. The input is video data with overlay information, and the output provides video that contributes to the user's viewing experience. The terminal optimizes the video display using playback software.

[0299] (Application Example 1)

[0300] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0301] Currently, there is a challenge in smooth communication among family members who speak different languages. In particular, important conversations in daily life can be hindered by language barriers. This can impede the sharing of emotions and the transmission of intentions, potentially weakening family ties.

[0302] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0303] In this invention, the server includes processing means for recognizing linguistic expressions from video information, processing means for translating the recognized linguistic expressions into a different language, and processing means for overlaying and displaying the translated linguistic expressions on the video information. This enables smooth, real-time communication between members of a household who speak different languages, and reduces communication barriers caused by language differences.

[0304] "Visual information" refers to visual data, specifically information related to vision acquired through video equipment.

[0305] "Linguistic expression" refers to texts or symbols that concretely represent content or information conveyed through language.

[0306] "Recognition processing means" refers to technologies and methods for analyzing input data and identifying its content.

[0307] The "processing means for translation" is a technology or system for converting information expressed in one language into another language.

[0308] The "processing means for superimposed display" is a technology or method for visually presenting new information by superimposing it on existing video information.

[0309] "Audio information" is data related to sounds that can be aurally received.

[0310] The "processing means for documentation" is a technology or system for converting the acquired audio information into text format.

[0311] The "processing means for subtitle display" is a technology or means for visually presenting language information by adding it to video.

[0312] To implement this invention, first, the server plays a central role. The server receives audio information and video information transmitted from a communication robot within a home. The server utilizes Amazon Transcribe and Google Translate API to document the audio information and translate its content into different languages. In addition, the server uses Tesseract OCR to recognize the language expressions included in the video information and similarly translate them into different languages.

[0313] The converted language expressions and text are processed by the server into data structures corresponding to their respective display formats. As a result, the robot within the home can superimpose and display the translated subtitles on the video information or play the translated audio.

[0314] The terminal, here a home robot, provides the translated information to the user visually or aurally. As a result, the user can be supported in real-time communication with family members who use different languages.

[0315] For example, if a parent says "What do you want for lunch?" in Japanese, the robot will display the subtitle "What do you want for lunch?" to the child. Sometimes, a translated voice message will also play simultaneously. An example of a prompt message is, "Please translate the Japanese voice input into English in real time."

[0316] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0317] Step 1:

[0318] The device (a home robot) captures conversations within the home as voice input via its microphone. This input is sent to the server in stream format. The server then converts this voice data into text using Amazon Transcribe. This process results in the creation of a documented voice.

[0319] Step 2:

[0320] The server uses the Google Translate API to convert transcribed speech information into a different language specified by the user. The input is transcribed Japanese data, and the output is translated English text. The translation results are stored in a database and used in subsequent processes.

[0321] Step 3:

[0322] The device uses its camera to capture video information from within the home. This video data is transferred to a server, which uses Tesseract OCR to extract text information from the video. The input is a still image or a video frame, and the output is the extracted Japanese text.

[0323] Step 4:

[0324] The server also translates the text information extracted by OCR into the specified language using the Google Translate API. The input is the extracted Japanese text information, and the output is the translated English text information.

[0325] Step 5:

[0326] The server integrates the translated audio and video text and prepares it for display on the home robot's screen. The user will see English subtitles overlaid on the video data. This step includes video synchronization and subtitle formatting adjustments.

[0327] Step 6:

[0328] The device receives integrated data and provides it to the user. The user can then understand domestic conversations in other languages ​​through voice guidance and subtitles.

[0329] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0330] This invention is a multilingual system that allows users to view lessons and lectures in different languages ​​in real time, and further incorporates an emotion engine that recognizes the user's emotions in real time and provides information accordingly. This system mainly consists of three components: a server, a terminal, and a user.

[0331] Users connect to an online platform using their devices to view lectures and presentations in real time. The devices have the capability to acquire audio and video data from users and transmit it to a server. The server applies speech recognition to the acquired audio data and converts it to text. It also has the functionality to translate the textualized audio data into a language specified by the user.

[0332] Simultaneously, the server uses optical character recognition (OCR) to detect text information from the video data and translates the recognized text information into different languages ​​as needed. The translated text and audio text are then overlaid and provided to the user as subtitles.

[0333] A distinctive feature of this invention is the incorporation of an emotion engine. The emotion engine analyzes the user's voice tone, speed, and facial expression data to evaluate the user's emotional state in real time. The terminal acquires necessary data through its camera and microphone, and the server analyzes this data using the emotion engine. The obtained emotional information is used to optimize the user experience. For example, if the emotion engine detects that the user is confused, the system can provide additional explanations.

[0334] As a concrete example, when an English-speaking user watches a lecture conducted in Japanese, the device acquires Japanese audio and video, and the server translates this data into English and provides it. Furthermore, if the user expresses surprise or confusion, the system automatically provides corresponding content to support the user's understanding. This provides a rich learning experience that transcends language and emotional barriers.

[0335] The following describes the processing flow.

[0336] Step 1:

[0337] The user accesses the online platform via their device and begins the class or lecture they wish to watch. The device acquires video data through its camera and collects audio data through its microphone. This data is then prepared for streaming to the server.

[0338] Step 2:

[0339] The terminal sends audio data to the server at specific time intervals. The server processes the received audio data using speech recognition and converts the audio content into text format. This conversion is performed using a speech recognition algorithm.

[0340] Step 3:

[0341] The server sends the text data obtained through speech recognition to a translation API, which translates it into the target language specified in the assignment. The translated text data is then formatted in a user-friendly format.

[0342] Step 4:

[0343] The terminal continuously streams video data in real time, and the server analyzes each frame of the video. The server uses optical character recognition (OCR) to extract text information from the video and generates digital text data.

[0344] Step 5:

[0345] The text data obtained by OCR is also translated into the target language using a translation API. The server overlays the translated text data onto the video, preparing it for display on the user's screen.

[0346] Step 6:

[0347] The emotion engine is activated, and the server analyzes the user's facial expression and voice data transmitted from the terminal. It recognizes the emotional signs the user is showing and evaluates those emotions in real time.

[0348] Step 7:

[0349] Based on the emotion recognition results, the server takes actions that correspond to the user's emotions. For example, if the server determines that the user is confused, it automatically provides additional explanations or hints. This helps users achieve better understanding despite language barriers.

[0350] (Example 2)

[0351] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0352] Understanding lectures and presentations in different languages ​​in real time is difficult for many users. Furthermore, the inability to receive appropriate emotional responses to the content of lectures and presentations limits the user experience. To solve these problems, real-time language translation and information delivery that responds to the user's emotions are necessary.

[0353] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0354] In this invention, the server includes means for recognizing text from video information, means for recognizing and documenting audio information, and means for collecting and evaluating the user's voice and facial expression information in real time in order to analyze their emotional state. This enables the user to understand content in different languages ​​in real time and to receive information tailored to their individual emotional state.

[0355] "Visual information" refers to visual data acquired through cameras and digital devices, enabling a visual understanding of the content.

[0356] "Notation" refers to the characters and symbols contained within video information, and these should be recognized in order to convert that information into a format that users can understand.

[0357] "Acoustic information" refers to audio data acquired through microphones or other means, which conveys auditory content or information.

[0358] "Documentation" refers to the process of recognizing acoustic information and converting it into text, with the aim of transforming collected data into a clear and searchable format.

[0359] "Emotional state" refers to the mental and emotional state of a user, evaluated by analyzing user behavior indicators such as voice tone and facial expression data.

[0360] "Evaluating in real time" refers to a process where data is acquired and analyzed simultaneously, so that the information is immediately reflected in the data.

[0361] This invention is a system that enables real-time viewing of multilingual lessons and lectures, and further provides information tailored to the user's emotional state. The system mainly consists of three components: a server, a terminal, and the user.

[0362] First, users connect to an online platform using their device and watch classes or lectures in real time. The device then uses its built-in camera and microphone to acquire video and audio information.

[0363] After the server receives the data sent from the terminal, the following processes take place: The server applies speech recognition technology to the audio information and documents the speech as text. This process uses speech recognition modules such as speech recognition software APIs. Furthermore, this text information is translated into a language that the user can understand by a multilingual translation system. In this step, for example, the use of a translation API can be considered.

[0364] Regarding video information, the server uses optical character recognition technology to analyze the text within the video and extract the text information. This text information is also translated into different languages ​​and displayed overlaid on the video information, enabling real-time subtitle generation.

[0365] Furthermore, to analyze the user's emotional state, the device transmits voice tone and facial expression information to the server. The server evaluates this in real time using emotion analysis technology and provides additional information tailored to the user's level of understanding and emotions. This allows users to understand the content of lectures and classes more effectively.

[0366] As a concrete example, when an English-speaking user watches a lecture delivered in Japanese, the device acquires the Japanese audio and video, and the server translates it into English and displays subtitles in real time. In this case, if the user appears confused, the system can automatically provide additional English annotations or explanations.

[0367] An example of a prompt to input into a generative AI model would be: "Translate the audio and text of a lecture given in Japanese into English and display them as subtitles in real time. Also, provide additional explanations if the user becomes confused." This allows users to enjoy a learning experience that transcends language and emotional barriers.

[0368] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0369] Step 1:

[0370] The user connects to the online platform using their device. Based on the user's actions, the device opens a web browser or dedicated application and accesses a URL or address that streams real-time classes or lectures. The platform then begins streaming the video and audio data of the classes or lectures to the device.

[0371] Input: User connection request

[0372] Output: Real-time video and audio data

[0373] Step 2:

[0374] The device uses its camera and microphone to send acquired video and audio information to the server. In this process, video data is sent to the server in video stream format (e.g., H.264), and audio data is sent in audio stream format (e.g., AAC).

[0375] Input: Real-time video and audio data

[0376] Output: Streaming data to the server

[0377] Step 3:

[0378] The server converts the received acoustic information into text information using speech recognition technology. The speech recognition module (e.g., speech recognition software API) analyzes the acoustic signal, statistically evaluates the extracted phonemes, and generates the corresponding string.

[0379] Input: Streamed audio data

[0380] Output: Text information (text-converted audio data)

[0381] Step 4:

[0382] The server translates text information into the specified language using a multilingual translation system. A multilingual translation module (e.g., a translation API) takes text data as input and applies a translation algorithm to generate text data corresponding to a specific target language.

[0383] Input: Transcribed audio data

[0384] Output: Translated text information

[0385] Step 5:

[0386] The server applies optical character recognition (OCR) technology to the video information, analyzing the text within the video to extract character information. The OCR system identifies text areas from the video frame, analyzes the font, character shape, color, etc. used within them, and generates corresponding text data.

[0387] Input: Streamed video data

[0388] Output: Analyzed text information (text in the video)

[0389] Step 6:

[0390] The server translates the text information acquired by OCR into different languages ​​and converts it into a format that can be overlaid on the video information. The translated text is generated as a subtitle file for visualization and is composited into the streaming video.

[0391] Input: OCR result text information

[0392] Output: Translated subtitle text

[0393] Step 7:

[0394] The device's camera and microphone collect the user's voice tone and facial expression information in real time and send it to the server. The server analyzes this data using an emotion analysis module and evaluates the user's emotional state in real time.

[0395] Input: User's voice tone and facial expression data

[0396] Output: Real-time sentiment evaluation results

[0397] Step 8:

[0398] Based on the sentiment analysis results, the server determines and sends additional information necessary to optimize the user experience. This process selects emotionally relevant hints and supplementary explanations, presenting them in a user-friendly format.

[0399] Input: Sentiment evaluation result

[0400] Output: Additional information provided to the user

[0401] (Application Example 2)

[0402] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0403] When viewing lectures or classes delivered in different languages ​​in real time, there is a need to eliminate the delays and confusion caused by language differences and to provide personalized information that responds to the viewer's emotions. However, conventional technologies have lacked the ability to provide information based on the viewer's emotions, making it difficult to optimize the viewer experience. Therefore, new technologies are needed to effectively solve these problems.

[0404] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0405] In this invention, the server includes means for recognizing characters from a video signal, means for translating the recognized characters into a different language, means for overlaying and displaying the translated characters on the video signal, and means for recognizing an audio signal and converting it into text. This enables real-time analysis of the viewer's emotional state while viewing content in different languages, facilitating understanding and providing personalized information tailored to their emotions.

[0406] A "video signal" is a signal obtained by converting changes in light into an electrical signal, and it is a medium for transmitting visual information.

[0407] "Means of recognizing characters" refers to technology that extracts character information from video signals in digital format, thereby enabling automated character reading.

[0408] "Means of translation into different languages" refers to technologies that convert text or sound from one language to another, facilitating communication between multiple languages.

[0409] "Methods of overlaying" refer to techniques that visually display additional information on top of the original image, providing viewers with extra information.

[0410] An "audio signal" is a signal obtained by converting fluctuations in sound into an electrical signal, and it is a medium for transmitting auditory information.

[0411] "Means of recognizing speech and converting it into text" refers to technology that interprets speech signals and converts them into textual information, and is a means of visualizing speech.

[0412] "Methods for analyzing emotions in real time" refer to technologies that immediately evaluate a user's emotional state based on audio and video data, making it possible to grasp their emotions at that moment.

[0413] "Personalized information delivery" refers to providing information optimized according to the user's specific needs and circumstances, thereby offering a more effective experience.

[0414] This invention is a system that enables real-time viewing of lectures and classes delivered in different languages, and provides personalized information tailored to the viewer's emotions. The system mainly consists of three components: a server, a terminal, and a user.

[0415] The device is equipped with a camera and microphone to acquire audio and video signals. This data is sent to a server. The server uses a speech recognition algorithm to convert the audio signals into text and translate them into different languages. The translated audio text is displayed as visual information, overlaid on the video signal.

[0416] The server also uses optical character recognition (OCR) technology to recognize characters within the video signal. The recognized characters are translated into a specified language and overlaid on the video signal for the user to see.

[0417] Furthermore, the server uses a generative AI model to analyze the user's voice tone and speed, as well as video data, to evaluate the user's emotional state in real time. This allows it to detect emotions such as surprise or confusion and provide additional information corresponding to those emotions. For example, if a user expresses surprise during a lecture, relevant background information is presented to clarify the meaning of this emotion.

[0418] As a concrete example, when a user watches a history lecture delivered in Japanese but in English, the system displays subtitles with real-time translation and provides additional information about the historical context when the user expresses surprise or questions. An example of a prompt to the generative AI model in such a system might be, "Surprised user detected from user emotion data. Please provide background information related to the content being viewed."

[0419] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0420] Step 1:

[0421] The terminal uses the user's camera and microphone to acquire video and audio signals. The input consists of real-time visual and audio data, which are then transmitted to the server in digital format.

[0422] Step 2:

[0423] The server applies a speech recognition algorithm to the received audio signal. The input is an audio signal, and this data is output as text data. This process converts the audio content into text.

[0424] Step 3:

[0425] The server translates text data obtained through speech recognition into different languages. The input is text data, and the translation engine outputs the translated text in the specified language. This translation result is then used in the next step.

[0426] Step 4:

[0427] The server uses optical character recognition (OCR) technology to recognize characters from video signals. The input is a video signal, and the extracted character information is output as text data. This data is used in a later translation step.

[0428] Step 5:

[0429] The server translates the characters recognized in the video into a different language. The input is character information detected by OCR, and this is output as text in the specified language.

[0430] Step 6:

[0431] The server overlays translated text and audio data onto the video signal. The input is the translated text and video signal, and the output is a subtitled video presented to the user. This subtitle information visually supplements the user's understanding.

[0432] Step 7:

[0433] The server uses a generative AI model to analyze the user's voice tone and facial expressions from the video, and evaluates their emotions. The input is audio and video data, and the output is the user's emotion evaluation result.

[0434] Step 8:

[0435] Based on the sentiment evaluation results, the server provides additional information tailored to the user's state. The input consists of the sentiment evaluation results and information about the content being viewed, while the output is additional information to aid user understanding. This makes it easier for users to gain a deeper understanding of the content's context.

[0436] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0437] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0438] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0439] [Third Embodiment]

[0440] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0441] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0442] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0443] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0444] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0445] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0446] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0447] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0448] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0449] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0450] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0451] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0452] This invention provides a multilingual system that enables speakers of different languages ​​to view lecture and presentation content in real time. This system primarily functions through three entities: a server, a terminal, and a user.

[0453] First, the user accesses online classes or lectures using their device. The device acquires audio and video data in real time and sends it to the server. The server performs speech recognition on the received data and converts the audio data into text. Then, it uses a translation API to translate this text into the specified language.

[0454] Next, regarding video data, the terminal transfers the video it captures or records to the server. The server uses optical character recognition (OCR) to extract text information from the video. This text information is also translated into different languages ​​as needed.

[0455] The translated audio and video text are integrated by the server and provided to the user as subtitles and video overlays. The device receives this and displays it on the user's screen in real time. This allows users to understand the content of lectures and presentations in their native language.

[0456] As a concrete example, when an English-speaking user watches a lecture delivered in Japanese, the device acquires Japanese audio and video and sends them to the server. The server translates the Japanese audio into English and displays it as subtitles. In addition, the Japanese text displayed on the slides is recognized by OCR, translated into English, and provided to the user. This process enables smooth content reception that transcends language barriers.

[0457] The following describes the processing flow.

[0458] Step 1:

[0459] The user accesses the online platform using their device and begins the class or lecture they wish to watch. The device acquires video and audio data in real time and prepares to stream this data to the server.

[0460] Step 2:

[0461] The terminal sends the streamed audio data to the server at regular intervals. The server performs speech recognition processing on the received audio data, converting the speech into text. A speech recognition algorithm is used for this conversion.

[0462] Step 3:

[0463] The server sends the text obtained through speech recognition to a translation API, which then translates it into the specified target language. The translation result is formatted as subtitle data and timestamped.

[0464] Step 4:

[0465] Simultaneously, the terminal continuously streams video data to the server. The server uses OCR (Optical Character Recognition) to detect text information from each frame of the video.

[0466] Step 5:

[0467] The text information extracted by OCR is also translated into the target language using a translation API. The server overlays the translated text onto the video frame, generating a video stream that can be viewed by the user along with subtitles.

[0468] Step 6:

[0469] The server encodes the translated subtitles and overlaid video in real time and delivers them to the device. The device receives this stream and displays it visually on the user's display.

[0470] Step 7:

[0471] Users will be able to understand the content of lectures and presentations in real time through translated videos and subtitles displayed on their devices.

[0472] (Example 1)

[0473] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0474] When speakers of different languages ​​watch lectures or presentations in real time, a language barrier presents a challenge. This challenge arises from the lack of efficient systems that can translate and display different languages ​​within a realistic timeframe.

[0475] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0476] In this invention, the server includes means for compressing and transmitting audio and video data received from the viewer's terminal, means for converting the received audio data into text information, and means for translating the text information into multiple languages. This makes it possible to view and understand information in different languages ​​in real time.

[0477] "Audio data received from the viewer's device" refers to information that represents the waveform of sound transmitted from the device used by the user in digital format.

[0478] "Means for compressing and transmitting video data" refers to technologies that reduce the amount of data in order to efficiently transmit video information.

[0479] "Methods for converting acoustic data into textual information" refers to technologies that analyze sound waveforms and convert them into corresponding strings of characters.

[0480] "Means of translating textual information into multiple languages" refers to the function of software that converts text written in one language into another language.

[0481] "Methods for overlaying information onto video data" refers to techniques that visually display additional information by overlaying it onto specific parts of a video.

[0482] "A means of acquiring and translating textual information from video data using optical technology" refers to a technology that recognizes text within an image and translates it into another language.

[0483] "A means of displaying translated text information in conjunction with video data" refers to a technology that displays translated text information on the screen at a timing corresponding to the content of the video.

[0484] This invention is a real-time lecture and presentation viewing system that supports multiple languages. The system mainly consists of three components: a server, a terminal, and a user.

[0485] Users access online classes and lectures using their devices. These devices include smartphones, tablets, or computers, and they utilize online meeting tools via an internet connection. An example of such a meeting tool is the general term "online meeting system."

[0486] The device uses a microphone and camera to acquire real-time audio and video data and sends this data to a server. The server converts the audio data into text information using a speech recognition algorithm. Specifically, a "speech recognition system" is used for this process. The converted text information is then translated into the desired language using a translation API.

[0487] Regarding video data, the server uses optical technology to extract text information from the video. An example of this optical technology is an "OCR system." This text information is then translated using a translation API.

[0488] The server overlays the translated text onto the video data in real time. The receiving terminal then displays this result as subtitles on the user's screen. This allows users to understand the content of lectures and presentations in their own language.

[0489] As a concrete example, consider a scenario where an English-speaking user is watching a lecture conducted in Japanese. The device acquires Japanese audio and video and sends them to the server. On the server, the audio data is translated into English text and displayed as subtitles. Similarly, the text within the video is translated into English and provided to the user. In this way, content can be received smoothly, transcending language barriers.

[0490] Example of a prompt for a generative AI model: "Please describe in detail the programmatic processing flow for viewing an online lecture in Japanese with real-time English subtitles."

[0491] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0492] Step 1:

[0493] The user accesses online classes and lectures using their device. The device, via its internet connection, launches the online conferencing system and acquires audio and video data of the lecture in real time. In this step, the video and audio data of the online lecture are used as input, and this data is passed directly to the next step as output.

[0494] Step 2:

[0495] The terminal sends the acquired audio and video data to the server. The data is compressed before transmission and optimized for faster processing on the server. The input for this step is the raw audio and video data acquired by the terminal, and the output is the compressed data sent to the server.

[0496] Step 3:

[0497] The server receives compressed audio data and converts it into text information using a speech recognition system. In this conversion, the audio waveform data is used as input, and the corresponding text data is generated as output. Specifically, the server performs calculations such as noise reduction and speech segmentation.

[0498] Step 4:

[0499] The server translates the generated text information into multiple languages ​​using a translation API. The input is text information converted from speech, and the output is text translated into the user's desired language. The server performs contextual analysis and other processes to maintain translation accuracy throughout this process.

[0500] Step 5:

[0501] The server acquires text information from video data using optical technology. Here, an OCR system analyzes video frames and extracts text. The input is compressed video data, and the output is text information within the video. The server filters the data according to the characteristics of the video.

[0502] Step 6:

[0503] The system translates text information obtained using OCR technology into the language specified by the translation API. The input is raw text information from the OCR, and the output is translated text information. The server maintains the translation results in a consistent format.

[0504] Step 7:

[0505] The server integrates translated text and audio-text information and generates subtitles by overlaying them onto the video data. The input is translated text information, and the output is video data with the overlay. The server uses a video synchronization function to adjust the timing of the subtitle display.

[0506] Step 8:

[0507] The terminal receives video data with overlays sent from the server and displays it on the user's screen in real time. The input is video data with overlay information, and the output provides video that contributes to the user's viewing experience. The terminal optimizes the video display using playback software.

[0508] (Application Example 1)

[0509] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0510] Currently, there is a challenge in smooth communication among family members who speak different languages. In particular, important conversations in daily life can be hindered by language barriers. This can impede the sharing of emotions and the transmission of intentions, potentially weakening family ties.

[0511] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0512] In this invention, the server includes processing means for recognizing linguistic expressions from video information, processing means for translating the recognized linguistic expressions into a different language, and processing means for overlaying and displaying the translated linguistic expressions on the video information. This enables smooth, real-time communication between members of a household who speak different languages, and reduces communication barriers caused by language differences.

[0513] "Visual information" refers to visual data, specifically information related to vision acquired through video equipment.

[0514] "Linguistic expression" refers to texts or symbols that concretely represent content or information conveyed through language.

[0515] "Recognition processing means" refers to technologies and methods for analyzing input data and identifying its content.

[0516] A "translation processing method" refers to a technology or system for converting information expressed in one language into another language.

[0517] "Processing methods for overlaying information" refer to technologies and techniques for visually presenting new information by overlaying it on top of existing video information.

[0518] "Auditory information" refers to data related to sounds that can be received aurally.

[0519] "Documentation processing means" refers to technologies and systems for converting acquired audio information into text format.

[0520] "Subtitle display processing means" refers to technologies and methods for adding linguistic information to video and presenting it visually.

[0521] To implement this invention, a server plays a central role. The server receives audio and video information transmitted from a home communication robot. The server utilizes Amazon Transcribe and the Google Translate API to document the audio information and translate its contents into different languages. In addition, the server recognizes linguistic expressions contained in the video information using Tesseract OCR and similarly translates them into different languages.

[0522] The converted language expressions and texts are processed on the server into data structures appropriate for each display format. This allows home robots to overlay translated subtitles onto video information or play translated audio.

[0523] The device, in this case a home robot, provides the user with translated information in visual or audio format. This allows the user to communicate in real time with family members who speak different languages.

[0524] For example, if a parent says "What do you want for lunch?" in Japanese, the robot will display the subtitle "What do you want for lunch?" to the child. Sometimes, a translated voice message will also play simultaneously. An example of a prompt message is, "Please translate the Japanese voice input into English in real time."

[0525] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0526] Step 1:

[0527] The device (a home robot) captures conversations within the home as voice input via its microphone. This input is sent to the server in stream format. The server then converts this voice data into text using Amazon Transcribe. This process results in the creation of a documented voice.

[0528] Step 2:

[0529] The server uses the Google Translate API to convert transcribed speech information into a different language specified by the user. The input is transcribed Japanese data, and the output is translated English text. The translation results are stored in a database and used in subsequent processes.

[0530] Step 3:

[0531] The device uses its camera to capture video information from within the home. This video data is transferred to a server, which uses Tesseract OCR to extract text information from the video. The input is a still image or a video frame, and the output is the extracted Japanese text.

[0532] Step 4:

[0533] The server also translates the text information extracted by OCR into the specified language using the Google Translate API. The input is the extracted Japanese text information, and the output is the translated English text information.

[0534] Step 5:

[0535] The server integrates the translated audio and video text and prepares it for display on the home robot's screen. The user will see English subtitles overlaid on the video data. This step includes video synchronization and subtitle formatting adjustments.

[0536] Step 6:

[0537] The device receives integrated data and provides it to the user. The user can then understand domestic conversations in other languages ​​through voice guidance and subtitles.

[0538] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0539] This invention is a multilingual system that allows users to view lessons and lectures in different languages ​​in real time, and further incorporates an emotion engine that recognizes the user's emotions in real time and provides information accordingly. This system mainly consists of three components: a server, a terminal, and a user.

[0540] Users connect to an online platform using their devices to view lectures and presentations in real time. The devices have the capability to acquire audio and video data from users and transmit it to a server. The server applies speech recognition to the acquired audio data and converts it to text. It also has the functionality to translate the textualized audio data into a language specified by the user.

[0541] Simultaneously, the server uses optical character recognition (OCR) to detect text information from the video data and translates the recognized text information into different languages ​​as needed. The translated text and audio text are then overlaid and provided to the user as subtitles.

[0542] A distinctive feature of this invention is the incorporation of an emotion engine. The emotion engine analyzes the user's voice tone, speed, and facial expression data to evaluate the user's emotional state in real time. The terminal acquires necessary data through its camera and microphone, and the server analyzes this data using the emotion engine. The obtained emotional information is used to optimize the user experience. For example, if the emotion engine detects that the user is confused, the system can provide additional explanations.

[0543] As a concrete example, when an English-speaking user watches a lecture conducted in Japanese, the device acquires Japanese audio and video, and the server translates this data into English and provides it. Furthermore, if the user expresses surprise or confusion, the system automatically provides corresponding content to support the user's understanding. This provides a rich learning experience that transcends language and emotional barriers.

[0544] The following describes the processing flow.

[0545] Step 1:

[0546] The user accesses the online platform via their device and begins the class or lecture they wish to watch. The device acquires video data through its camera and collects audio data through its microphone. This data is then prepared for streaming to the server.

[0547] Step 2:

[0548] The terminal sends audio data to the server at specific time intervals. The server processes the received audio data using speech recognition and converts the audio content into text format. This conversion is performed using a speech recognition algorithm.

[0549] Step 3:

[0550] The server sends the text data obtained through speech recognition to a translation API, which translates it into the target language specified in the assignment. The translated text data is then formatted in a user-friendly format.

[0551] Step 4:

[0552] The terminal continuously streams video data in real time, and the server analyzes each frame of the video. The server uses optical character recognition (OCR) to extract text information from the video and generates digital text data.

[0553] Step 5:

[0554] The text data obtained by OCR is also translated into the target language using a translation API. The server overlays the translated text data onto the video, preparing it for display on the user's screen.

[0555] Step 6:

[0556] The emotion engine is activated, and the server analyzes the user's facial expression and voice data transmitted from the terminal. It recognizes the emotional signs the user is showing and evaluates those emotions in real time.

[0557] Step 7:

[0558] Based on the emotion recognition results, the server takes actions that correspond to the user's emotions. For example, if the server determines that the user is confused, it automatically provides additional explanations or hints. This helps users achieve better understanding despite language barriers.

[0559] (Example 2)

[0560] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0561] Understanding lectures and presentations in different languages ​​in real time is difficult for many users. Furthermore, the inability to receive appropriate emotional responses to the content of lectures and presentations limits the user experience. To solve these problems, real-time language translation and information delivery that responds to the user's emotions are necessary.

[0562] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0563] In this invention, the server includes means for recognizing text from video information, means for recognizing and documenting audio information, and means for collecting and evaluating the user's voice and facial expression information in real time in order to analyze their emotional state. This enables the user to understand content in different languages ​​in real time and to receive information tailored to their individual emotional state.

[0564] "Visual information" refers to visual data acquired through cameras and digital devices, enabling a visual understanding of the content.

[0565] "Notation" refers to the characters and symbols contained within video information, and these should be recognized in order to convert that information into a format that users can understand.

[0566] "Acoustic information" refers to audio data acquired through microphones or other means, which conveys auditory content or information.

[0567] "Documentation" refers to the process of recognizing acoustic information and converting it into text, with the aim of transforming collected data into a clear and searchable format.

[0568] "Emotional state" refers to the mental and emotional state of a user, evaluated by analyzing user behavior indicators such as voice tone and facial expression data.

[0569] "Evaluating in real time" refers to a process where data is acquired and analyzed simultaneously, so that the information is immediately reflected in the data.

[0570] This invention is a system that enables real-time viewing of multilingual lessons and lectures, and further provides information tailored to the user's emotional state. The system mainly consists of three components: a server, a terminal, and the user.

[0571] First, users connect to an online platform using their device and watch classes or lectures in real time. The device then uses its built-in camera and microphone to acquire video and audio information.

[0572] After the server receives the data sent from the terminal, the following processes take place: The server applies speech recognition technology to the audio information and documents the speech as text. This process uses speech recognition modules such as speech recognition software APIs. Furthermore, this text information is translated into a language that the user can understand by a multilingual translation system. In this step, for example, the use of a translation API can be considered.

[0573] Regarding video information, the server uses optical character recognition technology to analyze the text within the video and extract the text information. This text information is also translated into different languages ​​and displayed overlaid on the video information, enabling real-time subtitle generation.

[0574] Furthermore, to analyze the user's emotional state, the device transmits voice tone and facial expression information to the server. The server evaluates this in real time using emotion analysis technology and provides additional information tailored to the user's level of understanding and emotions. This allows users to understand the content of lectures and classes more effectively.

[0575] As a concrete example, when an English-speaking user watches a lecture delivered in Japanese, the device acquires the Japanese audio and video, and the server translates it into English and displays subtitles in real time. In this case, if the user appears confused, the system can automatically provide additional English annotations or explanations.

[0576] An example of a prompt to input into a generative AI model would be: "Translate the audio and text of a lecture given in Japanese into English and display them as subtitles in real time. Also, provide additional explanations if the user becomes confused." This allows users to enjoy a learning experience that transcends language and emotional barriers.

[0577] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0578] Step 1:

[0579] The user connects to the online platform using their device. Based on the user's actions, the device opens a web browser or dedicated application and accesses a URL or address that streams real-time classes or lectures. The platform then begins streaming the video and audio data of the classes or lectures to the device.

[0580] Input: User connection request

[0581] Output: Real-time video and audio data

[0582] Step 2:

[0583] The device uses its camera and microphone to send acquired video and audio information to the server. In this process, video data is sent to the server in video stream format (e.g., H.264), and audio data is sent in audio stream format (e.g., AAC).

[0584] Input: Real-time video and audio data

[0585] Output: Streaming data to the server

[0586] Step 3:

[0587] The server converts the received acoustic information into text information using speech recognition technology. The speech recognition module (e.g., speech recognition software API) analyzes the acoustic signal, statistically evaluates the extracted phonemes, and generates the corresponding string.

[0588] Input: Streamed audio data

[0589] Output: Text information (text-converted audio data)

[0590] Step 4:

[0591] The server translates text information into the specified language using a multilingual translation system. A multilingual translation module (e.g., a translation API) takes text data as input and applies a translation algorithm to generate text data corresponding to a specific target language.

[0592] Input: Transcribed audio data

[0593] Output: Translated text information

[0594] Step 5:

[0595] The server applies optical character recognition (OCR) technology to the video information, analyzing the text within the video to extract character information. The OCR system identifies text areas from the video frame, analyzes the font, character shape, color, etc. used within them, and generates corresponding text data.

[0596] Input: Streamed video data

[0597] Output: Analyzed text information (text in the video)

[0598] Step 6:

[0599] The server translates the text information acquired by OCR into different languages ​​and converts it into a format that can be overlaid on the video information. The translated text is generated as a subtitle file for visualization and is composited into the streaming video.

[0600] Input: OCR result text information

[0601] Output: Translated subtitle text

[0602] Step 7:

[0603] The device's camera and microphone collect the user's voice tone and facial expression information in real time and send it to the server. The server analyzes this data using an emotion analysis module and evaluates the user's emotional state in real time.

[0604] Input: User's voice tone and facial expression data

[0605] Output: Real-time sentiment evaluation results

[0606] Step 8:

[0607] Based on the sentiment analysis results, the server determines and sends additional information necessary to optimize the user experience. This process selects emotionally relevant hints and supplementary explanations, presenting them in a user-friendly format.

[0608] Input: Sentiment evaluation result

[0609] Output: Additional information provided to the user

[0610] (Application Example 2)

[0611] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0612] When viewing lectures or classes delivered in different languages ​​in real time, there is a need to eliminate the delays and confusion caused by language differences and to provide personalized information that responds to the viewer's emotions. However, conventional technologies have lacked the ability to provide information based on the viewer's emotions, making it difficult to optimize the viewer experience. Therefore, new technologies are needed to effectively solve these problems.

[0613] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0614] In this invention, the server includes means for recognizing characters from a video signal, means for translating the recognized characters into a different language, means for overlaying and displaying the translated characters on the video signal, and means for recognizing an audio signal and converting it into text. This enables real-time analysis of the viewer's emotional state while viewing content in different languages, facilitating understanding and providing personalized information tailored to their emotions.

[0615] A "video signal" is a signal obtained by converting changes in light into an electrical signal, and it is a medium for transmitting visual information.

[0616] "Means of recognizing characters" refers to technology that extracts character information from video signals in digital format, thereby enabling automated character reading.

[0617] "Means of translation into different languages" refers to technologies that convert text or sound from one language to another, facilitating communication between multiple languages.

[0618] "Methods of overlaying" refer to techniques that visually display additional information on top of the original image, providing viewers with extra information.

[0619] An "audio signal" is a signal obtained by converting fluctuations in sound into an electrical signal, and it is a medium for transmitting auditory information.

[0620] "Means of recognizing speech and converting it into text" refers to technology that interprets speech signals and converts them into textual information, and is a means of visualizing speech.

[0621] "Methods for analyzing emotions in real time" refer to technologies that immediately evaluate a user's emotional state based on audio and video data, making it possible to grasp their emotions at that moment.

[0622] "Personalized information delivery" refers to providing information optimized according to the user's specific needs and circumstances, thereby offering a more effective experience.

[0623] This invention is a system that enables real-time viewing of lectures and classes delivered in different languages, and provides personalized information tailored to the viewer's emotions. The system mainly consists of three components: a server, a terminal, and a user.

[0624] The device is equipped with a camera and microphone to acquire audio and video signals. This data is sent to a server. The server uses a speech recognition algorithm to convert the audio signals into text and translate them into different languages. The translated audio text is displayed as visual information, overlaid on the video signal.

[0625] The server also uses optical character recognition (OCR) technology to recognize characters within the video signal. The recognized characters are translated into a specified language and overlaid on the video signal for the user to see.

[0626] Furthermore, the server uses a generative AI model to analyze the user's voice tone and speed, as well as video data, to evaluate the user's emotional state in real time. This allows it to detect emotions such as surprise or confusion and provide additional information corresponding to those emotions. For example, if a user expresses surprise during a lecture, relevant background information is presented to clarify the meaning of this emotion.

[0627] As a concrete example, when a user watches a history lecture delivered in Japanese but in English, the system displays subtitles with real-time translation and provides additional information about the historical context when the user expresses surprise or questions. An example of a prompt to the generative AI model in such a system might be, "Surprised user detected from user emotion data. Please provide background information related to the content being viewed."

[0628] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0629] Step 1:

[0630] The terminal uses the user's camera and microphone to acquire video and audio signals. The input consists of real-time visual and audio data, which are then transmitted to the server in digital format.

[0631] Step 2:

[0632] The server applies a speech recognition algorithm to the received audio signal. The input is an audio signal, and this data is output as text data. This process converts the audio content into text.

[0633] Step 3:

[0634] The server translates text data obtained through speech recognition into different languages. The input is text data, and the translation engine outputs the translated text in the specified language. This translation result is then used in the next step.

[0635] Step 4:

[0636] The server uses optical character recognition (OCR) technology to recognize characters from video signals. The input is a video signal, and the extracted character information is output as text data. This data is used in a later translation step.

[0637] Step 5:

[0638] The server translates the characters recognized in the video into a different language. The input is character information detected by OCR, and this is output as text in the specified language.

[0639] Step 6:

[0640] The server overlays translated text and audio data onto the video signal. The input is the translated text and video signal, and the output is a subtitled video presented to the user. This subtitle information visually supplements the user's understanding.

[0641] Step 7:

[0642] The server uses a generative AI model to analyze the user's voice tone and facial expressions from the video, and evaluates their emotions. The input is audio and video data, and the output is the user's emotion evaluation result.

[0643] Step 8:

[0644] Based on the sentiment evaluation results, the server provides additional information tailored to the user's state. The input consists of the sentiment evaluation results and information about the content being viewed, while the output is additional information to aid user understanding. This makes it easier for users to gain a deeper understanding of the content's context.

[0645] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0646] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0647] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0648] [Fourth Embodiment]

[0649] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0650] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0651] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0652] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0653] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0654] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0655] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0656] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0657] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0658] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0659] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0660] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0661] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0662] This invention provides a multilingual system that enables speakers of different languages ​​to view lecture and presentation content in real time. This system primarily functions through three entities: a server, a terminal, and a user.

[0663] First, the user accesses online classes or lectures using their device. The device acquires audio and video data in real time and sends it to the server. The server performs speech recognition on the received data and converts the audio data into text. Then, it uses a translation API to translate this text into the specified language.

[0664] Next, regarding video data, the terminal transfers the video it captures or records to the server. The server uses optical character recognition (OCR) to extract text information from the video. This text information is also translated into different languages ​​as needed.

[0665] The translated audio and video text are integrated by the server and provided to the user as subtitles and video overlays. The device receives this and displays it on the user's screen in real time. This allows users to understand the content of lectures and presentations in their native language.

[0666] As a concrete example, when an English-speaking user watches a lecture delivered in Japanese, the device acquires Japanese audio and video and sends them to the server. The server translates the Japanese audio into English and displays it as subtitles. In addition, the Japanese text displayed on the slides is recognized by OCR, translated into English, and provided to the user. This process enables smooth content reception that transcends language barriers.

[0667] The following describes the processing flow.

[0668] Step 1:

[0669] The user accesses the online platform using their device and begins the class or lecture they wish to watch. The device acquires video and audio data in real time and prepares to stream this data to the server.

[0670] Step 2:

[0671] The terminal sends the streamed audio data to the server at regular intervals. The server performs speech recognition processing on the received audio data, converting the speech into text. A speech recognition algorithm is used for this conversion.

[0672] Step 3:

[0673] The server sends the text obtained through speech recognition to a translation API, which then translates it into the specified target language. The translation result is formatted as subtitle data and timestamped.

[0674] Step 4:

[0675] Simultaneously, the terminal continuously streams video data to the server. The server uses OCR (Optical Character Recognition) to detect text information from each frame of the video.

[0676] Step 5:

[0677] The text information extracted by OCR is also translated into the target language using a translation API. The server overlays the translated text onto the video frame, generating a video stream that can be viewed by the user along with subtitles.

[0678] Step 6:

[0679] The server encodes the translated subtitles and overlaid video in real time and delivers them to the device. The device receives this stream and displays it visually on the user's display.

[0680] Step 7:

[0681] Users will be able to understand the content of lectures and presentations in real time through translated videos and subtitles displayed on their devices.

[0682] (Example 1)

[0683] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0684] When speakers of different languages ​​watch lectures or presentations in real time, a language barrier presents a challenge. This challenge arises from the lack of efficient systems that can translate and display different languages ​​within a realistic timeframe.

[0685] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0686] In this invention, the server includes means for compressing and transmitting audio and video data received from the viewer's terminal, means for converting the received audio data into text information, and means for translating the text information into multiple languages. This makes it possible to view and understand information in different languages ​​in real time.

[0687] "Audio data received from the viewer's device" refers to information that represents the waveform of sound transmitted from the device used by the user in digital format.

[0688] "Means for compressing and transmitting video data" refers to technologies that reduce the amount of data in order to efficiently transmit video information.

[0689] "Methods for converting acoustic data into textual information" refers to technologies that analyze sound waveforms and convert them into corresponding strings of characters.

[0690] "Means of translating textual information into multiple languages" refers to the function of software that converts text written in one language into another language.

[0691] "Methods for overlaying information onto video data" refers to techniques that visually display additional information by overlaying it onto specific parts of a video.

[0692] "A means of acquiring and translating textual information from video data using optical technology" refers to a technology that recognizes text within an image and translates it into another language.

[0693] "A means of displaying translated text information in conjunction with video data" refers to a technology that displays translated text information on the screen at a timing corresponding to the content of the video.

[0694] This invention is a real-time lecture and presentation viewing system that supports multiple languages. The system mainly consists of three components: a server, a terminal, and a user.

[0695] Users access online classes and lectures using their devices. These devices include smartphones, tablets, or computers, and they utilize online meeting tools via an internet connection. An example of such a meeting tool is the general term "online meeting system."

[0696] The device uses a microphone and camera to acquire real-time audio and video data and sends this data to a server. The server converts the audio data into text information using a speech recognition algorithm. Specifically, a "speech recognition system" is used for this process. The converted text information is then translated into the desired language using a translation API.

[0697] Regarding video data, the server uses optical technology to extract text information from the video. An example of this optical technology is an "OCR system." This text information is then translated using a translation API.

[0698] The server overlays the translated text onto the video data in real time. The receiving terminal then displays this result as subtitles on the user's screen. This allows users to understand the content of lectures and presentations in their own language.

[0699] As a concrete example, consider a scenario where an English-speaking user is watching a lecture conducted in Japanese. The device acquires Japanese audio and video and sends them to the server. On the server, the audio data is translated into English text and displayed as subtitles. Similarly, the text within the video is translated into English and provided to the user. In this way, content can be received smoothly, transcending language barriers.

[0700] Example of a prompt for a generative AI model: "Please describe in detail the programmatic processing flow for viewing an online lecture in Japanese with real-time English subtitles."

[0701] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0702] Step 1:

[0703] The user accesses online classes and lectures using their device. The device, via its internet connection, launches the online conferencing system and acquires audio and video data of the lecture in real time. In this step, the video and audio data of the online lecture are used as input, and this data is passed directly to the next step as output.

[0704] Step 2:

[0705] The terminal sends the acquired audio and video data to the server. The data is compressed before transmission and optimized for faster processing on the server. The input for this step is the raw audio and video data acquired by the terminal, and the output is the compressed data sent to the server.

[0706] Step 3:

[0707] The server receives compressed audio data and converts it into text information using a speech recognition system. In this conversion, the audio waveform data is used as input, and the corresponding text data is generated as output. Specifically, the server performs calculations such as noise reduction and speech segmentation.

[0708] Step 4:

[0709] The server translates the generated text information into multiple languages ​​using a translation API. The input is text information converted from speech, and the output is text translated into the user's desired language. The server performs contextual analysis and other processes to maintain translation accuracy throughout this process.

[0710] Step 5:

[0711] The server acquires text information from video data using optical technology. Here, an OCR system analyzes video frames and extracts text. The input is compressed video data, and the output is text information within the video. The server filters the data according to the characteristics of the video.

[0712] Step 6:

[0713] The system translates text information obtained using OCR technology into the language specified by the translation API. The input is raw text information from the OCR, and the output is translated text information. The server maintains the translation results in a consistent format.

[0714] Step 7:

[0715] The server integrates translated text and audio-text information and generates subtitles by overlaying them onto the video data. The input is translated text information, and the output is video data with the overlay. The server uses a video synchronization function to adjust the timing of the subtitle display.

[0716] Step 8:

[0717] The terminal receives video data with overlays sent from the server and displays it on the user's screen in real time. The input is video data with overlay information, and the output provides video that contributes to the user's viewing experience. The terminal optimizes the video display using playback software.

[0718] (Application Example 1)

[0719] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0720] Currently, there is a challenge in smooth communication among family members who speak different languages. In particular, important conversations in daily life can be hindered by language barriers. This can impede the sharing of emotions and the transmission of intentions, potentially weakening family ties.

[0721] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0722] In this invention, the server includes processing means for recognizing linguistic expressions from video information, processing means for translating the recognized linguistic expressions into a different language, and processing means for overlaying and displaying the translated linguistic expressions on the video information. This enables smooth, real-time communication between members of a household who speak different languages, and reduces communication barriers caused by language differences.

[0723] "Visual information" refers to visual data, specifically information related to vision acquired through video equipment.

[0724] "Linguistic expression" refers to texts or symbols that concretely represent content or information conveyed through language.

[0725] "Recognition processing means" refers to technologies and methods for analyzing input data and identifying its content.

[0726] A "translation processing method" refers to a technology or system for converting information expressed in one language into another language.

[0727] "Processing methods for overlaying information" refer to technologies and techniques for visually presenting new information by overlaying it on top of existing video information.

[0728] "Auditory information" refers to data related to sounds that can be received aurally.

[0729] "Documentation processing means" refers to technologies and systems for converting acquired audio information into text format.

[0730] "Subtitle display processing means" refers to technologies and methods for adding linguistic information to video and presenting it visually.

[0731] To implement this invention, a server plays a central role. The server receives audio and video information transmitted from a home communication robot. The server utilizes Amazon Transcribe and the Google Translate API to document the audio information and translate its contents into different languages. In addition, the server recognizes linguistic expressions contained in the video information using Tesseract OCR and similarly translates them into different languages.

[0732] The converted language expressions and texts are processed on the server into data structures appropriate for each display format. This allows home robots to overlay translated subtitles onto video information or play translated audio.

[0733] The device, in this case a home robot, provides the user with translated information in visual or audio format. This allows the user to communicate in real time with family members who speak different languages.

[0734] For example, if a parent says "What do you want for lunch?" in Japanese, the robot will display the subtitle "What do you want for lunch?" to the child. Sometimes, a translated voice message will also play simultaneously. An example of a prompt message is, "Please translate the Japanese voice input into English in real time."

[0735] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0736] Step 1:

[0737] The device (a home robot) captures conversations within the home as voice input via its microphone. This input is sent to the server in stream format. The server then converts this voice data into text using Amazon Transcribe. This process results in the creation of a documented voice.

[0738] Step 2:

[0739] The server uses the Google Translate API to convert transcribed speech information into a different language specified by the user. The input is transcribed Japanese data, and the output is translated English text. The translation results are stored in a database and used in subsequent processes.

[0740] Step 3:

[0741] The device uses its camera to capture video information from within the home. This video data is transferred to a server, which uses Tesseract OCR to extract text information from the video. The input is a still image or a video frame, and the output is the extracted Japanese text.

[0742] Step 4:

[0743] The server also translates the text information extracted by OCR into the specified language using the Google Translate API. The input is the extracted Japanese text information, and the output is the translated English text information.

[0744] Step 5:

[0745] The server integrates the translated audio and video text and prepares it for display on the home robot's screen. The user will see English subtitles overlaid on the video data. This step includes video synchronization and subtitle formatting adjustments.

[0746] Step 6:

[0747] The device receives integrated data and provides it to the user. The user can then understand domestic conversations in other languages ​​through voice guidance and subtitles.

[0748] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0749] This invention is a multilingual system that allows users to view lessons and lectures in different languages ​​in real time, and further incorporates an emotion engine that recognizes the user's emotions in real time and provides information accordingly. This system mainly consists of three components: a server, a terminal, and a user.

[0750] Users connect to an online platform using their devices to view lectures and presentations in real time. The devices have the capability to acquire audio and video data from users and transmit it to a server. The server applies speech recognition to the acquired audio data and converts it to text. It also has the functionality to translate the textualized audio data into a language specified by the user.

[0751] Simultaneously, the server uses optical character recognition (OCR) to detect text information from the video data and translates the recognized text information into different languages ​​as needed. The translated text and audio text are then overlaid and provided to the user as subtitles.

[0752] A distinctive feature of this invention is the incorporation of an emotion engine. The emotion engine analyzes the user's voice tone, speed, and facial expression data to evaluate the user's emotional state in real time. The terminal acquires necessary data through its camera and microphone, and the server analyzes this data using the emotion engine. The obtained emotional information is used to optimize the user experience. For example, if the emotion engine detects that the user is confused, the system can provide additional explanations.

[0753] As a concrete example, when an English-speaking user watches a lecture conducted in Japanese, the device acquires Japanese audio and video, and the server translates this data into English and provides it. Furthermore, if the user expresses surprise or confusion, the system automatically provides corresponding content to support the user's understanding. This provides a rich learning experience that transcends language and emotional barriers.

[0754] The following describes the processing flow.

[0755] Step 1:

[0756] The user accesses the online platform via their device and begins the class or lecture they wish to watch. The device acquires video data through its camera and collects audio data through its microphone. This data is then prepared for streaming to the server.

[0757] Step 2:

[0758] The terminal sends audio data to the server at specific time intervals. The server processes the received audio data using speech recognition and converts the audio content into text format. This conversion is performed using a speech recognition algorithm.

[0759] Step 3:

[0760] The server sends the text data obtained through speech recognition to a translation API, which translates it into the target language specified in the assignment. The translated text data is then formatted in a user-friendly format.

[0761] Step 4:

[0762] The terminal continuously streams video data in real time, and the server analyzes each frame of the video. The server uses optical character recognition (OCR) to extract text information from the video and generates digital text data.

[0763] Step 5:

[0764] The text data obtained by OCR is also translated into the target language using a translation API. The server overlays the translated text data onto the video, preparing it for display on the user's screen.

[0765] Step 6:

[0766] The emotion engine is activated, and the server analyzes the user's facial expression and voice data transmitted from the terminal. It recognizes the emotional signs the user is showing and evaluates those emotions in real time.

[0767] Step 7:

[0768] Based on the emotion recognition results, the server takes actions that correspond to the user's emotions. For example, if the server determines that the user is confused, it automatically provides additional explanations or hints. This helps users achieve better understanding despite language barriers.

[0769] (Example 2)

[0770] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0771] Understanding lectures and presentations in different languages ​​in real time is difficult for many users. Furthermore, the inability to receive appropriate emotional responses to the content of lectures and presentations limits the user experience. To solve these problems, real-time language translation and information delivery that responds to the user's emotions are necessary.

[0772] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0773] In this invention, the server includes means for recognizing text from video information, means for recognizing and documenting audio information, and means for collecting and evaluating the user's voice and facial expression information in real time in order to analyze their emotional state. This enables the user to understand content in different languages ​​in real time and to receive information tailored to their individual emotional state.

[0774] "Visual information" refers to visual data acquired through cameras and digital devices, enabling a visual understanding of the content.

[0775] "Notation" refers to the characters and symbols contained within video information, and these should be recognized in order to convert that information into a format that users can understand.

[0776] "Acoustic information" refers to audio data acquired through microphones or other means, which conveys auditory content or information.

[0777] "Documentation" refers to the process of recognizing acoustic information and converting it into text, with the aim of transforming collected data into a clear and searchable format.

[0778] "Emotional state" refers to the mental and emotional state of a user, evaluated by analyzing user behavior indicators such as voice tone and facial expression data.

[0779] "Evaluating in real time" refers to a process where data is acquired and analyzed simultaneously, so that the information is immediately reflected in the data.

[0780] This invention is a system that enables real-time viewing of multilingual lessons and lectures, and further provides information tailored to the user's emotional state. The system mainly consists of three components: a server, a terminal, and the user.

[0781] First, users connect to an online platform using their device and watch classes or lectures in real time. The device then uses its built-in camera and microphone to acquire video and audio information.

[0782] After the server receives the data sent from the terminal, the following processes take place: The server applies speech recognition technology to the audio information and documents the speech as text. This process uses speech recognition modules such as speech recognition software APIs. Furthermore, this text information is translated into a language that the user can understand by a multilingual translation system. In this step, for example, the use of a translation API can be considered.

[0783] Regarding video information, the server uses optical character recognition technology to analyze the text within the video and extract the text information. This text information is also translated into different languages ​​and displayed overlaid on the video information, enabling real-time subtitle generation.

[0784] Furthermore, to analyze the user's emotional state, the device transmits voice tone and facial expression information to the server. The server evaluates this in real time using emotion analysis technology and provides additional information tailored to the user's level of understanding and emotions. This allows users to understand the content of lectures and classes more effectively.

[0785] As a concrete example, when an English-speaking user watches a lecture delivered in Japanese, the device acquires the Japanese audio and video, and the server translates it into English and displays subtitles in real time. In this case, if the user appears confused, the system can automatically provide additional English annotations or explanations.

[0786] An example of a prompt to input into a generative AI model would be: "Translate the audio and text of a lecture given in Japanese into English and display them as subtitles in real time. Also, provide additional explanations if the user becomes confused." This allows users to enjoy a learning experience that transcends language and emotional barriers.

[0787] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0788] Step 1:

[0789] The user connects to the online platform using their device. Based on the user's actions, the device opens a web browser or dedicated application and accesses a URL or address that streams real-time classes or lectures. The platform then begins streaming the video and audio data of the classes or lectures to the device.

[0790] Input: User connection request

[0791] Output: Real-time video and audio data

[0792] Step 2:

[0793] The device uses its camera and microphone to send acquired video and audio information to the server. In this process, video data is sent to the server in video stream format (e.g., H.264), and audio data is sent in audio stream format (e.g., AAC).

[0794] Input: Real-time video and audio data

[0795] Output: Streaming data to the server

[0796] Step 3:

[0797] The server converts the received acoustic information into text information using speech recognition technology. The speech recognition module (e.g., speech recognition software API) analyzes the acoustic signal, statistically evaluates the extracted phonemes, and generates the corresponding string.

[0798] Input: Streamed audio data

[0799] Output: Text information (text-converted audio data)

[0800] Step 4:

[0801] The server translates text information into the specified language using a multilingual translation system. A multilingual translation module (e.g., a translation API) takes text data as input and applies a translation algorithm to generate text data corresponding to a specific target language.

[0802] Input: Transcribed audio data

[0803] Output: Translated text information

[0804] Step 5:

[0805] The server applies optical character recognition (OCR) technology to the video information, analyzing the text within the video to extract character information. The OCR system identifies text areas from the video frame, analyzes the font, character shape, color, etc. used within them, and generates corresponding text data.

[0806] Input: Streamed video data

[0807] Output: Analyzed text information (text in the video)

[0808] Step 6:

[0809] The server translates the text information acquired by OCR into different languages ​​and converts it into a format that can be overlaid on the video information. The translated text is generated as a subtitle file for visualization and is composited into the streaming video.

[0810] Input: OCR result text information

[0811] Output: Translated subtitle text

[0812] Step 7:

[0813] The device's camera and microphone collect the user's voice tone and facial expression information in real time and send it to the server. The server analyzes this data using an emotion analysis module and evaluates the user's emotional state in real time.

[0814] Input: User's voice tone and facial expression data

[0815] Output: Real-time sentiment evaluation results

[0816] Step 8:

[0817] Based on the sentiment analysis results, the server determines and sends additional information necessary to optimize the user experience. This process selects emotionally relevant hints and supplementary explanations, presenting them in a user-friendly format.

[0818] Input: Sentiment evaluation result

[0819] Output: Additional information provided to the user

[0820] (Application Example 2)

[0821] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0822] When viewing lectures or classes delivered in different languages ​​in real time, there is a need to eliminate the delays and confusion caused by language differences and to provide personalized information that responds to the viewer's emotions. However, conventional technologies have lacked the ability to provide information based on the viewer's emotions, making it difficult to optimize the viewer experience. Therefore, new technologies are needed to effectively solve these problems.

[0823] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0824] In this invention, the server includes means for recognizing characters from a video signal, means for translating the recognized characters into a different language, means for overlaying and displaying the translated characters on the video signal, and means for recognizing an audio signal and converting it into text. This enables real-time analysis of the viewer's emotional state while viewing content in different languages, facilitating understanding and providing personalized information tailored to their emotions.

[0825] A "video signal" is a signal obtained by converting changes in light into an electrical signal, and it is a medium for transmitting visual information.

[0826] "Means of recognizing characters" refers to technology that extracts character information from video signals in digital format, thereby enabling automated character reading.

[0827] "Means of translation into different languages" refers to technologies that convert text or sound from one language to another, facilitating communication between multiple languages.

[0828] "Methods of overlaying" refer to techniques that visually display additional information on top of the original image, providing viewers with extra information.

[0829] An "audio signal" is a signal obtained by converting fluctuations in sound into an electrical signal, and it is a medium for transmitting auditory information.

[0830] "Means of recognizing speech and converting it into text" refers to technology that interprets speech signals and converts them into textual information, and is a means of visualizing speech.

[0831] "Methods for analyzing emotions in real time" refer to technologies that immediately evaluate a user's emotional state based on audio and video data, making it possible to grasp their emotions at that moment.

[0832] "Personalized information delivery" refers to providing information optimized according to the user's specific needs and circumstances, thereby offering a more effective experience.

[0833] This invention is a system that enables real-time viewing of lectures and classes delivered in different languages, and provides personalized information tailored to the viewer's emotions. The system mainly consists of three components: a server, a terminal, and a user.

[0834] The device is equipped with a camera and microphone to acquire audio and video signals. This data is sent to a server. The server uses a speech recognition algorithm to convert the audio signals into text and translate them into different languages. The translated audio text is displayed as visual information, overlaid on the video signal.

[0835] The server also uses optical character recognition (OCR) technology to recognize characters within the video signal. The recognized characters are translated into a specified language and overlaid on the video signal for the user to see.

[0836] Furthermore, the server uses a generative AI model to analyze the user's voice tone and speed, as well as video data, to evaluate the user's emotional state in real time. This allows it to detect emotions such as surprise or confusion and provide additional information corresponding to those emotions. For example, if a user expresses surprise during a lecture, relevant background information is presented to clarify the meaning of this emotion.

[0837] As a concrete example, when a user watches a history lecture delivered in Japanese but in English, the system displays subtitles with real-time translation and provides additional information about the historical context when the user expresses surprise or questions. An example of a prompt to the generative AI model in such a system might be, "Surprised user detected from user emotion data. Please provide background information related to the content being viewed."

[0838] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0839] Step 1:

[0840] The terminal uses the user's camera and microphone to acquire video and audio signals. The input consists of real-time visual and audio data, which are then transmitted to the server in digital format.

[0841] Step 2:

[0842] The server applies a speech recognition algorithm to the received audio signal. The input is an audio signal, and this data is output as text data. This process converts the audio content into text.

[0843] Step 3:

[0844] The server translates text data obtained through speech recognition into different languages. The input is text data, and the translation engine outputs the translated text in the specified language. This translation result is then used in the next step.

[0845] Step 4:

[0846] The server uses optical character recognition (OCR) technology to recognize characters from video signals. The input is a video signal, and the extracted character information is output as text data. This data is used in a later translation step.

[0847] Step 5:

[0848] The server translates the characters recognized in the video into a different language. The input is character information detected by OCR, and this is output as text in the specified language.

[0849] Step 6:

[0850] The server overlays translated text and audio data onto the video signal. The input is the translated text and video signal, and the output is a subtitled video presented to the user. This subtitle information visually supplements the user's understanding.

[0851] Step 7:

[0852] The server uses a generative AI model to analyze the user's voice tone and facial expressions from the video, and evaluates their emotions. The input is audio and video data, and the output is the user's emotion evaluation result.

[0853] Step 8:

[0854] Based on the sentiment evaluation results, the server provides additional information tailored to the user's state. The input consists of the sentiment evaluation results and information about the content being viewed, while the output is additional information to aid user understanding. This makes it easier for users to gain a deeper understanding of the content's context.

[0855] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0856] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0857] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0858] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0859] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0860] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0861] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0862] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0863] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0864] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0865] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0866] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0867] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0868] 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.

[0869] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0870] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0871] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0872] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0873] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0874] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0875] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0876] The following is further disclosed regarding the embodiments described above.

[0877] (Claim 1)

[0878] A method for recognizing text from video data,

[0879] A means for translating the recognized characters into a different language,

[0880] A means for overlaying and displaying the translated text on the video data,

[0881] A means of recognizing and converting audio data into text,

[0882] A means of translating transcribed audio data into different languages,

[0883] A means of displaying subtitles by synchronizing translated audio data with video data,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, wherein the recognition of the aforementioned voice data is performed using a voice recognition algorithm.

[0887] (Claim 3)

[0888] The system according to claim 1, wherein the character recognition uses optical character recognition technology.

[0889] "Example 1"

[0890] (Claim 1)

[0891] A means for compressing and transmitting audio and video data received from a viewer's device,

[0892] means for converting the received acoustic data into text information,

[0893] A means for translating the aforementioned textual information into multiple languages,

[0894] A means for overlaying the translated text information onto the video data,

[0895] A method for obtaining and translating text information from video data using optical technology,

[0896] A means of displaying translated text information in conjunction with video data,

[0897] A system that includes this.

[0898] (Claim 2)

[0899] The system according to claim 1, wherein the conversion of the acoustic data uses a specific acoustic recognition algorithm.

[0900] (Claim 3)

[0901] The system according to claim 1, wherein the information acquisition uses visual information recognition technology.

[0902] "Application Example 1"

[0903] (Claim 1)

[0904] A processing means for recognizing linguistic expressions from video information,

[0905] Processing means for translating the recognized language expression into a different language,

[0906] Processing means for overlaying translated language expressions onto the video information,

[0907] A processing means for recognizing and documenting audio information,

[0908] A processing means for translating documented audio information into different languages,

[0909] A processing means for displaying translated audio information as subtitles corresponding to video information,

[0910] Processing means that provides translation results visually or audibly to support conversations in the home,

[0911] A system that includes this.

[0912] (Claim 2)

[0913] The system according to claim 1, wherein the recognition of the aforementioned voice information utilizes a voice analysis algorithm.

[0914] (Claim 3)

[0915] The system according to claim 1, wherein the language expression recognition utilizes visual recognition technology.

[0916] "Example 2 of combining an emotion engine"

[0917] (Claim 1)

[0918] A means of recognizing text from video information,

[0919] A means for translating the recognized notation into a different language,

[0920] A means for overlaying the translated text onto the aforementioned video information,

[0921] A means of recognizing and documenting acoustic information,

[0922] A means of translating documented acoustic information into different languages,

[0923] A means of displaying translated audio information as subtitles in sync with video information,

[0924] A means of collecting and evaluating user voice and facial expression information in real time in order to analyze their emotional state,

[0925] A means of providing additional information according to the user's emotional state,

[0926] A system that includes this.

[0927] (Claim 2)

[0928] The system according to claim 1, wherein the recognition of the acoustic information is performed using a speech recognition method.

[0929] (Claim 3)

[0930] The system according to claim 1, wherein the notation recognition uses optical notation recognition technology.

[0931] "Application example 2 when combining with an emotional engine"

[0932] (Claim 1)

[0933] A means of recognizing characters from video signals,

[0934] A means for translating the recognized characters into a different language,

[0935] A means for displaying the translated characters superimposed on the video signal,

[0936] A means of recognizing audio signals and converting them into text,

[0937] A means of translating transcribed audio signals into different languages,

[0938] A means of displaying subtitles in sync with the video signal after translating the audio signal,

[0939] A means for analyzing the user's emotions in real time and providing additional information based on the analysis results,

[0940] An information processing system that includes this.

[0941] (Claim 2)

[0942] The information processing system according to claim 1, wherein the recognition of the voice signal uses a voice recognition algorithm, and the emotion analysis takes into account the tone and speed of the voice.

[0943] (Claim 3)

[0944] The information processing system according to claim 1, wherein the character recognition uses optical character recognition technology, and the emotion analysis analyzes facial expressions based on the user's video data. [Explanation of symbols]

[0945] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A method for recognizing text from video data, A means for translating the recognized characters into a different language, A means for overlaying and displaying the translated text on the video data, A means of recognizing and converting audio data into text, A means of translating transcribed audio data into different languages, A means of displaying subtitles by synchronizing translated audio data with video data, A system that includes this.

2. The system according to claim 1, wherein the recognition of the aforementioned voice data is performed using a voice recognition algorithm.

3. The system according to claim 1, wherein the character recognition uses optical character recognition technology.