system

Abstract

Provide a system. A photographing means for photographing a video; a transmitting means for transmitting the captured video via the Internet; recognition means for recognizing mouth movements from the received video; a conversion means for converting the recognized mouth movements into text; a translation means for translating the converted text into another language; display means for displaying the translated text; A system including:

Description

[Technical Field]

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

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

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

[0004] Currently, due to the language barrier, fans at overseas idol concerts are unable to understand what the idols are saying in real time, resulting in delayed responses. This creates a communication gap and detracts from the fan experience. Furthermore, existing translation devices and applications lack immediacy because they do not provide real-time translation from lip movements. This makes it difficult for fans to fully enjoy the excitement of the concert. [Means for solving the problem]

[0005] The present invention provides a system that captures an idol's lip movements in real time through a user's portable device and transmits the video to a server via the Internet. The server recognizes the lip movements from the video, converts them into text, and translates the text into the user's native language. A lip recognition means using a machine learning model generates accurate text from the video, and a translation engine quickly translates the text, achieving real-time translation. As a result, the user can display the translated text on their own device in real time, directly understanding what the overseas idol is saying and responding immediately.

[0006] "Photography means" refers to a camera or other device used to capture footage of a subject.

[0007] "Transmission means" refers to a device or software that has the functionality to transmit the captured video to another device or server via the Internet or other communication network.

[0008] "Recognition means" refers to software or algorithms that have the functionality to analyze mouth movements from received video data and identify what is being said.

[0009] "Conversion means" means software or algorithms capable of converting data generated from recognized mouth movements into text.

[0010] "Translation Tools" means software or services that have the functionality to translate the Converted Text into other languages.

[0011] "Display means" refers to a device such as a screen or display for visually presenting the translated text to the user. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0013] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0016] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0017] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0018] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0025] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0032] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0033] The present invention is a system that enables a user to use a portable device to understand in real time what is being said at a concert of an overseas idol, etc. Specific embodiments of this system will be described below.

[0034] Users can use binoculars or smartphones with built-in cameras to film the idols speaking at concert venues. The footage is captured on the device and the video data is sent to a server via the Internet.

[0035] The server analyzes the received video data and recognizes lip movements. This recognition is performed using a machine learning model. The server identifies what is being said from the lip movements and generates that content as text. This text is expressed in the recognized language. For example, if a Korean idol says "안녕하세요," the server generates the text "안녕하세요."

[0036] The generated text is then translated by the server into the user's native language using a common translation engine. For example, translation is performed from English to Japanese or from Korean to Japanese. This translation step converts the original text "안녕하세요" into the Japanese word "Hello."

[0037] The translated text is sent from the server to the device, which can then display the received translation results on the user's screen in real time, allowing the user to instantly understand what the idol is saying and respond appropriately.

[0038] Specific examples

[0039] Consider a scenario in which a user is attending a Korean idol concert. In this system, the user begins filming the idol's mouth using a camera built into their binoculars. The device captures the video and sends the data to a server via the Internet. The server analyzes the lip movements from the video and uses a machine learning model to generate the text "안녕하세요." The server then translates this text into Japanese, meaning "hello." Finally, the translated text is sent to the device and displayed in real time on the user's smartphone screen.

[0040] The processing flow will be explained below.

[0041] Step 1:

[0042] The user points the camera built into the binoculars at the idol's mouth and takes a video. The device then starts up and the capture function is turned on.

[0043] Step 2:

[0044] The device acquires video data from the camera in real time. This video data is captured frame by frame (for example, 30 fps).

[0045] Step 3:

[0046] The video data captured by the device is efficiently compressed and sent to a server over the Internet using a low-latency communication protocol.

[0047] Step 4:

[0048] To analyze the video data received by the server, the position of the mouth is identified for each frame and the mouth area is extracted.

[0049] Step 5:

[0050] The server uses a machine learning model to analyze the mouth movements based on the extracted mouth area data and converts them into corresponding text (audio). In this process, the Korean character string "안녕하세요" (hello) is generated.

[0051] Step 6:

[0052] The server receives the converted text and translates it into the user's native language. Through the translation engine, the Korean "안녕하세요" is converted into the Japanese "Hello."

[0053] Step 7:

[0054] The server sends the translation results to the device in real time using a fast and reliable communication protocol.

[0055] Step 8:

[0056] The device receives the translation result ("Hello" in Japanese) and displays it on the user's smartphone screen in real time, allowing the user to instantly understand what the idol is saying.

[0057] This allows users to understand what the idol is saying during the concert in real time and respond immediately.

[0058] Example 1

[0059] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0060] In recent years, the demand for global entertainment has increased, especially with the number of concerts held in various countries by overseas music artists and idols. However, due to language barriers, users often find it difficult to understand what is being said at overseas concerts, limiting real-time communication and enjoyment. For this reason, there is a need for a system that can understand multilingual conversations in real time.

[0061] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0062] In this invention, the server includes a camera for shooting video, a transmitter for transmitting the video via a network, and a recognition unit for recognizing lip movements from the received video, thereby enabling users to overcome language barriers at overseas concerts and understand what is being said in real time.

[0063] "Capturing means" refers to a device or function for capturing video.

[0064] The "transmission means" is a device or function for transmitting captured video data to another device or server via a network.

[0065] "Recognition means" refers to a device or function for analyzing and recognizing specific information (in this case, mouth movements) from received video data.

[0066] The "conversion means" is a device or function for converting the recognized information into another format such as text data.

[0067] The "translation means" is a device or function for translating the converted text data into another language.

[0068] "Display means" refers to a device or function for visually displaying translated text data on a user's device.

[0069] A "machine learning algorithm" is a computational model that learns certain patterns or rules based on a dataset and then uses that knowledge to analyze new data.

[0070] An "automated translation algorithm" is a computational model for converting text from one language to another.

[0071] MODE FOR CARRYING OUT THE INVENTION

[0072] The present invention is a system that enables a user to use a portable device to understand in real time what is being said at a concert of an overseas idol, etc. A specific embodiment of this system will be described below.

[0073] Users can use binoculars or smartphones with built-in cameras to film the idols speaking at concert venues. The footage is captured on the device and the video data is sent to a server via a network.

[0074] The server analyzes the received video data and recognizes lip movements. This recognition is performed using a machine learning algorithm. Specifically, it can use the TENSORFLOW (registered trademark) model, a common machine learning framework, or a cloud-based machine learning API. The server identifies what is being said from the lip movements and generates that content as text. For example, if a Korean idol says "안녕하세요," the server generates the text "안녕하세요."

[0075] The generated text is then translated by the server into the user's native language using an automatic translation algorithm. Specifically, common translation engines such as Google® Translation API or DeepL Translation API can be used. This translation step converts the original text "안녕하세요" into the Japanese word "Hello."

[0076] The translated text is sent from the server to the device, which can then display the received translation results on the user's device in real time, allowing the user to instantly understand what the idol is saying and respond appropriately.

[0077] Specific examples

[0078] For example, consider a scenario in which a user is attending a Korean idol concert. In this system, the user begins filming the idol's mouth using a camera built into their binoculars. The device captures the video and sends the data over the network to a server. The server analyzes the lip movements from the video and generates the text "안녕하세요" using a TensorFlow model. The server then translates this text into Japanese, meaning "hello," using the Google Translate API. Finally, the translated text is sent to the device and displayed in real time on the user's smartphone screen.

[0079] Prompt Sentence Examples

[0080] "Describe a system that allows you to understand what Korean idols are saying at their concerts in real time. Users take video using the built-in camera on their smartphones or binoculars and send the data to a server. The server uses a machine learning model to analyze their mouth movements and generate text from what they're saying. It then uses a translation engine to translate the text into the user's native language, and finally displays it on the user's device."

[0081] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0082] Step 1:

[0083] At a concert venue, users use a camera built into their smartphone or binoculars to take a picture of the idol's mouth.

[0084] Specifically, users simply open their device's camera app and point the camera at the idol's face, and the footage is captured in 1080p high definition.

[0085] Step 2:

[0086] The terminal transmits the captured video data to a server via the Internet in real time.

[0087] Specifically, the captured video data is compressed and sent via a network protocol (e.g. HTTP / HTTPS), the data is digitally encrypted, and the video data is received as input and sent to a server as output.

[0088] Step 3:

[0089] The server analyzes the received video data and runs machine learning algorithms to recognize mouth movements.

[0090] Specifically, the server stores video data in Google Cloud Storage and analyzes mouth movements using a TensorFlow model, taking video data as input and generating recognized mouth movement data as output.

[0091] Step 4:

[0092] The server analyzes the recognized mouth movement data and generates text of what is being said.

[0093] Specifically, the server uses a machine learning algorithm to infer what is being said from mouth movements and generate text data, such as "안녕하세요." It receives mouth movement data as input and generates text data as output.

[0094] Step 5:

[0095] The server translates the generated text data into the user's native language using an automatic translation algorithm.

[0096] Specifically, the server calls the Google Translate API to translate the input text "안녕하세요" into Japanese "Hello." It receives text data as input and generates translated text data as output.

[0097] Step 6:

[0098] The server transmits the translated text data to the user's terminal.

[0099] Specifically, the translation data is encrypted using the HTTPS protocol and sent to the device. The translated text data is received as input and sent to the device as output.

[0100] Step 7:

[0101] The terminal displays the received translation data on the user's device in real time.

[0102] Specifically, the device displays the translated data as a pop-up window or scrolling subtitles so that the user can visually confirm it. The device receives the translated data as input and displays it on the user's screen as output.

[0103] (Application example 1)

[0104] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0105] Conventional translation systems are designed to support real-time communication between people who speak different languages, but they have had challenges in analyzing and responding immediately to conversations that include visual elements, such as eye contact and gestures. In certain situations, such as brick-and-mortar stores in tourist areas, where multinational customers frequently visit, employees are required to respond smoothly in different languages, but this also poses challenges.

[0106] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0107] In this invention, the server includes a camera for capturing video, a transmitter for transmitting the captured video via the Internet, and a recognition unit for recognizing mouth movements from the received video, thereby enabling accurate understanding of foreign language conversations in real time and quick and appropriate responses to multinational customers.

[0108] The "capture means" is a device for capturing an image of an object, and includes, for example, a camera device built into smart glasses.

[0109] The "transmission means" is a communication module for transmitting the captured video data to a server via the Internet.

[0110] "Recognition means" includes a set of algorithms and machine learning models used to identify a subject's mouth movements from received video data.

[0111] The "conversion means" includes a program or algorithm for converting the recognized mouth movements into a text format.

[0112] "Translation means" includes a translation engine or corresponding software for converting the generated text into another language.

[0113] "Display means" includes a display device or projection system for visually presenting the translated text to a user.

[0114] A "head-mounted display" is a wearable device that can display images and information in real time when worn by the user.

[0115] "Generative AI model" refers to an artificial intelligence algorithm used to extract specific information from video data, specifically a model for analyzing mouth movements.

[0116] A "prompt" is an input sentence used to instruct a generative AI model or other algorithm to effectively perform the parsing or translation process.

[0117] This invention is a system that uses smart glasses worn by store staff to support real-time communication with customers who speak a foreign language. This system is implemented using the following hardware and software.

[0118] Hardware

[0119] 1. Smart Glasses

[0120] Photographic method: A built-in camera is used to capture a photo of the customer's mouth in real time.

[0121] Display means: A display is used to display the translated text to the user.

[0122] 2. Cloud Server

[0123] Transmission means: Receives video data sent from the smart glasses via the Internet.

[0124] software

[0125] 1. Generative AI Models

[0126] Recognition method: Runs on a cloud server and analyzes mouth movements from received video data.

[0127] 2. Conversion Method

[0128] Text generation algorithm: Recognizes mouth movements and converts the analysis results into text format.

[0129] 3. Translation Methods

[0130] Translation engine: Used to translate the generated text into the user's native language (e.g. Google Translate API).

[0131] Data processing and calculation procedures

[0132] 1. Video capture: The user (store staff) wears smart glasses and uses the built-in camera to capture what the customer is saying.

[0133] 2. Data transmission: The smart glasses transmit the captured video data to a cloud server via the Internet.

[0134] 3. Data analysis: The cloud server analyzes the received video data and uses a generative AI model to recognize the customer's mouth movements.

[0135] 4. Text Conversion: After the mouth movements are recognized, the content is converted into text format.

[0136] 5. Translation: The generated text is translated into the user's native language using a translation engine.

[0137] 6. Display: The translated text will be displayed on the smart glasses display in real time.

[0138] Specific examples

[0139] For example, a store staff member wearing smart glasses films a Korean tourist greeting "안녕하세요." The smart glasses send this video data to a cloud server, which uses a generative AI model to analyze the lip movements of "안녕하세요" and converts it into text. The translation engine then translates this text into Japanese, meaning "hello," and the translation is displayed on the staff member's smart glasses screen.

[0140] Prompt Sentence Examples

[0141] "Analyze the video data and output what is being said as text."

[0142] "Please translate the generated text into Japanese in real time."

[0143] In this way, users can smoothly communicate with customers who speak a foreign language.

[0144] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0145] Step 1:

[0146] The user wears the smart glasses and the built-in camera captures what the customer is saying.

[0147] Input: Image of customer's mouth

[0148] Output: Recorded video data

[0149] Specific operation: The built-in camera of the smart glasses captures video in real time and temporarily stores the video data within the device.

[0150] Step 2:

[0151] The device transmits the captured video data to a cloud server via the Internet.

[0152] Input: Video data stored on the device

[0153] Output: Video data sent to the cloud server

[0154] Specific operation: The terminal's communication module uploads the video data to a cloud server via the Internet.

[0155] Step 3:

[0156] The server recognizes mouth movements using a generative AI model from the video data it receives.

[0157] Input: Video data sent to the cloud server

[0158] Output: Mouth movement recognition results

[0159] How it works: A cloud server uses a generative AI model (e.g., a machine learning algorithm) to analyze the video data and extract lip movements in text format.

[0160] Step 4:

[0161] The server uses the information it recognizes from mouth movements to convert it into text using a text conversion algorithm.

[0162] Input: Mouth movement recognition results

[0163] Output: The generated text

[0164] Specific operation: The server automatically generates text based on the analysis of mouth movements and saves it as text data.

[0165] Step 5:

[0166] The server translates the generated text into the user's native language using a translation engine.

[0167] Input: Generated text

[0168] Output: The translated text

[0169] Specific operation: The cloud server uses a translation engine (e.g., Google Translate API) to translate the text in real time and generate the translation result.

[0170] Step 6:

[0171] The translated text is displayed on the display of the user's smart glasses.

[0172] Input: Translated text

[0173] Output: Translated text displayed on the smart glasses display

[0174] Specific operation: The translation results are sent from the cloud server to the smart glasses, and the text is displayed on the smart glasses' display in real time.

[0175] This allows users to communicate smoothly with customers who speak a foreign language.

[0176] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0177] The present invention provides a system that uses a user's portable device to understand what is being said at events such as overseas idol concerts in real time and recognize the user's emotions. Specific embodiments of this system are described below.

[0178] Users film an idol speaking at a concert venue using binoculars or a smartphone with a built-in camera. The video is captured on the device and sent to a server via the internet. The server analyzes the received video data and recognizes lip movements. This recognition is performed using a machine learning model. The server identifies what is being said from the lip movements and generates that content as text. This text is expressed in the recognized language. For example, if a Korean idol says "안녕하세요," the server generates the text "안녕하세요."

[0179] The generated text is then translated by the server into the user's native language using a common translation engine. For example, translation is performed from English to Japanese or from Korean to Japanese. This translation step converts the original text "안녕하세요" into the Japanese word "Hello."

[0180] Furthermore, the server is equipped with an emotion engine that analyzes the user's emotions. The emotion engine identifies the user's emotions by analyzing the user's facial expressions and voice data. For example, if the user is smiling, it can be judged as "joyful," and if the user's voice tone is calm, it can be judged as "neutral."

[0181] The translated text and the user's emotional data are sent from the server to the device. The device then displays the translation results and emotional data on the user's screen in real time. It is also possible to adjust the display method based on the emotional data. For example, if the user is excited, the text can be made larger or its color changed to emphasize it more visually.

[0182] Specific examples

[0183] Consider a scenario in which a user is attending a Korean idol concert. In this system, the user begins filming the idol's mouth using a camera built into their binoculars. The device captures the video and sends the data over the Internet to a server. The server analyzes the lip movements from the video and uses a machine learning model to generate the text "안녕하세요." The server then translates this text into Japanese, meaning "hello."

[0184] Furthermore, the server's emotion engine captures the user's facial expression with a camera and determines whether the user is smiling. If the user is smiling, the user's emotion is recorded as "happiness." The server then sends the translated text and emotion data to the device, and displays the text "Hello" and a colorful image reflecting the emotion of happiness on the user's smartphone screen. This allows the user to understand what the idol is saying in real time and respond in a way that matches their own emotions.

[0185] The processing flow will be explained below.

[0186] Step 1:

[0187] The user points the camera built into the binoculars at the idol's mouth and takes a video. The device then activates the video capture function and acquires the video data in real time.

[0188] Step 2:

[0189] The video data captured by the device is efficiently compressed and sent to a server over the Internet using data compression algorithms and high-speed communication protocols.

[0190] Step 3:

[0191] The server analyzes the received video data, locates the mouth position for each frame, and extracts the mouth area.

[0192] Step 4:

[0193] The server uses a machine learning model to analyze the mouth movements based on the extracted mouth area data and converts them into corresponding text (audio). For example, the Korean text "안녕하세요" is generated.

[0194] Step 5:

[0195] The server receives the converted text and translates it into the user's native language. Using a translation engine, the Korean "안녕하세요" is translated into the Japanese "Hello."

[0196] Step 6:

[0197] The device captures the user's facial expressions with a camera and sends the video data to a server.

[0198] Step 7:

[0199] The server analyzes the received facial expression data to identify the user's emotions. The emotion engine analyzes the user's facial and voice data to detect emotions such as "happiness," "sadness," and "surprise."

[0200] Step 8:

[0201] The server sends the translated text and identified emotion data to the device using a low-latency communication protocol.

[0202] Step 9:

[0203] The device adjusts the way the text is displayed based on the translated text and emotion data it receives. For example, if the user's emotion is "joy," the device changes the color and displays the text in a larger, more emphasized size.

[0204] Step 10:

[0205] The device then displays the final translation results on the user's smartphone screen in real time, allowing the user to instantly understand what the idol is saying and respond according to their own emotions.

[0206] Example 2

[0207] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0208] Conventional technologies have made it difficult for users to understand what is being said in real time at overseas concerts and events. Furthermore, they have been unable to display information that reflects the user's emotions, resulting in a poor user experience. This invention aims to combine real-time translation and emotion analysis to enable users to easily understand what is being said at overseas concerts and other events and receive appropriate feedback based on their emotions.

[0209] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a photographing device, a transmitting device, a recognizing device, a converting device, a translating device, a display device, an emotion analyzing device, and an integrating device. This makes it possible to analyze the video photographed by the user in real time, translate what is being said, and display it according to the user's emotion.

[0210] A "photography device" is a device for capturing video or images.

[0211] A "transmitting device" is a device for transmitting acquired video or image data to other devices or servers via a communication network.

[0212] A "recognition device" is a device that recognizes specific patterns or movements from received video or images.

[0213] A "conversion device" is a device for converting recognized data into another format or representation (e.g., text).

[0214] A "translation device" is a device for translating text expressed in one language into another language.

[0215] A "display device" is a device for visually displaying information to a user.

[0216] An "emotion analysis device" is a device that analyzes a user's facial expressions and voice data to identify the user's emotions.

[0217] An "integration device" is a device that integrates multiple pieces of data (for example, translated text and emotion data) and processes them as a single piece of information.

[0218] A "communications network" is a network system for sending and receiving data.

[0219] The present invention provides a system that uses a portable device to understand what is being said at events such as concerts by overseas idols in real time, and also recognizes the emotions of the user. A specific embodiment of this system will be described.

[0220] Users can use binoculars or smartphones with built-in cameras to film the idols speaking at concert venues. It is desirable for the filming device to have high-precision focus adjustment and image stabilization functions. Possible filming devices include smartphones, digital cameras, and video cameras.

[0221] The video is captured on the device and then transmitted to a server via a communications network (e.g., the Internet or a 5G network). The device compresses the data and converts the file format appropriately for efficient transmission. The communications technology used may be Wi-Fi, LTE, or 5G.

[0222] The server analyzes the received video data. Machine learning models (e.g., OpenCV, Dlib, TensorFlow) are used for the analysis. The server recognizes lip movements from the video and converts what is being said into text data using AI algorithms. For example, if a Korean idol says "안녕하세요," the server recognizes this as the text "안녕하세요." This process can be effectively performed using real-time processing with a GPU.

[0223] The generated text is then translated by the server into the user's native language using common translation engines (e.g., Google Translate API, DeepL). To improve translation accuracy, multiple translation candidates are compared in real time and the best one is selected. For example, the Korean text "안녕하세요" is converted to the Japanese "Hello."

[0224] Furthermore, the server is equipped with an emotion analysis device that analyzes the user's emotions. This device analyzes the user's facial expressions and voice data to identify the user's emotions. For example, by using Microsoft® Azure® facial recognition API or IBM Watson®, the system can analyze the user's facial expressions and tone of voice, and if the user is smiling, it will determine that the user is "happy."

[0225] The translated text and emotion data are sent from the server to the device. The data is encrypted before transmission to ensure security. The integration device integrates the translated text and emotion data and converts it into a format to be displayed on the user's device. The device then displays the received information on the user's screen in real time. For example, the text "Hello" is displayed along with an icon (😊) indicating the user's emotion of "happiness." The color and size of the text can also be dynamically changed depending on the emotion data. If the user is excited, the text can be displayed in red and larger to visually emphasize it.

[0226] As a concrete example, consider a scenario in which a user is attending a Korean idol concert. In this system, the user uses a camera built into binoculars to capture the idol's mouth, and the device captures the video and sends the data to a server over the Internet. The server analyzes the lip movements from the video data and uses a machine learning model to generate the text "안녕하세요," which is then translated into "hello." The server's emotion analyzer analyzes the user's facial expression and determines that the user is "happy" if they are smiling. The server then sends the translated text and emotion data to the device, displays "hello" on the user's screen, and adds a smiling icon to provide real-time understanding and emotional feedback.

[0227] The following are examples of prompt sentences:

[0228] "A user is attending a Korean idol concert. They use binoculars with built-in cameras to film the idol speaking. The device captures the video data and sends it to a server via a communication network. The server analyzes the mouth movements from the video and uses a machine learning model to translate the generated text, '안녕하세요', into Japanese and converts it to 'Hello.' The server then analyzes the user's facial expressions and, if the user is smiling, identifies the emotion of joy. The server then sends the emotion data along with the translated text to the user's device in real time. The user's device then displays the information on its screen."

[0229] The above is a specific embodiment for carrying out the invention of this system.

[0230] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0231] Step 1: User captures video on device

[0232] At the concert venue, users use a mobile device (e.g., binoculars or a smartphone with a built-in camera) to capture images of the idol's mouth and facial expressions. The user captures the image using the device's camera with high-precision focus adjustment and image stabilization functions.

[0233] Input: A mobile device held by the user

[0234] Output: Highly accurate video data of idols

[0235] Step 2: The device sends the video data to the server

[0236] The device compresses the captured video data and transmits it to a server via a communication network (e.g., the Internet or a 5G network). The file format is efficiently converted to reduce the amount of data.

[0237] Input: Captured video data

[0238] Output: Compressed video data sent to the server

[0239] What it does: The device uses a compression algorithm to convert the video data into MP4 format, then uses the device's communications module to send the data over the internet to a server.

[0240] Step 3: The server analyzes the video data

[0241] The server analyzes the received video data and recognizes the idol's lip movements using machine learning models (e.g., OpenCV, Dlib, TensorFlow), then uses AI algorithms to convert what is being said into text.

[0242] Input: Compressed video data

[0243] Output: Text data generated from lip movements

[0244] How it works: The server uses a GPU to analyze the mouth movements of each video frame and inputs that data into an AI model, which then converts the recognized mouth movements into text.

[0245] Step 4: The server translates the text

[0246] The server translates the generated text data into the user's native language using a common translation engine (e.g., Google Translate API, DeepL) and selects the best translation from multiple candidates.

[0247] Input: Recognized text data

[0248] Output: Translated text data

[0249] Specific operation: The server calls the translation API to translate the text data into other languages ​​and selects the most appropriate translation result.

[0250] Step 5: The server analyzes the sentiment

[0251] The server uses an emotion analysis engine (e.g., Microsoft Azure's Emotion API, IBM Watson) to analyze the user's facial expressions and voice data. It analyzes the user's facial expressions and tone of voice to identify their emotions.

[0252] Input: User's facial expressions and voice data

[0253] Output: Identified emotion data

[0254] Specific operation: The server uses an emotion analysis engine to analyze the user's facial features and voice tone to identify the type of emotion.

[0255] Step 6: The server sends the results to the device

[0256] The server transmits the translated text and emotion data to the terminal. The data is encrypted to ensure security. The server then uses an integration device to integrate the translated text and emotion data and convert them into data to be transmitted.

[0257] Input: Translated text data and emotion data

[0258] Output: Encrypted result data

[0259] Specific operation: The server uses a data encryption algorithm to encrypt the translation text and emotion data and transmits them to the terminal via a communication protocol.

[0260] Step 7: The terminal displays the results

[0261] Based on the received result data, the device displays the translated text and the emotion reflected on the user's screen in real time, dynamically adjusting the display method according to the emotion data.

[0262] Input: Brain-coded result data (translated text, emotion data)

[0263] Output: Translated text and emotion displayed on the user screen

[0264] Specific operation: The terminal decodes the result data and displays it in the user interface in an appropriate format. For example, if the user is excited, the text will be displayed in red and large.

[0265] The above is the specific processing flow of this system.

[0266] (Application example 2)

[0267] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0268] Conventional video analytics systems have difficulty understanding what is being said during an event, limiting their use, especially in situations where real-time translation into multiple languages ​​is required. Furthermore, there are no systems that can analyze user emotions and adjust the way information is displayed based on those emotions. As a result, there are a lack of ways for users to enrich their event experience.

[0269] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0270] In this invention, the server includes a photographing means for photographing video, a transmitting means for transmitting the photographed video via the Internet, a recognition means for recognizing lip movements from the received video, a converting means for converting the recognized lip movements into text, a translating means for translating the converted text into another language, a displaying means for displaying the translated text, an emotion recognition means for recognizing the emotional state of a user, and an adjusting means for adjusting the display method of the translated text in accordance with the emotional state of the user. This enables a user to understand the content of an overseas event in real time and dynamically adjust the display method of information in accordance with their own emotions.

[0271] "Capturing means" refers to devices or mechanisms for capturing images. Specifically, this applies to cameras and video cameras.

[0272] The "transmission means" is a function or device for transmitting the captured video data to a server via the Internet.

[0273] The "recognition means" is a mechanism for analyzing and identifying specific information, such as mouth movements, from received video. Generally, a machine learning model is used.

[0274] The "conversion means" is a function or device for converting information (for example, mouth movements) recognized by the recognition means into another format such as character data.

[0275] A "translation means" is a function or device for converting the converted text into another language.

[0276] "Display means" is a function or device for visually displaying the translated text to the user.

[0277] The "emotion recognition means" is a mechanism for analyzing data such as the user's facial expressions and voice, and identifying the user's emotional state.

[0278] The "adjustment means" is a function or device for dynamically changing the way the translated text is displayed depending on the emotional state of the user as identified by the emotion recognition means.

[0279] This invention is a system that uses a portable device to understand the content of speech at a specific event in real time and adjusts the way information is displayed based on the user's emotional state. This system is realized using the following hardware and software.

[0280] Hardware and software used

[0281] Hardware: Smartphone, smart glasses, head-mounted display (HMD), camera, internet connection

[0282] Software: Machine learning models (e.g., TensorFlow, PyTorch), translation engines (e.g., Google Translate API, Microsoft Translator API), emotion recognition engines (e.g., Google Cloud Vision API)

[0283] System action

[0284] First, a user captures the event video in real time using a smartphone or compatible device (smart glasses, HMD). This captured video data is sent to a server via the Internet. The server receives the video data and proceeds to the next step.

[0285] The server uses a machine learning model to recognize mouth movements from the received video data. Specifically, tools such as TensorFlow and PyTorch analyze mouth movements, and the recognized mouth movements are converted into text data. Since the converted text data is often difficult to understand as is, it is then translated into the user's native language using a translation engine. The Google Translate API and Microsoft Translator API are used for translation.

[0286] The server then uses an emotion recognition engine to analyze the user's emotional state. Facial and voice data captured by the user's device is sent to the server, where emotion analysis is performed using software such as Google Cloud Vision API. For example, if the user is smiling, it is determined to be "happy."

[0287] This data (translated text and emotional state) is then sent back to the user's device and presented to them through a display. Depending on the user's emotional state, the way the text is displayed is adjusted. For example, if the user is excited, the text will be displayed larger and in a more vibrant color to emphasize the visual impact.

[0288] Specific examples

[0289] For example, if a user is attending a Korean idol concert, their device will capture a video of the idol's mouth. The video data is sent to a server, where a remark such as "안녕하세요 (Hello)" is converted into text and then translated into Japanese. At the same time, the user's smile is captured and determined to be "joy" by an emotion recognition engine. Based on this, a colorful image reflecting the emotion of joy is displayed on the user's device along with the text "Hello."

[0290] Example prompt

[0291] Prompt: How can I translate Korean idols' comments in real time and display them based on the user's emotions?

[0292] This allows users to overcome language barriers and understand the event content in real time, resulting in a richer experience.

[0293] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0294] Step 1:

[0295] A user captures video of an event in real time using a smartphone or a compatible device (smart glasses, HMD). The input is video data from a camera, and the output is this video data. The user captures by taking a picture of a specific person or scene using the device.

[0296] Step 2:

[0297] The captured video data is sent to a server via the Internet. The input is the captured video data, and the output is the video data sent to the server via the Internet. The device converts the captured data into a certain format and sends it to the server via the Internet connection.

[0298] Step 3:

[0299] The server uses a machine learning model to analyze the received video data and recognize mouth movements. The input is the received video data, and the output is text data based on the recognized mouth movements. The server uses a machine learning model (TensorFlow or PyTorch) to analyze the speech content from the mouth movements and convert it into text.

[0300] Step 4:

[0301] The converted text data is translated into the user's native language using a translation engine. The input is the original text data converted from the recognized mouth movements, and the output is the translated text data. The server uses the Google Translate API or Microsoft Translator API to translate the original text into the user's native language.

[0302] Step 5:

[0303] An emotion recognition engine is used to analyze the user's emotional state. The input is the user's facial expression and voice data, and the output is the user's emotional state. The device captures the user's facial expression and voice data and sends it to a server, which then performs emotion analysis using Google Cloud Vision API or similar.

[0304] Step 6:

[0305] The information display method is adjusted based on the translated text data and the emotional state. The input is the translated text data and the emotional state, and the output is the final display data in the adjusted display method. The server adjusts, for example, the size and color of the text according to the emotional state and sends it to the user's device.

[0306] Step 7:

[0307] The final display data is displayed on the user's device screen. The input is the adjusted display data from the server, and the output is the text information displayed on the user's device. The terminal displays the information to the user in an appropriate format based on the data received.

[0308] This processing flow allows users to understand the content of events in real time and experience dynamic displays that respond to their emotions.

[0309] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0310] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0311] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0312] [Second embodiment]

[0313] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0314] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0315] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0316] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0317] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0318] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0319] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0320] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0321] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0322] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0323] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0324] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0325] The present invention is a system that enables a user to use a portable device to understand in real time what is being said at a concert of an overseas idol, etc. Specific embodiments of this system will be described below.

[0326] Users can use binoculars or smartphones with built-in cameras to film the idols speaking at concert venues. The footage is captured on the device and the video data is sent to a server via the Internet.

[0327] The server analyzes the received video data and recognizes lip movements. This recognition is performed using a machine learning model. The server identifies what is being said from the lip movements and generates that content as text. This text is expressed in the recognized language. For example, if a Korean idol says "안녕하세요," the server generates the text "안녕하세요."

[0328] The generated text is then translated by the server into the user's native language using a common translation engine. For example, translation is performed from English to Japanese or from Korean to Japanese. This translation step converts the original text "안녕하세요" into the Japanese word "Hello."

[0329] The translated text is sent from the server to the device, which can then display the received translation results on the user's screen in real time, allowing the user to instantly understand what the idol is saying and respond appropriately.

[0330] Specific examples

[0331] Consider a scenario in which a user is attending a Korean idol concert. In this system, the user begins filming the idol's mouth using a camera built into their binoculars. The device captures the video and sends the data to a server via the Internet. The server analyzes the lip movements from the video and uses a machine learning model to generate the text "안녕하세요." The server then translates this text into Japanese, meaning "hello." Finally, the translated text is sent to the device and displayed in real time on the user's smartphone screen.

[0332] The processing flow will be explained below.

[0333] Step 1:

[0334] The user points the camera built into the binoculars at the idol's mouth and takes a video. The device then starts up and the capture function is turned on.

[0335] Step 2:

[0336] The device acquires video data from the camera in real time. This video data is captured frame by frame (for example, 30 fps).

[0337] Step 3:

[0338] The video data captured by the device is efficiently compressed and sent to a server over the Internet using a low-latency communication protocol.

[0339] Step 4:

[0340] To analyze the video data received by the server, the position of the mouth is identified for each frame and the mouth area is extracted.

[0341] Step 5:

[0342] The server uses a machine learning model to analyze the mouth movements based on the extracted mouth area data and converts them into corresponding text (audio). In this process, the Korean character string "안녕하세요" (hello) is generated.

[0343] Step 6:

[0344] The server receives the converted text and translates it into the user's native language. Through the translation engine, the Korean "안녕하세요" is converted into the Japanese "Hello."

[0345] Step 7:

[0346] The server sends the translation results to the device in real time using a fast and reliable communication protocol.

[0347] Step 8:

[0348] The device receives the translation result ("Hello" in Japanese) and displays it on the user's smartphone screen in real time, allowing the user to instantly understand what the idol is saying.

[0349] This allows users to understand what the idol is saying during the concert in real time and respond immediately.

[0350] Example 1

[0351] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0352] In recent years, the demand for global entertainment has increased, especially with the number of concerts held in various countries by overseas music artists and idols. However, due to language barriers, users often find it difficult to understand what is being said at overseas concerts, limiting real-time communication and enjoyment. For this reason, there is a need for a system that can understand multilingual conversations in real time.

[0353] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0354] In this invention, the server includes a camera for shooting video, a transmitter for transmitting the video via a network, and a recognition unit for recognizing lip movements from the received video, thereby enabling users to overcome language barriers at overseas concerts and understand what is being said in real time.

[0355] "Capturing means" refers to a device or function for capturing video.

[0356] The "transmission means" is a device or function for transmitting captured video data to another device or server via a network.

[0357] "Recognition means" refers to a device or function for analyzing and recognizing specific information (in this case, mouth movements) from received video data.

[0358] The "conversion means" is a device or function for converting the recognized information into another format such as text data.

[0359] The "translation means" is a device or function for translating the converted text data into another language.

[0360] "Display means" refers to a device or function for visually displaying translated text data on a user's device.

[0361] A "machine learning algorithm" is a computational model that learns certain patterns or rules based on a dataset and then uses that knowledge to analyze new data.

[0362] An "automated translation algorithm" is a computational model for converting text from one language to another.

[0363] MODE FOR CARRYING OUT THE INVENTION

[0364] The present invention is a system that enables a user to use a portable device to understand in real time what is being said at a concert of an overseas idol, etc. A specific embodiment of this system will be described below.

[0365] Users can use binoculars or smartphones with built-in cameras to film the idols speaking at concert venues. The footage is captured on the device and the video data is sent to a server via a network.

[0366] The server analyzes the received video data and recognizes lip movements. This recognition is performed using a machine learning algorithm. Specifically, it can use the TensorFlow model, a common machine learning framework, or a cloud-based machine learning API. The server identifies what is being said from the lip movements and generates that content as text. For example, if a Korean idol says "안녕하세요," the server generates the text "안녕하세요."

[0367] The generated text is then translated by the server into the user's native language using an automatic translation algorithm. Specifically, common translation engines such as Google Translate API or DeepL Translate API can be used. This translation step converts the original text "안녕하세요" into the Japanese "Hello."

[0368] The translated text is sent from the server to the device, which can then display the received translation results on the user's device in real time, allowing the user to instantly understand what the idol is saying and respond appropriately.

[0369] Specific examples

[0370] For example, consider a scenario in which a user is attending a Korean idol concert. In this system, the user begins filming the idol's mouth using a camera built into their binoculars. The device captures the video and sends the data over the network to a server. The server analyzes the lip movements from the video and generates the text "안녕하세요" using a TensorFlow model. The server then translates this text into Japanese, meaning "hello," using the Google Translate API. Finally, the translated text is sent to the device and displayed in real time on the user's smartphone screen.

[0371] Prompt Sentence Examples

[0372] "Describe a system that allows you to understand what Korean idols are saying at their concerts in real time. Users take video using the built-in camera on their smartphones or binoculars and send the data to a server. The server uses a machine learning model to analyze their mouth movements and generate text from what they're saying. It then uses a translation engine to translate the text into the user's native language, and finally displays it on the user's device."

[0373] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0374] Step 1:

[0375] At a concert venue, users use a camera built into their smartphone or binoculars to take a picture of the idol's mouth.

[0376] Specifically, users simply open their device's camera app and point the camera at the idol's face, and the footage is captured in 1080p high definition.

[0377] Step 2:

[0378] The terminal transmits the captured video data to a server via the Internet in real time.

[0379] Specifically, the captured video data is compressed and sent via a network protocol (e.g. HTTP / HTTPS), the data is digitally encrypted, and the video data is received as input and sent to a server as output.

[0380] Step 3:

[0381] The server analyzes the received video data and runs machine learning algorithms to recognize mouth movements.

[0382] Specifically, the server stores video data in Google Cloud Storage and analyzes mouth movements using a TensorFlow model, taking video data as input and generating recognized mouth movement data as output.

[0383] Step 4:

[0384] The server analyzes the recognized mouth movement data and generates text of what is being said.

[0385] Specifically, the server uses a machine learning algorithm to infer what is being said from mouth movements and generate text data, such as "안녕하세요." It receives mouth movement data as input and generates text data as output.

[0386] Step 5:

[0387] The server translates the generated text data into the user's native language using an automatic translation algorithm.

[0388] Specifically, the server calls the Google Translate API to translate the input text "안녕하세요" into Japanese "Hello." It receives text data as input and generates translated text data as output.

[0389] Step 6:

[0390] The server transmits the translated text data to the user's terminal.

[0391] Specifically, the translation data is encrypted using the HTTPS protocol and sent to the device. The translated text data is received as input and sent to the device as output.

[0392] Step 7:

[0393] The terminal displays the received translation data on the user's device in real time.

[0394] Specifically, the device displays the translated data as a pop-up window or scrolling subtitles so that the user can visually confirm it. The device receives the translated data as input and displays it on the user's screen as output.

[0395] (Application example 1)

[0396] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0397] Conventional translation systems are designed to support real-time communication between people who speak different languages, but they have had challenges in analyzing and responding immediately to conversations that include visual elements, such as eye contact and gestures. In certain situations, such as brick-and-mortar stores in tourist areas, where multinational customers frequently visit, employees are required to respond smoothly in different languages, but this also poses challenges.

[0398] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0399] In this invention, the server includes a camera for capturing video, a transmitter for transmitting the captured video via the Internet, and a recognition unit for recognizing mouth movements from the received video, thereby enabling accurate understanding of foreign language conversations in real time and quick and appropriate responses to multinational customers.

[0400] The "capture means" is a device for capturing an image of an object, and includes, for example, a camera device built into smart glasses.

[0401] The "transmission means" is a communication module for transmitting the captured video data to a server via the Internet.

[0402] "Recognition means" includes a set of algorithms and machine learning models used to identify a subject's mouth movements from received video data.

[0403] The "conversion means" includes a program or algorithm for converting the recognized mouth movements into a text format.

[0404] "Translation means" includes a translation engine or corresponding software for converting the generated text into another language.

[0405] "Display means" includes a display device or projection system for visually presenting the translated text to a user.

[0406] A "head-mounted display" is a wearable device that can display images and information in real time when worn by the user.

[0407] "Generative AI model" refers to an artificial intelligence algorithm used to extract specific information from video data, specifically a model for analyzing mouth movements.

[0408] A "prompt" is an input sentence used to instruct a generative AI model or other algorithm to effectively perform the parsing or translation process.

[0409] This invention is a system that uses smart glasses worn by store staff to support real-time communication with customers who speak a foreign language. This system is implemented using the following hardware and software.

[0410] Hardware

[0411] 1. Smart Glasses

[0412] Photographic method: A built-in camera is used to capture a photo of the customer's mouth in real time.

[0413] Display means: A display is used to display the translated text to the user.

[0414] 2. Cloud Server

[0415] Transmission means: Receives video data sent from the smart glasses via the Internet.

[0416] software

[0417] 1. Generative AI Models

[0418] Recognition method: Runs on a cloud server and analyzes mouth movements from received video data.

[0419] 2. Conversion Method

[0420] Text generation algorithm: Recognizes mouth movements and converts the analysis results into text format.

[0421] 3. Translation Methods

[0422] Translation engine: Used to translate the generated text into the user's native language (e.g. Google Translate API).

[0423] Data processing and calculation procedures

[0424] 1. Video capture: The user (store staff) wears smart glasses and uses the built-in camera to capture what the customer is saying.

[0425] 2. Data transmission: The smart glasses transmit the captured video data to a cloud server via the Internet.

[0426] 3. Data analysis: The cloud server analyzes the received video data and uses a generative AI model to recognize the customer's mouth movements.

[0427] 4. Text Conversion: After the mouth movements are recognized, the content is converted into text format.

[0428] 5. Translation: The generated text is translated into the user's native language using a translation engine.

[0429] 6. Display: The translated text will be displayed on the smart glasses display in real time.

[0430] Specific examples

[0431] For example, a store staff member wearing smart glasses films a Korean tourist greeting "안녕하세요." The smart glasses send this video data to a cloud server, which uses a generative AI model to analyze the lip movements of "안녕하세요" and converts it into text. The translation engine then translates this text into Japanese, meaning "hello," and the translation is displayed on the staff member's smart glasses screen.

[0432] Prompt Sentence Examples

[0433] "Analyze the video data and output what is being said as text."

[0434] "Please translate the generated text into Japanese in real time."

[0435] In this way, users can smoothly communicate with customers who speak a foreign language.

[0436] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0437] Step 1:

[0438] The user wears the smart glasses and the built-in camera captures what the customer is saying.

[0439] Input: Image of customer's mouth

[0440] Output: Recorded video data

[0441] Specific operation: The built-in camera of the smart glasses captures video in real time and temporarily stores the video data within the device.

[0442] Step 2:

[0443] The device transmits the captured video data to a cloud server via the Internet.

[0444] Input: Video data stored on the device

[0445] Output: Video data sent to the cloud server

[0446] Specific operation: The terminal's communication module uploads the video data to a cloud server via the Internet.

[0447] Step 3:

[0448] The server recognizes mouth movements using a generative AI model from the video data it receives.

[0449] Input: Video data sent to the cloud server

[0450] Output: Mouth movement recognition results

[0451] How it works: A cloud server uses a generative AI model (e.g., a machine learning algorithm) to analyze the video data and extract lip movements in text format.

[0452] Step 4:

[0453] The server uses the information it recognizes from mouth movements to convert it into text using a text conversion algorithm.

[0454] Input: Mouth movement recognition results

[0455] Output: The generated text

[0456] Specific operation: The server automatically generates text based on the analysis of mouth movements and saves it as text data.

[0457] Step 5:

[0458] The server translates the generated text into the user's native language using a translation engine.

[0459] Input: Generated text

[0460] Output: The translated text

[0461] Specific operation: The cloud server uses a translation engine (e.g., Google Translate API) to translate the text in real time and generate the translation result.

[0462] Step 6:

[0463] The translated text is displayed on the display of the user's smart glasses.

[0464] Input: Translated text

[0465] Output: Translated text displayed on the smart glasses display

[0466] Specific operation: The translation results are sent from the cloud server to the smart glasses, and the text is displayed on the smart glasses' display in real time.

[0467] This allows users to communicate smoothly with customers who speak a foreign language.

[0468] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0469] The present invention provides a system that uses a user's portable device to understand what is being said at events such as overseas idol concerts in real time and recognize the user's emotions. Specific embodiments of this system are described below.

[0470] Users film an idol speaking at a concert venue using binoculars or a smartphone with a built-in camera. The video is captured on the device and sent to a server via the internet. The server analyzes the received video data and recognizes lip movements. This recognition is performed using a machine learning model. The server identifies what is being said from the lip movements and generates that content as text. This text is expressed in the recognized language. For example, if a Korean idol says "안녕하세요," the server generates the text "안녕하세요."

[0471] The generated text is then translated by the server into the user's native language using a common translation engine. For example, translation is performed from English to Japanese or from Korean to Japanese. This translation step converts the original text "안녕하세요" into the Japanese word "Hello."

[0472] Furthermore, the server is equipped with an emotion engine that analyzes the user's emotions. The emotion engine identifies the user's emotions by analyzing the user's facial expressions and voice data. For example, if the user is smiling, it can be judged as "joyful," and if the user's voice tone is calm, it can be judged as "neutral."

[0473] The translated text and the user's emotional data are sent from the server to the device. The device then displays the translation results and emotional data on the user's screen in real time. It is also possible to adjust the display method based on the emotional data. For example, if the user is excited, the text can be made larger or its color changed to emphasize it more visually.

[0474] Specific examples

[0475] Consider a scenario in which a user is attending a Korean idol concert. In this system, the user begins filming the idol's mouth using a camera built into their binoculars. The device captures the video and sends the data over the Internet to a server. The server analyzes the lip movements from the video and uses a machine learning model to generate the text "안녕하세요." The server then translates this text into Japanese, meaning "hello."

[0476] Furthermore, the server's emotion engine captures the user's facial expression with a camera and determines whether the user is smiling. If the user is smiling, the user's emotion is recorded as "happiness." The server then sends the translated text and emotion data to the device, and displays the text "Hello" and a colorful image reflecting the emotion of happiness on the user's smartphone screen. This allows the user to understand what the idol is saying in real time and respond in a way that matches their own emotions.

[0477] The processing flow will be explained below.

[0478] Step 1:

[0479] The user points the camera built into the binoculars at the idol's mouth and takes a video. The device then activates the video capture function and acquires the video data in real time.

[0480] Step 2:

[0481] The video data captured by the device is efficiently compressed and sent to a server over the Internet using data compression algorithms and high-speed communication protocols.

[0482] Step 3:

[0483] The server analyzes the received video data, locates the mouth position for each frame, and extracts the mouth area.

[0484] Step 4:

[0485] The server uses a machine learning model to analyze the mouth movements based on the extracted mouth area data and converts them into corresponding text (audio). For example, the Korean text "안녕하세요" is generated.

[0486] Step 5:

[0487] The server receives the converted text and translates it into the user's native language. Using a translation engine, the Korean "안녕하세요" is translated into the Japanese "Hello."

[0488] Step 6:

[0489] The device captures the user's facial expressions with a camera and sends the video data to a server.

[0490] Step 7:

[0491] The server analyzes the received facial expression data to identify the user's emotions. The emotion engine analyzes the user's facial and voice data to detect emotions such as "happiness," "sadness," and "surprise."

[0492] Step 8:

[0493] The server sends the translated text and identified emotion data to the device using a low-latency communication protocol.

[0494] Step 9:

[0495] The device adjusts the way the text is displayed based on the translated text and emotion data it receives. For example, if the user's emotion is "joy," the device changes the color and displays the text in a larger, more emphasized size.

[0496] Step 10:

[0497] The device then displays the final translation results on the user's smartphone screen in real time, allowing the user to instantly understand what the idol is saying and respond according to their own emotions.

[0498] Example 2

[0499] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0500] Conventional technologies have made it difficult for users to understand what is being said in real time at overseas concerts and events. Furthermore, they have been unable to display information that reflects the user's emotions, resulting in a poor user experience. This invention aims to combine real-time translation and emotion analysis to enable users to easily understand what is being said at overseas concerts and other events and receive appropriate feedback based on their emotions.

[0501] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a photographing device, a transmitting device, a recognizing device, a converting device, a translating device, a display device, an emotion analyzing device, and an integrating device. This makes it possible to analyze the video photographed by the user in real time, translate what is being said, and display it according to the user's emotion.

[0502] A "photography device" is a device for capturing video or images.

[0503] A "transmitting device" is a device for transmitting acquired video or image data to other devices or servers via a communication network.

[0504] A "recognition device" is a device that recognizes specific patterns or movements from received video or images.

[0505] A "conversion device" is a device for converting recognized data into another format or representation (e.g., text).

[0506] A "translation device" is a device for translating text expressed in one language into another language.

[0507] A "display device" is a device for visually displaying information to a user.

[0508] An "emotion analysis device" is a device that analyzes a user's facial expressions and voice data to identify the user's emotions.

[0509] An "integration device" is a device that integrates multiple pieces of data (for example, translated text and emotion data) and processes them as a single piece of information.

[0510] A "communications network" is a network system for sending and receiving data.

[0511] The present invention provides a system that uses a portable device to understand what is being said at events such as concerts by overseas idols in real time, and also recognizes the emotions of the user. A specific embodiment of this system will be described.

[0512] Users can use binoculars or smartphones with built-in cameras to film the idols speaking at concert venues. It is desirable for the filming device to have high-precision focus adjustment and image stabilization functions. Possible filming devices include smartphones, digital cameras, and video cameras.

[0513] The video is captured on the device and then transmitted to a server via a communications network (e.g., the Internet or a 5G network). The device compresses the data and converts the file format appropriately for efficient transmission. The communications technology used may be Wi-Fi, LTE, or 5G.

[0514] The server analyzes the received video data. Machine learning models (e.g., OpenCV, Dlib, TensorFlow) are used for the analysis. The server recognizes lip movements from the video and converts what is being said into text data using AI algorithms. For example, if a Korean idol says "안녕하세요," the server recognizes this as the text "안녕하세요." This process can be effectively performed using real-time processing with a GPU.

[0515] The generated text is then translated by the server into the user's native language using common translation engines (e.g., Google Translate API, DeepL). To improve translation accuracy, multiple translation candidates are compared in real time and the best one is selected. For example, the Korean text "안녕하세요" is converted to the Japanese "Hello."

[0516] Furthermore, the server is equipped with an emotion analysis device that analyzes the user's emotions. This device analyzes the user's facial expressions and voice data to identify the user's emotions. For example, by using Microsoft Azure's facial recognition API or IBM Watson, the device can analyze the user's facial expressions and tone of voice, and if the user is smiling, it will determine that the user is "happy."

[0517] The translated text and emotion data are sent from the server to the device. The data is encrypted before transmission to ensure security. The integration device integrates the translated text and emotion data and converts it into a format to be displayed on the user's device. The device then displays the received information on the user's screen in real time. For example, the text "Hello" is displayed along with an icon (😊) indicating the user's emotion of "happiness." The color and size of the text can also be dynamically changed depending on the emotion data. If the user is excited, the text can be displayed in red and larger to visually emphasize it.

[0518] As a concrete example, consider a scenario in which a user is attending a Korean idol concert. In this system, the user uses a camera built into binoculars to capture the idol's mouth, and the device captures the video and sends the data to a server over the Internet. The server analyzes the lip movements from the video data and uses a machine learning model to generate the text "안녕하세요," which is then translated into "hello." The server's emotion analyzer analyzes the user's facial expression and determines that the user is "happy" if they are smiling. The server then sends the translated text and emotion data to the device, displays "hello" on the user's screen, and adds a smiling icon to provide real-time understanding and emotional feedback.

[0519] The following are examples of prompt sentences:

[0520] "A user is attending a Korean idol concert. They use binoculars with built-in cameras to film the idol speaking. The device captures the video data and sends it to a server via a communication network. The server analyzes the mouth movements from the video and uses a machine learning model to translate the generated text, '안녕하세요', into Japanese and converts it to 'Hello.' The server then analyzes the user's facial expressions and, if the user is smiling, identifies the emotion of joy. The server then sends the emotion data along with the translated text to the user's device in real time. The user's device then displays the information on its screen."

[0521] The above is a specific embodiment for carrying out the invention of this system.

[0522] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0523] Step 1: User captures video on device

[0524] At the concert venue, users use a mobile device (e.g., binoculars or a smartphone with a built-in camera) to capture images of the idol's mouth and facial expressions. The user captures the image using the device's camera with high-precision focus adjustment and image stabilization functions.

[0525] Input: A mobile device held by the user

[0526] Output: Highly accurate video data of idols

[0527] Step 2: The device sends the video data to the server

[0528] The device compresses the captured video data and transmits it to a server via a communication network (e.g., the Internet or a 5G network). The file format is efficiently converted to reduce the amount of data.

[0529] Input: Captured video data

[0530] Output: Compressed video data sent to the server

[0531] What it does: The device uses a compression algorithm to convert the video data into MP4 format, then uses the device's communications module to send the data over the internet to a server.

[0532] Step 3: The server analyzes the video data

[0533] The server analyzes the received video data and recognizes the idol's lip movements using machine learning models (e.g., OpenCV, Dlib, TensorFlow), then uses AI algorithms to convert what is being said into text.

[0534] Input: Compressed video data

[0535] Output: Text data generated from lip movements

[0536] How it works: The server uses a GPU to analyze the mouth movements of each video frame and inputs that data into an AI model, which then converts the recognized mouth movements into text.

[0537] Step 4: The server translates the text

[0538] The server translates the generated text data into the user's native language using a common translation engine (e.g., Google Translate API, DeepL) and selects the best translation from multiple candidates.

[0539] Input: Recognized text data

[0540] Output: Translated text data

[0541] Specific operation: The server calls the translation API to translate the text data into other languages ​​and selects the most appropriate translation result.

[0542] Step 5: The server analyzes the sentiment

[0543] The server uses an emotion analysis engine (e.g., Microsoft Azure's Emotion API, IBM Watson) to analyze the user's facial expressions and voice data. It analyzes the user's facial expressions and tone of voice to identify their emotions.

[0544] Input: User's facial expressions and voice data

[0545] Output: Identified emotion data

[0546] Specific operation: The server uses an emotion analysis engine to analyze the user's facial features and voice tone to identify the type of emotion.

[0547] Step 6: The server sends the results to the device

[0548] The server transmits the translated text and emotion data to the terminal. The data is encrypted to ensure security. The server then uses an integration device to integrate the translated text and emotion data and convert them into data to be transmitted.

[0549] Input: Translated text data and emotion data

[0550] Output: Encrypted result data

[0551] Specific operation: The server uses a data encryption algorithm to encrypt the translation text and emotion data and transmits them to the terminal via a communication protocol.

[0552] Step 7: The terminal displays the results

[0553] Based on the received result data, the device displays the translated text and the emotion reflected on the user's screen in real time, dynamically adjusting the display method according to the emotion data.

[0554] Input: Brain-coded result data (translated text, emotion data)

[0555] Output: Translated text and emotion displayed on the user screen

[0556] Specific operation: The terminal decodes the result data and displays it in the user interface in an appropriate format. For example, if the user is excited, the text will be displayed in red and large.

[0557] The above is the specific processing flow of this system.

[0558] (Application example 2)

[0559] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0560] Conventional video analytics systems have difficulty understanding what is being said during an event, limiting their use, especially in situations where real-time translation into multiple languages ​​is required. Furthermore, there are no systems that can analyze user emotions and adjust the way information is displayed based on those emotions. As a result, there are a lack of ways for users to enrich their event experience.

[0561] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0562] In this invention, the server includes a photographing means for photographing video, a transmitting means for transmitting the photographed video via the Internet, a recognition means for recognizing lip movements from the received video, a converting means for converting the recognized lip movements into text, a translating means for translating the converted text into another language, a displaying means for displaying the translated text, an emotion recognition means for recognizing the emotional state of a user, and an adjusting means for adjusting the display method of the translated text in accordance with the emotional state of the user. This enables a user to understand the content of an overseas event in real time and dynamically adjust the display method of information in accordance with their own emotions.

[0563] "Capturing means" refers to devices or mechanisms for capturing images. Specifically, this applies to cameras and video cameras.

[0564] The "transmission means" is a function or device for transmitting the captured video data to a server via the Internet.

[0565] The "recognition means" is a mechanism for analyzing and identifying specific information, such as mouth movements, from received video. Generally, a machine learning model is used.

[0566] The "conversion means" is a function or device for converting information (for example, mouth movements) recognized by the recognition means into another format such as character data.

[0567] A "translation means" is a function or device for converting the converted text into another language.

[0568] "Display means" is a function or device for visually displaying the translated text to the user.

[0569] The "emotion recognition means" is a mechanism for analyzing data such as the user's facial expressions and voice, and identifying the user's emotional state.

[0570] The "adjustment means" is a function or device for dynamically changing the way the translated text is displayed depending on the emotional state of the user as identified by the emotion recognition means.

[0571] This invention is a system that uses a portable device to understand the content of speech at a specific event in real time and adjusts the way information is displayed based on the user's emotional state. This system is realized using the following hardware and software.

[0572] Hardware and software used

[0573] Hardware: Smartphone, smart glasses, head-mounted display (HMD), camera, internet connection

[0574] Software: Machine learning models (e.g., TensorFlow, PyTorch), translation engines (e.g., Google Translate API, Microsoft Translator API), emotion recognition engines (e.g., Google Cloud Vision API)

[0575] System action

[0576] First, a user captures the event video in real time using a smartphone or compatible device (smart glasses, HMD). This captured video data is sent to a server via the Internet. The server receives the video data and proceeds to the next step.

[0577] The server uses a machine learning model to recognize mouth movements from the received video data. Specifically, tools such as TensorFlow and PyTorch analyze mouth movements, and the recognized mouth movements are converted into text data. Since the converted text data is often difficult to understand as is, it is then translated into the user's native language using a translation engine. The Google Translate API and Microsoft Translator API are used for translation.

[0578] The server then uses an emotion recognition engine to analyze the user's emotional state. Facial and voice data captured by the user's device is sent to the server, where emotion analysis is performed using software such as Google Cloud Vision API. For example, if the user is smiling, it is determined to be "happy."

[0579] This data (translated text and emotional state) is then sent back to the user's device and presented to them through a display. Depending on the user's emotional state, the way the text is displayed is adjusted. For example, if the user is excited, the text will be displayed larger and in a more vibrant color to emphasize the visual impact.

[0580] Specific examples

[0581] For example, if a user is attending a Korean idol concert, their device will capture a video of the idol's mouth. The video data is sent to a server, where a remark such as "안녕하세요 (Hello)" is converted into text and then translated into Japanese. At the same time, the user's smile is captured and determined to be "joy" by an emotion recognition engine. Based on this, a colorful image reflecting the emotion of joy is displayed on the user's device along with the text "Hello."

[0582] Example prompt

[0583] Prompt: How can I translate Korean idols' comments in real time and display them based on the user's emotions?

[0584] This allows users to overcome language barriers and understand the event content in real time, resulting in a richer experience.

[0585] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0586] Step 1:

[0587] A user captures video of an event in real time using a smartphone or a compatible device (smart glasses, HMD). The input is video data from a camera, and the output is this video data. The user captures by taking a picture of a specific person or scene using the device.

[0588] Step 2:

[0589] The captured video data is sent to a server via the Internet. The input is the captured video data, and the output is the video data sent to the server via the Internet. The device converts the captured data into a certain format and sends it to the server via the Internet connection.

[0590] Step 3:

[0591] The server uses a machine learning model to analyze the received video data and recognize mouth movements. The input is the received video data, and the output is text data based on the recognized mouth movements. The server uses a machine learning model (TensorFlow or PyTorch) to analyze the speech content from the mouth movements and convert it into text.

[0592] Step 4:

[0593] The converted text data is translated into the user's native language using a translation engine. The input is the original text data converted from the recognized mouth movements, and the output is the translated text data. The server uses the Google Translate API or Microsoft Translator API to translate the original text into the user's native language.

[0594] Step 5:

[0595] An emotion recognition engine is used to analyze the user's emotional state. The input is the user's facial expression and voice data, and the output is the user's emotional state. The device captures the user's facial expression and voice data and sends it to a server, which then performs emotion analysis using Google Cloud Vision API or similar.

[0596] Step 6:

[0597] The information display method is adjusted based on the translated text data and the emotional state. The input is the translated text data and the emotional state, and the output is the final display data in the adjusted display method. The server adjusts, for example, the size and color of the text according to the emotional state and sends it to the user's device.

[0598] Step 7:

[0599] The final display data is displayed on the user's device screen. The input is the adjusted display data from the server, and the output is the text information displayed on the user's device. The terminal displays the information to the user in an appropriate format based on the data received.

[0600] This processing flow allows users to understand the content of events in real time and experience dynamic displays that respond to their emotions.

[0601] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0602] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0603] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0604] [Third embodiment]

[0605] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0606] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0607] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0608] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0609] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0610] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0611] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0612] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0613] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0614] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0615] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0616] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0617] The present invention is a system that enables a user to use a portable device to understand in real time what is being said at a concert of an overseas idol, etc. Specific embodiments of this system will be described below.

[0618] Users can use binoculars or smartphones with built-in cameras to film the idols speaking at concert venues. The footage is captured on the device and the video data is sent to a server via the Internet.

[0619] The server analyzes the received video data and recognizes lip movements. This recognition is performed using a machine learning model. The server identifies what is being said from the lip movements and generates that content as text. This text is expressed in the recognized language. For example, if a Korean idol says "안녕하세요," the server generates the text "안녕하세요."

[0620] The generated text is then translated by the server into the user's native language using a common translation engine. For example, translation is performed from English to Japanese or from Korean to Japanese. This translation step converts the original text "안녕하세요" into the Japanese word "Hello."

[0621] The translated text is sent from the server to the device, which can then display the received translation results on the user's screen in real time, allowing the user to instantly understand what the idol is saying and respond appropriately.

[0622] Specific examples

[0623] Consider a scenario in which a user is attending a Korean idol concert. In this system, the user begins filming the idol's mouth using a camera built into their binoculars. The device captures the video and sends the data to a server via the Internet. The server analyzes the lip movements from the video and uses a machine learning model to generate the text "안녕하세요." The server then translates this text into Japanese, meaning "hello." Finally, the translated text is sent to the device and displayed in real time on the user's smartphone screen.

[0624] The processing flow will be explained below.

[0625] Step 1:

[0626] The user points the camera built into the binoculars at the idol's mouth and takes a video. The device then starts up and the capture function is turned on.

[0627] Step 2:

[0628] The device acquires video data from the camera in real time. This video data is captured frame by frame (for example, 30 fps).

[0629] Step 3:

[0630] The video data captured by the device is efficiently compressed and sent to a server over the Internet using a low-latency communication protocol.

[0631] Step 4:

[0632] To analyze the video data received by the server, the position of the mouth is identified for each frame and the mouth area is extracted.

[0633] Step 5:

[0634] The server uses a machine learning model to analyze the mouth movements based on the extracted mouth area data and converts them into corresponding text (audio). In this process, the Korean character string "안녕하세요" (hello) is generated.

[0635] Step 6:

[0636] The server receives the converted text and translates it into the user's native language. Through the translation engine, the Korean "안녕하세요" is converted into the Japanese "Hello."

[0637] Step 7:

[0638] The server sends the translation results to the device in real time using a fast and reliable communication protocol.

[0639] Step 8:

[0640] The device receives the translation result ("Hello" in Japanese) and displays it on the user's smartphone screen in real time, allowing the user to instantly understand what the idol is saying.

[0641] This allows users to understand what the idol is saying during the concert in real time and respond immediately.

[0642] Example 1

[0643] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0644] In recent years, the demand for global entertainment has increased, especially with the number of concerts held in various countries by overseas music artists and idols. However, due to language barriers, users often find it difficult to understand what is being said at overseas concerts, limiting real-time communication and enjoyment. For this reason, there is a need for a system that can understand multilingual conversations in real time.

[0645] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0646] In this invention, the server includes a camera for shooting video, a transmitter for transmitting the video via a network, and a recognition unit for recognizing lip movements from the received video, thereby enabling users to overcome language barriers at overseas concerts and understand what is being said in real time.

[0647] "Capturing means" refers to a device or function for capturing video.

[0648] The "transmission means" is a device or function for transmitting captured video data to another device or server via a network.

[0649] "Recognition means" refers to a device or function for analyzing and recognizing specific information (in this case, mouth movements) from received video data.

[0650] The "conversion means" is a device or function for converting the recognized information into another format such as text data.

[0651] The "translation means" is a device or function for translating the converted text data into another language.

[0652] "Display means" refers to a device or function for visually displaying translated text data on a user's device.

[0653] A "machine learning algorithm" is a computational model that learns certain patterns or rules based on a dataset and then uses that knowledge to analyze new data.

[0654] An "automated translation algorithm" is a computational model for converting text from one language to another.

[0655] MODE FOR CARRYING OUT THE INVENTION

[0656] The present invention is a system that enables a user to use a portable device to understand in real time what is being said at a concert of an overseas idol, etc. A specific embodiment of this system will be described below.

[0657] Users can use binoculars or smartphones with built-in cameras to film the idols speaking at concert venues. The footage is captured on the device and the video data is sent to a server via a network.

[0658] The server analyzes the received video data and recognizes lip movements. This recognition is performed using a machine learning algorithm. Specifically, it can use the TensorFlow model, a common machine learning framework, or a cloud-based machine learning API. The server identifies what is being said from the lip movements and generates that content as text. For example, if a Korean idol says "안녕하세요," the server generates the text "안녕하세요."

[0659] The generated text is then translated by the server into the user's native language using an automatic translation algorithm. Specifically, common translation engines such as Google Translate API or DeepL Translate API can be used. This translation step converts the original text "안녕하세요" into the Japanese "Hello."

[0660] The translated text is sent from the server to the device, which can then display the received translation results on the user's device in real time, allowing the user to instantly understand what the idol is saying and respond appropriately.

[0661] Specific examples

[0662] For example, consider a scenario in which a user is attending a Korean idol concert. In this system, the user begins filming the idol's mouth using a camera built into their binoculars. The device captures the video and sends the data over the network to a server. The server analyzes the lip movements from the video and generates the text "안녕하세요" using a TensorFlow model. The server then translates this text into Japanese, meaning "hello," using the Google Translate API. Finally, the translated text is sent to the device and displayed in real time on the user's smartphone screen.

[0663] Prompt Sentence Examples

[0664] "Describe a system that allows you to understand what Korean idols are saying at their concerts in real time. Users take video using the built-in camera on their smartphones or binoculars and send the data to a server. The server uses a machine learning model to analyze their mouth movements and generate text from what they're saying. It then uses a translation engine to translate the text into the user's native language, and finally displays it on the user's device."

[0665] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0666] Step 1:

[0667] At a concert venue, users use a camera built into their smartphone or binoculars to take a picture of the idol's mouth.

[0668] Specifically, users simply open their device's camera app and point the camera at the idol's face, and the footage is captured in 1080p high definition.

[0669] Step 2:

[0670] The terminal transmits the captured video data to a server via the Internet in real time.

[0671] Specifically, the captured video data is compressed and sent via a network protocol (e.g. HTTP / HTTPS), the data is digitally encrypted, and the video data is received as input and sent to a server as output.

[0672] Step 3:

[0673] The server analyzes the received video data and runs machine learning algorithms to recognize mouth movements.

[0674] Specifically, the server stores video data in Google Cloud Storage and analyzes mouth movements using a TensorFlow model, taking video data as input and generating recognized mouth movement data as output.

[0675] Step 4:

[0676] The server analyzes the recognized mouth movement data and generates text of what is being said.

[0677] Specifically, the server uses a machine learning algorithm to infer what is being said from mouth movements and generate text data, such as "안녕하세요." It receives mouth movement data as input and generates text data as output.

[0678] Step 5:

[0679] The server translates the generated text data into the user's native language using an automatic translation algorithm.

[0680] Specifically, the server calls the Google Translate API to translate the input text "안녕하세요" into Japanese "Hello." It receives text data as input and generates translated text data as output.

[0681] Step 6:

[0682] The server transmits the translated text data to the user's terminal.

[0683] Specifically, the translation data is encrypted using the HTTPS protocol and sent to the device. The translated text data is received as input and sent to the device as output.

[0684] Step 7:

[0685] The terminal displays the received translation data on the user's device in real time.

[0686] Specifically, the device displays the translated data as a pop-up window or scrolling subtitles so that the user can visually confirm it. The device receives the translated data as input and displays it on the user's screen as output.

[0687] (Application example 1)

[0688] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0689] Conventional translation systems are designed to support real-time communication between people who speak different languages, but they have had challenges in analyzing and responding immediately to conversations that include visual elements, such as eye contact and gestures. In certain situations, such as brick-and-mortar stores in tourist areas, where multinational customers frequently visit, employees are required to respond smoothly in different languages, but this also poses challenges.

[0690] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0691] In this invention, the server includes a camera for capturing video, a transmitter for transmitting the captured video via the Internet, and a recognition unit for recognizing mouth movements from the received video, thereby enabling accurate understanding of foreign language conversations in real time and quick and appropriate responses to multinational customers.

[0692] The "capture means" is a device for capturing an image of an object, and includes, for example, a camera device built into smart glasses.

[0693] The "transmission means" is a communication module for transmitting the captured video data to a server via the Internet.

[0694] "Recognition means" includes a set of algorithms and machine learning models used to identify a subject's mouth movements from received video data.

[0695] The "conversion means" includes a program or algorithm for converting the recognized mouth movements into a text format.

[0696] "Translation means" includes a translation engine or corresponding software for converting the generated text into another language.

[0697] "Display means" includes a display device or projection system for visually presenting the translated text to a user.

[0698] A "head-mounted display" is a wearable device that can display images and information in real time when worn by the user.

[0699] "Generative AI model" refers to an artificial intelligence algorithm used to extract specific information from video data, specifically a model for analyzing mouth movements.

[0700] A "prompt" is an input sentence used to instruct a generative AI model or other algorithm to effectively perform the parsing or translation process.

[0701] This invention is a system that uses smart glasses worn by store staff to support real-time communication with customers who speak a foreign language. This system is implemented using the following hardware and software.

[0702] Hardware

[0703] 1. Smart Glasses

[0704] Photographic method: A built-in camera is used to capture a photo of the customer's mouth in real time.

[0705] Display means: A display is used to display the translated text to the user.

[0706] 2. Cloud Server

[0707] Transmission means: Receives video data sent from the smart glasses via the Internet.

[0708] software

[0709] 1. Generative AI Models

[0710] Recognition method: Runs on a cloud server and analyzes mouth movements from received video data.

[0711] 2. Conversion Method

[0712] Text generation algorithm: Recognizes mouth movements and converts the analysis results into text format.

[0713] 3. Translation Methods

[0714] Translation engine: Used to translate the generated text into the user's native language (e.g. Google Translate API).

[0715] Data processing and calculation procedures

[0716] 1. Video capture: The user (store staff) wears smart glasses and uses the built-in camera to capture what the customer is saying.

[0717] 2. Data transmission: The smart glasses transmit the captured video data to a cloud server via the Internet.

[0718] 3. Data analysis: The cloud server analyzes the received video data and uses a generative AI model to recognize the customer's mouth movements.

[0719] 4. Text Conversion: After the mouth movements are recognized, the content is converted into text format.

[0720] 5. Translation: The generated text is translated into the user's native language using a translation engine.

[0721] 6. Display: The translated text will be displayed on the smart glasses display in real time.

[0722] Specific examples

[0723] For example, a store staff member wearing smart glasses films a Korean tourist greeting "안녕하세요." The smart glasses send this video data to a cloud server, which uses a generative AI model to analyze the lip movements of "안녕하세요" and converts it into text. The translation engine then translates this text into Japanese, meaning "hello," and the translation is displayed on the staff member's smart glasses screen.

[0724] Prompt Sentence Examples

[0725] "Analyze the video data and output what is being said as text."

[0726] "Please translate the generated text into Japanese in real time."

[0727] In this way, users can smoothly communicate with customers who speak a foreign language.

[0728] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0729] Step 1:

[0730] The user wears the smart glasses and the built-in camera captures what the customer is saying.

[0731] Input: Image of customer's mouth

[0732] Output: Recorded video data

[0733] Specific operation: The built-in camera of the smart glasses captures video in real time and temporarily stores the video data within the device.

[0734] Step 2:

[0735] The device transmits the captured video data to a cloud server via the Internet.

[0736] Input: Video data stored on the device

[0737] Output: Video data sent to the cloud server

[0738] Specific operation: The terminal's communication module uploads the video data to a cloud server via the Internet.

[0739] Step 3:

[0740] The server recognizes mouth movements using a generative AI model from the video data it receives.

[0741] Input: Video data sent to the cloud server

[0742] Output: Mouth movement recognition results

[0743] How it works: A cloud server uses a generative AI model (e.g., a machine learning algorithm) to analyze the video data and extract lip movements in text format.

[0744] Step 4:

[0745] The server uses the information it recognizes from mouth movements to convert it into text using a text conversion algorithm.

[0746] Input: Mouth movement recognition results

[0747] Output: The generated text

[0748] Specific operation: The server automatically generates text based on the analysis of mouth movements and saves it as text data.

[0749] Step 5:

[0750] The server translates the generated text into the user's native language using a translation engine.

[0751] Input: Generated text

[0752] Output: The translated text

[0753] Specific operation: The cloud server uses a translation engine (e.g., Google Translate API) to translate the text in real time and generate the translation result.

[0754] Step 6:

[0755] The translated text is displayed on the display of the user's smart glasses.

[0756] Input: Translated text

[0757] Output: Translated text displayed on the smart glasses display

[0758] Specific operation: The translation results are sent from the cloud server to the smart glasses, and the text is displayed on the smart glasses' display in real time.

[0759] This allows users to communicate smoothly with customers who speak a foreign language.

[0760] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0761] The present invention provides a system that uses a user's portable device to understand what is being said at events such as overseas idol concerts in real time and recognize the user's emotions. Specific embodiments of this system are described below.

[0762] Users film an idol speaking at a concert venue using binoculars or a smartphone with a built-in camera. The video is captured on the device and sent to a server via the internet. The server analyzes the received video data and recognizes lip movements. This recognition is performed using a machine learning model. The server identifies what is being said from the lip movements and generates that content as text. This text is expressed in the recognized language. For example, if a Korean idol says "안녕하세요," the server generates the text "안녕하세요."

[0763] The generated text is then translated by the server into the user's native language using a common translation engine. For example, translation is performed from English to Japanese or from Korean to Japanese. This translation step converts the original text "안녕하세요" into the Japanese word "Hello."

[0764] Furthermore, the server is equipped with an emotion engine that analyzes the user's emotions. The emotion engine identifies the user's emotions by analyzing the user's facial expressions and voice data. For example, if the user is smiling, it can be judged as "joyful," and if the user's voice tone is calm, it can be judged as "neutral."

[0765] The translated text and the user's emotional data are sent from the server to the device. The device then displays the translation results and emotional data on the user's screen in real time. It is also possible to adjust the display method based on the emotional data. For example, if the user is excited, the text can be made larger or its color changed to emphasize it more visually.

[0766] Specific examples

[0767] Consider a scenario in which a user is attending a Korean idol concert. In this system, the user begins filming the idol's mouth using a camera built into their binoculars. The device captures the video and sends the data over the Internet to a server. The server analyzes the lip movements from the video and uses a machine learning model to generate the text "안녕하세요." The server then translates this text into Japanese, meaning "hello."

[0768] Furthermore, the server's emotion engine captures the user's facial expression with a camera and determines whether the user is smiling. If the user is smiling, the user's emotion is recorded as "happiness." The server then sends the translated text and emotion data to the device, and displays the text "Hello" and a colorful image reflecting the emotion of happiness on the user's smartphone screen. This allows the user to understand what the idol is saying in real time and respond in a way that matches their own emotions.

[0769] The processing flow will be explained below.

[0770] Step 1:

[0771] The user points the camera built into the binoculars at the idol's mouth and takes a video. The device then activates the video capture function and acquires the video data in real time.

[0772] Step 2:

[0773] The video data captured by the device is efficiently compressed and sent to a server over the Internet using data compression algorithms and high-speed communication protocols.

[0774] Step 3:

[0775] The server analyzes the received video data, locates the mouth position for each frame, and extracts the mouth area.

[0776] Step 4:

[0777] The server uses a machine learning model to analyze the mouth movements based on the extracted mouth area data and converts them into corresponding text (audio). For example, the Korean text "안녕하세요" is generated.

[0778] Step 5:

[0779] The server receives the converted text and translates it into the user's native language. Using a translation engine, the Korean "안녕하세요" is translated into the Japanese "Hello."

[0780] Step 6:

[0781] The device captures the user's facial expressions with a camera and sends the video data to a server.

[0782] Step 7:

[0783] The server analyzes the received facial expression data to identify the user's emotions. The emotion engine analyzes the user's facial and voice data to detect emotions such as "happiness," "sadness," and "surprise."

[0784] Step 8:

[0785] The server sends the translated text and identified emotion data to the device using a low-latency communication protocol.

[0786] Step 9:

[0787] The device adjusts the way the text is displayed based on the translated text and emotion data it receives. For example, if the user's emotion is "joy," the device changes the color and displays the text in a larger, more emphasized size.

[0788] Step 10:

[0789] The device then displays the final translation results on the user's smartphone screen in real time, allowing the user to instantly understand what the idol is saying and respond according to their own emotions.

[0790] Example 2

[0791] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0792] Conventional technologies have made it difficult for users to understand what is being said in real time at overseas concerts and events. Furthermore, they have been unable to display information that reflects the user's emotions, resulting in a poor user experience. This invention aims to combine real-time translation and emotion analysis to enable users to easily understand what is being said at overseas concerts and other events and receive appropriate feedback based on their emotions.

[0793] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a photographing device, a transmitting device, a recognizing device, a converting device, a translating device, a display device, an emotion analyzing device, and an integrating device. This makes it possible to analyze the video photographed by the user in real time, translate what is being said, and display it according to the user's emotion.

[0794] A "photography device" is a device for capturing video or images.

[0795] A "transmitting device" is a device for transmitting acquired video or image data to other devices or servers via a communication network.

[0796] A "recognition device" is a device that recognizes specific patterns or movements from received video or images.

[0797] A "conversion device" is a device for converting recognized data into another format or representation (e.g., text).

[0798] A "translation device" is a device for translating text expressed in one language into another language.

[0799] A "display device" is a device for visually displaying information to a user.

[0800] An "emotion analysis device" is a device that analyzes a user's facial expressions and voice data to identify the user's emotions.

[0801] An "integration device" is a device that integrates multiple pieces of data (for example, translated text and emotion data) and processes them as a single piece of information.

[0802] A "communications network" is a network system for sending and receiving data.

[0803] The present invention provides a system that uses a portable device to understand what is being said at events such as concerts by overseas idols in real time, and also recognizes the emotions of the user. A specific embodiment of this system will be described.

[0804] Users can use binoculars or smartphones with built-in cameras to film the idols speaking at concert venues. It is desirable for the filming device to have high-precision focus adjustment and image stabilization functions. Possible filming devices include smartphones, digital cameras, and video cameras.

[0805] The video is captured on the device and then transmitted to a server via a communications network (e.g., the Internet or a 5G network). The device compresses the data and converts the file format appropriately for efficient transmission. The communications technology used may be Wi-Fi, LTE, or 5G.

[0806] The server analyzes the received video data. Machine learning models (e.g., OpenCV, Dlib, TensorFlow) are used for the analysis. The server recognizes lip movements from the video and converts what is being said into text data using AI algorithms. For example, if a Korean idol says "안녕하세요," the server recognizes this as the text "안녕하세요." This process can be effectively performed using real-time processing with a GPU.

[0807] The generated text is then translated by the server into the user's native language using common translation engines (e.g., Google Translate API, DeepL). To improve translation accuracy, multiple translation candidates are compared in real time and the best one is selected. For example, the Korean text "안녕하세요" is converted to the Japanese "Hello."

[0808] Furthermore, the server is equipped with an emotion analysis device that analyzes the user's emotions. This device analyzes the user's facial expressions and voice data to identify the user's emotions. For example, by using Microsoft Azure's facial recognition API or IBM Watson, the device can analyze the user's facial expressions and tone of voice, and if the user is smiling, it will determine that the user is "happy."

[0809] The translated text and emotion data are sent from the server to the device. The data is encrypted before transmission to ensure security. The integration device integrates the translated text and emotion data and converts it into a format to be displayed on the user's device. The device then displays the received information on the user's screen in real time. For example, the text "Hello" is displayed along with an icon (😊) indicating the user's emotion of "happiness." The color and size of the text can also be dynamically changed depending on the emotion data. If the user is excited, the text can be displayed in red and larger to visually emphasize it.

[0810] As a concrete example, consider a scenario in which a user is attending a Korean idol concert. In this system, the user uses a camera built into binoculars to capture the idol's mouth, and the device captures the video and sends the data to a server over the Internet. The server analyzes the lip movements from the video data and uses a machine learning model to generate the text "안녕하세요," which is then translated into "hello." The server's emotion analyzer analyzes the user's facial expression and determines that the user is "happy" if they are smiling. The server then sends the translated text and emotion data to the device, displays "hello" on the user's screen, and adds a smiling icon to provide real-time understanding and emotional feedback.

[0811] The following are examples of prompt sentences:

[0812] "A user is attending a Korean idol concert. They use binoculars with built-in cameras to film the idol speaking. The device captures the video data and sends it to a server via a communication network. The server analyzes the mouth movements from the video and uses a machine learning model to translate the generated text, '안녕하세요', into Japanese and converts it to 'Hello.' The server then analyzes the user's facial expressions and, if the user is smiling, identifies the emotion of joy. The server then sends the emotion data along with the translated text to the user's device in real time. The user's device then displays the information on its screen."

[0813] The above is a specific embodiment for carrying out the invention of this system.

[0814] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0815] Step 1: User captures video on device

[0816] At the concert venue, users use a mobile device (e.g., binoculars or a smartphone with a built-in camera) to capture images of the idol's mouth and facial expressions. The user captures the image using the device's camera with high-precision focus adjustment and image stabilization functions.

[0817] Input: A mobile device held by the user

[0818] Output: Highly accurate video data of idols

[0819] Step 2: The device sends the video data to the server

[0820] The device compresses the captured video data and transmits it to a server via a communication network (e.g., the Internet or a 5G network). The file format is efficiently converted to reduce the amount of data.

[0821] Input: Captured video data

[0822] Output: Compressed video data sent to the server

[0823] What it does: The device uses a compression algorithm to convert the video data into MP4 format, then uses the device's communications module to send the data over the internet to a server.

[0824] Step 3: The server analyzes the video data

[0825] The server analyzes the received video data and recognizes the idol's lip movements using machine learning models (e.g., OpenCV, Dlib, TensorFlow), then uses AI algorithms to convert what is being said into text.

[0826] Input: Compressed video data

[0827] Output: Text data generated from lip movements

[0828] How it works: The server uses a GPU to analyze the mouth movements of each video frame and inputs that data into an AI model, which then converts the recognized mouth movements into text.

[0829] Step 4: The server translates the text

[0830] The server translates the generated text data into the user's native language using a common translation engine (e.g., Google Translate API, DeepL) and selects the best translation from multiple candidates.

[0831] Input: Recognized text data

[0832] Output: Translated text data

[0833] Specific operation: The server calls the translation API to translate the text data into other languages ​​and selects the most appropriate translation result.

[0834] Step 5: The server analyzes the sentiment

[0835] The server uses an emotion analysis engine (e.g., Microsoft Azure's Emotion API, IBM Watson) to analyze the user's facial expressions and voice data. It analyzes the user's facial expressions and tone of voice to identify their emotions.

[0836] Input: User's facial expressions and voice data

[0837] Output: Identified emotion data

[0838] Specific operation: The server uses an emotion analysis engine to analyze the user's facial features and voice tone to identify the type of emotion.

[0839] Step 6: The server sends the results to the device

[0840] The server transmits the translated text and emotion data to the terminal. The data is encrypted to ensure security. The server then uses an integration device to integrate the translated text and emotion data and convert them into data to be transmitted.

[0841] Input: Translated text data and emotion data

[0842] Output: Encrypted result data

[0843] Specific operation: The server uses a data encryption algorithm to encrypt the translation text and emotion data and transmits them to the terminal via a communication protocol.

[0844] Step 7: The terminal displays the results

[0845] Based on the received result data, the device displays the translated text and the emotion reflected on the user's screen in real time, dynamically adjusting the display method according to the emotion data.

[0846] Input: Brain-coded result data (translated text, emotion data)

[0847] Output: Translated text and emotion displayed on the user screen

[0848] Specific operation: The terminal decodes the result data and displays it in the user interface in an appropriate format. For example, if the user is excited, the text will be displayed in red and large.

[0849] The above is the specific processing flow of this system.

[0850] (Application example 2)

[0851] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0852] Conventional video analytics systems have difficulty understanding what is being said during an event, limiting their use, especially in situations where real-time translation into multiple languages ​​is required. Furthermore, there are no systems that can analyze user emotions and adjust the way information is displayed based on those emotions. As a result, there are a lack of ways for users to enrich their event experience.

[0853] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0854] In this invention, the server includes a photographing means for photographing video, a transmitting means for transmitting the photographed video via the Internet, a recognition means for recognizing lip movements from the received video, a converting means for converting the recognized lip movements into text, a translating means for translating the converted text into another language, a displaying means for displaying the translated text, an emotion recognition means for recognizing the emotional state of a user, and an adjusting means for adjusting the display method of the translated text in accordance with the emotional state of the user. This enables a user to understand the content of an overseas event in real time and dynamically adjust the display method of information in accordance with their own emotions.

[0855] "Capturing means" refers to devices or mechanisms for capturing images. Specifically, this applies to cameras and video cameras.

[0856] The "transmission means" is a function or device for transmitting the captured video data to a server via the Internet.

[0857] The "recognition means" is a mechanism for analyzing and identifying specific information, such as mouth movements, from received video. Generally, a machine learning model is used.

[0858] The "conversion means" is a function or device for converting information (for example, mouth movements) recognized by the recognition means into another format such as character data.

[0859] A "translation means" is a function or device for converting the converted text into another language.

[0860] "Display means" is a function or device for visually displaying the translated text to the user.

[0861] The "emotion recognition means" is a mechanism for analyzing data such as the user's facial expressions and voice, and identifying the user's emotional state.

[0862] The "adjustment means" is a function or device for dynamically changing the way the translated text is displayed depending on the emotional state of the user as identified by the emotion recognition means.

[0863] This invention is a system that uses a portable device to understand the content of speech at a specific event in real time and adjusts the way information is displayed based on the user's emotional state. This system is realized using the following hardware and software.

[0864] Hardware and software used

[0865] Hardware: Smartphone, smart glasses, head-mounted display (HMD), camera, internet connection

[0866] Software: Machine learning models (e.g., TensorFlow, PyTorch), translation engines (e.g., Google Translate API, Microsoft Translator API), emotion recognition engines (e.g., Google Cloud Vision API)

[0867] System action

[0868] First, a user captures the event video in real time using a smartphone or compatible device (smart glasses, HMD). This captured video data is sent to a server via the Internet. The server receives the video data and proceeds to the next step.

[0869] The server uses a machine learning model to recognize mouth movements from the received video data. Specifically, tools such as TensorFlow and PyTorch analyze mouth movements, and the recognized mouth movements are converted into text data. Since the converted text data is often difficult to understand as is, it is then translated into the user's native language using a translation engine. The Google Translate API and Microsoft Translator API are used for translation.

[0870] The server then uses an emotion recognition engine to analyze the user's emotional state. Facial and voice data captured by the user's device is sent to the server, where emotion analysis is performed using software such as Google Cloud Vision API. For example, if the user is smiling, it is determined to be "happy."

[0871] This data (translated text and emotional state) is then sent back to the user's device and presented to them through a display. Depending on the user's emotional state, the way the text is displayed is adjusted. For example, if the user is excited, the text will be displayed larger and in a more vibrant color to emphasize the visual impact.

[0872] Specific examples

[0873] For example, if a user is attending a Korean idol concert, their device will capture a video of the idol's mouth. The video data is sent to a server, where a remark such as "안녕하세요 (Hello)" is converted into text and then translated into Japanese. At the same time, the user's smile is captured and determined to be "joy" by an emotion recognition engine. Based on this, a colorful image reflecting the emotion of joy is displayed on the user's device along with the text "Hello."

[0874] Example prompt

[0875] Prompt: How can I translate Korean idols' comments in real time and display them based on the user's emotions?

[0876] This allows users to overcome language barriers and understand the event content in real time, resulting in a richer experience.

[0877] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0878] Step 1:

[0879] A user captures video of an event in real time using a smartphone or a compatible device (smart glasses, HMD). The input is video data from a camera, and the output is this video data. The user captures by taking a picture of a specific person or scene using the device.

[0880] Step 2:

[0881] The captured video data is sent to a server via the Internet. The input is the captured video data, and the output is the video data sent to the server via the Internet. The device converts the captured data into a certain format and sends it to the server via the Internet connection.

[0882] Step 3:

[0883] The server uses a machine learning model to analyze the received video data and recognize mouth movements. The input is the received video data, and the output is text data based on the recognized mouth movements. The server uses a machine learning model (TensorFlow or PyTorch) to analyze the speech content from the mouth movements and convert it into text.

[0884] Step 4:

[0885] The converted text data is translated into the user's native language using a translation engine. The input is the original text data converted from the recognized mouth movements, and the output is the translated text data. The server uses the Google Translate API or Microsoft Translator API to translate the original text into the user's native language.

[0886] Step 5:

[0887] An emotion recognition engine is used to analyze the user's emotional state. The input is the user's facial expression and voice data, and the output is the user's emotional state. The device captures the user's facial expression and voice data and sends it to a server, which then performs emotion analysis using Google Cloud Vision API or similar.

[0888] Step 6:

[0889] The information display method is adjusted based on the translated text data and the emotional state. The input is the translated text data and the emotional state, and the output is the final display data in the adjusted display method. The server adjusts, for example, the size and color of the text according to the emotional state and sends it to the user's device.

[0890] Step 7:

[0891] The final display data is displayed on the user's device screen. The input is the adjusted display data from the server, and the output is the text information displayed on the user's device. The terminal displays the information to the user in an appropriate format based on the data received.

[0892] This processing flow allows users to understand the content of events in real time and experience dynamic displays that respond to their emotions.

[0893] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0894] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0895] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0896] [Fourth embodiment]

[0897] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0898] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0899] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0900] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0901] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0902] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0903] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0904] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0905] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0906] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0907] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0908] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0909] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0910] The present invention is a system that enables a user to use a portable device to understand in real time what is being said at a concert of an overseas idol, etc. Specific embodiments of this system will be described below.

[0911] Users can use binoculars or smartphones with built-in cameras to film the idols speaking at concert venues. The footage is captured on the device and the video data is sent to a server via the Internet.

[0912] The server analyzes the received video data and recognizes lip movements. This recognition is performed using a machine learning model. The server identifies what is being said from the lip movements and generates that content as text. This text is expressed in the recognized language. For example, if a Korean idol says "안녕하세요," the server generates the text "안녕하세요."

[0913] The generated text is then translated by the server into the user's native language using a common translation engine. For example, translation is performed from English to Japanese or from Korean to Japanese. This translation step converts the original text "안녕하세요" into the Japanese word "Hello."

[0914] The translated text is sent from the server to the device, which can then display the received translation results on the user's screen in real time, allowing the user to instantly understand what the idol is saying and respond appropriately.

[0915] Specific examples

[0916] Consider a scenario in which a user is attending a Korean idol concert. In this system, the user begins filming the idol's mouth using a camera built into their binoculars. The device captures the video and sends the data to a server via the Internet. The server analyzes the lip movements from the video and uses a machine learning model to generate the text "안녕하세요." The server then translates this text into Japanese, meaning "hello." Finally, the translated text is sent to the device and displayed in real time on the user's smartphone screen.

[0917] The processing flow will be explained below.

[0918] Step 1:

[0919] The user points the camera built into the binoculars at the idol's mouth and takes a video. The device then starts up and the capture function is turned on.

[0920] Step 2:

[0921] The device acquires video data from the camera in real time. This video data is captured frame by frame (for example, 30 fps).

[0922] Step 3:

[0923] The video data captured by the device is efficiently compressed and sent to a server over the Internet using a low-latency communication protocol.

[0924] Step 4:

[0925] To analyze the video data received by the server, the position of the mouth is identified for each frame and the mouth area is extracted.

[0926] Step 5:

[0927] The server uses a machine learning model to analyze the mouth movements based on the extracted mouth area data and converts them into corresponding text (audio). In this process, the Korean character string "안녕하세요" (hello) is generated.

[0928] Step 6:

[0929] The server receives the converted text and translates it into the user's native language. Through the translation engine, the Korean "안녕하세요" is converted into the Japanese "Hello."

[0930] Step 7:

[0931] The server sends the translation results to the device in real time using a fast and reliable communication protocol.

[0932] Step 8:

[0933] The device receives the translation result ("Hello" in Japanese) and displays it on the user's smartphone screen in real time, allowing the user to instantly understand what the idol is saying.

[0934] This allows users to understand what the idol is saying during the concert in real time and respond immediately.

[0935] Example 1

[0936] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0937] In recent years, the demand for global entertainment has increased, especially with the number of concerts held in various countries by overseas music artists and idols. However, due to language barriers, users often find it difficult to understand what is being said at overseas concerts, limiting real-time communication and enjoyment. For this reason, there is a need for a system that can understand multilingual conversations in real time.

[0938] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0939] In this invention, the server includes a camera for shooting video, a transmitter for transmitting the video via a network, and a recognition unit for recognizing lip movements from the received video, thereby enabling users to overcome language barriers at overseas concerts and understand what is being said in real time.

[0940] "Capturing means" refers to a device or function for capturing video.

[0941] The "transmission means" is a device or function for transmitting captured video data to another device or server via a network.

[0942] "Recognition means" refers to a device or function for analyzing and recognizing specific information (in this case, mouth movements) from received video data.

[0943] The "conversion means" is a device or function for converting the recognized information into another format such as text data.

[0944] The "translation means" is a device or function for translating the converted text data into another language.

[0945] "Display means" refers to a device or function for visually displaying translated text data on a user's device.

[0946] A "machine learning algorithm" is a computational model that learns certain patterns or rules based on a dataset and then uses that knowledge to analyze new data.

[0947] An "automated translation algorithm" is a computational model for converting text from one language to another.

[0948] MODE FOR CARRYING OUT THE INVENTION

[0949] The present invention is a system that enables a user to use a portable device to understand in real time what is being said at a concert of an overseas idol, etc. A specific embodiment of this system will be described below.

[0950] Users can use binoculars or smartphones with built-in cameras to film the idols speaking at concert venues. The footage is captured on the device and the video data is sent to a server via a network.

[0951] The server analyzes the received video data and recognizes lip movements. This recognition is performed using a machine learning algorithm. Specifically, it can use the TensorFlow model, a common machine learning framework, or a cloud-based machine learning API. The server identifies what is being said from the lip movements and generates that content as text. For example, if a Korean idol says "안녕하세요," the server generates the text "안녕하세요."

[0952] The generated text is then translated by the server into the user's native language using an automatic translation algorithm. Specifically, common translation engines such as Google Translate API or DeepL Translate API can be used. This translation step converts the original text "안녕하세요" into the Japanese "Hello."

[0953] The translated text is sent from the server to the device, which can then display the received translation results on the user's device in real time, allowing the user to instantly understand what the idol is saying and respond appropriately.

[0954] Specific examples

[0955] For example, consider a scenario in which a user is attending a Korean idol concert. In this system, the user begins filming the idol's mouth using a camera built into their binoculars. The device captures the video and sends the data over the network to a server. The server analyzes the lip movements from the video and generates the text "안녕하세요" using a TensorFlow model. The server then translates this text into Japanese, meaning "hello," using the Google Translate API. Finally, the translated text is sent to the device and displayed in real time on the user's smartphone screen.

[0956] Prompt Sentence Examples

[0957] "Describe a system that allows you to understand what Korean idols are saying at their concerts in real time. Users take video using the built-in camera on their smartphones or binoculars and send the data to a server. The server uses a machine learning model to analyze their mouth movements and generate text from what they're saying. It then uses a translation engine to translate the text into the user's native language, and finally displays it on the user's device."

[0958] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0959] Step 1:

[0960] At a concert venue, users use a camera built into their smartphone or binoculars to take a picture of the idol's mouth.

[0961] Specifically, users simply open their device's camera app and point the camera at the idol's face, and the footage is captured in 1080p high definition.

[0962] Step 2:

[0963] The terminal transmits the captured video data to a server via the Internet in real time.

[0964] Specifically, the captured video data is compressed and sent via a network protocol (e.g. HTTP / HTTPS), the data is digitally encrypted, and the video data is received as input and sent to a server as output.

[0965] Step 3:

[0966] The server analyzes the received video data and runs machine learning algorithms to recognize mouth movements.

[0967] Specifically, the server stores video data in Google Cloud Storage and analyzes mouth movements using a TensorFlow model, taking video data as input and generating recognized mouth movement data as output.

[0968] Step 4:

[0969] The server analyzes the recognized mouth movement data and generates text of what is being said.

[0970] Specifically, the server uses a machine learning algorithm to infer what is being said from mouth movements and generate text data, such as "안녕하세요." It receives mouth movement data as input and generates text data as output.

[0971] Step 5:

[0972] The server translates the generated text data into the user's native language using an automatic translation algorithm.

[0973] Specifically, the server calls the Google Translate API to translate the input text "안녕하세요" into Japanese "Hello." It receives text data as input and generates translated text data as output.

[0974] Step 6:

[0975] The server transmits the translated text data to the user's terminal.

[0976] Specifically, the translation data is encrypted using the HTTPS protocol and sent to the device. The translated text data is received as input and sent to the device as output.

[0977] Step 7:

[0978] The terminal displays the received translation data on the user's device in real time.

[0979] Specifically, the device displays the translated data as a pop-up window or scrolling subtitles so that the user can visually confirm it. The device receives the translated data as input and displays it on the user's screen as output.

[0980] (Application example 1)

[0981] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0982] Conventional translation systems are designed to support real-time communication between people who speak different languages, but they have had challenges in analyzing and responding immediately to conversations that include visual elements, such as eye contact and gestures. In certain situations, such as brick-and-mortar stores in tourist areas, where multinational customers frequently visit, employees are required to respond smoothly in different languages, but this also poses challenges.

[0983] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0984] In this invention, the server includes a camera for capturing video, a transmitter for transmitting the captured video via the Internet, and a recognition unit for recognizing mouth movements from the received video, thereby enabling accurate understanding of foreign language conversations in real time and quick and appropriate responses to multinational customers.

[0985] The "capture means" is a device for capturing an image of an object, and includes, for example, a camera device built into smart glasses.

[0986] The "transmission means" is a communication module for transmitting the captured video data to a server via the Internet.

[0987] "Recognition means" includes a set of algorithms and machine learning models used to identify a subject's mouth movements from received video data.

[0988] The "conversion means" includes a program or algorithm for converting the recognized mouth movements into a text format.

[0989] "Translation means" includes a translation engine or corresponding software for converting the generated text into another language.

[0990] "Display means" includes a display device or projection system for visually presenting the translated text to a user.

[0991] A "head-mounted display" is a wearable device that can display images and information in real time when worn by the user.

[0992] "Generative AI model" refers to an artificial intelligence algorithm used to extract specific information from video data, specifically a model for analyzing mouth movements.

[0993] A "prompt" is an input sentence used to instruct a generative AI model or other algorithm to effectively perform the parsing or translation process.

[0994] This invention is a system that uses smart glasses worn by store staff to support real-time communication with customers who speak a foreign language. This system is implemented using the following hardware and software.

[0995] Hardware

[0996] 1. Smart Glasses

[0997] Photographic method: A built-in camera is used to capture a photo of the customer's mouth in real time.

[0998] Display means: A display is used to display the translated text to the user.

[0999] 2. Cloud Server

[1000] Transmission means: Receives video data sent from the smart glasses via the Internet.

[1001] software

[1002] 1. Generative AI Models

[1003] Recognition method: Runs on a cloud server and analyzes mouth movements from received video data.

[1004] 2. Conversion Method

[1005] Text generation algorithm: Recognizes mouth movements and converts the analysis results into text format.

[1006] 3. Translation Methods

[1007] Translation engine: Used to translate the generated text into the user's native language (e.g. Google Translate API).

[1008] Data processing and calculation procedures

[1009] 1. Video capture: The user (store staff) wears smart glasses and uses the built-in camera to capture what the customer is saying.

[1010] 2. Data transmission: The smart glasses transmit the captured video data to a cloud server via the Internet.

[1011] 3. Data analysis: The cloud server analyzes the received video data and uses a generative AI model to recognize the customer's mouth movements.

[1012] 4. Text Conversion: After the mouth movements are recognized, the content is converted into text format.

[1013] 5. Translation: The generated text is translated into the user's native language using a translation engine.

[1014] 6. Display: The translated text will be displayed on the smart glasses display in real time.

[1015] Specific examples

[1016] For example, a store staff member wearing smart glasses films a Korean tourist greeting "안녕하세요." The smart glasses send this video data to a cloud server, which uses a generative AI model to analyze the lip movements of "안녕하세요" and converts it into text. The translation engine then translates this text into Japanese, meaning "hello," and the translation is displayed on the staff member's smart glasses screen.

[1017] Prompt Sentence Examples

[1018] "Analyze the video data and output what is being said as text."

[1019] "Please translate the generated text into Japanese in real time."

[1020] In this way, users can smoothly communicate with customers who speak a foreign language.

[1021] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1022] Step 1:

[1023] The user wears the smart glasses and the built-in camera captures what the customer is saying.

[1024] Input: Image of customer's mouth

[1025] Output: Recorded video data

[1026] Specific operation: The built-in camera of the smart glasses captures video in real time and temporarily stores the video data within the device.

[1027] Step 2:

[1028] The device transmits the captured video data to a cloud server via the Internet.

[1029] Input: Video data stored on the device

[1030] Output: Video data sent to the cloud server

[1031] Specific operation: The terminal's communication module uploads the video data to a cloud server via the Internet.

[1032] Step 3:

[1033] The server recognizes mouth movements using a generative AI model from the video data it receives.

[1034] Input: Video data sent to the cloud server

[1035] Output: Mouth movement recognition results

[1036] How it works: A cloud server uses a generative AI model (e.g., a machine learning algorithm) to analyze the video data and extract lip movements in text format.

[1037] Step 4:

[1038] The server uses the information it recognizes from mouth movements to convert it into text using a text conversion algorithm.

[1039] Input: Mouth movement recognition results

[1040] Output: The generated text

[1041] Specific operation: The server automatically generates text based on the analysis of mouth movements and saves it as text data.

[1042] Step 5:

[1043] The server translates the generated text into the user's native language using a translation engine.

[1044] Input: Generated text

[1045] Output: The translated text

[1046] Specific operation: The cloud server uses a translation engine (e.g., Google Translate API) to translate the text in real time and generate the translation result.

[1047] Step 6:

[1048] The translated text is displayed on the display of the user's smart glasses.

[1049] Input: Translated text

[1050] Output: Translated text displayed on the smart glasses display

[1051] Specific operation: The translation results are sent from the cloud server to the smart glasses, and the text is displayed on the smart glasses' display in real time.

[1052] This allows users to communicate smoothly with customers who speak a foreign language.

[1053] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1054] The present invention provides a system that uses a user's portable device to understand what is being said at events such as overseas idol concerts in real time and recognize the user's emotions. Specific embodiments of this system are described below.

[1055] Users film an idol speaking at a concert venue using binoculars or a smartphone with a built-in camera. The video is captured on the device and sent to a server via the internet. The server analyzes the received video data and recognizes lip movements. This recognition is performed using a machine learning model. The server identifies what is being said from the lip movements and generates that content as text. This text is expressed in the recognized language. For example, if a Korean idol says "안녕하세요," the server generates the text "안녕하세요."

[1056] The generated text is then translated by the server into the user's native language using a common translation engine. For example, translation is performed from English to Japanese or from Korean to Japanese. This translation step converts the original text "안녕하세요" into the Japanese word "Hello."

[1057] Furthermore, the server is equipped with an emotion engine that analyzes the user's emotions. The emotion engine identifies the user's emotions by analyzing the user's facial expressions and voice data. For example, if the user is smiling, it can be judged as "joyful," and if the user's voice tone is calm, it can be judged as "neutral."

[1058] The translated text and the user's emotional data are sent from the server to the device. The device then displays the translation results and emotional data on the user's screen in real time. It is also possible to adjust the display method based on the emotional data. For example, if the user is excited, the text can be made larger or its color changed to emphasize it more visually.

[1059] Specific examples

[1060] Consider a scenario in which a user is attending a Korean idol concert. In this system, the user begins filming the idol's mouth using a camera built into their binoculars. The device captures the video and sends the data over the Internet to a server. The server analyzes the lip movements from the video and uses a machine learning model to generate the text "안녕하세요." The server then translates this text into Japanese, meaning "hello."

[1061] Furthermore, the server's emotion engine captures the user's facial expression with a camera and determines whether the user is smiling. If the user is smiling, the user's emotion is recorded as "happiness." The server then sends the translated text and emotion data to the device, and displays the text "Hello" and a colorful image reflecting the emotion of happiness on the user's smartphone screen. This allows the user to understand what the idol is saying in real time and respond in a way that matches their own emotions.

[1062] The processing flow will be explained below.

[1063] Step 1:

[1064] The user points the camera built into the binoculars at the idol's mouth and takes a video. The device then activates the video capture function and acquires the video data in real time.

[1065] Step 2:

[1066] The video data captured by the device is efficiently compressed and sent to a server over the Internet using data compression algorithms and high-speed communication protocols.

[1067] Step 3:

[1068] The server analyzes the received video data, locates the mouth position for each frame, and extracts the mouth area.

[1069] Step 4:

[1070] The server uses a machine learning model to analyze the mouth movements based on the extracted mouth area data and converts them into corresponding text (audio). For example, the Korean text "안녕하세요" is generated.

[1071] Step 5:

[1072] The server receives the converted text and translates it into the user's native language. Using a translation engine, the Korean "안녕하세요" is translated into the Japanese "Hello."

[1073] Step 6:

[1074] The device captures the user's facial expressions with a camera and sends the video data to a server.

[1075] Step 7:

[1076] The server analyzes the received facial expression data to identify the user's emotions. The emotion engine analyzes the user's facial and voice data to detect emotions such as "happiness," "sadness," and "surprise."

[1077] Step 8:

[1078] The server sends the translated text and identified emotion data to the device using a low-latency communication protocol.

[1079] Step 9:

[1080] The device adjusts the way the text is displayed based on the translated text and emotion data it receives. For example, if the user's emotion is "joy," the device changes the color and displays the text in a larger, more emphasized size.

[1081] Step 10:

[1082] The device then displays the final translation results on the user's smartphone screen in real time, allowing the user to instantly understand what the idol is saying and respond according to their own emotions.

[1083] Example 2

[1084] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1085] Conventional technologies have made it difficult for users to understand what is being said in real time at overseas concerts and events. Furthermore, they have been unable to display information that reflects the user's emotions, resulting in a poor user experience. This invention aims to combine real-time translation and emotion analysis to enable users to easily understand what is being said at overseas concerts and other events and receive appropriate feedback based on their emotions.

[1086] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a photographing device, a transmitting device, a recognizing device, a converting device, a translating device, a display device, an emotion analyzing device, and an integrating device. This makes it possible to analyze the video photographed by the user in real time, translate what is being said, and display it according to the user's emotion.

[1087] A "photography device" is a device for capturing video or images.

[1088] A "transmitting device" is a device for transmitting acquired video or image data to other devices or servers via a communication network.

[1089] A "recognition device" is a device that recognizes specific patterns or movements from received video or images.

[1090] A "conversion device" is a device for converting recognized data into another format or representation (e.g., text).

[1091] A "translation device" is a device for translating text expressed in one language into another language.

[1092] A "display device" is a device for visually displaying information to a user.

[1093] An "emotion analysis device" is a device that analyzes a user's facial expressions and voice data to identify the user's emotions.

[1094] An "integration device" is a device that integrates multiple pieces of data (for example, translated text and emotion data) and processes them as a single piece of information.

[1095] A "communications network" is a network system for sending and receiving data.

[1096] The present invention provides a system that uses a portable device to understand what is being said at events such as concerts by overseas idols in real time, and also recognizes the emotions of the user. A specific embodiment of this system will be described.

[1097] Users can use binoculars or smartphones with built-in cameras to film the idols speaking at concert venues. It is desirable for the filming device to have high-precision focus adjustment and image stabilization functions. Possible filming devices include smartphones, digital cameras, and video cameras.

[1098] The video is captured on the device and then transmitted to a server via a communications network (e.g., the Internet or a 5G network). The device compresses the data and converts the file format appropriately for efficient transmission. The communications technology used may be Wi-Fi, LTE, or 5G.

[1099] The server analyzes the received video data. Machine learning models (e.g., OpenCV, Dlib, TensorFlow) are used for the analysis. The server recognizes lip movements from the video and converts what is being said into text data using AI algorithms. For example, if a Korean idol says "안녕하세요," the server recognizes this as the text "안녕하세요." This process can be effectively performed using real-time processing with a GPU.

[1100] The generated text is then translated by the server into the user's native language using common translation engines (e.g., Google Translate API, DeepL). To improve translation accuracy, multiple translation candidates are compared in real time and the best one is selected. For example, the Korean text "안녕하세요" is converted to the Japanese "Hello."

[1101] Furthermore, the server is equipped with an emotion analysis device that analyzes the user's emotions. This device analyzes the user's facial expressions and voice data to identify the user's emotions. For example, by using Microsoft Azure's facial recognition API or IBM Watson, the device can analyze the user's facial expressions and tone of voice, and if the user is smiling, it will determine that the user is "happy."

[1102] The translated text and emotion data are sent from the server to the device. The data is encrypted before transmission to ensure security. The integration device integrates the translated text and emotion data and converts it into a format to be displayed on the user's device. The device then displays the received information on the user's screen in real time. For example, the text "Hello" is displayed along with an icon (😊) indicating the user's emotion of "happiness." The color and size of the text can also be dynamically changed depending on the emotion data. If the user is excited, the text can be displayed in red and larger to visually emphasize it.

[1103] As a concrete example, consider a scenario in which a user is attending a Korean idol concert. In this system, the user uses a camera built into binoculars to capture the idol's mouth, and the device captures the video and sends the data to a server over the Internet. The server analyzes the lip movements from the video data and uses a machine learning model to generate the text "안녕하세요," which is then translated into "hello." The server's emotion analyzer analyzes the user's facial expression and determines that the user is "happy" if they are smiling. The server then sends the translated text and emotion data to the device, displays "hello" on the user's screen, and adds a smiling icon to provide real-time understanding and emotional feedback.

[1104] The following are examples of prompt sentences:

[1105] "A user is attending a Korean idol concert. They use binoculars with built-in cameras to film the idol speaking. The device captures the video data and sends it to a server via a communication network. The server analyzes the mouth movements from the video and uses a machine learning model to translate the generated text, '안녕하세요', into Japanese and converts it to 'Hello.' The server then analyzes the user's facial expressions and, if the user is smiling, identifies the emotion of joy. The server then sends the emotion data along with the translated text to the user's device in real time. The user's device then displays the information on its screen."

[1106] The above is a specific embodiment for carrying out the invention of this system.

[1107] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1108] Step 1: User captures video on device

[1109] At the concert venue, users use a mobile device (e.g., binoculars or a smartphone with a built-in camera) to capture images of the idol's mouth and facial expressions. The user captures the image using the device's camera with high-precision focus adjustment and image stabilization functions.

[1110] Input: A mobile device held by the user

[1111] Output: Highly accurate video data of idols

[1112] Step 2: The device sends the video data to the server

[1113] The device compresses the captured video data and transmits it to a server via a communication network (e.g., the Internet or a 5G network). The file format is efficiently converted to reduce the amount of data.

[1114] Input: Captured video data

[1115] Output: Compressed video data sent to the server

[1116] What it does: The device uses a compression algorithm to convert the video data into MP4 format, then uses the device's communications module to send the data over the internet to a server.

[1117] Step 3: The server analyzes the video data

[1118] The server analyzes the received video data and recognizes the idol's lip movements using machine learning models (e.g., OpenCV, Dlib, TensorFlow), then uses AI algorithms to convert what is being said into text.

[1119] Input: Compressed video data

[1120] Output: Text data generated from lip movements

[1121] How it works: The server uses a GPU to analyze the mouth movements of each video frame and inputs that data into an AI model, which then converts the recognized mouth movements into text.

[1122] Step 4: The server translates the text

[1123] The server translates the generated text data into the user's native language using a common translation engine (e.g., Google Translate API, DeepL) and selects the best translation from multiple candidates.

[1124] Input: Recognized text data

[1125] Output: Translated text data

[1126] Specific operation: The server calls the translation API to translate the text data into other languages ​​and selects the most appropriate translation result.

[1127] Step 5: The server analyzes the sentiment

[1128] The server uses an emotion analysis engine (e.g., Microsoft Azure's Emotion API, IBM Watson) to analyze the user's facial expressions and voice data. It analyzes the user's facial expressions and tone of voice to identify their emotions.

[1129] Input: User's facial expressions and voice data

[1130] Output: Identified emotion data

[1131] Specific operation: The server uses an emotion analysis engine to analyze the user's facial features and voice tone to identify the type of emotion.

[1132] Step 6: The server sends the results to the device

[1133] The server transmits the translated text and emotion data to the terminal. The data is encrypted to ensure security. The server then uses an integration device to integrate the translated text and emotion data and convert them into data to be transmitted.

[1134] Input: Translated text data and emotion data

[1135] Output: Encrypted result data

[1136] Specific operation: The server uses a data encryption algorithm to encrypt the translation text and emotion data and transmits them to the terminal via a communication protocol.

[1137] Step 7: The terminal displays the results

[1138] Based on the received result data, the device displays the translated text and the emotion reflected on the user's screen in real time, dynamically adjusting the display method according to the emotion data.

[1139] Input: Brain-coded result data (translated text, emotion data)

[1140] Output: Translated text and emotion displayed on the user screen

[1141] Specific operation: The terminal decodes the result data and displays it in the user interface in an appropriate format. For example, if the user is excited, the text will be displayed in red and large.

[1142] The above is the specific processing flow of this system.

[1143] (Application example 2)

[1144] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1145] Conventional video analytics systems have difficulty understanding what is being said during an event, limiting their use, especially in situations where real-time translation into multiple languages ​​is required. Furthermore, there are no systems that can analyze user emotions and adjust the way information is displayed based on those emotions. As a result, there are a lack of ways for users to enrich their event experience.

[1146] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1147] In this invention, the server includes a photographing means for photographing video, a transmitting means for transmitting the photographed video via the Internet, a recognition means for recognizing lip movements from the received video, a converting means for converting the recognized lip movements into text, a translating means for translating the converted text into another language, a displaying means for displaying the translated text, an emotion recognition means for recognizing the emotional state of a user, and an adjusting means for adjusting the display method of the translated text in accordance with the emotional state of the user. This enables a user to understand the content of an overseas event in real time and dynamically adjust the display method of information in accordance with their own emotions.

[1148] "Capturing means" refers to devices or mechanisms for capturing images. Specifically, this applies to cameras and video cameras.

[1149] The "transmission means" is a function or device for transmitting the captured video data to a server via the Internet.

[1150] The "recognition means" is a mechanism for analyzing and identifying specific information, such as mouth movements, from received video. Generally, a machine learning model is used.

[1151] The "conversion means" is a function or device for converting information (for example, mouth movements) recognized by the recognition means into another format such as character data.

[1152] A "translation means" is a function or device for converting the converted text into another language.

[1153] "Display means" is a function or device for visually displaying the translated text to the user.

[1154] The "emotion recognition means" is a mechanism for analyzing data such as the user's facial expressions and voice, and identifying the user's emotional state.

[1155] The "adjustment means" is a function or device for dynamically changing the way the translated text is displayed depending on the emotional state of the user as identified by the emotion recognition means.

[1156] This invention is a system that uses a portable device to understand the content of speech at a specific event in real time and adjusts the way information is displayed based on the user's emotional state. This system is realized using the following hardware and software.

[1157] Hardware and software used

[1158] Hardware: Smartphone, smart glasses, head-mounted display (HMD), camera, internet connection

[1159] Software: Machine learning models (e.g., TensorFlow, PyTorch), translation engines (e.g., Google Translate API, Microsoft Translator API), emotion recognition engines (e.g., Google Cloud Vision API)

[1160] System action

[1161] First, a user captures the event video in real time using a smartphone or compatible device (smart glasses, HMD). This captured video data is sent to a server via the Internet. The server receives the video data and proceeds to the next step.

[1162] The server uses a machine learning model to recognize mouth movements from the received video data. Specifically, tools such as TensorFlow and PyTorch analyze mouth movements, and the recognized mouth movements are converted into text data. Since the converted text data is often difficult to understand as is, it is then translated into the user's native language using a translation engine. The Google Translate API and Microsoft Translator API are used for translation.

[1163] The server then uses an emotion recognition engine to analyze the user's emotional state. Facial and voice data captured by the user's device is sent to the server, where emotion analysis is performed using software such as Google Cloud Vision API. For example, if the user is smiling, it is determined to be "happy."

[1164] This data (translated text and emotional state) is then sent back to the user's device and presented to them through a display. Depending on the user's emotional state, the way the text is displayed is adjusted. For example, if the user is excited, the text will be displayed larger and in a more vibrant color to emphasize the visual impact.

[1165] Specific examples

[1166] For example, if a user is attending a Korean idol concert, their device will capture a video of the idol's mouth. The video data is sent to a server, where a remark such as "안녕하세요 (Hello)" is converted into text and then translated into Japanese. At the same time, the user's smile is captured and determined to be "joy" by an emotion recognition engine. Based on this, a colorful image reflecting the emotion of joy is displayed on the user's device along with the text "Hello."

[1167] Example prompt

[1168] Prompt: How can I translate Korean idols' comments in real time and display them based on the user's emotions?

[1169] This allows users to overcome language barriers and understand the event content in real time, resulting in a richer experience.

[1170] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1171] Step 1:

[1172] A user captures video of an event in real time using a smartphone or a compatible device (smart glasses, HMD). The input is video data from a camera, and the output is this video data. The user captures by taking a picture of a specific person or scene using the device.

[1173] Step 2:

[1174] The captured video data is sent to a server via the Internet. The input is the captured video data, and the output is the video data sent to the server via the Internet. The device converts the captured data into a certain format and sends it to the server via the Internet connection.

[1175] Step 3:

[1176] The server uses a machine learning model to analyze the received video data and recognize mouth movements. The input is the received video data, and the output is text data based on the recognized mouth movements. The server uses a machine learning model (TensorFlow or PyTorch) to analyze the speech content from the mouth movements and convert it into text.

[1177] Step 4:

[1178] The converted text data is translated into the user's native language using a translation engine. The input is the original text data converted from the recognized mouth movements, and the output is the translated text data. The server uses the Google Translate API or Microsoft Translator API to translate the original text into the user's native language.

[1179] Step 5:

[1180] An emotion recognition engine is used to analyze the user's emotional state. The input is the user's facial expression and voice data, and the output is the user's emotional state. The device captures the user's facial expression and voice data and sends it to a server, which then performs emotion analysis using Google Cloud Vision API or similar.

[1181] Step 6:

[1182] The information display method is adjusted based on the translated text data and the emotional state. The input is the translated text data and the emotional state, and the output is the final display data in the adjusted display method. The server adjusts, for example, the size and color of the text according to the emotional state and sends it to the user's device.

[1183] Step 7:

[1184] The final display data is displayed on the user's device screen. The input is the adjusted display data from the server, and the output is the text information displayed on the user's device. The terminal displays the information to the user in an appropriate format based on the data received.

[1185] This processing flow allows users to understand the content of events in real time and experience dynamic displays that respond to their emotions.

[1186] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1187] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1188] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1189] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1190] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1191] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1192] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1193] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1194] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1195] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1196] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1197] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1198] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1199] 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.

[1200] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1201] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1202] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1203] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1204] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1205] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1206] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1207] The following is further disclosed regarding the above embodiment.

[1208] (Claim 1)

[1209] a means for capturing video;

[1210] a transmitting means for transmitting the captured video via the Internet;

[1211] recognition means for recognizing mouth movements from the received video;

[1212] a conversion means for converting the recognized mouth movements into text;

[1213] a translation means for translating the converted text into another language;

[1214] display means for displaying the translated text;

[1215] A system including:

[1216] (Claim 2)

[1217] 2. The system of claim 1, wherein the recognition means uses a machine learning model to recognize mouth movements.

[1218] (Claim 3)

[1219] 10. The system of claim 1, wherein the translation means uses a translation engine to translate the text.

[1220] "Example 1"

[1221] (Claim 1)

[1222] a means for capturing video;

[1223] a transmitting means for transmitting the captured video via a network;

[1224] recognition means for recognizing mouth movements from the received video;

[1225] a conversion means for converting the recognized mouth movements into text;

[1226] a translation means for translating the converted text into another language;

[1227] display means for displaying the translated text;

[1228] A system including:

[1229] (Claim 2)

[1230] 2. The system of claim 1, wherein the recognition means uses a machine learning algorithm to recognize mouth movements.

[1231] (Claim 3)

[1232] 10. The system of claim 1, wherein the translation means uses an automatic translation algorithm to translate the text.

[1233] "Application Example 1"

[1234] (Claim 1)

[1235] a means for capturing video;

[1236] a transmitting means for transmitting the captured video via the Internet;

[1237] recognition means for recognizing mouth movements from the received video;

[1238] a conversion means for converting the recognized mouth movements into text;

[1239] a translation means for translating the converted text into another language;

[1240] display means for displaying the translated text;

[1241] a head mounted display means having a display means for displaying the translated text to the wearer in real time;

[1242] A system including:

[1243] (Claim 2)

[1244] 10. The system of claim 1, wherein the recognition means uses a generative AI model to recognize mouth movements.

[1245] (Claim 3)

[1246] 10. The system of claim 1, wherein the translation means uses a translation engine to translate the text.

[1247] "Example 2: Combining Emotion Engines"

[1248] (Claim 1)

[1249] A photographing device,

[1250] a transmitting device that transmits the captured video via a communication network;

[1251] a recognition device that recognizes mouth movements from the received video;

[1252] a conversion device that converts the recognized mouth movements into text;

[1253] a translation device for translating the converted text into another language;

[1254] a display device for displaying the translated text;

[1255] an emotion analysis device that analyzes the emotions of a user;

[1256] an integration device that integrates the sentiment analysis results with the translated text;

[1257] A system including:

[1258] (Claim 2)

[1259] 10. The system of claim 1, wherein the recognizer uses a machine learning model to recognize mouth movements.

[1260] (Claim 3)

[1261] 10. The system of claim 1, wherein the translation device uses a translation engine to translate the text.

[1262] (Claim 4)

[1263] 2. The system according to claim 1, wherein the emotion analysis device identifies the emotion of the user by analyzing facial expressions and voice data.

[1264] (Claim 5)

[1265] 10. The system of claim 1, wherein the display device adjusts the display method based on the integrated data.

[1266] "Application example 2 when combining emotion engines"

[1267] (Claim 1)

[1268] a means for capturing video;

[1269] a transmitting means for transmitting the captured video via the Internet;

[1270] recognition means for recognizing mouth movements from the received video;

[1271] a conversion means for converting the recognized mouth movements into text;

[1272] a translation means for translating the converted text into another language;

[1273] display means for displaying the translated text;

[1274] emotion recognition means for recognizing an emotional state of a user;

[1275] an adjusting means for adjusting the display of the translated text depending on the emotional state of the user;

[1276] A system including:

[1277] (Claim 2)

[1278] 2. The system of claim 1, wherein the recognition means uses a machine learning model to recognize mouth movements.

[1279] (Claim 3)

[1280] 10. The system of claim 1, wherein the translation means uses a translation engine to translate the text. [Explanation of symbols]

[1281] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for capturing video; a transmitting means for transmitting the captured video via the Internet; recognition means for recognizing mouth movements from the received video; a conversion means for converting the recognized mouth movements into text; a translation means for translating the converted text into another language; display means for displaying the translated text; A system including:

2. 10. The system of claim 1, wherein the recognition means uses a machine learning model to recognize mouth movements.

3. 10. The system of claim 1, wherein the translation means uses a translation engine to translate the text.

Images