system

Abstract

Provide a system. A method for capturing a speaker's voice includes: means for converting the captured audio data into text data; A means for translating the converted text data in real time; means for transmitting the translated text data based on the language setting of each participant; a means for displaying the transmitted translation data; 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] During online meetings with business partners who speak different languages, it can be difficult to communicate accurately and smoothly in real time. Conventional translation tools and manual translation require a great deal of time and effort, resulting in reduced efficiency. Furthermore, issues with translation accuracy and speed can disrupt the flow of conversation and lead to misunderstandings. To solve these issues, there is a demand for a system that can automatically translate spoken content in real time and display it in the language of each participant. [Means for solving the problem]

[0005] The present invention provides a system including a means for capturing a speaker's voice, a means for converting the captured voice data into text data, a means for translating the converted text data in real time, a means for transmitting the translated text data based on each participant's preferred language, and a means for displaying the transmitted translation data. Specifically, the means for capturing voice data utilizes a real-time voice recognition engine, and the means for translating utilizes an automatic translation service. This system facilitates communication between participants who speak different languages. The system further includes a means for reading the participant's preferred language from a database or configuration file, and a means for transmitting the translated text data using socket communication. This improves the efficiency and accuracy of the entire system and enables smooth multilingual communication in real time.

[0006] A "means for capturing speaker voice" is a device or method for collecting the voices of meeting participants as digital data.

[0007] A "means for converting voice data to text data" is a process or system that analyzes captured voice data and converts it into corresponding text data.

[0008] "Means for translating text data in real time" refers to software or a service that instantly translates received text data into multiple languages.

[0009] "Means for transmitting based on each participant's preferred language" refers to a process or system that delivers translated text data according to the language preference selected by each participant.

[0010] The "means for displaying the transmitted translation data" refers to a screen and interface for appropriately displaying the received translation data on each participant's terminal.

[0011] "Means for utilizing a real-time speech recognition engine" refers to technology or software for analyzing voice data in real time and instantly converting it into text data.

[0012] "Means for using an automated translation service" means an online service or software for automatically performing translation.

[0013] "Means for reading from a database or configuration file" refers to a data storage means for saving participant language preference information and accessing it as needed.

[0014] "Means for transmitting using socket communication" refers to a communication means for transmitting data to another terminal via a network. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention provides a system for facilitating communication between participants who speak different languages ​​in online business meetings. The system provides a series of processes for capturing users' speech in real time, converting the speech data into text data, translating the text data into the language set by each participant, and displaying the translation results on each terminal.

[0037] System Configuration

[0038] 1. User voice input

[0039] Terminal: A user speaks through a meeting application.

[0040] Terminal: The speech is captured using a high-precision microphone and prepared for processing as voice data.

[0041] 2. Voice Recognition

[0042] Terminal: The captured voice data is sent to a real-time voice recognition engine, which converts the voice data into text data.

[0043] Terminal: Conversion process is performed using voice recognition technology such as Google (registered trademark) Speech Recognition API.

[0044] 3. Sending text data

[0045] Terminal: The converted text data is sent to the server using a secure communication method (e.g., socket communication).

[0046] 4. Translation of text data

[0047] Server: Translates the received text data using an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant.

[0048] Server: Saves the translation results and prepares them for transmission to each participant's device.

[0049] 5. Sending and displaying translation data

[0050] Server: Translated text data is sent to each device according to the participant's language setting.

[0051] Terminal: The received translation data is displayed on the user interface and shown to participants in real time.

[0052] Example of operation

[0053] Speaker A (English) → User B (Japanese)

[0054] 1. User A says "Hello, how are you?" in a meeting.

[0055] 2. The device captures user A's voice and converts it into voice data.

[0056] 3. The device sends the captured voice data to a real-time voice recognition engine, which converts it into text data such as "Hello, how are you?"

[0057] 4. The device sends the converted text data to the server.

[0058] 5. The server receives the text data and retrieves User B's preferred language (Japanese) from the database.

[0059] 6. The server sends the text data "Hello, how are you?" to the machine translation engine, which translates it into Japanese and obtains the text data "Hello, how are you?"

[0060] 7. The server sends the translated text data to User B's device.

[0061] 8. User B's device displays the received translation data, "Hello, how are you?", on the user interface and shows it to User B.

[0062] This series of processes enables multiple users who speak different languages ​​to communicate smoothly. The system operates in real time, realizing multilingual business meetings while reducing the burden on users.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The user begins speaking through the meeting application. The microphone on the user's device begins capturing audio.

[0066] Step 2:

[0067] The device temporarily stores the captured voice data and prepares it for transmission to a real-time speech recognition engine (e.g., Google Speech Recognition API).

[0068] Step 3:

[0069] The device uses a real-time speech recognition engine to convert the captured voice data into text data. Specifically, the speech recognition engine analyzes the voice waveform and converts it into corresponding text.

[0070] Step 4:

[0071] The terminal sends the converted text data to the server via a secure communication protocol (e.g., socket communication). The text data is properly formatted and sent.

[0072] Step 5:

[0073] The server receives the text data sent from the device, analyzes the received data, and accesses a database or configuration file to identify the preferred language of each participant.

[0074] Step 6:

[0075] The server uses an automatic translation engine (e.g., Google Translate API) to translate the text data into the language set by each participant. The translation engine translates "Hello, how are you?" into "Hello, how are you?"

[0076] Step 7:

[0077] The server transmits the translated text data to the appropriate terminal based on each participant's language setting, and is configured to appropriately format and transmit the translated data.

[0078] Step 8:

[0079] The terminal receives the translation data sent from the server, and the received translation data is appropriately analyzed and displayed on the user interface.

[0080] Step 9:

[0081] The user can check the translation data displayed on the device screen and then make the next utterance or action, enabling smooth communication with translations in real time during meetings.

[0082] This series of processing flows enables seamless online business meetings between multiple participants who speak different languages.

[0083] Example 1

[0084] 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."

[0085] In online business meetings, smooth communication between participants who speak different languages ​​is difficult, and this issue, due to the lack of real-time language translation and proper display, reduces the effectiveness and efficiency of meetings.

[0086] 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.

[0087] In this invention, the server includes means for acquiring the speaker's voice, means for converting the acquired voice data into text data, means for securely transmitting the converted text data, means for transmitting the translated text data based on the language set by each participant, and means for displaying the transmitted translated data, thereby enabling smooth real-time communication between participants who speak different languages.

[0088] A "speaker" is a user who speaks in an online meeting.

[0089] The "means for acquiring voice" refers to a device or software for capturing the voice spoken by the user and storing it as voice data.

[0090] The "means for converting voice data into text data" is a voice recognition technology or engine for converting captured voice data into text form.

[0091] "Means for secure transmission" refers to communication means or protocols for securely transmitting acquired data to another terminal or server.

[0092] A "real-time translation means" is a translation engine or service for rapidly converting text data into different languages.

[0093] "Language set by each participant" refers to the display language set by each user participating in the online meeting.

[0094] The "means for displaying translated data" is a user interface for displaying the translated text on each user's terminal.

[0095] The present invention provides a system for facilitating communication between participants who speak different languages ​​in online business meetings. The system provides a series of processes for capturing users' speech in real time, converting the speech data into text data, translating the text data into the language of each participant, and displaying the translation results on each terminal.

[0096] First, the user speaks using a meeting application. At this time, the user's device uses a high-precision microphone to capture what is being said and stores it as voice data. The captured voice data is sent to a real-time voice recognition engine, which converts the voice data into text data. This voice recognition uses the Google Speech Recognition API.

[0097] The converted text data is then sent to the server using a secure communication method (e.g., socket communication). The server translates the received text data using an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant. The translated text data is then saved and prepared for transmission to each participant's device.

[0098] Finally, the server sends the translated text data to each participant's device, which then displays the received translation data on its user interface, making it available to meeting participants in real time. This allows multiple users who speak different languages ​​to communicate smoothly.

[0099] As a specific example, when speaker A says "Hello, how are you?" in English, the voice data is captured by the device's microphone and converted into text data "Hello, how are you?" by a speech recognition engine. This text data is sent to the server, which translates it into Japanese based on the language setting of user B, generating text data "Hello, how are you?". Finally, this translated text data is sent to user B's device and displayed.

[0100] Examples of prompt statements

[0101] Design a system that translates speech in online business meetings in real time. Generate instructions for a system that meets the following criteria:

[0102] 1. Capture what the user says and convert it into audio data.

[0103] 2. Convert the audio data into text data.

[0104] 3. Send the text data securely to the server.

[0105] 4. The server uses a translation engine to translate the text data into the user's specified language.

[0106] 5. The translation results are sent to each user's device and displayed in real time.

[0107] This system allows smooth communication between users who speak different languages, and real-time translation minimizes time loss, enabling efficient business meetings.

[0108] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0109] Program processing flow

[0110] Step 1:

[0111] A user speaks using a meeting application. The input is the user's voice, and the output is the audio data captured by the device's microphone. In concrete terms, User A speaks, "Hello, how are you?"

[0112] Step 2:

[0113] The device uses a high-precision microphone to capture the speech as voice data. The input is the voice data generated in step 1, and the output is the captured voice data. Specifically, the device's microphone records User A's voice.

[0114] Step 3:

[0115] The device sends the captured voice data to a real-time voice recognition engine. The input is the captured voice data, and the output is text data generated by the voice recognition engine. Specifically, the device sends the voice data in real time to the Google Speech Recognition API, which generates the text data "Hello, how are you?"

[0116] Step 4:

[0117] The terminal sends the converted text data to the server using a secure communication method (e.g., socket communication). The input is text data, and the output is text data sent to the server. Specifically, the terminal sends the text data "Hello, how are you?" to the server.

[0118] Step 5:

[0119] The server sends the received text data to an automatic translation engine based on the language setting of each participant. The input is the text data and the participant's language setting information, and the output is the translated text data. Specifically, the server sends the text data to the Google Translate API, which translates "Hello, how are you?" into Japanese "Hello, how are you?"

[0120] Step 6:

[0121] The server uses a translation engine to save the translated text data and prepares it to be sent to each participant's device. The input is the translated text data, and the output is the text data prepared for sending. Specifically, the server saves the translated data for "Hello, how are you?" and generates data to be sent to the device.

[0122] Step 7:

[0123] The server sends the translated text data to each device according to the participant's language setting. The input is the text data prepared for transmission, and the output is the translated data sent to each device. In concrete terms, the server sends the data "Hello, how are you?" to User B's device.

[0124] Step 8:

[0125] The device displays the received translation data on the user interface and shows it to the participants in real time. The input is the received translation data, and the output is the translated text displayed on the device's user interface. Specifically, User B's device displays "Hello, how are you?"

[0126] (Application example 1)

[0127] 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."

[0128] In factories, communication between workers who speak different languages ​​is often difficult, which can hinder work efficiency and safety. Language barriers can be a serious obstacle, especially when sharing emergency instructions or complex work procedures. Technology is needed to solve this problem and improve work efficiency and safety.

[0129] 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.

[0130] In this invention, the server includes means for capturing the speaker's voice, means for converting the captured voice data into text data, means for translating the converted text data in real time, means for transmitting the translated text data based on the language set by each participant, means for displaying the transmitted translated data, means for supporting communication between workers who speak different languages, and means for converting the translated text data into voice and playing it back on a speaker. This enables workers in a factory who speak different languages ​​to understand each other in real time and communicate smoothly.

[0131] "Speaker" refers to a person who produces sound.

[0132] "Voice data" refers to data that is a digital recording of a speaker's voice.

[0133] "Text data" refers to digital data that has been converted from audio data into text.

[0134] "Real-time" refers to processing that occurs almost immediately, without delay.

[0135] "Translation" refers to converting text data expressed in one language into another language.

[0136] "Preferred language" refers to the language that the user of the system has selected to use.

[0137] "Send" refers to the act of moving data from one device to another.

[0138] "Display" refers to the output of digital data in a visually perceptible form.

[0139] "In-factory" refers to the interior of an industrial facility where manufacturing or assembly takes place.

[0140] "Worker" refers to a worker who performs work within a factory.

[0141] "Supporting communication" refers to providing assistance to facilitate smooth communication.

[0142] A "speaker" refers to a device for outputting audio data as sound waves.

[0143] "Convert to audio" refers to converting text data into audio format data.

[0144] This invention is a system for supporting communication between workers who speak different languages ​​in a factory. This system includes the following components:

[0145] Hardware

[0146] High-definition microphone: Used to capture the speaker's voice.

[0147] Speech Recognition Processor: Used to process captured voice data and convert it into text data.

[0148] Server: Translates the converted text data and sends the translated data based on the language setting of each participant.

[0149] Display: Used to visually display the translated text data.

[0150] Speaker: Used to play back the translated text data as audio.

[0151] software

[0152] Speech recognition engine: Uses the Google Speech Recognition API or similar to convert captured voice data into text data.

[0153] Translation engine: Translates text data in real time using APIs such as Google Translate.

[0154] Data communication: A secure socket communication protocol for sending and receiving converted text data and translation data.

[0155] Robot control system: The entire system is controlled in an integrated manner using ROS (Robot Operating System).

[0156] System Operation Description

[0157] Step 1: Voice Input

[0158] When a user speaks into the microphone, the voice data is captured by a high-precision microphone. For example, Worker A (an English speaker) speaks, "The machine needs maintenance."

[0159] Step 2: Voice Recognition

[0160] The captured voice data is sent to a speech recognition processor and converted into text data in real time using the Google Speech Recognition API. In this case, the voice data is converted into the text data "The machine needs maintenance."

[0161] Step 3: Send data

[0162] The converted text data is sent to the server using a secure socket communication protocol.

[0163] Step 4: Translating the text data

[0164] The server uses the Google Translate API to translate the received text in real time based on the language settings of each participant. For example, "The machine needs maintenance" is translated to "The machine needs maintenance."

[0165] Step 5: Send and view translation data

[0166] The translated text data is sent to the terminal of Worker B (Japanese speaker) and displayed on the screen. The translated text data is also played aloud through a speaker.

[0167] Specific examples

[0168] Below is a concrete example of how the system works.

[0169] 1. Worker A says, "The machine needs maintenance."

[0170] 2. A high-definition microphone captures your voice and sends it to a speech recognition processor.

[0171] 3. The Google Speech Recognition API converts the audio data into "The machine needs maintenance."

[0172] 4. The text data is sent to the server via a secure socket communication protocol.

[0173] 5. The Google Translate API translates the text data into "Machine maintenance required."

[0174] 6. The translated text data is sent to Worker B's device and displayed on the screen.

[0175] 7. The translated text data is played back through the speaker as a voice saying, "Machine maintenance is required."

[0176] Prompt example

[0177] Below is a concrete example of a prompt using the Google Speech Recognition API and the Google Translate API.

[0178] Speech recognition prompt:

[0179] Please recognize the following phrase: "The machine needs maintenance".

[0180] Translation prompt:

[0181] Translate the following English text to Japanese: "The machine needs maintenance".

[0182] This will enable workers in a factory who speak different languages ​​to understand each other in real time and communicate smoothly.

[0183] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0184] Step 1:

[0185] When a user speaks into a high-definition microphone, their voice is captured. The input is the user's voice, which is captured as digital voice data by the high-definition microphone. Specifically, worker A speaks, "The machine needs maintenance." This digital voice data is passed to the next processing step.

[0186] Step 2:

[0187] The device sends the captured voice data to a speech recognition processor, which converts the voice data into text using the Google Speech Recognition API. The digital voice data is processed as input, and the text "The machine needs maintenance" is generated as output.

[0188] Step 3:

[0189] The terminal sends the converted text data to the server through a secure socket communication protocol. The input contains the text data "The machine needs maintenance". The output is the same data transmitted to the server.

[0190] Step 4:

[0191] The server uses the Google Translate API to translate the received text data based on the language set by each participant. The input is the text data "The machine needs maintenance," and the output is the translated text data "Machine maintenance is required."

[0192] Step 5:

[0193] The server sends the translated text data to the terminal. At this time, it sends the most appropriate translation data based on the language setting of each participant. The input includes the translated text data "Machine maintenance required." The output is transferred to the terminal.

[0194] Step 6:

[0195] The device displays the received translation data on a display. Specifically, it visually displays the text data "Machine maintenance required." The device also converts the translated text data into audio data and plays it as audio through a speaker. The input includes the translated text data "Machine maintenance required." The output is that this data is displayed on the display and the speaker plays the audio "Machine maintenance required."

[0196] 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.

[0197] The present invention provides a system for facilitating communication between participants who speak different languages ​​in online business meetings, and also combines an emotion engine to recognize the speaker's emotions and improve communication accuracy. The system provides a series of processes: capturing a user's speech in real time, converting the speech data into text data, translating the text data into the language set by each participant, and displaying the translation results and emotional information on each terminal.

[0198] System Configuration

[0199] 1. User voice input

[0200] Terminal: A user speaks through a meeting application.

[0201] Terminal: The speech is captured using a high-precision microphone and prepared for processing as voice data.

[0202] 2. Voice Recognition

[0203] Terminal: The captured voice data is sent to a real-time voice recognition engine, which converts the voice data into text data.

[0204] Terminal: Use a speech recognition engine (e.g., Google Speech Recognition API) to perform the conversion process.

[0205] 3. Emotion analysis

[0206] Terminal: Captured voice data is sent to the emotion engine, which analyzes the speaker's emotional state.

[0207] Device: The emotion engine analyzes the voice data and extracts emotional information such as "anger," "joy," and "sadness."

[0208] 4. Sending text data

[0209] Terminal: The converted text data and analyzed emotion information are sent to the server via a secure communication protocol (e.g., socket communication).

[0210] 5. Translation of text data

[0211] Server: Translates the received text data using an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant.

[0212] Server: Saves the translation results and prepares them for transmission to each participant's device.

[0213] 6. Adding Emotional Information

[0214] Server: Adds emotional information provided by the emotion engine to the translated text data and adds markers indicating emotions to each text.

[0215] 7. Sending and displaying translation data

[0216] Server: Translates the text data and emotion information to each participant's device.

[0217] Terminal: The received translation data and emotion information are displayed on the user interface and shown to participants in real time.

[0218] Example of operation

[0219] Speaker A (English) → User B (Japanese)

[0220] 1. User A says "I am very happy to be here" in a meeting.

[0221] 2. The device captures user A's voice and converts it into voice data.

[0222] 3. The device sends the captured voice data to a real-time voice recognition engine and converts it into text data such as "I am very happy to be here."

[0223] 4. The device sends the voice data to the emotion engine, which analyzes and extracts the emotion of "joy."

[0224] 5. The device sends the converted text data and emotion information to the server.

[0225] 6. The server receives the text data and retrieves User B's preferred language (Japanese) from the database.

[0226] 7. The server sends the text data "I am very happy to be here." to the machine translation engine, which translates it into Japanese and obtains the text data "I am very happy to be here."

[0227] 8. The server adds the emotional information "joy" to the translated text data.

[0228] 9. The server sends the translated text data and emotion information to User B's device.

[0229] 10. User B's device receives the translated data "I'm so happy to be here" and displays the emotional information "joy" on the user interface for User B to see.

[0230] This series of processes allows users who speak different languages ​​to communicate smoothly while understanding the emotions of the other person. The system operates in real time, making multilingual business meetings possible while reducing the burden on users.

[0231] The processing flow will be explained below.

[0232] Step 1:

[0233] The user begins speaking through the meeting application. The microphone on the user's device begins capturing audio.

[0234] Step 2:

[0235] The device temporarily stores the captured voice data and prepares it for transmission to a real-time speech recognition engine (e.g., Google Speech Recognition API).

[0236] Step 3:

[0237] The device uses a real-time speech recognition engine to convert the captured voice data into text data. Specifically, the speech recognition engine analyzes the voice waveform and converts it into corresponding text.

[0238] Step 4:

[0239] The device sends the voice data to the emotion engine, which analyzes the speaker's emotions. The emotion engine analyzes the voice data and extracts emotional information such as "joy," "sadness," and "anger."

[0240] Step 5:

[0241] The converted text data and analyzed emotion information are sent to the server via a secure communication protocol (e.g., socket communication). The text data and emotion information are appropriately formatted and sent.

[0242] Step 6:

[0243] The server receives the text data and emotion information sent from the device, analyzes the received data, and accesses a database or configuration file to identify the preferred language of each participant.

[0244] Step 7:

[0245] The server uses an automatic translation engine (e.g., Google Translate API) to translate the text data into the language set by each participant. The translation engine translates "I am very happy to be here." into "I am very happy to be here."

[0246] Step 8:

[0247] The server adds emotional information provided by the emotion engine to the translated text data and adds markers indicating emotions to each piece of text. For example, adding "(joy)" after "I'm so happy to be here."

[0248] Step 9:

[0249] The server sends the translated text data and emotion information to the appropriate device based on each participant's language settings. The data is properly formatted and sent quickly.

[0250] Step 10:

[0251] The device receives the translation data and emotion information sent from the server, and the received data is analyzed appropriately and displayed on the user interface.

[0252] Step 11:

[0253] The user can check the translation data and emotional information displayed on the device screen and then make the next utterance or action, allowing for smooth sharing of translated communication and emotional information in real time during meetings.

[0254] This process flow not only enables seamless communication between multiple participants who speak different languages, but also makes it easier for each user to understand the emotions of the other speaker. The system operates in real time, reducing the burden on users and supporting efficient multilingual business meetings.

[0255] Example 2

[0256] 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."

[0257] In online business meetings, there is a demand for systems that facilitate smooth communication between participants who speak different languages. Conventional systems convert voice data into text or translate it, but they lack the ability to convey the speaker's emotional information, making it difficult to improve the accuracy of communication and understanding between participants.

[0258] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0259] In this invention, the server includes means for capturing the speaker's voice, means for converting the captured voice data into text data, means for extracting emotional information from the captured voice data and adding the emotional information to the text data, means for translating the converted text data in real time, means for transmitting the translated text data based on the language set by each participant, and means for displaying the transmitted translated data, thereby enabling participants who speak different languages ​​to communicate while understanding the speaker's emotions in real time.

[0260] The "means for capturing the speaker's voice" is a function for acquiring the user's speech as digital voice data using a device such as a high-precision microphone.

[0261] The "means for converting captured voice data into text data" is a function for inputting the acquired voice data into a voice recognition engine and converting the voice content into text format.

[0262] "Means for translating converted text data in real time" refers to a function for translating text data in real time using software or a service that automatically translates text data into another language.

[0263] The "means for transmitting translated text data based on the language set by each participant" is a function for appropriately transmitting translated text data based on the language set in advance by each participant.

[0264] The "means for displaying the transmitted translation data" is a function for visually displaying the received translation data on the terminal of each participant.

[0265] "Means for extracting emotional information from captured voice data and adding the emotional information to text data" refers to a function that analyzes the emotional state of the speaker from captured voice data using a voice analysis engine or the like and adds the emotional information to the text data.

[0266] This invention is a system for facilitating communication between participants who speak different languages ​​in online business meetings, incorporating an emotion engine that recognizes the speaker's emotions to improve communication accuracy. This system provides a series of processes: capturing a user's speech in real time, converting the speech data into text data, translating the text data into the language set by each participant, and displaying the translation results and emotional information on each terminal.

[0267] Hardware and Software Configuration

[0268] 1. User voice input

[0269] Device: The user speaks through the meeting application. The device uses a high-precision microphone to capture the user's speech and save it as digital audio data.

[0270] 2. Voice Recognition

[0271] Device: Sends captured voice data to a real-time speech recognition engine, such as the Google Speech Recognition API, and converts the speech into text.

[0272] 3. Emotion analysis

[0273] Terminal: Sends voice data to the emotion engine and analyzes the speaker's emotional state. The emotion engine extracts emotional information such as "anger," "joy," and "sadness."

[0274] 4. Sending text data

[0275] Terminal: The converted text data and emotion information are sent to the server via a secure communication protocol (e.g., socket communication).

[0276] 5. Translation of text data

[0277] Server: Translates the received text data using an automatic translation engine such as Google Translate API based on the language settings of each participant. The translation results are saved and prepared for transmission to each participant's device.

[0278] 6. Adding Emotional Information

[0279] Server: Adds emotional information provided by the emotion engine to the translated text data and adds markers indicating emotions to each text.

[0280] 7. Sending and displaying translation data

[0281] Server: Translates the text data and emotional information to each participant's device. Each participant's device displays the received translation data and emotional information on a user interface, allowing participants to see it in real time.

[0282] Specific examples

[0283] Speaker A (English) → User B (Japanese)

[0284] 1. User A says "I am very happy to be here" in a meeting.

[0285] 2. The device captures user A's voice and converts it into voice data.

[0286] 3. The device sends the captured voice data to the Google Speech Recognition API, which converts it into text data such as "I am very happy to be here."

[0287] 4. The device sends the voice data to the emotion engine, which analyzes and extracts the emotion of "joy."

[0288] 5. The device sends the converted text data and emotion information to the server.

[0289] 6. The server receives the text data and retrieves User B's preferred language (Japanese) from the database.

[0290] 7. The server sends the text data "I am very happy to be here." to the Google Translate API, which translates it into Japanese and obtains the text data "I am very happy to be here."

[0291] 8. The server adds the emotion information "joy" to the translated text data. Example: "I'm so happy to be here. [Joy]"

[0292] 9. The server sends the translated text data and emotion information to User B's device.

[0293] 10. User B's device receives the translated data "I'm so happy to be here" and displays the emotional information "joy" on the user interface for User B to see.

[0294] This process allows users who speak different languages ​​to communicate smoothly while understanding each other's emotions. The system operates in real time, making multilingual business meetings possible while reducing the burden on users.

[0295] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0296] Step 1:

[0297] The user speaks

[0298] Terminal: A user speaks through a meeting application. For example, User A says, "I am very happy to be here." This voice is captured by a high-precision microphone and acquired as digital audio data.

[0299] Input: The audio spoken by the user.

[0300] Specific operation: A high-performance microphone captures the user's voice and stores it in memory as audio data.

[0301] Step 2:

[0302] Converting audio data to text data

[0303] On the device: The captured voice data is sent to the Google Speech Recognition API, which converts the speech into text.

[0304] Input: Captured audio data.

[0305] Output: The converted text data "I am very happy to be here."

[0306] Specific operation: The device sends voice data to the Google Speech Recognition API and obtains the text data "I am very happy to be here."

[0307] Step 3:

[0308] Sentiment analysis of voice data

[0309] Terminal: Sends voice data to the emotion engine and analyzes the speaker's emotional state. For example, the emotion engine analyzes and extracts the emotion "joy."

[0310] Input: Transduced text data and captured audio data.

[0311] Output: Analyzed emotion information "joy".

[0312] Specific operation: The device sends voice data to the emotion engine and obtains the emotion information "joy."

[0313] Step 4:

[0314] Text data and emotional information sent to server

[0315] Terminal: The converted text data and analyzed emotion information are sent to the server via a secure communication protocol (e.g., socket communication).

[0316] Input: Text data "I am very happy to be here." and emotion information "joy."

[0317] Output: The data sent to the server.

[0318] Specific operation: The device assembles text data and emotional information into packets and securely transmits them to the server.

[0319] Step 5:

[0320] Text data translation

[0321] Server: Sends the received text data to the Google Translate API and translates it based on the language settings of each participant.

[0322] Input: Text data "I am very happy to be here."

[0323] Output: The translated text "I'm so happy to be here."

[0324] Specific operation: The server sends text data to the Google Translate API and obtains the translated text data.

[0325] Step 6:

[0326] Adding emotional information to text data

[0327] Server: Adds the emotional information "joy" to the translated text data. For example, "I'm so happy to be here. [Joy]."

[0328] Input: Translated text data "I'm so happy to be here" and emotion information "joy".

[0329] Output: Text data with emotional information added: "I'm so happy to be here. [Joy]".

[0330] What it does: The server adds emotion information to the translated text and formats it.

[0331] Step 7:

[0332] Transmitting and displaying translation data and emotional information to the device

[0333] Server: Translates the text data and emotion information to each participant's device.

[0334] Terminal: The received translation data and emotion information are displayed on the user interface and shown to participants in real time.

[0335] Input: Text data with emotional information added: "I'm so happy to be here. [Joy]".

[0336] Output: The displayed translation data and sentiment information.

[0337] Specific operation: The server sends text data with added emotional information to the terminal, which then displays it on the user interface.

[0338] These steps enable participants who speak different languages ​​to communicate in real time while understanding each other's emotions. This system combines speech recognition and emotion analysis using generative AI models with machine translation services to facilitate international business meetings.

[0339] (Application example 2)

[0340] 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."

[0341] When people who speak different languages ​​communicate in the same space, it is difficult not only to translate between languages, but also to convey the speaker's emotions and nuances appropriately. In this situation, it is necessary to improve the accuracy of communication, especially in navigation systems for autonomous vehicles, because understanding the driver's emotions and intentions is directly linked to safety and usability.

[0342] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing the speaker's voice, means for converting the captured voice data into text data, means for translating the converted text data in real time, means for analyzing the speaker's emotional state, means for adding the analyzed emotional information to translation data, means for transmitting the translated text data based on the language set by each participant, and means for displaying the transmitted translation data. This enables smooth communication that includes emotions between users who speak different languages, improving safety and comfort even in navigation systems for autonomous vehicles.

[0343] "Speaker" refers to a person who produces sound.

[0344] "Audio capturing means" refers to a device or system for digitally recording a speaker's voice.

[0345] "Audio Data" means audio information recorded in digital form.

[0346] "Text data" refers to text information converted through speech recognition, translation, etc.

[0347] "Means for converting" refers to the technology or system for converting voice data into text data.

[0348] "Real-time translation means" refers to technologies or systems that instantly convert input text data into a different language.

[0349] "Language set by each participant" refers to the language setting of the user for whom the translation results are to be displayed.

[0350] "Transmitting means" refers to a technology or system that transmits the generated data to other devices or systems via a network.

[0351] "Display means" refers to the technology or system used to present information to the user through a user interface.

[0352] "Means for analyzing emotional state" refers to technologies or systems that analyze the speaker's emotions from voice data.

[0353] "Emotional information" refers to data that indicates the emotional state of the speaker.

[0354] "Means for adding to translated data" refers to technologies and systems that add analyzed emotional information to translated text data.

[0355] "Server" refers to a computing device or system for processing and managing data.

[0356] This invention relates to a multilingual and emotion-sensitive navigation system for autonomous vehicles. The system captures a speaker's voice, converts the voice data into text data, translates it in real time, analyzes the speaker's emotional state, adds the analyzed emotional information to the translated data, transmits it based on the language settings of each participant, and displays the transmitted translated data, thereby enabling smooth, emotion-sensitive communication between users who speak different languages.

[0357] Hardware used

[0358] High-precision microphone

[0359] In-vehicle terminal (including display)

[0360] server

[0361] Software used

[0362] Speech recognition engine (e.g., Google Speech Recognition API)

[0363] Machine translation engine (e.g. Google Translate API)

[0364] Sentiment analysis engine (e.g. emotion_recognition_library)

[0365] Program processing and data processing

[0366] 1. User voice input

[0367] A high-precision microphone connected to the in-vehicle terminal captures the user's speech in real time, and the captured speech is sent to the in-vehicle terminal as voice data.

[0368] 2. Voice Recognition

[0369] The voice data captured by the in-vehicle device is converted into text data using the Google Speech Recognition API.

[0370] 3. Emotion analysis

[0371] The in-vehicle device analyzes the converted text data using the emotion_recognition_library and extracts the speaker's emotional state (e.g., "anger," "joy," "sadness").

[0372] 4. Data Transmission

[0373] The in-vehicle terminal transmits the converted text data and analyzed emotion information to the server using a secure communication protocol (e.g., socket communication).

[0374] 5. Text Translation

[0375] The server translates the received text data using the Google Translate API based on the user's language settings.

[0376] 6. Adding Emotional Information

[0377] The server adds emotional information to the translated text data and adds markers indicating emotions to each text.

[0378] 7. Data transmission and display

[0379] The server sends the translated text data and emotion information to the in-vehicle device, which then displays the received translation data on the display, allowing the user to see it in real time.

[0380] Specific examples

[0381] For example, if a user in an autonomous vehicle says to the navigation system, "I am feeling a bit anxious about the traffic ahead," the system will process it as follows: It captures the audio, uses speech recognition, and converts it into text data: "I am feeling a bit anxious about the traffic ahead." It then extracts the emotional information "anxiety" through emotion analysis and sends it to the server using a secure communication protocol. The server translates the text data into Japanese and generates text data: "I am a bit anxious about the traffic ahead." It adds the emotional information "anxiety" to the translation result and sends it to the in-vehicle device. The in-vehicle device then displays the emotional information "anxiety" on the display, showing it to the user in real time, allowing other passengers and the system to understand the user's emotions and take appropriate action.

[0382] Prompt Sentence Examples

[0383] "Please explain the glossary and multilingual translation process in an in-car navigation system."

[0384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0385] Step 1:

[0386] User voice input

[0387] In an autonomous vehicle, a user speaks instructions to the navigation system. The voice is captured through a high-precision microphone and input as voice data into the in-vehicle terminal. At this stage, the input data is raw voice data. The in-vehicle terminal uses a voice capture module to convert it into a digital format, ready to be sent to the voice recognition engine.

[0388] Step 2:

[0389] Voice Recognition

[0390] The in-vehicle device sends the captured voice data to a real-time voice recognition engine (e.g., Google Speech Recognition API) and converts the voice data into text data. In this process, the input is the captured voice data and the output is the converted text data. The voice recognition engine analyzes the voice data and generates the corresponding text data.

[0391] Step 3:

[0392] Emotion analysis

[0393] The in-vehicle device sends the text data of the speech recognition results and the original speech data to the emotion engine, which analyzes the speaker's emotional state. At this stage, the input is speech data and text data, and the output is analyzed emotional information. The emotion engine uses a feature extraction algorithm to classify emotions into categories such as "anger," "joy," and "sadness."

[0394] Step 4:

[0395] Data transmission

[0396] The in-vehicle terminal transmits the converted text data and analyzed emotion information to the server using a secure communication protocol. The input is the converted text data and emotion information, and the output is the data transmitted to the server. The data is encrypted before transmission to ensure security.

[0397] Step 5:

[0398] Text Translation

[0399] The server sends the received text data to an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant, and obtains the translated text data. The input is the received text data and the user's language settings, and the output is the translated text data. The translation engine analyzes the source text and generates the corresponding translation.

[0400] Step 6:

[0401] Adding emotional information

[0402] The server adds emotional information to the translated text data using an emotion engine and adds markers indicating emotions to each text. The input is the translated text data and emotional information, and the output is the translated text data with the emotional markers added. The server integrates the emotional markers into the metadata of the text data.

[0403] Step 7:

[0404] Data transmission and display

[0405] The server sends the translated text data and emotion information to the in-vehicle terminal. The in-vehicle terminal displays the received translation data on the display, showing it to the user in real time. The input is emotion information and translated text data, and the output is the information displayed on the in-vehicle terminal's display. The display module receives the data and displays it on the screen.

[0406] As a result, smooth communication between multiple languages, including emotions, can be realized.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] [Second embodiment]

[0411] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0412] 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.

[0413] 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).

[0414] 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.

[0415] 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.

[0416] 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).

[0417] 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. 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.

[0418] 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.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] 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."

[0423] The present invention provides a system for facilitating communication between participants who speak different languages ​​in online business meetings. The system provides a series of processes for capturing users' speech in real time, converting the speech data into text data, translating the text data into the language set by each participant, and displaying the translation results on each terminal.

[0424] System Configuration

[0425] 1. User voice input

[0426] Terminal: A user speaks through a meeting application.

[0427] Terminal: The speech is captured using a high-precision microphone and prepared for processing as voice data.

[0428] 2. Voice Recognition

[0429] Terminal: The captured voice data is sent to a real-time voice recognition engine, which converts the voice data into text data.

[0430] Device: Conversion process is performed using voice recognition technology such as Google Speech Recognition API.

[0431] 3. Sending text data

[0432] Terminal: The converted text data is sent to the server using a secure communication method (e.g., socket communication).

[0433] 4. Translation of text data

[0434] Server: Translates the received text data using an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant.

[0435] Server: Saves the translation results and prepares them for transmission to each participant's device.

[0436] 5. Sending and displaying translation data

[0437] Server: Translated text data is sent to each device according to the participant's language setting.

[0438] Terminal: The received translation data is displayed on the user interface and shown to participants in real time.

[0439] Example of operation

[0440] Speaker A (English) → User B (Japanese)

[0441] 1. User A says "Hello, how are you?" in a meeting.

[0442] 2. The device captures user A's voice and converts it into voice data.

[0443] 3. The device sends the captured voice data to a real-time voice recognition engine, which converts it into text data such as "Hello, how are you?"

[0444] 4. The device sends the converted text data to the server.

[0445] 5. The server receives the text data and retrieves User B's preferred language (Japanese) from the database.

[0446] 6. The server sends the text data "Hello, how are you?" to the machine translation engine, which translates it into Japanese and obtains the text data "Hello, how are you?"

[0447] 7. The server sends the translated text data to User B's device.

[0448] 8. User B's device displays the received translation data, "Hello, how are you?", on the user interface and shows it to User B.

[0449] This series of processes enables multiple users who speak different languages ​​to communicate smoothly. The system operates in real time, realizing multilingual business meetings while reducing the burden on users.

[0450] The processing flow will be explained below.

[0451] Step 1:

[0452] The user begins speaking through the meeting application. The microphone on the user's device begins capturing audio.

[0453] Step 2:

[0454] The device temporarily stores the captured voice data and prepares it for transmission to a real-time speech recognition engine (e.g., Google Speech Recognition API).

[0455] Step 3:

[0456] The device uses a real-time speech recognition engine to convert the captured voice data into text data. Specifically, the speech recognition engine analyzes the voice waveform and converts it into corresponding text.

[0457] Step 4:

[0458] The terminal sends the converted text data to the server via a secure communication protocol (e.g., socket communication). The text data is properly formatted and sent.

[0459] Step 5:

[0460] The server receives the text data sent from the device, analyzes the received data, and accesses a database or configuration file to identify the preferred language of each participant.

[0461] Step 6:

[0462] The server uses an automatic translation engine (e.g., Google Translate API) to translate the text data into the language set by each participant. The translation engine translates "Hello, how are you?" into "Hello, how are you?"

[0463] Step 7:

[0464] The server transmits the translated text data to the appropriate terminal based on each participant's language setting, and is configured to appropriately format and transmit the translated data.

[0465] Step 8:

[0466] The terminal receives the translation data sent from the server, and the received translation data is appropriately analyzed and displayed on the user interface.

[0467] Step 9:

[0468] The user can check the translation data displayed on the device screen and then make the next utterance or action, enabling smooth communication with translations in real time during meetings.

[0469] This series of processing flows enables seamless online business meetings between multiple participants who speak different languages.

[0470] Example 1

[0471] 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."

[0472] In online business meetings, smooth communication between participants who speak different languages ​​is difficult, and this issue, due to the lack of real-time language translation and proper display, reduces the effectiveness and efficiency of meetings.

[0473] 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.

[0474] In this invention, the server includes means for acquiring the speaker's voice, means for converting the acquired voice data into text data, means for securely transmitting the converted text data, means for transmitting the translated text data based on the language set by each participant, and means for displaying the transmitted translated data, thereby enabling smooth real-time communication between participants who speak different languages.

[0475] A "speaker" is a user who speaks in an online meeting.

[0476] The "means for acquiring voice" refers to a device or software for capturing the voice spoken by the user and storing it as voice data.

[0477] The "means for converting voice data into text data" is a voice recognition technology or engine for converting captured voice data into text form.

[0478] "Means for secure transmission" refers to communication means or protocols for securely transmitting acquired data to another terminal or server.

[0479] A "real-time translation means" is a translation engine or service for rapidly converting text data into different languages.

[0480] "Language set by each participant" refers to the display language set by each user participating in the online meeting.

[0481] The "means for displaying translated data" is a user interface for displaying the translated text on each user's terminal.

[0482] The present invention provides a system for facilitating communication between participants who speak different languages ​​in online business meetings. The system provides a series of processes for capturing users' speech in real time, converting the speech data into text data, translating the text data into the language of each participant, and displaying the translation results on each terminal.

[0483] First, the user speaks using a meeting application. At this time, the user's device uses a high-precision microphone to capture what is being said and stores it as voice data. The captured voice data is sent to a real-time voice recognition engine, which converts the voice data into text data. This voice recognition uses the Google Speech Recognition API.

[0484] The converted text data is then sent to the server using a secure communication method (e.g., socket communication). The server translates the received text data using an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant. The translated text data is then saved and prepared for transmission to each participant's device.

[0485] Finally, the server sends the translated text data to each participant's device, which then displays the received translation data on its user interface, making it available to meeting participants in real time. This allows multiple users who speak different languages ​​to communicate smoothly.

[0486] As a specific example, when speaker A says "Hello, how are you?" in English, the voice data is captured by the device's microphone and converted into text data "Hello, how are you?" by a speech recognition engine. This text data is sent to the server, which translates it into Japanese based on the language setting of user B, generating text data "Hello, how are you?". Finally, this translated text data is sent to user B's device and displayed.

[0487] Examples of prompt statements

[0488] Design a system that translates speech in online business meetings in real time. Generate instructions for a system that meets the following criteria:

[0489] 1. Capture what the user says and convert it into audio data.

[0490] 2. Convert the audio data into text data.

[0491] 3. Send the text data securely to the server.

[0492] 4. The server uses a translation engine to translate the text data into the user's specified language.

[0493] 5. The translation results are sent to each user's device and displayed in real time.

[0494] This system allows smooth communication between users who speak different languages, and real-time translation minimizes time loss, enabling efficient business meetings.

[0495] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0496] Program processing flow

[0497] Step 1:

[0498] A user speaks using a meeting application. The input is the user's voice, and the output is the audio data captured by the device's microphone. In concrete terms, User A speaks, "Hello, how are you?"

[0499] Step 2:

[0500] The device uses a high-precision microphone to capture the speech as voice data. The input is the voice data generated in step 1, and the output is the captured voice data. Specifically, the device's microphone records User A's voice.

[0501] Step 3:

[0502] The device sends the captured voice data to a real-time voice recognition engine. The input is the captured voice data, and the output is text data generated by the voice recognition engine. Specifically, the device sends the voice data in real time to the Google Speech Recognition API, which generates the text data "Hello, how are you?"

[0503] Step 4:

[0504] The terminal sends the converted text data to the server using a secure communication method (e.g., socket communication). The input is text data, and the output is text data sent to the server. Specifically, the terminal sends the text data "Hello, how are you?" to the server.

[0505] Step 5:

[0506] The server sends the received text data to an automatic translation engine based on the language setting of each participant. The input is the text data and the participant's language setting information, and the output is the translated text data. Specifically, the server sends the text data to the Google Translate API, which translates "Hello, how are you?" into Japanese "Hello, how are you?"

[0507] Step 6:

[0508] The server uses a translation engine to save the translated text data and prepares it to be sent to each participant's device. The input is the translated text data, and the output is the text data prepared for sending. Specifically, the server saves the translated data for "Hello, how are you?" and generates data to be sent to the device.

[0509] Step 7:

[0510] The server sends the translated text data to each device according to the participant's language setting. The input is the text data prepared for transmission, and the output is the translated data sent to each device. In concrete terms, the server sends the data "Hello, how are you?" to User B's device.

[0511] Step 8:

[0512] The device displays the received translation data on the user interface and shows it to the participants in real time. The input is the received translation data, and the output is the translated text displayed on the device's user interface. Specifically, User B's device displays "Hello, how are you?"

[0513] (Application example 1)

[0514] 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."

[0515] In factories, communication between workers who speak different languages ​​is often difficult, which can hinder work efficiency and safety. Language barriers can be a serious obstacle, especially when sharing emergency instructions or complex work procedures. Technology is needed to solve this problem and improve work efficiency and safety.

[0516] 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.

[0517] In this invention, the server includes means for capturing the speaker's voice, means for converting the captured voice data into text data, means for translating the converted text data in real time, means for transmitting the translated text data based on the language set by each participant, means for displaying the transmitted translated data, means for supporting communication between workers who speak different languages, and means for converting the translated text data into voice and playing it back on a speaker. This enables workers in a factory who speak different languages ​​to understand each other in real time and communicate smoothly.

[0518] "Speaker" refers to a person who produces sound.

[0519] "Voice data" refers to data that is a digital recording of a speaker's voice.

[0520] "Text data" refers to digital data that has been converted from audio data into text.

[0521] "Real-time" refers to processing that occurs almost immediately, without delay.

[0522] "Translation" refers to converting text data expressed in one language into another language.

[0523] "Preferred language" refers to the language that the user of the system has selected to use.

[0524] "Send" refers to the act of moving data from one device to another.

[0525] "Display" refers to the output of digital data in a visually perceptible form.

[0526] "In-factory" refers to the interior of an industrial facility where manufacturing or assembly takes place.

[0527] "Worker" refers to a worker who performs work within a factory.

[0528] "Supporting communication" refers to providing assistance to facilitate smooth communication.

[0529] A "speaker" refers to a device for outputting audio data as sound waves.

[0530] "Convert to audio" refers to converting text data into audio format data.

[0531] This invention is a system for supporting communication between workers who speak different languages ​​in a factory. This system includes the following components:

[0532] Hardware

[0533] High-definition microphone: Used to capture the speaker's voice.

[0534] Speech Recognition Processor: Used to process captured voice data and convert it into text data.

[0535] Server: Translates the converted text data and sends the translated data based on the language setting of each participant.

[0536] Display: Used to visually display the translated text data.

[0537] Speaker: Used to play back the translated text data as audio.

[0538] software

[0539] Speech recognition engine: Uses the Google Speech Recognition API or similar to convert captured voice data into text data.

[0540] Translation engine: Translates text data in real time using APIs such as Google Translate.

[0541] Data communication: A secure socket communication protocol for sending and receiving converted text data and translation data.

[0542] Robot control system: The entire system is controlled in an integrated manner using ROS (Robot Operating System).

[0543] System Operation Description

[0544] Step 1: Voice Input

[0545] When a user speaks into the microphone, the voice data is captured by a high-precision microphone. For example, Worker A (an English speaker) speaks, "The machine needs maintenance."

[0546] Step 2: Voice Recognition

[0547] The captured voice data is sent to a speech recognition processor and converted into text data in real time using the Google Speech Recognition API. In this case, the voice data is converted into the text data "The machine needs maintenance."

[0548] Step 3: Send data

[0549] The converted text data is sent to the server using a secure socket communication protocol.

[0550] Step 4: Translating the text data

[0551] The server uses the Google Translate API to translate the received text in real time based on the language settings of each participant. For example, "The machine needs maintenance" is translated to "The machine needs maintenance."

[0552] Step 5: Send and view translation data

[0553] The translated text data is sent to the terminal of Worker B (Japanese speaker) and displayed on the screen. The translated text data is also played aloud through a speaker.

[0554] Specific examples

[0555] Below is a concrete example of how the system works.

[0556] 1. Worker A says, "The machine needs maintenance."

[0557] 2. A high-definition microphone captures your voice and sends it to a speech recognition processor.

[0558] 3. The Google Speech Recognition API converts the audio data into "The machine needs maintenance."

[0559] 4. The text data is sent to the server via a secure socket communication protocol.

[0560] 5. The Google Translate API translates the text data into "Machine maintenance required."

[0561] 6. The translated text data is sent to Worker B's device and displayed on the screen.

[0562] 7. The translated text data is played back through the speaker as a voice saying, "Machine maintenance is required."

[0563] Prompt example

[0564] Below is a concrete example of a prompt using the Google Speech Recognition API and the Google Translate API.

[0565] Speech recognition prompt:

[0566] Please recognize the following phrase: "The machine needs maintenance".

[0567] Translation prompt:

[0568] Translate the following English text to Japanese: "The machine needs maintenance".

[0569] This will enable workers in a factory who speak different languages ​​to understand each other in real time and communicate smoothly.

[0570] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0571] Step 1:

[0572] When a user speaks into a high-definition microphone, their voice is captured. The input is the user's voice, which is captured as digital voice data by the high-definition microphone. Specifically, worker A speaks, "The machine needs maintenance." This digital voice data is passed to the next processing step.

[0573] Step 2:

[0574] The device sends the captured voice data to a speech recognition processor, which converts the voice data into text using the Google Speech Recognition API. The digital voice data is processed as input, and the text "The machine needs maintenance" is generated as output.

[0575] Step 3:

[0576] The terminal sends the converted text data to the server through a secure socket communication protocol. The input contains the text data "The machine needs maintenance". The output is the same data transmitted to the server.

[0577] Step 4:

[0578] The server uses the Google Translate API to translate the received text data based on the language set by each participant. The input is the text data "The machine needs maintenance," and the output is the translated text data "Machine maintenance is required."

[0579] Step 5:

[0580] The server sends the translated text data to the terminal. At this time, it sends the most appropriate translation data based on the language setting of each participant. The input includes the translated text data "Machine maintenance required." The output is transferred to the terminal.

[0581] Step 6:

[0582] The device displays the received translation data on a display. Specifically, it visually displays the text data "Machine maintenance required." The device also converts the translated text data into audio data and plays it as audio through a speaker. The input includes the translated text data "Machine maintenance required." The output is that this data is displayed on the display and the speaker plays the audio "Machine maintenance required."

[0583] 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.

[0584] The present invention provides a system for facilitating communication between participants who speak different languages ​​in online business meetings, and also combines an emotion engine to recognize the speaker's emotions and improve communication accuracy. The system provides a series of processes: capturing a user's speech in real time, converting the speech data into text data, translating the text data into the language set by each participant, and displaying the translation results and emotional information on each terminal.

[0585] System Configuration

[0586] 1. User voice input

[0587] Terminal: A user speaks through a meeting application.

[0588] Terminal: The speech is captured using a high-precision microphone and prepared for processing as voice data.

[0589] 2. Voice Recognition

[0590] Terminal: The captured voice data is sent to a real-time voice recognition engine, which converts the voice data into text data.

[0591] Terminal: Use a speech recognition engine (e.g., Google Speech Recognition API) to perform the conversion process.

[0592] 3. Emotion analysis

[0593] Terminal: Captured voice data is sent to the emotion engine, which analyzes the speaker's emotional state.

[0594] Device: The emotion engine analyzes the voice data and extracts emotional information such as "anger," "joy," and "sadness."

[0595] 4. Sending text data

[0596] Terminal: The converted text data and analyzed emotion information are sent to the server via a secure communication protocol (e.g., socket communication).

[0597] 5. Translation of text data

[0598] Server: Translates the received text data using an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant.

[0599] Server: Saves the translation results and prepares them for transmission to each participant's device.

[0600] 6. Adding Emotional Information

[0601] Server: Adds emotional information provided by the emotion engine to the translated text data and adds markers indicating emotions to each text.

[0602] 7. Sending and displaying translation data

[0603] Server: Translates the text data and emotion information to each participant's device.

[0604] Terminal: The received translation data and emotion information are displayed on the user interface and shown to participants in real time.

[0605] Example of operation

[0606] Speaker A (English) → User B (Japanese)

[0607] 1. User A says "I am very happy to be here" in a meeting.

[0608] 2. The device captures user A's voice and converts it into voice data.

[0609] 3. The device sends the captured voice data to a real-time voice recognition engine and converts it into text data such as "I am very happy to be here."

[0610] 4. The device sends the voice data to the emotion engine, which analyzes and extracts the emotion of "joy."

[0611] 5. The device sends the converted text data and emotion information to the server.

[0612] 6. The server receives the text data and retrieves User B's preferred language (Japanese) from the database.

[0613] 7. The server sends the text data "I am very happy to be here." to the machine translation engine, which translates it into Japanese and obtains the text data "I am very happy to be here."

[0614] 8. The server adds the emotional information "joy" to the translated text data.

[0615] 9. The server sends the translated text data and emotion information to User B's device.

[0616] 10. User B's device receives the translated data "I'm so happy to be here" and displays the emotional information "joy" on the user interface for User B to see.

[0617] This series of processes allows users who speak different languages ​​to communicate smoothly while understanding the emotions of the other person. The system operates in real time, making multilingual business meetings possible while reducing the burden on users.

[0618] The processing flow will be explained below.

[0619] Step 1:

[0620] The user begins speaking through the meeting application. The microphone on the user's device begins capturing audio.

[0621] Step 2:

[0622] The device temporarily stores the captured voice data and prepares it for transmission to a real-time speech recognition engine (e.g., Google Speech Recognition API).

[0623] Step 3:

[0624] The device uses a real-time speech recognition engine to convert the captured voice data into text data. Specifically, the speech recognition engine analyzes the voice waveform and converts it into corresponding text.

[0625] Step 4:

[0626] The device sends the voice data to the emotion engine, which analyzes the speaker's emotions. The emotion engine analyzes the voice data and extracts emotional information such as "joy," "sadness," and "anger."

[0627] Step 5:

[0628] The converted text data and analyzed emotion information are sent to the server via a secure communication protocol (e.g., socket communication). The text data and emotion information are appropriately formatted and sent.

[0629] Step 6:

[0630] The server receives the text data and emotion information sent from the device, analyzes the received data, and accesses a database or configuration file to identify the preferred language of each participant.

[0631] Step 7:

[0632] The server uses an automatic translation engine (e.g., Google Translate API) to translate the text data into the language set by each participant. The translation engine translates "I am very happy to be here." into "I am very happy to be here."

[0633] Step 8:

[0634] The server adds emotional information provided by the emotion engine to the translated text data and adds markers indicating emotions to each piece of text. For example, adding "(joy)" after "I'm so happy to be here."

[0635] Step 9:

[0636] The server sends the translated text data and emotion information to the appropriate device based on each participant's language settings. The data is properly formatted and sent quickly.

[0637] Step 10:

[0638] The device receives the translation data and emotion information sent from the server, and the received data is analyzed appropriately and displayed on the user interface.

[0639] Step 11:

[0640] The user can check the translation data and emotional information displayed on the device screen and then make the next utterance or action, allowing for smooth sharing of translated communication and emotional information in real time during meetings.

[0641] This process flow not only enables seamless communication between multiple participants who speak different languages, but also makes it easier for each user to understand the emotions of the other speaker. The system operates in real time, reducing the burden on users and supporting efficient multilingual business meetings.

[0642] Example 2

[0643] 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."

[0644] In online business meetings, there is a demand for systems that facilitate smooth communication between participants who speak different languages. Conventional systems convert voice data into text or translate it, but they lack the ability to convey the speaker's emotional information, making it difficult to improve the accuracy of communication and understanding between participants.

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

[0646] In this invention, the server includes means for capturing the speaker's voice, means for converting the captured voice data into text data, means for extracting emotional information from the captured voice data and adding the emotional information to the text data, means for translating the converted text data in real time, means for transmitting the translated text data based on the language set by each participant, and means for displaying the transmitted translated data, thereby enabling participants who speak different languages ​​to communicate while understanding the speaker's emotions in real time.

[0647] The "means for capturing the speaker's voice" is a function for acquiring the user's speech as digital voice data using a device such as a high-precision microphone.

[0648] The "means for converting captured voice data into text data" is a function for inputting the acquired voice data into a voice recognition engine and converting the voice content into text format.

[0649] "Means for translating converted text data in real time" refers to a function for translating text data in real time using software or a service that automatically translates text data into another language.

[0650] The "means for transmitting translated text data based on the language set by each participant" is a function for appropriately transmitting translated text data based on the language set in advance by each participant.

[0651] The "means for displaying the transmitted translation data" is a function for visually displaying the received translation data on the terminal of each participant.

[0652] "Means for extracting emotional information from captured voice data and adding the emotional information to text data" refers to a function that analyzes the emotional state of the speaker from captured voice data using a voice analysis engine or the like and adds the emotional information to the text data.

[0653] This invention is a system for facilitating communication between participants who speak different languages ​​in online business meetings, incorporating an emotion engine that recognizes the speaker's emotions to improve communication accuracy. This system provides a series of processes: capturing a user's speech in real time, converting the speech data into text data, translating the text data into the language set by each participant, and displaying the translation results and emotional information on each terminal.

[0654] Hardware and Software Configuration

[0655] 1. User voice input

[0656] Device: The user speaks through the meeting application. The device uses a high-precision microphone to capture the user's speech and save it as digital audio data.

[0657] 2. Voice Recognition

[0658] Device: Sends captured voice data to a real-time speech recognition engine, such as the Google Speech Recognition API, and converts the speech into text.

[0659] 3. Emotion analysis

[0660] Terminal: Sends voice data to the emotion engine and analyzes the speaker's emotional state. The emotion engine extracts emotional information such as "anger," "joy," and "sadness."

[0661] 4. Sending text data

[0662] Terminal: The converted text data and emotion information are sent to the server via a secure communication protocol (e.g., socket communication).

[0663] 5. Translation of text data

[0664] Server: Translates the received text data using an automatic translation engine such as Google Translate API based on the language settings of each participant. The translation results are saved and prepared for transmission to each participant's device.

[0665] 6. Adding Emotional Information

[0666] Server: Adds emotional information provided by the emotion engine to the translated text data and adds markers indicating emotions to each text.

[0667] 7. Sending and displaying translation data

[0668] Server: Translates the text data and emotional information to each participant's device. Each participant's device displays the received translation data and emotional information on a user interface, allowing participants to see it in real time.

[0669] Specific examples

[0670] Speaker A (English) → User B (Japanese)

[0671] 1. User A says "I am very happy to be here" in a meeting.

[0672] 2. The device captures user A's voice and converts it into voice data.

[0673] 3. The device sends the captured voice data to the Google Speech Recognition API, which converts it into text data such as "I am very happy to be here."

[0674] 4. The device sends the voice data to the emotion engine, which analyzes and extracts the emotion of "joy."

[0675] 5. The device sends the converted text data and emotion information to the server.

[0676] 6. The server receives the text data and retrieves User B's preferred language (Japanese) from the database.

[0677] 7. The server sends the text data "I am very happy to be here." to the Google Translate API, which translates it into Japanese and obtains the text data "I am very happy to be here."

[0678] 8. The server adds the emotion information "joy" to the translated text data. Example: "I'm so happy to be here. [Joy]"

[0679] 9. The server sends the translated text data and emotion information to User B's device.

[0680] 10. User B's device receives the translated data "I'm so happy to be here" and displays the emotional information "joy" on the user interface for User B to see.

[0681] This process allows users who speak different languages ​​to communicate smoothly while understanding each other's emotions. The system operates in real time, making multilingual business meetings possible while reducing the burden on users.

[0682] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0683] Step 1:

[0684] The user speaks

[0685] Terminal: A user speaks through a meeting application. For example, User A says, "I am very happy to be here." This voice is captured by a high-precision microphone and acquired as digital audio data.

[0686] Input: The audio spoken by the user.

[0687] Specific operation: A high-performance microphone captures the user's voice and stores it in memory as audio data.

[0688] Step 2:

[0689] Converting audio data to text data

[0690] On the device: The captured voice data is sent to the Google Speech Recognition API, which converts the speech into text.

[0691] Input: Captured audio data.

[0692] Output: The converted text data "I am very happy to be here."

[0693] Specific operation: The device sends voice data to the Google Speech Recognition API and obtains the text data "I am very happy to be here."

[0694] Step 3:

[0695] Sentiment analysis of voice data

[0696] Terminal: Sends voice data to the emotion engine and analyzes the speaker's emotional state. For example, the emotion engine analyzes and extracts the emotion "joy."

[0697] Input: Transduced text data and captured audio data.

[0698] Output: Analyzed emotion information "joy".

[0699] Specific operation: The device sends voice data to the emotion engine and obtains the emotion information "joy."

[0700] Step 4:

[0701] Text data and emotional information sent to server

[0702] Terminal: The converted text data and analyzed emotion information are sent to the server via a secure communication protocol (e.g., socket communication).

[0703] Input: Text data "I am very happy to be here." and emotion information "joy."

[0704] Output: The data sent to the server.

[0705] Specific operation: The device assembles text data and emotional information into packets and securely transmits them to the server.

[0706] Step 5:

[0707] Text data translation

[0708] Server: Sends the received text data to the Google Translate API and translates it based on the language settings of each participant.

[0709] Input: Text data "I am very happy to be here."

[0710] Output: The translated text "I'm so happy to be here."

[0711] Specific operation: The server sends text data to the Google Translate API and obtains the translated text data.

[0712] Step 6:

[0713] Adding emotional information to text data

[0714] Server: Adds the emotional information "joy" to the translated text data. For example, "I'm so happy to be here. [Joy]."

[0715] Input: Translated text data "I'm so happy to be here" and emotion information "joy".

[0716] Output: Text data with emotional information added: "I'm so happy to be here. [Joy]".

[0717] What it does: The server adds emotion information to the translated text and formats it.

[0718] Step 7:

[0719] Transmitting and displaying translation data and emotional information to the device

[0720] Server: Translates the text data and emotion information to each participant's device.

[0721] Terminal: The received translation data and emotion information are displayed on the user interface and shown to participants in real time.

[0722] Input: Text data with emotional information added: "I'm so happy to be here. [Joy]".

[0723] Output: The displayed translation data and sentiment information.

[0724] Specific operation: The server sends text data with added emotional information to the terminal, which then displays it on the user interface.

[0725] These steps enable participants who speak different languages ​​to communicate in real time while understanding each other's emotions. This system combines speech recognition and emotion analysis using generative AI models with machine translation services to facilitate international business meetings.

[0726] (Application example 2)

[0727] 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."

[0728] When people who speak different languages ​​communicate in the same space, it is difficult not only to translate between languages, but also to convey the speaker's emotions and nuances appropriately. In this situation, it is necessary to improve the accuracy of communication, especially in navigation systems for autonomous vehicles, because understanding the driver's emotions and intentions is directly linked to safety and usability.

[0729] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing the speaker's voice, means for converting the captured voice data into text data, means for translating the converted text data in real time, means for analyzing the speaker's emotional state, means for adding the analyzed emotional information to translation data, means for transmitting the translated text data based on the language set by each participant, and means for displaying the transmitted translation data. This enables smooth communication that includes emotions between users who speak different languages, improving safety and comfort even in navigation systems for autonomous vehicles.

[0730] "Speaker" refers to a person who produces sound.

[0731] "Audio capturing means" refers to a device or system for digitally recording a speaker's voice.

[0732] "Audio Data" means audio information recorded in digital form.

[0733] "Text data" refers to text information converted through speech recognition, translation, etc.

[0734] "Means for converting" refers to the technology or system for converting voice data into text data.

[0735] "Real-time translation means" refers to technologies or systems that instantly convert input text data into a different language.

[0736] "Language set by each participant" refers to the language setting of the user for whom the translation results are to be displayed.

[0737] "Transmitting means" refers to a technology or system that transmits the generated data to other devices or systems via a network.

[0738] "Display means" refers to the technology or system used to present information to the user through a user interface.

[0739] "Means for analyzing emotional state" refers to technologies or systems that analyze the speaker's emotions from voice data.

[0740] "Emotional information" refers to data that indicates the emotional state of the speaker.

[0741] "Means for adding to translated data" refers to technologies and systems that add analyzed emotional information to translated text data.

[0742] "Server" refers to a computing device or system for processing and managing data.

[0743] This invention relates to a multilingual and emotion-sensitive navigation system for autonomous vehicles. The system captures a speaker's voice, converts the voice data into text data, translates it in real time, analyzes the speaker's emotional state, adds the analyzed emotional information to the translated data, transmits it based on the language settings of each participant, and displays the transmitted translated data, thereby enabling smooth, emotion-sensitive communication between users who speak different languages.

[0744] Hardware used

[0745] High-precision microphone

[0746] In-vehicle terminal (including display)

[0747] server

[0748] Software used

[0749] Speech recognition engine (e.g., Google Speech Recognition API)

[0750] Machine translation engine (e.g. Google Translate API)

[0751] Sentiment analysis engine (e.g. emotion_recognition_library)

[0752] Program processing and data processing

[0753] 1. User voice input

[0754] A high-precision microphone connected to the in-vehicle terminal captures the user's speech in real time, and the captured speech is sent to the in-vehicle terminal as voice data.

[0755] 2. Voice Recognition

[0756] The voice data captured by the in-vehicle device is converted into text data using the Google Speech Recognition API.

[0757] 3. Emotion analysis

[0758] The in-vehicle device analyzes the converted text data using the emotion_recognition_library and extracts the speaker's emotional state (e.g., "anger," "joy," "sadness").

[0759] 4. Data Transmission

[0760] The in-vehicle terminal transmits the converted text data and analyzed emotion information to the server using a secure communication protocol (e.g., socket communication).

[0761] 5. Text Translation

[0762] The server translates the received text data using the Google Translate API based on the user's language settings.

[0763] 6. Adding Emotional Information

[0764] The server adds emotional information to the translated text data and adds markers indicating emotions to each text.

[0765] 7. Data transmission and display

[0766] The server sends the translated text data and emotion information to the in-vehicle device, which then displays the received translation data on the display, allowing the user to see it in real time.

[0767] Specific examples

[0768] For example, if a user in an autonomous vehicle says to the navigation system, "I am feeling a bit anxious about the traffic ahead," the system will process it as follows: It captures the audio, uses speech recognition, and converts it into text data: "I am feeling a bit anxious about the traffic ahead." It then extracts the emotional information "anxiety" through emotion analysis and sends it to the server using a secure communication protocol. The server translates the text data into Japanese and generates text data: "I am a bit anxious about the traffic ahead." It adds the emotional information "anxiety" to the translation result and sends it to the in-vehicle device. The in-vehicle device then displays the emotional information "anxiety" on the display, showing it to the user in real time, allowing other passengers and the system to understand the user's emotions and take appropriate action.

[0769] Prompt Sentence Examples

[0770] "Please explain the glossary and multilingual translation process in an in-car navigation system."

[0771] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0772] Step 1:

[0773] User voice input

[0774] In an autonomous vehicle, a user speaks instructions to the navigation system. The voice is captured through a high-precision microphone and input as voice data into the in-vehicle terminal. At this stage, the input data is raw voice data. The in-vehicle terminal uses a voice capture module to convert it into a digital format, ready to be sent to the voice recognition engine.

[0775] Step 2:

[0776] Voice Recognition

[0777] The in-vehicle device sends the captured voice data to a real-time voice recognition engine (e.g., Google Speech Recognition API) and converts the voice data into text data. In this process, the input is the captured voice data and the output is the converted text data. The voice recognition engine analyzes the voice data and generates the corresponding text data.

[0778] Step 3:

[0779] Emotion analysis

[0780] The in-vehicle device sends the text data of the speech recognition results and the original speech data to the emotion engine, which analyzes the speaker's emotional state. At this stage, the input is speech data and text data, and the output is analyzed emotional information. The emotion engine uses a feature extraction algorithm to classify emotions into categories such as "anger," "joy," and "sadness."

[0781] Step 4:

[0782] Data transmission

[0783] The in-vehicle terminal transmits the converted text data and analyzed emotion information to the server using a secure communication protocol. The input is the converted text data and emotion information, and the output is the data transmitted to the server. The data is encrypted before transmission to ensure security.

[0784] Step 5:

[0785] Text Translation

[0786] The server sends the received text data to an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant, and obtains the translated text data. The input is the received text data and the user's language settings, and the output is the translated text data. The translation engine analyzes the source text and generates the corresponding translation.

[0787] Step 6:

[0788] Adding emotional information

[0789] The server adds emotional information to the translated text data using an emotion engine and adds markers indicating emotions to each text. The input is the translated text data and emotional information, and the output is the translated text data with the emotional markers added. The server integrates the emotional markers into the metadata of the text data.

[0790] Step 7:

[0791] Data transmission and display

[0792] The server sends the translated text data and emotion information to the in-vehicle terminal. The in-vehicle terminal displays the received translation data on the display, showing it to the user in real time. The input is emotion information and translated text data, and the output is the information displayed on the in-vehicle terminal's display. The display module receives the data and displays it on the screen.

[0793] As a result, smooth communication between multiple languages, including emotions, can be realized.

[0794] 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.

[0795] 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.

[0796] 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.

[0797] [Third embodiment]

[0798] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0799] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0800] 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).

[0801] 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.

[0802] 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.

[0803] 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).

[0804] 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. 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.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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."

[0810] The present invention provides a system for facilitating communication between participants who speak different languages ​​in online business meetings. The system provides a series of processes for capturing users' speech in real time, converting the speech data into text data, translating the text data into the language set by each participant, and displaying the translation results on each terminal.

[0811] System Configuration

[0812] 1. User voice input

[0813] Terminal: A user speaks through a meeting application.

[0814] Terminal: The speech is captured using a high-precision microphone and prepared for processing as voice data.

[0815] 2. Voice Recognition

[0816] Terminal: The captured voice data is sent to a real-time voice recognition engine, which converts the voice data into text data.

[0817] Device: Conversion process is performed using voice recognition technology such as Google Speech Recognition API.

[0818] 3. Sending text data

[0819] Terminal: The converted text data is sent to the server using a secure communication method (e.g., socket communication).

[0820] 4. Translation of text data

[0821] Server: Translates the received text data using an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant.

[0822] Server: Saves the translation results and prepares them for transmission to each participant's device.

[0823] 5. Sending and displaying translation data

[0824] Server: Translated text data is sent to each device according to the participant's language setting.

[0825] Terminal: The received translation data is displayed on the user interface and shown to participants in real time.

[0826] Example of operation

[0827] Speaker A (English) → User B (Japanese)

[0828] 1. User A says "Hello, how are you?" in a meeting.

[0829] 2. The device captures user A's voice and converts it into voice data.

[0830] 3. The device sends the captured voice data to a real-time voice recognition engine, which converts it into text data such as "Hello, how are you?"

[0831] 4. The device sends the converted text data to the server.

[0832] 5. The server receives the text data and retrieves User B's preferred language (Japanese) from the database.

[0833] 6. The server sends the text data "Hello, how are you?" to the machine translation engine, which translates it into Japanese and obtains the text data "Hello, how are you?"

[0834] 7. The server sends the translated text data to User B's device.

[0835] 8. User B's device displays the received translation data, "Hello, how are you?", on the user interface and shows it to User B.

[0836] This series of processes enables multiple users who speak different languages ​​to communicate smoothly. The system operates in real time, realizing multilingual business meetings while reducing the burden on users.

[0837] The processing flow will be explained below.

[0838] Step 1:

[0839] The user begins speaking through the meeting application. The microphone on the user's device begins capturing audio.

[0840] Step 2:

[0841] The device temporarily stores the captured voice data and prepares it for transmission to a real-time speech recognition engine (e.g., Google Speech Recognition API).

[0842] Step 3:

[0843] The device uses a real-time speech recognition engine to convert the captured voice data into text data. Specifically, the speech recognition engine analyzes the voice waveform and converts it into corresponding text.

[0844] Step 4:

[0845] The terminal sends the converted text data to the server via a secure communication protocol (e.g., socket communication). The text data is properly formatted and sent.

[0846] Step 5:

[0847] The server receives the text data sent from the device, analyzes the received data, and accesses a database or configuration file to identify the preferred language of each participant.

[0848] Step 6:

[0849] The server uses an automatic translation engine (e.g., Google Translate API) to translate the text data into the language set by each participant. The translation engine translates "Hello, how are you?" into "Hello, how are you?"

[0850] Step 7:

[0851] The server transmits the translated text data to the appropriate terminal based on each participant's language setting, and is configured to appropriately format and transmit the translated data.

[0852] Step 8:

[0853] The terminal receives the translation data sent from the server, and the received translation data is appropriately analyzed and displayed on the user interface.

[0854] Step 9:

[0855] The user can check the translation data displayed on the device screen and then make the next utterance or action, enabling smooth communication with translations in real time during meetings.

[0856] This series of processing flows enables seamless online business meetings between multiple participants who speak different languages.

[0857] Example 1

[0858] 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."

[0859] In online business meetings, smooth communication between participants who speak different languages ​​is difficult, and this issue, due to the lack of real-time language translation and proper display, reduces the effectiveness and efficiency of meetings.

[0860] 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.

[0861] In this invention, the server includes means for acquiring the speaker's voice, means for converting the acquired voice data into text data, means for securely transmitting the converted text data, means for transmitting the translated text data based on the language set by each participant, and means for displaying the transmitted translated data, thereby enabling smooth real-time communication between participants who speak different languages.

[0862] A "speaker" is a user who speaks in an online meeting.

[0863] The "means for acquiring voice" refers to a device or software for capturing the voice spoken by the user and storing it as voice data.

[0864] The "means for converting voice data into text data" is a voice recognition technology or engine for converting captured voice data into text form.

[0865] "Means for secure transmission" refers to communication means or protocols for securely transmitting acquired data to another terminal or server.

[0866] A "real-time translation means" is a translation engine or service for rapidly converting text data into different languages.

[0867] "Language set by each participant" refers to the display language set by each user participating in the online meeting.

[0868] The "means for displaying translated data" is a user interface for displaying the translated text on each user's terminal.

[0869] The present invention provides a system for facilitating communication between participants who speak different languages ​​in online business meetings. The system provides a series of processes for capturing users' speech in real time, converting the speech data into text data, translating the text data into the language of each participant, and displaying the translation results on each terminal.

[0870] First, the user speaks using a meeting application. At this time, the user's device uses a high-precision microphone to capture what is being said and stores it as voice data. The captured voice data is sent to a real-time voice recognition engine, which converts the voice data into text data. This voice recognition uses the Google Speech Recognition API.

[0871] The converted text data is then sent to the server using a secure communication method (e.g., socket communication). The server translates the received text data using an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant. The translated text data is then saved and prepared for transmission to each participant's device.

[0872] Finally, the server sends the translated text data to each participant's device, which then displays the received translation data on its user interface, making it available to meeting participants in real time. This allows multiple users who speak different languages ​​to communicate smoothly.

[0873] As a specific example, when speaker A says "Hello, how are you?" in English, the voice data is captured by the device's microphone and converted into text data "Hello, how are you?" by a speech recognition engine. This text data is sent to the server, which translates it into Japanese based on the language setting of user B, generating text data "Hello, how are you?". Finally, this translated text data is sent to user B's device and displayed.

[0874] Examples of prompt statements

[0875] Design a system that translates speech in online business meetings in real time. Generate instructions for a system that meets the following criteria:

[0876] 1. Capture what the user says and convert it into audio data.

[0877] 2. Convert the audio data into text data.

[0878] 3. Send the text data securely to the server.

[0879] 4. The server uses a translation engine to translate the text data into the user's specified language.

[0880] 5. The translation results are sent to each user's device and displayed in real time.

[0881] This system allows smooth communication between users who speak different languages, and real-time translation minimizes time loss, enabling efficient business meetings.

[0882] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0883] Program processing flow

[0884] Step 1:

[0885] A user speaks using a meeting application. The input is the user's voice, and the output is the audio data captured by the device's microphone. In concrete terms, User A speaks, "Hello, how are you?"

[0886] Step 2:

[0887] The device uses a high-precision microphone to capture the speech as voice data. The input is the voice data generated in step 1, and the output is the captured voice data. Specifically, the device's microphone records User A's voice.

[0888] Step 3:

[0889] The device sends the captured voice data to a real-time voice recognition engine. The input is the captured voice data, and the output is text data generated by the voice recognition engine. Specifically, the device sends the voice data in real time to the Google Speech Recognition API, which generates the text data "Hello, how are you?"

[0890] Step 4:

[0891] The terminal sends the converted text data to the server using a secure communication method (e.g., socket communication). The input is text data, and the output is text data sent to the server. Specifically, the terminal sends the text data "Hello, how are you?" to the server.

[0892] Step 5:

[0893] The server sends the received text data to an automatic translation engine based on the language setting of each participant. The input is the text data and the participant's language setting information, and the output is the translated text data. Specifically, the server sends the text data to the Google Translate API, which translates "Hello, how are you?" into Japanese "Hello, how are you?"

[0894] Step 6:

[0895] The server uses a translation engine to save the translated text data and prepares it to be sent to each participant's device. The input is the translated text data, and the output is the text data prepared for sending. Specifically, the server saves the translated data for "Hello, how are you?" and generates data to be sent to the device.

[0896] Step 7:

[0897] The server sends the translated text data to each device according to the participant's language setting. The input is the text data prepared for transmission, and the output is the translated data sent to each device. In concrete terms, the server sends the data "Hello, how are you?" to User B's device.

[0898] Step 8:

[0899] The device displays the received translation data on the user interface and shows it to the participants in real time. The input is the received translation data, and the output is the translated text displayed on the device's user interface. Specifically, User B's device displays "Hello, how are you?"

[0900] (Application example 1)

[0901] 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."

[0902] In factories, communication between workers who speak different languages ​​is often difficult, which can hinder work efficiency and safety. Language barriers can be a serious obstacle, especially when sharing emergency instructions or complex work procedures. Technology is needed to solve this problem and improve work efficiency and safety.

[0903] 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.

[0904] In this invention, the server includes means for capturing the speaker's voice, means for converting the captured voice data into text data, means for translating the converted text data in real time, means for transmitting the translated text data based on the language set by each participant, means for displaying the transmitted translated data, means for supporting communication between workers who speak different languages, and means for converting the translated text data into voice and playing it back on a speaker. This enables workers in a factory who speak different languages ​​to understand each other in real time and communicate smoothly.

[0905] "Speaker" refers to a person who produces sound.

[0906] "Voice data" refers to data that is a digital recording of a speaker's voice.

[0907] "Text data" refers to digital data that has been converted from audio data into text.

[0908] "Real-time" refers to processing that occurs almost immediately, without delay.

[0909] "Translation" refers to converting text data expressed in one language into another language.

[0910] "Preferred language" refers to the language that the user of the system has selected to use.

[0911] "Send" refers to the act of moving data from one device to another.

[0912] "Display" refers to the output of digital data in a visually perceptible form.

[0913] "In-factory" refers to the interior of an industrial facility where manufacturing or assembly takes place.

[0914] "Worker" refers to a worker who performs work within a factory.

[0915] "Supporting communication" refers to providing assistance to facilitate smooth communication.

[0916] A "speaker" refers to a device for outputting audio data as sound waves.

[0917] "Convert to audio" refers to converting text data into audio format data.

[0918] This invention is a system for supporting communication between workers who speak different languages ​​in a factory. This system includes the following components:

[0919] Hardware

[0920] High-definition microphone: Used to capture the speaker's voice.

[0921] Speech Recognition Processor: Used to process captured voice data and convert it into text data.

[0922] Server: Translates the converted text data and sends the translated data based on the language setting of each participant.

[0923] Display: Used to visually display the translated text data.

[0924] Speaker: Used to play back the translated text data as audio.

[0925] software

[0926] Speech recognition engine: Uses the Google Speech Recognition API or similar to convert captured voice data into text data.

[0927] Translation engine: Translates text data in real time using APIs such as Google Translate.

[0928] Data communication: A secure socket communication protocol for sending and receiving converted text data and translation data.

[0929] Robot control system: The entire system is controlled in an integrated manner using ROS (Robot Operating System).

[0930] System Operation Description

[0931] Step 1: Voice Input

[0932] When a user speaks into the microphone, the voice data is captured by a high-precision microphone. For example, Worker A (an English speaker) speaks, "The machine needs maintenance."

[0933] Step 2: Voice Recognition

[0934] The captured voice data is sent to a speech recognition processor and converted into text data in real time using the Google Speech Recognition API. In this case, the voice data is converted into the text data "The machine needs maintenance."

[0935] Step 3: Send data

[0936] The converted text data is sent to the server using a secure socket communication protocol.

[0937] Step 4: Translating the text data

[0938] The server uses the Google Translate API to translate the received text in real time based on the language settings of each participant. For example, "The machine needs maintenance" is translated to "The machine needs maintenance."

[0939] Step 5: Send and view translation data

[0940] The translated text data is sent to the terminal of Worker B (Japanese speaker) and displayed on the screen. The translated text data is also played aloud through a speaker.

[0941] Specific examples

[0942] Below is a concrete example of how the system works.

[0943] 1. Worker A says, "The machine needs maintenance."

[0944] 2. A high-definition microphone captures your voice and sends it to a speech recognition processor.

[0945] 3. The Google Speech Recognition API converts the audio data into "The machine needs maintenance."

[0946] 4. The text data is sent to the server via a secure socket communication protocol.

[0947] 5. The Google Translate API translates the text data into "Machine maintenance required."

[0948] 6. The translated text data is sent to Worker B's device and displayed on the screen.

[0949] 7. The translated text data is played back through the speaker as a voice saying, "Machine maintenance is required."

[0950] Prompt example

[0951] Below is a concrete example of a prompt using the Google Speech Recognition API and the Google Translate API.

[0952] Speech recognition prompt:

[0953] Please recognize the following phrase: "The machine needs maintenance".

[0954] Translation prompt:

[0955] Translate the following English text to Japanese: "The machine needs maintenance".

[0956] This will enable workers in a factory who speak different languages ​​to understand each other in real time and communicate smoothly.

[0957] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0958] Step 1:

[0959] When a user speaks into a high-definition microphone, their voice is captured. The input is the user's voice, which is captured as digital voice data by the high-definition microphone. Specifically, worker A speaks, "The machine needs maintenance." This digital voice data is passed to the next processing step.

[0960] Step 2:

[0961] The device sends the captured voice data to a speech recognition processor, which converts the voice data into text using the Google Speech Recognition API. The digital voice data is processed as input, and the text "The machine needs maintenance" is generated as output.

[0962] Step 3:

[0963] The terminal sends the converted text data to the server through a secure socket communication protocol. The input contains the text data "The machine needs maintenance". The output is the same data transmitted to the server.

[0964] Step 4:

[0965] The server uses the Google Translate API to translate the received text data based on the language set by each participant. The input is the text data "The machine needs maintenance," and the output is the translated text data "Machine maintenance is required."

[0966] Step 5:

[0967] The server sends the translated text data to the terminal. At this time, it sends the most appropriate translation data based on the language setting of each participant. The input includes the translated text data "Machine maintenance required." The output is transferred to the terminal.

[0968] Step 6:

[0969] The device displays the received translation data on a display. Specifically, it visually displays the text data "Machine maintenance required." The device also converts the translated text data into audio data and plays it as audio through a speaker. The input includes the translated text data "Machine maintenance required." The output is that this data is displayed on the display and the speaker plays the audio "Machine maintenance required."

[0970] 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.

[0971] The present invention provides a system for facilitating communication between participants who speak different languages ​​in online business meetings, and also combines an emotion engine to recognize the speaker's emotions and improve communication accuracy. The system provides a series of processes: capturing a user's speech in real time, converting the speech data into text data, translating the text data into the language set by each participant, and displaying the translation results and emotional information on each terminal.

[0972] System Configuration

[0973] 1. User voice input

[0974] Terminal: A user speaks through a meeting application.

[0975] Terminal: The speech is captured using a high-precision microphone and prepared for processing as voice data.

[0976] 2. Voice Recognition

[0977] Terminal: The captured voice data is sent to a real-time voice recognition engine, which converts the voice data into text data.

[0978] Terminal: Use a speech recognition engine (e.g., Google Speech Recognition API) to perform the conversion process.

[0979] 3. Emotion analysis

[0980] Terminal: Captured voice data is sent to the emotion engine, which analyzes the speaker's emotional state.

[0981] Device: The emotion engine analyzes the voice data and extracts emotional information such as "anger," "joy," and "sadness."

[0982] 4. Sending text data

[0983] Terminal: The converted text data and analyzed emotion information are sent to the server via a secure communication protocol (e.g., socket communication).

[0984] 5. Translation of text data

[0985] Server: Translates the received text data using an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant.

[0986] Server: Saves the translation results and prepares them for transmission to each participant's device.

[0987] 6. Adding Emotional Information

[0988] Server: Adds emotional information provided by the emotion engine to the translated text data and adds markers indicating emotions to each text.

[0989] 7. Sending and displaying translation data

[0990] Server: Translates the text data and emotion information to each participant's device.

[0991] Terminal: The received translation data and emotion information are displayed on the user interface and shown to participants in real time.

[0992] Example of operation

[0993] Speaker A (English) → User B (Japanese)

[0994] 1. User A says "I am very happy to be here" in a meeting.

[0995] 2. The device captures user A's voice and converts it into voice data.

[0996] 3. The device sends the captured voice data to a real-time voice recognition engine and converts it into text data such as "I am very happy to be here."

[0997] 4. The device sends the voice data to the emotion engine, which analyzes and extracts the emotion of "joy."

[0998] 5. The device sends the converted text data and emotion information to the server.

[0999] 6. The server receives the text data and retrieves User B's preferred language (Japanese) from the database.

[1000] 7. The server sends the text data "I am very happy to be here." to the machine translation engine, which translates it into Japanese and obtains the text data "I am very happy to be here."

[1001] 8. The server adds the emotional information "joy" to the translated text data.

[1002] 9. The server sends the translated text data and emotion information to User B's device.

[1003] 10. User B's device receives the translated data "I'm so happy to be here" and displays the emotional information "joy" on the user interface for User B to see.

[1004] This series of processes allows users who speak different languages ​​to communicate smoothly while understanding the emotions of the other person. The system operates in real time, making multilingual business meetings possible while reducing the burden on users.

[1005] The processing flow will be explained below.

[1006] Step 1:

[1007] The user begins speaking through the meeting application. The microphone on the user's device begins capturing audio.

[1008] Step 2:

[1009] The device temporarily stores the captured voice data and prepares it for transmission to a real-time speech recognition engine (e.g., Google Speech Recognition API).

[1010] Step 3:

[1011] The device uses a real-time speech recognition engine to convert the captured voice data into text data. Specifically, the speech recognition engine analyzes the voice waveform and converts it into corresponding text.

[1012] Step 4:

[1013] The device sends the voice data to the emotion engine, which analyzes the speaker's emotions. The emotion engine analyzes the voice data and extracts emotional information such as "joy," "sadness," and "anger."

[1014] Step 5:

[1015] The converted text data and analyzed emotion information are sent to the server via a secure communication protocol (e.g., socket communication). The text data and emotion information are appropriately formatted and sent.

[1016] Step 6:

[1017] The server receives the text data and emotion information sent from the device, analyzes the received data, and accesses a database or configuration file to identify the preferred language of each participant.

[1018] Step 7:

[1019] The server uses an automatic translation engine (e.g., Google Translate API) to translate the text data into the language set by each participant. The translation engine translates "I am very happy to be here." into "I am very happy to be here."

[1020] Step 8:

[1021] The server adds emotional information provided by the emotion engine to the translated text data and adds markers indicating emotions to each piece of text. For example, adding "(joy)" after "I'm so happy to be here."

[1022] Step 9:

[1023] The server sends the translated text data and emotion information to the appropriate device based on each participant's language settings. The data is properly formatted and sent quickly.

[1024] Step 10:

[1025] The device receives the translation data and emotion information sent from the server, and the received data is analyzed appropriately and displayed on the user interface.

[1026] Step 11:

[1027] The user can check the translation data and emotional information displayed on the device screen and then make the next utterance or action, allowing for smooth sharing of translated communication and emotional information in real time during meetings.

[1028] This process flow not only enables seamless communication between multiple participants who speak different languages, but also makes it easier for each user to understand the emotions of the other speaker. The system operates in real time, reducing the burden on users and supporting efficient multilingual business meetings.

[1029] Example 2

[1030] 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."

[1031] In online business meetings, there is a demand for systems that facilitate smooth communication between participants who speak different languages. Conventional systems convert voice data into text or translate it, but they lack the ability to convey the speaker's emotional information, making it difficult to improve the accuracy of communication and understanding between participants.

[1032] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1033] In this invention, the server includes means for capturing the speaker's voice, means for converting the captured voice data into text data, means for extracting emotional information from the captured voice data and adding the emotional information to the text data, means for translating the converted text data in real time, means for transmitting the translated text data based on the language set by each participant, and means for displaying the transmitted translated data, thereby enabling participants who speak different languages ​​to communicate while understanding the speaker's emotions in real time.

[1034] The "means for capturing the speaker's voice" is a function for acquiring the user's speech as digital voice data using a device such as a high-precision microphone.

[1035] The "means for converting captured voice data into text data" is a function for inputting the acquired voice data into a voice recognition engine and converting the voice content into text format.

[1036] "Means for translating converted text data in real time" refers to a function for translating text data in real time using software or a service that automatically translates text data into another language.

[1037] The "means for transmitting translated text data based on the language set by each participant" is a function for appropriately transmitting translated text data based on the language set in advance by each participant.

[1038] The "means for displaying the transmitted translation data" is a function for visually displaying the received translation data on the terminal of each participant.

[1039] "Means for extracting emotional information from captured voice data and adding the emotional information to text data" refers to a function that analyzes the emotional state of the speaker from captured voice data using a voice analysis engine or the like and adds the emotional information to the text data.

[1040] This invention is a system for facilitating communication between participants who speak different languages ​​in online business meetings, incorporating an emotion engine that recognizes the speaker's emotions to improve communication accuracy. This system provides a series of processes: capturing a user's speech in real time, converting the speech data into text data, translating the text data into the language set by each participant, and displaying the translation results and emotional information on each terminal.

[1041] Hardware and Software Configuration

[1042] 1. User voice input

[1043] Device: The user speaks through the meeting application. The device uses a high-precision microphone to capture the user's speech and save it as digital audio data.

[1044] 2. Voice Recognition

[1045] Device: Sends captured voice data to a real-time speech recognition engine, such as the Google Speech Recognition API, and converts the speech into text.

[1046] 3. Emotion analysis

[1047] Terminal: Sends voice data to the emotion engine and analyzes the speaker's emotional state. The emotion engine extracts emotional information such as "anger," "joy," and "sadness."

[1048] 4. Sending text data

[1049] Terminal: The converted text data and emotion information are sent to the server via a secure communication protocol (e.g., socket communication).

[1050] 5. Translation of text data

[1051] Server: Translates the received text data using an automatic translation engine such as Google Translate API based on the language settings of each participant. The translation results are saved and prepared for transmission to each participant's device.

[1052] 6. Adding Emotional Information

[1053] Server: Adds emotional information provided by the emotion engine to the translated text data and adds markers indicating emotions to each text.

[1054] 7. Sending and displaying translation data

[1055] Server: Translates the text data and emotional information to each participant's device. Each participant's device displays the received translation data and emotional information on a user interface, allowing participants to see it in real time.

[1056] Specific examples

[1057] Speaker A (English) → User B (Japanese)

[1058] 1. User A says "I am very happy to be here" in a meeting.

[1059] 2. The device captures user A's voice and converts it into voice data.

[1060] 3. The device sends the captured voice data to the Google Speech Recognition API, which converts it into text data such as "I am very happy to be here."

[1061] 4. The device sends the voice data to the emotion engine, which analyzes and extracts the emotion of "joy."

[1062] 5. The device sends the converted text data and emotion information to the server.

[1063] 6. The server receives the text data and retrieves User B's preferred language (Japanese) from the database.

[1064] 7. The server sends the text data "I am very happy to be here." to the Google Translate API, which translates it into Japanese and obtains the text data "I am very happy to be here."

[1065] 8. The server adds the emotion information "joy" to the translated text data. Example: "I'm so happy to be here. [Joy]"

[1066] 9. The server sends the translated text data and emotion information to User B's device.

[1067] 10. User B's device receives the translated data "I'm so happy to be here" and displays the emotional information "joy" on the user interface for User B to see.

[1068] This process allows users who speak different languages ​​to communicate smoothly while understanding each other's emotions. The system operates in real time, making multilingual business meetings possible while reducing the burden on users.

[1069] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1070] Step 1:

[1071] The user speaks

[1072] Terminal: A user speaks through a meeting application. For example, User A says, "I am very happy to be here." This voice is captured by a high-precision microphone and acquired as digital audio data.

[1073] Input: The audio spoken by the user.

[1074] Specific operation: A high-performance microphone captures the user's voice and stores it in memory as audio data.

[1075] Step 2:

[1076] Converting audio data to text data

[1077] On the device: The captured voice data is sent to the Google Speech Recognition API, which converts the speech into text.

[1078] Input: Captured audio data.

[1079] Output: The converted text data "I am very happy to be here."

[1080] Specific operation: The device sends voice data to the Google Speech Recognition API and obtains the text data "I am very happy to be here."

[1081] Step 3:

[1082] Sentiment analysis of voice data

[1083] Terminal: Sends voice data to the emotion engine and analyzes the speaker's emotional state. For example, the emotion engine analyzes and extracts the emotion "joy."

[1084] Input: Transduced text data and captured audio data.

[1085] Output: Analyzed emotion information "joy".

[1086] Specific operation: The device sends voice data to the emotion engine and obtains the emotion information "joy."

[1087] Step 4:

[1088] Text data and emotional information sent to server

[1089] Terminal: The converted text data and analyzed emotion information are sent to the server via a secure communication protocol (e.g., socket communication).

[1090] Input: Text data "I am very happy to be here." and emotion information "joy."

[1091] Output: The data sent to the server.

[1092] Specific operation: The device assembles text data and emotional information into packets and securely transmits them to the server.

[1093] Step 5:

[1094] Text data translation

[1095] Server: Sends the received text data to the Google Translate API and translates it based on the language settings of each participant.

[1096] Input: Text data "I am very happy to be here."

[1097] Output: The translated text "I'm so happy to be here."

[1098] Specific operation: The server sends text data to the Google Translate API and obtains the translated text data.

[1099] Step 6:

[1100] Adding emotional information to text data

[1101] Server: Adds the emotional information "joy" to the translated text data. For example, "I'm so happy to be here. [Joy]."

[1102] Input: Translated text data "I'm so happy to be here" and emotion information "joy".

[1103] Output: Text data with emotional information added: "I'm so happy to be here. [Joy]".

[1104] What it does: The server adds emotion information to the translated text and formats it.

[1105] Step 7:

[1106] Transmitting and displaying translation data and emotional information to the device

[1107] Server: Translates the text data and emotion information to each participant's device.

[1108] Terminal: The received translation data and emotion information are displayed on the user interface and shown to participants in real time.

[1109] Input: Text data with emotional information added: "I'm so happy to be here. [Joy]".

[1110] Output: The displayed translation data and sentiment information.

[1111] Specific operation: The server sends text data with added emotional information to the terminal, which then displays it on the user interface.

[1112] These steps enable participants who speak different languages ​​to communicate in real time while understanding each other's emotions. This system combines speech recognition and emotion analysis using generative AI models with machine translation services to facilitate international business meetings.

[1113] (Application example 2)

[1114] 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."

[1115] When people who speak different languages ​​communicate in the same space, it is difficult not only to translate between languages, but also to convey the speaker's emotions and nuances appropriately. In this situation, it is necessary to improve the accuracy of communication, especially in navigation systems for autonomous vehicles, because understanding the driver's emotions and intentions is directly linked to safety and usability.

[1116] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing the speaker's voice, means for converting the captured voice data into text data, means for translating the converted text data in real time, means for analyzing the speaker's emotional state, means for adding the analyzed emotional information to translation data, means for transmitting the translated text data based on the language set by each participant, and means for displaying the transmitted translation data. This enables smooth communication that includes emotions between users who speak different languages, improving safety and comfort even in navigation systems for autonomous vehicles.

[1117] "Speaker" refers to a person who produces sound.

[1118] "Audio capturing means" refers to a device or system for digitally recording a speaker's voice.

[1119] "Audio Data" means audio information recorded in digital form.

[1120] "Text data" refers to text information converted through speech recognition, translation, etc.

[1121] "Means for converting" refers to the technology or system for converting voice data into text data.

[1122] "Real-time translation means" refers to technologies or systems that instantly convert input text data into a different language.

[1123] "Language set by each participant" refers to the language setting of the user for whom the translation results are to be displayed.

[1124] "Transmitting means" refers to a technology or system that transmits the generated data to other devices or systems via a network.

[1125] "Display means" refers to the technology or system used to present information to the user through a user interface.

[1126] "Means for analyzing emotional state" refers to technologies or systems that analyze the speaker's emotions from voice data.

[1127] "Emotional information" refers to data that indicates the emotional state of the speaker.

[1128] "Means for adding to translated data" refers to technologies and systems that add analyzed emotional information to translated text data.

[1129] "Server" refers to a computing device or system for processing and managing data.

[1130] This invention relates to a multilingual and emotion-sensitive navigation system for autonomous vehicles. The system captures a speaker's voice, converts the voice data into text data, translates it in real time, analyzes the speaker's emotional state, adds the analyzed emotional information to the translated data, transmits it based on the language settings of each participant, and displays the transmitted translated data, thereby enabling smooth, emotion-sensitive communication between users who speak different languages.

[1131] Hardware used

[1132] High-precision microphone

[1133] In-vehicle terminal (including display)

[1134] server

[1135] Software used

[1136] Speech recognition engine (e.g., Google Speech Recognition API)

[1137] Machine translation engine (e.g. Google Translate API)

[1138] Sentiment analysis engine (e.g. emotion_recognition_library)

[1139] Program processing and data processing

[1140] 1. User voice input

[1141] A high-precision microphone connected to the in-vehicle terminal captures the user's speech in real time, and the captured speech is sent to the in-vehicle terminal as voice data.

[1142] 2. Voice Recognition

[1143] The voice data captured by the in-vehicle device is converted into text data using the Google Speech Recognition API.

[1144] 3. Emotion analysis

[1145] The in-vehicle device analyzes the converted text data using the emotion_recognition_library and extracts the speaker's emotional state (e.g., "anger," "joy," "sadness").

[1146] 4. Data Transmission

[1147] The in-vehicle terminal transmits the converted text data and analyzed emotion information to the server using a secure communication protocol (e.g., socket communication).

[1148] 5. Text Translation

[1149] The server translates the received text data using the Google Translate API based on the user's language settings.

[1150] 6. Adding Emotional Information

[1151] The server adds emotional information to the translated text data and adds markers indicating emotions to each text.

[1152] 7. Data transmission and display

[1153] The server sends the translated text data and emotion information to the in-vehicle device, which then displays the received translation data on the display, allowing the user to see it in real time.

[1154] Specific examples

[1155] For example, if a user in an autonomous vehicle says to the navigation system, "I am feeling a bit anxious about the traffic ahead," the system will process it as follows: It captures the audio, uses speech recognition, and converts it into text data: "I am feeling a bit anxious about the traffic ahead." It then extracts the emotional information "anxiety" through emotion analysis and sends it to the server using a secure communication protocol. The server translates the text data into Japanese and generates text data: "I am a bit anxious about the traffic ahead." It adds the emotional information "anxiety" to the translation result and sends it to the in-vehicle device. The in-vehicle device then displays the emotional information "anxiety" on the display, showing it to the user in real time, allowing other passengers and the system to understand the user's emotions and take appropriate action.

[1156] Prompt Sentence Examples

[1157] "Please explain the glossary and multilingual translation process in an in-car navigation system."

[1158] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1159] Step 1:

[1160] User voice input

[1161] In an autonomous vehicle, a user speaks instructions to the navigation system. The voice is captured through a high-precision microphone and input as voice data into the in-vehicle terminal. At this stage, the input data is raw voice data. The in-vehicle terminal uses a voice capture module to convert it into a digital format, ready to be sent to the voice recognition engine.

[1162] Step 2:

[1163] Voice Recognition

[1164] The in-vehicle device sends the captured voice data to a real-time voice recognition engine (e.g., Google Speech Recognition API) and converts the voice data into text data. In this process, the input is the captured voice data and the output is the converted text data. The voice recognition engine analyzes the voice data and generates the corresponding text data.

[1165] Step 3:

[1166] Emotion analysis

[1167] The in-vehicle device sends the text data of the speech recognition results and the original speech data to the emotion engine, which analyzes the speaker's emotional state. At this stage, the input is speech data and text data, and the output is analyzed emotional information. The emotion engine uses a feature extraction algorithm to classify emotions into categories such as "anger," "joy," and "sadness."

[1168] Step 4:

[1169] Data transmission

[1170] The in-vehicle terminal transmits the converted text data and analyzed emotion information to the server using a secure communication protocol. The input is the converted text data and emotion information, and the output is the data transmitted to the server. The data is encrypted before transmission to ensure security.

[1171] Step 5:

[1172] Text Translation

[1173] The server sends the received text data to an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant, and obtains the translated text data. The input is the received text data and the user's language settings, and the output is the translated text data. The translation engine analyzes the source text and generates the corresponding translation.

[1174] Step 6:

[1175] Adding emotional information

[1176] The server adds emotional information to the translated text data using an emotion engine and adds markers indicating emotions to each text. The input is the translated text data and emotional information, and the output is the translated text data with the emotional markers added. The server integrates the emotional markers into the metadata of the text data.

[1177] Step 7:

[1178] Data transmission and display

[1179] The server sends the translated text data and emotion information to the in-vehicle terminal. The in-vehicle terminal displays the received translation data on the display, showing it to the user in real time. The input is emotion information and translated text data, and the output is the information displayed on the in-vehicle terminal's display. The display module receives the data and displays it on the screen.

[1180] As a result, smooth communication between multiple languages, including emotions, can be realized.

[1181] 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.

[1182] 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.

[1183] 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.

[1184] [Fourth embodiment]

[1185] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1186] 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.

[1187] 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).

[1188] 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.

[1189] 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.

[1190] 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).

[1191] 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. 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.

[1192] 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.

[1193] 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.

[1194] 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.

[1195] 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.

[1196] 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.

[1197] 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."

[1198] The present invention provides a system for facilitating communication between participants who speak different languages ​​in online business meetings. The system provides a series of processes for capturing users' speech in real time, converting the speech data into text data, translating the text data into the language set by each participant, and displaying the translation results on each terminal.

[1199] System Configuration

[1200] 1. User voice input

[1201] Terminal: A user speaks through a meeting application.

[1202] Terminal: The speech is captured using a high-precision microphone and prepared for processing as voice data.

[1203] 2. Voice Recognition

[1204] Terminal: The captured voice data is sent to a real-time voice recognition engine, which converts the voice data into text data.

[1205] Device: Conversion process is performed using voice recognition technology such as Google Speech Recognition API.

[1206] 3. Sending text data

[1207] Terminal: The converted text data is sent to the server using a secure communication method (e.g., socket communication).

[1208] 4. Translation of text data

[1209] Server: Translates the received text data using an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant.

[1210] Server: Saves the translation results and prepares them for transmission to each participant's device.

[1211] 5. Sending and displaying translation data

[1212] Server: Translated text data is sent to each device according to the participant's language setting.

[1213] Terminal: The received translation data is displayed on the user interface and shown to participants in real time.

[1214] Example of operation

[1215] Speaker A (English) → User B (Japanese)

[1216] 1. User A says "Hello, how are you?" in a meeting.

[1217] 2. The device captures user A's voice and converts it into voice data.

[1218] 3. The device sends the captured voice data to a real-time voice recognition engine, which converts it into text data such as "Hello, how are you?"

[1219] 4. The device sends the converted text data to the server.

[1220] 5. The server receives the text data and retrieves User B's preferred language (Japanese) from the database.

[1221] 6. The server sends the text data "Hello, how are you?" to the machine translation engine, which translates it into Japanese and obtains the text data "Hello, how are you?"

[1222] 7. The server sends the translated text data to User B's device.

[1223] 8. User B's device displays the received translation data, "Hello, how are you?", on the user interface and shows it to User B.

[1224] This series of processes enables multiple users who speak different languages ​​to communicate smoothly. The system operates in real time, realizing multilingual business meetings while reducing the burden on users.

[1225] The processing flow will be explained below.

[1226] Step 1:

[1227] The user begins speaking through the meeting application. The microphone on the user's device begins capturing audio.

[1228] Step 2:

[1229] The device temporarily stores the captured voice data and prepares it for transmission to a real-time speech recognition engine (e.g., Google Speech Recognition API).

[1230] Step 3:

[1231] The device uses a real-time speech recognition engine to convert the captured voice data into text data. Specifically, the speech recognition engine analyzes the voice waveform and converts it into corresponding text.

[1232] Step 4:

[1233] The terminal sends the converted text data to the server via a secure communication protocol (e.g., socket communication). The text data is properly formatted and sent.

[1234] Step 5:

[1235] The server receives the text data sent from the device, analyzes the received data, and accesses a database or configuration file to identify the preferred language of each participant.

[1236] Step 6:

[1237] The server uses an automatic translation engine (e.g., Google Translate API) to translate the text data into the language set by each participant. The translation engine translates "Hello, how are you?" into "Hello, how are you?"

[1238] Step 7:

[1239] The server transmits the translated text data to the appropriate terminal based on each participant's language setting, and is configured to appropriately format and transmit the translated data.

[1240] Step 8:

[1241] The terminal receives the translation data sent from the server, and the received translation data is appropriately analyzed and displayed on the user interface.

[1242] Step 9:

[1243] The user can check the translation data displayed on the device screen and then make the next utterance or action, enabling smooth communication with translations in real time during meetings.

[1244] This series of processing flows enables seamless online business meetings between multiple participants who speak different languages.

[1245] Example 1

[1246] 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."

[1247] In online business meetings, smooth communication between participants who speak different languages ​​is difficult, and this issue, due to the lack of real-time language translation and proper display, reduces the effectiveness and efficiency of meetings.

[1248] 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.

[1249] In this invention, the server includes means for acquiring the speaker's voice, means for converting the acquired voice data into text data, means for securely transmitting the converted text data, means for transmitting the translated text data based on the language set by each participant, and means for displaying the transmitted translated data, thereby enabling smooth real-time communication between participants who speak different languages.

[1250] A "speaker" is a user who speaks in an online meeting.

[1251] The "means for acquiring voice" refers to a device or software for capturing the voice spoken by the user and storing it as voice data.

[1252] The "means for converting voice data into text data" is a voice recognition technology or engine for converting captured voice data into text form.

[1253] "Means for secure transmission" refers to communication means or protocols for securely transmitting acquired data to another terminal or server.

[1254] A "real-time translation means" is a translation engine or service for rapidly converting text data into different languages.

[1255] "Language set by each participant" refers to the display language set by each user participating in the online meeting.

[1256] The "means for displaying translated data" is a user interface for displaying the translated text on each user's terminal.

[1257] The present invention provides a system for facilitating communication between participants who speak different languages ​​in online business meetings. The system provides a series of processes for capturing users' speech in real time, converting the speech data into text data, translating the text data into the language of each participant, and displaying the translation results on each terminal.

[1258] First, the user speaks using a meeting application. At this time, the user's device uses a high-precision microphone to capture what is being said and stores it as voice data. The captured voice data is sent to a real-time voice recognition engine, which converts the voice data into text data. This voice recognition uses the Google Speech Recognition API.

[1259] The converted text data is then sent to the server using a secure communication method (e.g., socket communication). The server translates the received text data using an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant. The translated text data is then saved and prepared for transmission to each participant's device.

[1260] Finally, the server sends the translated text data to each participant's device, which then displays the received translation data on its user interface, making it available to meeting participants in real time. This allows multiple users who speak different languages ​​to communicate smoothly.

[1261] As a specific example, when speaker A says "Hello, how are you?" in English, the voice data is captured by the device's microphone and converted into text data "Hello, how are you?" by a speech recognition engine. This text data is sent to the server, which translates it into Japanese based on the language setting of user B, generating text data "Hello, how are you?". Finally, this translated text data is sent to user B's device and displayed.

[1262] Examples of prompt statements

[1263] Design a system that translates speech in online business meetings in real time. Generate instructions for a system that meets the following criteria:

[1264] 1. Capture what the user says and convert it into audio data.

[1265] 2. Convert the audio data into text data.

[1266] 3. Send the text data securely to the server.

[1267] 4. The server uses a translation engine to translate the text data into the user's specified language.

[1268] 5. The translation results are sent to each user's device and displayed in real time.

[1269] This system allows smooth communication between users who speak different languages, and real-time translation minimizes time loss, enabling efficient business meetings.

[1270] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1271] Program processing flow

[1272] Step 1:

[1273] A user speaks using a meeting application. The input is the user's voice, and the output is the audio data captured by the device's microphone. In concrete terms, User A speaks, "Hello, how are you?"

[1274] Step 2:

[1275] The device uses a high-precision microphone to capture the speech as voice data. The input is the voice data generated in step 1, and the output is the captured voice data. Specifically, the device's microphone records User A's voice.

[1276] Step 3:

[1277] The device sends the captured voice data to a real-time voice recognition engine. The input is the captured voice data, and the output is text data generated by the voice recognition engine. Specifically, the device sends the voice data in real time to the Google Speech Recognition API, which generates the text data "Hello, how are you?"

[1278] Step 4:

[1279] The terminal sends the converted text data to the server using a secure communication method (e.g., socket communication). The input is text data, and the output is text data sent to the server. Specifically, the terminal sends the text data "Hello, how are you?" to the server.

[1280] Step 5:

[1281] The server sends the received text data to an automatic translation engine based on the language setting of each participant. The input is the text data and the participant's language setting information, and the output is the translated text data. Specifically, the server sends the text data to the Google Translate API, which translates "Hello, how are you?" into Japanese "Hello, how are you?"

[1282] Step 6:

[1283] The server uses a translation engine to save the translated text data and prepares it to be sent to each participant's device. The input is the translated text data, and the output is the text data prepared for sending. Specifically, the server saves the translated data for "Hello, how are you?" and generates data to be sent to the device.

[1284] Step 7:

[1285] The server sends the translated text data to each device according to the participant's language setting. The input is the text data prepared for transmission, and the output is the translated data sent to each device. In concrete terms, the server sends the data "Hello, how are you?" to User B's device.

[1286] Step 8:

[1287] The device displays the received translation data on the user interface and shows it to the participants in real time. The input is the received translation data, and the output is the translated text displayed on the device's user interface. Specifically, User B's device displays "Hello, how are you?"

[1288] (Application example 1)

[1289] 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."

[1290] In factories, communication between workers who speak different languages ​​is often difficult, which can hinder work efficiency and safety. Language barriers can be a serious obstacle, especially when sharing emergency instructions or complex work procedures. Technology is needed to solve this problem and improve work efficiency and safety.

[1291] 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.

[1292] In this invention, the server includes means for capturing the speaker's voice, means for converting the captured voice data into text data, means for translating the converted text data in real time, means for transmitting the translated text data based on the language set by each participant, means for displaying the transmitted translated data, means for supporting communication between workers who speak different languages, and means for converting the translated text data into voice and playing it back on a speaker. This enables workers in a factory who speak different languages ​​to understand each other in real time and communicate smoothly.

[1293] "Speaker" refers to a person who produces sound.

[1294] "Voice data" refers to data that is a digital recording of a speaker's voice.

[1295] "Text data" refers to digital data that has been converted from audio data into text.

[1296] "Real-time" refers to processing that occurs almost immediately, without delay.

[1297] "Translation" refers to converting text data expressed in one language into another language.

[1298] "Preferred language" refers to the language that the user of the system has selected to use.

[1299] "Send" refers to the act of moving data from one device to another.

[1300] "Display" refers to the output of digital data in a visually perceptible form.

[1301] "In-factory" refers to the interior of an industrial facility where manufacturing or assembly takes place.

[1302] "Worker" refers to a worker who performs work within a factory.

[1303] "Supporting communication" refers to providing assistance to facilitate smooth communication.

[1304] A "speaker" refers to a device for outputting audio data as sound waves.

[1305] "Convert to audio" refers to converting text data into audio format data.

[1306] This invention is a system for supporting communication between workers who speak different languages ​​in a factory. This system includes the following components:

[1307] Hardware

[1308] High-definition microphone: Used to capture the speaker's voice.

[1309] Speech Recognition Processor: Used to process captured voice data and convert it into text data.

[1310] Server: Translates the converted text data and sends the translated data based on the language setting of each participant.

[1311] Display: Used to visually display the translated text data.

[1312] Speaker: Used to play back the translated text data as audio.

[1313] software

[1314] Speech recognition engine: Uses the Google Speech Recognition API or similar to convert captured voice data into text data.

[1315] Translation engine: Translates text data in real time using APIs such as Google Translate.

[1316] Data communication: A secure socket communication protocol for sending and receiving converted text data and translation data.

[1317] Robot control system: The entire system is controlled in an integrated manner using ROS (Robot Operating System).

[1318] System Operation Description

[1319] Step 1: Voice Input

[1320] When a user speaks into the microphone, the voice data is captured by a high-precision microphone. For example, Worker A (an English speaker) speaks, "The machine needs maintenance."

[1321] Step 2: Voice Recognition

[1322] The captured voice data is sent to a speech recognition processor and converted into text data in real time using the Google Speech Recognition API. In this case, the voice data is converted into the text data "The machine needs maintenance."

[1323] Step 3: Send data

[1324] The converted text data is sent to the server using a secure socket communication protocol.

[1325] Step 4: Translating the text data

[1326] The server uses the Google Translate API to translate the received text in real time based on the language settings of each participant. For example, "The machine needs maintenance" is translated to "The machine needs maintenance."

[1327] Step 5: Send and view translation data

[1328] The translated text data is sent to the terminal of Worker B (Japanese speaker) and displayed on the screen. The translated text data is also played aloud through a speaker.

[1329] Specific examples

[1330] Below is a concrete example of how the system works.

[1331] 1. Worker A says, "The machine needs maintenance."

[1332] 2. A high-definition microphone captures your voice and sends it to a speech recognition processor.

[1333] 3. The Google Speech Recognition API converts the audio data into "The machine needs maintenance."

[1334] 4. The text data is sent to the server via a secure socket communication protocol.

[1335] 5. The Google Translate API translates the text data into "Machine maintenance required."

[1336] 6. The translated text data is sent to Worker B's device and displayed on the screen.

[1337] 7. The translated text data is played back through the speaker as a voice saying, "Machine maintenance is required."

[1338] Prompt example

[1339] Below is a concrete example of a prompt using the Google Speech Recognition API and the Google Translate API.

[1340] Speech recognition prompt:

[1341] Please recognize the following phrase: "The machine needs maintenance".

[1342] Translation prompt:

[1343] Translate the following English text to Japanese: "The machine needs maintenance".

[1344] This will enable workers in a factory who speak different languages ​​to understand each other in real time and communicate smoothly.

[1345] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1346] Step 1:

[1347] When a user speaks into a high-definition microphone, their voice is captured. The input is the user's voice, which is captured as digital voice data by the high-definition microphone. Specifically, worker A speaks, "The machine needs maintenance." This digital voice data is passed to the next processing step.

[1348] Step 2:

[1349] The device sends the captured voice data to a speech recognition processor, which converts the voice data into text using the Google Speech Recognition API. The digital voice data is processed as input, and the text "The machine needs maintenance" is generated as output.

[1350] Step 3:

[1351] The terminal sends the converted text data to the server through a secure socket communication protocol. The input contains the text data "The machine needs maintenance". The output is the same data transmitted to the server.

[1352] Step 4:

[1353] The server uses the Google Translate API to translate the received text data based on the language set by each participant. The input is the text data "The machine needs maintenance," and the output is the translated text data "Machine maintenance is required."

[1354] Step 5:

[1355] The server sends the translated text data to the terminal. At this time, it sends the most appropriate translation data based on the language setting of each participant. The input includes the translated text data "Machine maintenance required." The output is transferred to the terminal.

[1356] Step 6:

[1357] The device displays the received translation data on a display. Specifically, it visually displays the text data "Machine maintenance required." The device also converts the translated text data into audio data and plays it as audio through a speaker. The input includes the translated text data "Machine maintenance required." The output is that this data is displayed on the display and the speaker plays the audio "Machine maintenance required."

[1358] 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.

[1359] The present invention provides a system for facilitating communication between participants who speak different languages ​​in online business meetings, and also combines an emotion engine to recognize the speaker's emotions and improve communication accuracy. The system provides a series of processes: capturing a user's speech in real time, converting the speech data into text data, translating the text data into the language set by each participant, and displaying the translation results and emotional information on each terminal.

[1360] System Configuration

[1361] 1. User voice input

[1362] Terminal: A user speaks through a meeting application.

[1363] Terminal: The speech is captured using a high-precision microphone and prepared for processing as voice data.

[1364] 2. Voice Recognition

[1365] Terminal: The captured voice data is sent to a real-time voice recognition engine, which converts the voice data into text data.

[1366] Terminal: Use a speech recognition engine (e.g., Google Speech Recognition API) to perform the conversion process.

[1367] 3. Emotion analysis

[1368] Terminal: Captured voice data is sent to the emotion engine, which analyzes the speaker's emotional state.

[1369] Device: The emotion engine analyzes the voice data and extracts emotional information such as "anger," "joy," and "sadness."

[1370] 4. Sending text data

[1371] Terminal: The converted text data and analyzed emotion information are sent to the server via a secure communication protocol (e.g., socket communication).

[1372] 5. Translation of text data

[1373] Server: Translates the received text data using an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant.

[1374] Server: Saves the translation results and prepares them for transmission to each participant's device.

[1375] 6. Adding Emotional Information

[1376] Server: Adds emotional information provided by the emotion engine to the translated text data and adds markers indicating emotions to each text.

[1377] 7. Sending and displaying translation data

[1378] Server: Translates the text data and emotion information to each participant's device.

[1379] Terminal: The received translation data and emotion information are displayed on the user interface and shown to participants in real time.

[1380] Example of operation

[1381] Speaker A (English) → User B (Japanese)

[1382] 1. User A says "I am very happy to be here" in a meeting.

[1383] 2. The device captures user A's voice and converts it into voice data.

[1384] 3. The device sends the captured voice data to a real-time voice recognition engine and converts it into text data such as "I am very happy to be here."

[1385] 4. The device sends the voice data to the emotion engine, which analyzes and extracts the emotion of "joy."

[1386] 5. The device sends the converted text data and emotion information to the server.

[1387] 6. The server receives the text data and retrieves User B's preferred language (Japanese) from the database.

[1388] 7. The server sends the text data "I am very happy to be here." to the machine translation engine, which translates it into Japanese and obtains the text data "I am very happy to be here."

[1389] 8. The server adds the emotional information "joy" to the translated text data.

[1390] 9. The server sends the translated text data and emotion information to User B's device.

[1391] 10. User B's device receives the translated data "I'm so happy to be here" and displays the emotional information "joy" on the user interface for User B to see.

[1392] This series of processes allows users who speak different languages ​​to communicate smoothly while understanding the emotions of the other person. The system operates in real time, making multilingual business meetings possible while reducing the burden on users.

[1393] The processing flow will be explained below.

[1394] Step 1:

[1395] The user begins speaking through the meeting application. The microphone on the user's device begins capturing audio.

[1396] Step 2:

[1397] The device temporarily stores the captured voice data and prepares it for transmission to a real-time speech recognition engine (e.g., Google Speech Recognition API).

[1398] Step 3:

[1399] The device uses a real-time speech recognition engine to convert the captured voice data into text data. Specifically, the speech recognition engine analyzes the voice waveform and converts it into corresponding text.

[1400] Step 4:

[1401] The device sends the voice data to the emotion engine, which analyzes the speaker's emotions. The emotion engine analyzes the voice data and extracts emotional information such as "joy," "sadness," and "anger."

[1402] Step 5:

[1403] The converted text data and analyzed emotion information are sent to the server via a secure communication protocol (e.g., socket communication). The text data and emotion information are appropriately formatted and sent.

[1404] Step 6:

[1405] The server receives the text data and emotion information sent from the device, analyzes the received data, and accesses a database or configuration file to identify the preferred language of each participant.

[1406] Step 7:

[1407] The server uses an automatic translation engine (e.g., Google Translate API) to translate the text data into the language set by each participant. The translation engine translates "I am very happy to be here." into "I am very happy to be here."

[1408] Step 8:

[1409] The server adds emotional information provided by the emotion engine to the translated text data and adds markers indicating emotions to each piece of text. For example, adding "(joy)" after "I'm so happy to be here."

[1410] Step 9:

[1411] The server sends the translated text data and emotion information to the appropriate device based on each participant's language settings. The data is properly formatted and sent quickly.

[1412] Step 10:

[1413] The device receives the translation data and emotion information sent from the server, and the received data is analyzed appropriately and displayed on the user interface.

[1414] Step 11:

[1415] The user can check the translation data and emotional information displayed on the device screen and then make the next utterance or action, allowing for smooth sharing of translated communication and emotional information in real time during meetings.

[1416] This process flow not only enables seamless communication between multiple participants who speak different languages, but also makes it easier for each user to understand the emotions of the other speaker. The system operates in real time, reducing the burden on users and supporting efficient multilingual business meetings.

[1417] Example 2

[1418] 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."

[1419] In online business meetings, there is a demand for systems that facilitate smooth communication between participants who speak different languages. Conventional systems convert voice data into text or translate it, but they lack the ability to convey the speaker's emotional information, making it difficult to improve the accuracy of communication and understanding between participants.

[1420] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1421] In this invention, the server includes means for capturing the speaker's voice, means for converting the captured voice data into text data, means for extracting emotional information from the captured voice data and adding the emotional information to the text data, means for translating the converted text data in real time, means for transmitting the translated text data based on the language set by each participant, and means for displaying the transmitted translated data, thereby enabling participants who speak different languages ​​to communicate while understanding the speaker's emotions in real time.

[1422] The "means for capturing the speaker's voice" is a function for acquiring the user's speech as digital voice data using a device such as a high-precision microphone.

[1423] The "means for converting captured voice data into text data" is a function for inputting the acquired voice data into a voice recognition engine and converting the voice content into text format.

[1424] "Means for translating converted text data in real time" refers to a function for translating text data in real time using software or a service that automatically translates text data into another language.

[1425] The "means for transmitting translated text data based on the language set by each participant" is a function for appropriately transmitting translated text data based on the language set in advance by each participant.

[1426] The "means for displaying the transmitted translation data" is a function for visually displaying the received translation data on the terminal of each participant.

[1427] "Means for extracting emotional information from captured voice data and adding the emotional information to text data" refers to a function that analyzes the emotional state of the speaker from captured voice data using a voice analysis engine or the like and adds the emotional information to the text data.

[1428] This invention is a system for facilitating communication between participants who speak different languages ​​in online business meetings, incorporating an emotion engine that recognizes the speaker's emotions to improve communication accuracy. This system provides a series of processes: capturing a user's speech in real time, converting the speech data into text data, translating the text data into the language set by each participant, and displaying the translation results and emotional information on each terminal.

[1429] Hardware and Software Configuration

[1430] 1. User voice input

[1431] Device: The user speaks through the meeting application. The device uses a high-precision microphone to capture the user's speech and save it as digital audio data.

[1432] 2. Voice Recognition

[1433] Device: Sends captured voice data to a real-time speech recognition engine, such as the Google Speech Recognition API, and converts the speech into text.

[1434] 3. Emotion analysis

[1435] Terminal: Sends voice data to the emotion engine and analyzes the speaker's emotional state. The emotion engine extracts emotional information such as "anger," "joy," and "sadness."

[1436] 4. Sending text data

[1437] Terminal: The converted text data and emotion information are sent to the server via a secure communication protocol (e.g., socket communication).

[1438] 5. Translation of text data

[1439] Server: Translates the received text data using an automatic translation engine such as Google Translate API based on the language settings of each participant. The translation results are saved and prepared for transmission to each participant's device.

[1440] 6. Adding Emotional Information

[1441] Server: Adds emotional information provided by the emotion engine to the translated text data and adds markers indicating emotions to each text.

[1442] 7. Sending and displaying translation data

[1443] Server: Translates the text data and emotional information to each participant's device. Each participant's device displays the received translation data and emotional information on a user interface, allowing participants to see it in real time.

[1444] Specific examples

[1445] Speaker A (English) → User B (Japanese)

[1446] 1. User A says "I am very happy to be here" in a meeting.

[1447] 2. The device captures user A's voice and converts it into voice data.

[1448] 3. The device sends the captured voice data to the Google Speech Recognition API, which converts it into text data such as "I am very happy to be here."

[1449] 4. The device sends the voice data to the emotion engine, which analyzes and extracts the emotion of "joy."

[1450] 5. The device sends the converted text data and emotion information to the server.

[1451] 6. The server receives the text data and retrieves User B's preferred language (Japanese) from the database.

[1452] 7. The server sends the text data "I am very happy to be here." to the Google Translate API, which translates it into Japanese and obtains the text data "I am very happy to be here."

[1453] 8. The server adds the emotion information "joy" to the translated text data. Example: "I'm so happy to be here. [Joy]"

[1454] 9. The server sends the translated text data and emotion information to User B's device.

[1455] 10. User B's device receives the translated data "I'm so happy to be here" and displays the emotional information "joy" on the user interface for User B to see.

[1456] This process allows users who speak different languages ​​to communicate smoothly while understanding each other's emotions. The system operates in real time, making multilingual business meetings possible while reducing the burden on users.

[1457] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1458] Step 1:

[1459] The user speaks

[1460] Terminal: A user speaks through a meeting application. For example, User A says, "I am very happy to be here." This voice is captured by a high-precision microphone and acquired as digital audio data.

[1461] Input: The audio spoken by the user.

[1462] Specific operation: A high-performance microphone captures the user's voice and stores it in memory as audio data.

[1463] Step 2:

[1464] Converting audio data to text data

[1465] On the device: The captured voice data is sent to the Google Speech Recognition API, which converts the speech into text.

[1466] Input: Captured audio data.

[1467] Output: The converted text data "I am very happy to be here."

[1468] Specific operation: The device sends voice data to the Google Speech Recognition API and obtains the text data "I am very happy to be here."

[1469] Step 3:

[1470] Sentiment analysis of voice data

[1471] Terminal: Sends voice data to the emotion engine and analyzes the speaker's emotional state. For example, the emotion engine analyzes and extracts the emotion "joy."

[1472] Input: Transduced text data and captured audio data.

[1473] Output: Analyzed emotion information "joy".

[1474] Specific operation: The device sends voice data to the emotion engine and obtains the emotion information "joy."

[1475] Step 4:

[1476] Text data and emotional information sent to server

[1477] Terminal: The converted text data and analyzed emotion information are sent to the server via a secure communication protocol (e.g., socket communication).

[1478] Input: Text data "I am very happy to be here." and emotion information "joy."

[1479] Output: The data sent to the server.

[1480] Specific operation: The device assembles text data and emotional information into packets and securely transmits them to the server.

[1481] Step 5:

[1482] Text data translation

[1483] Server: Sends the received text data to the Google Translate API and translates it based on the language settings of each participant.

[1484] Input: Text data "I am very happy to be here."

[1485] Output: The translated text "I'm so happy to be here."

[1486] Specific operation: The server sends text data to the Google Translate API and obtains the translated text data.

[1487] Step 6:

[1488] Adding emotional information to text data

[1489] Server: Adds the emotional information "joy" to the translated text data. For example, "I'm so happy to be here. [Joy]."

[1490] Input: Translated text data "I'm so happy to be here" and emotion information "joy".

[1491] Output: Text data with emotional information added: "I'm so happy to be here. [Joy]".

[1492] What it does: The server adds emotion information to the translated text and formats it.

[1493] Step 7:

[1494] Transmitting and displaying translation data and emotional information to the device

[1495] Server: Translates the text data and emotion information to each participant's device.

[1496] Terminal: The received translation data and emotion information are displayed on the user interface and shown to participants in real time.

[1497] Input: Text data with emotional information added: "I'm so happy to be here. [Joy]".

[1498] Output: The displayed translation data and sentiment information.

[1499] Specific operation: The server sends text data with added emotional information to the terminal, which then displays it on the user interface.

[1500] These steps enable participants who speak different languages ​​to communicate in real time while understanding each other's emotions. This system combines speech recognition and emotion analysis using generative AI models with machine translation services to facilitate international business meetings.

[1501] (Application example 2)

[1502] 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."

[1503] When people who speak different languages ​​communicate in the same space, it is difficult not only to translate between languages, but also to convey the speaker's emotions and nuances appropriately. In this situation, it is necessary to improve the accuracy of communication, especially in navigation systems for autonomous vehicles, because understanding the driver's emotions and intentions is directly linked to safety and usability.

[1504] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for capturing the speaker's voice, means for converting the captured voice data into text data, means for translating the converted text data in real time, means for analyzing the speaker's emotional state, means for adding the analyzed emotional information to translation data, means for transmitting the translated text data based on the language set by each participant, and means for displaying the transmitted translation data. This enables smooth communication that includes emotions between users who speak different languages, improving safety and comfort even in navigation systems for autonomous vehicles.

[1505] "Speaker" refers to a person who produces sound.

[1506] "Audio capturing means" refers to a device or system for digitally recording a speaker's voice.

[1507] "Audio Data" means audio information recorded in digital form.

[1508] "Text data" refers to text information converted through speech recognition, translation, etc.

[1509] "Means for converting" refers to the technology or system for converting voice data into text data.

[1510] "Real-time translation means" refers to technologies or systems that instantly convert input text data into a different language.

[1511] "Language set by each participant" refers to the language setting of the user for whom the translation results are to be displayed.

[1512] "Transmitting means" refers to a technology or system that transmits the generated data to other devices or systems via a network.

[1513] "Display means" refers to the technology or system used to present information to the user through a user interface.

[1514] "Means for analyzing emotional state" refers to technologies or systems that analyze the speaker's emotions from voice data.

[1515] "Emotional information" refers to data that indicates the emotional state of the speaker.

[1516] "Means for adding to translated data" refers to technologies and systems that add analyzed emotional information to translated text data.

[1517] "Server" refers to a computing device or system for processing and managing data.

[1518] This invention relates to a multilingual and emotion-sensitive navigation system for autonomous vehicles. The system captures a speaker's voice, converts the voice data into text data, translates it in real time, analyzes the speaker's emotional state, adds the analyzed emotional information to the translated data, transmits it based on the language settings of each participant, and displays the transmitted translated data, thereby enabling smooth, emotion-sensitive communication between users who speak different languages.

[1519] Hardware used

[1520] High-precision microphone

[1521] In-vehicle terminal (including display)

[1522] server

[1523] Software used

[1524] Speech recognition engine (e.g., Google Speech Recognition API)

[1525] Machine translation engine (e.g. Google Translate API)

[1526] Sentiment analysis engine (e.g. emotion_recognition_library)

[1527] Program processing and data processing

[1528] 1. User voice input

[1529] A high-precision microphone connected to the in-vehicle terminal captures the user's speech in real time, and the captured speech is sent to the in-vehicle terminal as voice data.

[1530] 2. Voice Recognition

[1531] The voice data captured by the in-vehicle device is converted into text data using the Google Speech Recognition API.

[1532] 3. Emotion analysis

[1533] The in-vehicle device analyzes the converted text data using the emotion_recognition_library and extracts the speaker's emotional state (e.g., "anger," "joy," "sadness").

[1534] 4. Data Transmission

[1535] The in-vehicle terminal transmits the converted text data and analyzed emotion information to the server using a secure communication protocol (e.g., socket communication).

[1536] 5. Text Translation

[1537] The server translates the received text data using the Google Translate API based on the user's language settings.

[1538] 6. Adding Emotional Information

[1539] The server adds emotional information to the translated text data and adds markers indicating emotions to each text.

[1540] 7. Data transmission and display

[1541] The server sends the translated text data and emotion information to the in-vehicle device, which then displays the received translation data on the display, allowing the user to see it in real time.

[1542] Specific examples

[1543] For example, if a user in an autonomous vehicle says to the navigation system, "I am feeling a bit anxious about the traffic ahead," the system will process it as follows: It captures the audio, uses speech recognition, and converts it into text data: "I am feeling a bit anxious about the traffic ahead." It then extracts the emotional information "anxiety" through emotion analysis and sends it to the server using a secure communication protocol. The server translates the text data into Japanese and generates text data: "I am a bit anxious about the traffic ahead." It adds the emotional information "anxiety" to the translation result and sends it to the in-vehicle device. The in-vehicle device then displays the emotional information "anxiety" on the display, showing it to the user in real time, allowing other passengers and the system to understand the user's emotions and take appropriate action.

[1544] Prompt Sentence Examples

[1545] "Please explain the glossary and multilingual translation process in an in-car navigation system."

[1546] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1547] Step 1:

[1548] User voice input

[1549] In an autonomous vehicle, a user speaks instructions to the navigation system. The voice is captured through a high-precision microphone and input as voice data into the in-vehicle terminal. At this stage, the input data is raw voice data. The in-vehicle terminal uses a voice capture module to convert it into a digital format, ready to be sent to the voice recognition engine.

[1550] Step 2:

[1551] Voice Recognition

[1552] The in-vehicle device sends the captured voice data to a real-time voice recognition engine (e.g., Google Speech Recognition API) and converts the voice data into text data. In this process, the input is the captured voice data and the output is the converted text data. The voice recognition engine analyzes the voice data and generates the corresponding text data.

[1553] Step 3:

[1554] Emotion analysis

[1555] The in-vehicle device sends the text data of the speech recognition results and the original speech data to the emotion engine, which analyzes the speaker's emotional state. At this stage, the input is speech data and text data, and the output is analyzed emotional information. The emotion engine uses a feature extraction algorithm to classify emotions into categories such as "anger," "joy," and "sadness."

[1556] Step 4:

[1557] Data transmission

[1558] The in-vehicle terminal transmits the converted text data and analyzed emotion information to the server using a secure communication protocol. The input is the converted text data and emotion information, and the output is the data transmitted to the server. The data is encrypted before transmission to ensure security.

[1559] Step 5:

[1560] Text Translation

[1561] The server sends the received text data to an automatic translation engine (e.g., Google Translate API) based on the language settings of each participant, and obtains the translated text data. The input is the received text data and the user's language settings, and the output is the translated text data. The translation engine analyzes the source text and generates the corresponding translation.

[1562] Step 6:

[1563] Adding emotional information

[1564] The server adds emotional information to the translated text data using an emotion engine and adds markers indicating emotions to each text. The input is the translated text data and emotional information, and the output is the translated text data with the emotional markers added. The server integrates the emotional markers into the metadata of the text data.

[1565] Step 7:

[1566] Data transmission and display

[1567] The server sends the translated text data and emotion information to the in-vehicle terminal. The in-vehicle terminal displays the received translation data on the display, showing it to the user in real time. The input is emotion information and translated text data, and the output is the information displayed on the in-vehicle terminal's display. The display module receives the data and displays it on the screen.

[1568] As a result, smooth communication between multiple languages, including emotions, can be realized.

[1569] 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.

[1570] 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.

[1571] 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.

[1572] 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.

[1573] 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.

[1574] 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.

[1575] 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).

[1576] 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.

[1577] 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."

[1578] 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.

[1579] 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).

[1580] 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.

[1581] 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.

[1582] 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.

[1583] 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.

[1584] 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.

[1585] 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.

[1586] 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.

[1587] 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.

[1588] 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.

[1589] 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.

[1590] The following is further disclosed regarding the above embodiment.

[1591] (Claim 1)

[1592] a means for capturing the speech of a speaker;

[1593] means for converting the captured audio data into text data;

[1594] A means for translating the converted text data in real time;

[1595] means for transmitting the translated text data based on the language setting of each participant;

[1596] a means for displaying the transmitted translation data;

[1597] A system including:

[1598] (Claim 2)

[1599] 10. The system of claim 1, wherein the means for capturing voice data utilizes a real-time voice recognition engine.

[1600] (Claim 3)

[1601] 10. The system of claim 1, wherein the translation means utilizes an automatic translation service.

[1602] (Claim 4)

[1603] 10. The system of claim 1, further comprising means for reading the participant's preferred language from a database or configuration file.

[1604] (Claim 5)

[1605] 2. The system according to claim 1, further comprising means for transmitting the translated text data using socket communication.

[1606] "Example 1"

[1607] (Claim 1)

[1608] A means for acquiring a speaker's voice;

[1609] means for converting the acquired voice data into text data;

[1610] means for securely transmitting the converted text data;

[1611] A means for translating transmitted text data in real time;

[1612] means for transmitting the translated text data based on the language setting of each participant;

[1613] a means for displaying the transmitted translation data;

[1614] A system including:

[1615] (Claim 2)

[1616] 2. The system of claim 1, wherein the means for acquiring voice data uses a real-time voice recognition engine.

[1617] (Claim 3)

[1618] 10. The system of claim 1, wherein the translation means utilizes an automatic translation engine.

[1619] "Application Example 1"

[1620] (Claim 1)

[1621] a means for capturing the speech of a speaker;

[1622] means for converting the captured audio data into text data;

[1623] A means for translating the converted text data in real time;

[1624] means for transmitting the translated text data based on the language setting of each participant;

[1625] a means for displaying the transmitted translation data;

[1626] A means to support communication between workers who speak different languages ​​within a factory;

[1627] A system including:

[1628] (Claim 2)

[1629] 10. The system of claim 1, wherein the means for capturing voice data utilizes a real-time voice recognition engine.

[1630] (Claim 3)

[1631] 10. The system of claim 1, wherein the translation means utilizes an automatic translation service.

[1632] (Claim 4)

[1633] 10. The system of claim 1, further comprising means for converting the translated text data into speech and playing it on a speaker to support real-time communication between workers who speak different languages.

[1634] "Example 2: Combining Emotion Engines"

[1635] (Claim 1)

[1636] a means for capturing the speech of a speaker;

[1637] means for converting the captured audio data into text data;

[1638] A means for translating the converted text data in real time;

[1639] means for transmitting the translated text data based on the language setting of each participant;

[1640] a means for displaying the transmitted translation data;

[1641] means for extracting emotional information from the captured voice data and adding the emotional information to the text data;

[1642] A system including:

[1643] (Claim 2)

[1644] 10. The system of claim 1, wherein the means for capturing voice data utilizes a real-time voice recognition engine.

[1645] (Claim 3)

[1646] 10. The system of claim 1, wherein the translation means utilizes an automatic translation service.

[1647] "Application example 2 when combining emotion engines"

[1648] (Claim 1)

[1649] a means for capturing the speech of a speaker;

[1650] means for converting the captured audio data into text data;

[1651] A means for translating the converted text data in real time;

[1652] means for transmitting the translated text data based on the language setting of each participant;

[1653] a means for displaying the transmitted translation data;

[1654] means for analyzing the emotional state of a speaker;

[1655] means for adding the analyzed emotion information to the translation data;

[1656] A system including:

[1657] (Claim 2)

[1658] 10. The system of claim 1, wherein the means for capturing voice data utilizes a real-time voice recognition engine.

[1659] (Claim 3)

[1660] 10. The system of claim 1, wherein the translation means utilizes an automatic translation service. [Explanation of symbols]

[1661] 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 the speech of a speaker; means for converting the captured audio data into text data; A means for translating the converted text data in real time; means for transmitting the translated text data based on the language setting of each participant; a means for displaying the transmitted translation data; A system including:

2. 10. The system of claim 1, wherein the means for capturing voice data utilizes a real-time voice recognition engine.

3. 2. The system of claim 1, wherein the translation means utilizes an automatic translation service.

4. 10. The system of claim 1, further comprising means for reading a participant's preferred language from a database or configuration file.

5. 2. The system according to claim 1, further comprising means for transmitting the translated text data using socket communication.

Images