system

Abstract

Provide a system. The system comprises: means for obtaining voice or text input from a user; means for identifying the language of the acquired input data; means for translating the identified language into a specified target language; means for presenting the translated results to a user; 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] Traditionally, communication between users who speak different languages ​​has been hindered by language barriers, making smooth information exchange and conversation difficult. Furthermore, document translation and conversation support are essential in international business, and efficient methods for doing so have been sought. The objective of this invention is to use generative AI to facilitate communication between users who speak different languages ​​and enable the rapid translation of documents written in different languages. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for acquiring voice or text input from a user, a means for identifying the language of the acquired input data, a means for translating the identified language into a specified target language, and a means for presenting the translation result to the user. Specifically, the system has a function for converting voice into text data using a speech recognition engine and a function for playing back the translation result aloud using a voice output device. This facilitates conversations between users who speak different languages ​​and enables rapid document translation.

[0006] "User" refers to an entity that uses a system to provide input and receive output.

[0007] "Speech" refers to input data in the form of words or sounds spoken by a user.

[0008] "Text" refers to data in the form of characters or sentences entered by a user.

[0009] "Means for obtaining input" refers to a function or device for receiving voice or text data provided by a user.

[0010] "Means for identifying language" refers to a function or device for determining the language of acquired input data.

[0011] "Means for translating" refers to a function or device for converting an identified language into another specified language.

[0012] "Presenting means" refers to a function or device for displaying or reproducing the translated results to the user.

[0013] A "voice recognition engine" refers to software or hardware that converts voice input into text data.

[0014] "Audio output device" refers to a function or device for reproducing text data as audio.

[0015] "Generative AI" refers to artificial intelligence models that learn from large amounts of data to perform a specified task (e.g., language translation). [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] Overall system overview

[0038] This invention is a language translation and communication assistance system that utilizes a generative AI model. This system provides multilingual, real-time translation functionality to enable users to communicate smoothly with others who speak different languages. It automatically identifies and translates the user's voice and text input, and presents the translation results to the user, thereby eliminating language barriers.

[0039] System program processing description

[0040] 1. Initialization and getting input

[0041] The user inputs voice or text into the terminal.

[0042] For example, if user A says "hello," this voice input is passed to the terminal.

[0043] 2. Speech Recognition and Language Identification

[0044] The device converts the voice input into text data.

[0045] A speech recognition engine is used to convert the voice data into text data such as "Hello."

[0046] The terminal transmits the acquired text data to the server.

[0047] The text data "Hello" and the language (Japanese) specified by the user are sent to the server.

[0048] The server identifies the language of the received data.

[0049] A generative AI model is used to confirm that the language of the received data is Japanese.

[0050] 3. Translation

[0051] The server checks the target language.

[0052] For example, if User B speaks English, the translation language is English.

[0053] The server sends a translation request to the generative AI model.

[0054] A request to translate the text data "Hello" into English is sent to the generative AI model.

[0055] The server receives the translation results from the generative AI model.

[0056] The translation result "Hello" is received.

[0057] 4. Providing translation results

[0058] The server sends the translation results to the terminal.

[0059] The translated data "Hello" is sent to the terminal.

[0060] The terminal displays or outputs the translation result to the user.

[0061] The device displays or plays as audio the text "Hello" to User B.

[0062] Specific use cases

[0063] Conversation assistance

[0064] Let us take the example of User A (speaking Japanese) having a conversation with User B (speaking English).

[0065] 1. User A says "Hello."

[0066] 2. The device converts the speech to text and sends the text "Hello" to the server.

[0067] 3. The server recognizes "hello" and translates it into English.

[0068] 4. The server sends the translation result "Hello" to the terminal.

[0069] 5. The device plays "Hello" aloud to User B.

[0070] Document Translation

[0071] Take for example the case where a user wants to translate a business letter in a foreign language.

[0072] 1. A user types or scans a business letter (in English) into a terminal.

[0073] 2. The device sends the scanned data to the server.

[0074] 3. The server sends a request to the generative AI model to translate the received data into Japanese.

[0075] 4. The server receives the translated Japanese business letter and sends it to the terminal.

[0076] 5. The device will display the translated business letter on the screen.

[0077] The system according to the present invention can provide real-time conversation assistance and document translation quickly and efficiently, and can greatly facilitate communication between different languages.

[0078] The processing flow will be explained below.

[0079] Step 1:

[0080] The user inputs voice or text. For example, if user A says "hello" in Japanese, the voice input is passed to the device.

[0081] Step 2:

[0082] The device converts the voice input into text data, and then uses a speech recognition engine to convert the voice data into the text data "Hello."

[0083] Step 3:

[0084] The device sends the acquired text data and the language information (Japanese) specified by the user to the server. Specifically, the text data "Hello" and the language information "Japanese" are sent to the server as the payload of the HTTP request.

[0085] Step 4:

[0086] The server analyzes the received data and extracts the text data "Hello" and the language information "Japanese" from the HTTP request.

[0087] Step 5:

[0088] The server double-checks the language of the data received. It uses a generative AI model to identify the language of the text data and confirms that it is the specified language (Japanese).

[0089] Step 6:

[0090] The server checks the language to translate to. For example, if User B is set to use English, it needs to be translated to "English".

[0091] Step 7:

[0092] The server sends a translation request to the generative AI model, requesting that the generative AI model translate the text data "Hello" into "English."

[0093] Step 8:

[0094] The server receives the translation result from the generative AI model. The translation result "Hello" is returned from the generative AI model to the server.

[0095] Step 9:

[0096] The server sends the translation result to the terminal. It then generates a response including the translation result "Hello" and sends it to the terminal as an HTTP response.

[0097] Step 10:

[0098] The device receives the translation result from the server and extracts the translation result "Hello" from the HTTP response.

[0099] Step 11:

[0100] The device presents the translation result to the user. Specifically, the text data "Hello" is displayed on the screen or played back as voice using a speech synthesis engine.

[0101] Step 12:

[0102] User B checks the translated message and continues the conversation. If User B says "How are you?", the process is repeated in the same way.

[0103] This step is designed to facilitate real-time conversations between users who speak different languages.

[0104] Example 1

[0105] 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."

[0106] There is a need for a system that enables smooth real-time communication between users who speak different languages. In particular, there is a need for technology that can quickly and accurately recognize voice input and translate it into the appropriate language. Another challenge is how to efficiently provide translation results to users.

[0107] 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.

[0108] In this invention, the server includes means for identifying the language of the received data using the generative AI model, means for confirming the specified target language, and means for sending a request to the generative AI model to translate the text data into the specified target language, thereby enabling real-time translation between users who speak different languages.

[0109] - "User" is the person who operates the system and inputs voice or text.

[0110] A "means for obtaining voice or text input" means any device or software for receiving voice or text data from a user. Examples include a microphone or keyboard.

[0111] "Means of converting voice data into text using voice recognition technology" refers to technology that analyzes voice data and converts it into text. A typical example is a voice recognition engine.

[0112] "Means for sending acquired text data to the server" refers to the communication means for transferring text data from the device to the server, including internet connection and API calls.

[0113] "Means for identifying the language of incoming data using a generative AI model" refers to technology that uses an artificial intelligence model to identify the language of text data. Specifically, this applies to language identification algorithms.

[0114] "Means for determining the desired target language" refers to a method for determining which language to translate into based on user preferences and other metadata. This may include database lookups or use of user profiles.

[0115] "Means for sending a request to a generative AI model to translate text data into a specified target language" refers to a method for sending an instruction to an AI translation model to translate specific text data, such as an API call or sending a prompt.

[0116] "Means for receiving translation results from a generative AI model" refers to a method by which a server obtains translated data from an AI model. Specifically, it includes a method for receiving API responses.

[0117] "Means for presenting the translated results to the user" refers to a method for displaying or playing back the translated text or audio in a way that is easy for the user to understand. This includes displaying on a display or playing the audio through an audio output device.

[0118] MODE FOR CARRYING OUT THE INVENTION

[0119] Overall system overview

[0120] This invention is a language translation and communication assistance system that utilizes a generative AI model. This system provides multilingual, real-time translation functionality to enable users to communicate smoothly with others who speak different languages. It automatically identifies and translates the user's voice and text input, and presents the translation results to the user, thereby eliminating language barriers.

[0121] Hardware and software used

[0122] 1. Audio input device: Uses a microphone to capture the user's voice.

[0123] 2. Terminal: A computing device (including smartphones and tablets) that receives user input and performs initial processing.

[0124] 3. Speech recognition technology: Use APIs such as Google (registered trademark) Cloud Speech-to-Text.

[0125] 4. Server: A remote computing resource for processing and interpreting data.

[0126] 5. Generative AI model: Translate text data using models such as OpenAI's GPT-4.

[0127] 6. Audio output device: A speaker to provide the translation results to the user audibly.

[0128] Specific example of system operation

[0129] Step 1: Getting input

[0130] The user speaks "Hello" into the device's microphone. This voice data is input into the device.

[0131] Step 2: Voice recognition and transmission

[0132] The device uses the Google Cloud Speech-to-Text API to convert the voice data into text data such as "Hello." The converted text data is then sent to the server.

[0133] Step 3: Server Processing

[0134] The server uses the generative AI model to verify that the language of the received data is Japanese. The server then verifies the language used by User B (e.g., English).

[0135] Step 4: Translate and receive the results

[0136] The server sends a request to the generative AI model to translate "Hello" into English. For example, it passes the prompt sentence "Please translate the following Japanese into English: Hello" to the generative AI model. It receives the translation result "Hello" from the generative AI model.

[0137] Step 5: Presenting the results

[0138] The server sends the translation result to the device, which then displays the text "Hello" to User B or plays the audio "Hello" using the Google Cloud Text-to-Speech API.

[0139] Specific use cases

[0140] Conversation assistance

[0141] A specific example of User A (speaking Japanese) assisting User B (speaking English) in a conversation is as follows.

[0142] 1. User A says "Hello."

[0143] 2. The device converts the speech to text and sends the text "Hello" to the server.

[0144] 3. The server recognizes "hello" and translates it into English.

[0145] 4. The server sends the translation result "Hello" to the terminal.

[0146] 5. The device plays "Hello" aloud to User B.

[0147] Document Translation

[0148] If a user wants to translate a business letter in a foreign language, a specific example is as follows.

[0149] 1. The user types or scans a business letter (e.g., in English) into the terminal.

[0150] 2. The device sends the scanned data to the server.

[0151] 3. The server sends a request to the generative AI model to translate the received data into Japanese.

[0152] 4. The server sends the translated Japanese business letter to the terminal.

[0153] 5. The device will display the translated business letter on the screen.

[0154] This system enables real-time conversation assistance and document translation between users who speak different languages ​​quickly and efficiently, greatly facilitating communication between different languages.

[0155] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0156] Step 1:

[0157] The user inputs voice or text into the device. The user speaks "Hello" into the microphone or types "Hello" on the keyboard. This causes the voice data or text data to be acquired by the device.

[0158] Input: User voice or text

[0159] Output: Audio or text data

[0160] Step 2:

[0161] The device converts the voice input into text data. The device uses the Google Cloud Speech-to-Text API to convert the voice data into text data such as "Hello." This allows the voice information to be stored in text format on the device.

[0162] Input: Audio data

[0163] Output: Text data "Hello"

[0164] Step 3:

[0165] The device sends the acquired text data to the server. The device then sends the text data "Hello" and the language specified by the user (Japanese in this case) to the server as an HTTP request. The server then receives the text data and the specified language.

[0166] Input: Text data "Hello"

[0167] Output: Text data sent to the server and the specified language

[0168] Step 4:

[0169] The server identifies the language of the incoming data. Using a generative AI model (e.g., OpenAI's GPT-4), the server analyzes the incoming data and confirms that the language is Japanese. This prepares the server for the next processing step.

[0170] Input: Text data sent to the server and the specified language

[0171] Output: Data confirmed to be in Japanese

[0172] Step 5:

[0173] The server checks the target language. For example, if user B's language is English, the server checks the internal database or user profile to confirm that the target language is English.

[0174] Input: User B's language setting data

[0175] Output: Confirmation of the target language (English)

[0176] Step 6:

[0177] The server sends a translation request to the generative AI model. The server sends an API request to the generative AI model to translate the text data "Hello" into English. In this case, an example prompt is sent in the form "Please translate the following Japanese into English: Hello."

[0178] Input: Text data "Hello", prompt "Please translate the following Japanese into English: Hello"

[0179] Output: The prompt text sent as an API request

[0180] Step 7:

[0181] The server receives the translation result from the generative AI model. The server receives "Hello" as the translation result from the generative AI model and stores this data on the server side. The server then checks whether the translation result was obtained correctly.

[0182] Input: Translation results from a generative AI model

[0183] Output: Translation result "Hello"

[0184] Step 8:

[0185] The server sends the translation result to the terminal. The server then sends the translated data, "Hello," to the terminal as an HTTP response. This allows the translation result to reach the terminal.

[0186] Input: Translation result "Hello"

[0187] Output: Translation results sent to the device

[0188] Step 9:

[0189] The device displays or speaks the translation result to the user. The device displays the text "Hello" to User B or uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to speak "Hello." This allows User B to understand the translation result.

[0190] Input: Translation result "Hello"

[0191] Output: "Hello" displayed to User B or spoken "Hello" played

[0192] (Application example 1)

[0193] 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."

[0194] In autonomous vehicles, there is a need to facilitate communication between passengers who speak different languages, and there is a need for a means to support real-time language translation, including navigation instructions.

[0195] 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.

[0196] In this invention, the server includes means for acquiring voice or text input from a user, means for identifying the language of the acquired input data, means for translating the identified language into a specified translation language, means for presenting the translated result to the user, means including a speech recognition engine for converting the voice input into text, means including a voice player for outputting the translated text by voice, means for supporting multilingual communication, and means implemented in the autonomous vehicle, thereby enabling smooth real-time communication between passengers who speak different languages ​​and the autonomous vehicle system.

[0197] "User" means an individual who uses this system.

[0198] A "means for obtaining voice or text input" refers to a device or software that has the function of receiving a user's voice or text data.

[0199] "Means for identifying the language of acquired input data" refers to algorithms or software for determining the language of received voice or text data.

[0200] "Means for translating into a specified target language" means any device or software capable of changing an identified language into another language.

[0201] "Means for presenting the translated results to the user" refers to devices or software that display or audibly output the translated information to the user.

[0202] A "voice recognition engine" is software or hardware that converts a user's voice input into text data.

[0203] An "audio output device" is a device that converts text data into audio and plays it back.

[0204] "Supporting multilingual communication" means enabling users who speak different languages ​​to communicate smoothly with each other.

[0205] An "autonomous vehicle" is a vehicle that can move autonomously without the need for human operation.

[0206] "Real-time" refers to immediate processing and response with minimal delay.

[0207] A "server" is a computer system that processes data and provides information.

[0208] Overall system overview

[0209] This invention is a system for facilitating multilingual communication within an autonomous vehicle. The system can take voice or text input, translate it into another language in real time, and present the translation results to the user. This enables smooth communication between passengers who speak different languages ​​and the autonomous vehicle system.

[0210] System program processing description

[0211] 1. Initialization and getting input

[0212] The server uses a microphone or text input device to obtain voice or text input from the user, and the passenger's spoken or typed voice is passed to the system.

[0213] 2. Speech Recognition and Language Identification

[0214] The server uses a speech recognition engine to convert speech input into text data, for example, when a user says, "Turn left at the next intersection," the speech recognition engine converts this speech into text data.

[0215] 3. Translation

[0216] The server translates the acquired text data using a multilingual generative AI model. For example, this model translates the text "Please turn left at the next intersection" into English as "Please turn left at the next intersection."

[0217] 4. Providing translation results

[0218] The server then presents the translated text to the user using a voice output device, which plays back the translation results as audio, facilitating communication between passengers who speak different languages.

[0219] Hardware / Software used

[0220] Hardware: Vehicle-mounted microphone, speaker, and text input device

[0221] software:

[0222] speech_recognition library: for converting speech data to text

[0223] googletrans library: for text translation

[0224] pyttsx3 library: for playing the translated text aloud

[0225] Specific examples

[0226] For example, if Japanese-speaking Passenger A says, "Please turn left at the next intersection," the system recognizes the speech, converts it to text, translates it into English, and plays it back aloud as, "Please turn left at the next intersection." This allows English-speaking Driver B to understand the instruction and for the autonomous vehicle to take the appropriate next action.

[0227] Examples of prompt statements

[0228] use speech_recognition, googletrans, and pyttsx3 libraries to implement a voice recognition, translation, and speech output system for a self-driving car application. The system needs to support real-time translation from Japanese to English and announce the translated text back to the user.

[0229] According to the embodiment of the present invention, users who speak different languages ​​can smoothly communicate with each other in real time within an autonomous vehicle.

[0230] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0231] Step 1:

[0232] The terminal receives voice or text input from the user. The input voice data or text data is temporarily saved. The input in this step is the user's voice or text, and the output is the received voice data or text data.

[0233] Step 2:

[0234] The device converts voice data into text using a voice recognition engine. To perform this process, the voice data is passed to the voice recognition engine and text data is obtained as the output. The input is voice data and the output is text data.

[0235] Step 3:

[0236] The terminal transmits the acquired text data to the server. The input is the text data converted by speech recognition, and the output is the text data transmitted to the server.

[0237] Step 4:

[0238] The server identifies the language of the received text data. To do this, it uses a generative AI model to analyze the linguistic characteristics of the text and determine what language the input is in. The input is the converted text data, and the output is the identified language information.

[0239] Step 5:

[0240] The server translates the identified language into the specified target language using a generative AI model. This process involves sending a request to translate the identified language into another specified language and receiving the translation result. The input is the identified language information and text data, and the output is the translated text data.

[0241] Step 6:

[0242] The server sends the translation result to the terminal. The input is the translated text data, and the output is the translated text data sent to the terminal.

[0243] Step 7:

[0244] The terminal presents the received translated text data to the user using a voice output device. To do this, the terminal passes the translated text data to a speech synthesis engine and plays the generated voice data as its output. The input is the translated text data, and the output is the voice data played to the user.

[0245] This process flow enables users who speak different languages ​​to communicate smoothly in real time.

[0246] 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.

[0247] Overall system overview

[0248] This invention is a language translation and communication assistance system that combines a generative AI model and an emotion engine. This system not only facilitates communication between users who speak different languages, but also recognizes the user's emotions and provides optimal communication assistance based on those emotions. This system provides multilingual real-time translation and emotion recognition functions.

[0249] System program processing description

[0250] 1. Initialization and getting input

[0251] The user inputs voice or text. For example, if user A says "hello" in Japanese, the voice input is passed to the device.

[0252] 2. Speech Recognition and Language Identification

[0253] The device converts the voice input into text data, and then uses a speech recognition engine to convert the voice data into the text data "Hello."

[0254] The device sends the acquired text data and the language information (Japanese) specified by the user to the server. Specifically, the text data "Hello" and the language information "Japanese" are sent to the server as the payload of the HTTP request.

[0255] The server analyzes the received data and extracts the text data "Hello" and the language information "Japanese" from the HTTP request.

[0256] The server double-checks the language of the data received. It uses a generative AI model to identify the language of the text data and confirms that it is the specified language (Japanese).

[0257] 3. Translation and Emotion Recognition

[0258] The server checks the language to translate to. For example, if User B is set to use English, it needs to be translated to "English".

[0259] The server sends a translation request to the generative AI model, requesting that the model translate the text data "Hello" into English.

[0260] The server receives the translation result from the generative AI model. The translation result "Hello" is returned from the generative AI model to the server.

[0261] The server uses an emotion engine to analyze the user's emotional state and recognize the user's emotions (e.g., joy, sadness, anger, etc.) from the voice features and text content.

[0262] 4. Providing translation results and responding to emotions

[0263] The server sends the translation result and emotion recognition result to the terminal. A response including the translation result "Hello" and the user's emotional state is generated and sent to the terminal.

[0264] The device receives the translation result and emotion recognition result from the server. The translation result "Hello" and the emotional state are extracted from the HTTP response.

[0265] The device presents the translation result to the user. Specifically, it displays the text data "Hello" on the screen or plays it as voice using a speech synthesis engine. The tone of the voice and the way it is presented are adjusted depending on the user's emotional state.

[0266] Specific use cases

[0267] Conversation assistance

[0268] Let us take the example of User A (speaking Japanese) having a conversation with User B (speaking English).

[0269] 1. User A says "Hello."

[0270] 2. The device converts the speech to text and sends the text "Hello" to the server.

[0271] 3. The server recognizes "hello" and translates it into English.

[0272] 4. The server recognizes User A's emotional state using the emotion engine.

[0273] 5. The server sends the translation result "Hello" and User A's emotional state to the device.

[0274] 6. The device plays "Hello" aloud to User B. If User A is happy, the audio tone is set to brighter.

[0275] Document Translation

[0276] Take for example the case where a user wants to translate a business letter in a foreign language.

[0277] 1. A user types or scans a business letter (in English) into a terminal.

[0278] 2. The device sends the scanned data to the server.

[0279] 3. The server sends a request to the generative AI model to translate the received data into Japanese.

[0280] 4. The server recognizes the user's emotions based on the content of the business letter.

[0281] 5. The server sends the translated Japanese business letter and emotional state to the terminal.

[0282] 6. The device will display the translated business letter on the screen, highlighting the important parts if the user is in a hurry.

[0283] The system of the present invention not only provides real-time conversation assistance and document translation quickly and efficiently, but also takes into account the user's emotions to provide optimal communication assistance, significantly facilitating communication between different languages ​​and improving the user experience.

[0284] The processing flow will be explained below.

[0285] Step 1:

[0286] The user inputs voice or text. For example, if user A says "hello" in Japanese, the voice input is passed to the device.

[0287] Step 2:

[0288] The device converts the voice input into text data, and then uses a speech recognition engine to convert the voice data into the text data "Hello."

[0289] Step 3:

[0290] The device sends the acquired text data and the language information (Japanese) specified by the user to the server. Specifically, the text data "Hello" and the language information "Japanese" are sent to the server as the payload of the HTTP request.

[0291] Step 4:

[0292] The server analyzes the received data and extracts the text data "Hello" and the language information "Japanese" from the HTTP request.

[0293] Step 5:

[0294] The server double-checks the language of the data received. It uses a generative AI model to identify the language of the text data and confirms that it is the specified language (Japanese).

[0295] Step 6:

[0296] The server uses an emotion engine to analyze the user's emotional state and recognize the user's emotions (e.g., joy, sadness, anger, etc.) from the voice features and text content.

[0297] Step 7:

[0298] The server checks the language to translate to. For example, if User B is set to use English, it needs to be translated to "English".

[0299] Step 8:

[0300] The server sends a translation request to the generative AI model, requesting that the model translate the text data "Hello" into English.

[0301] Step 9:

[0302] The server receives the translation result from the generative AI model. The translation result "Hello" is returned from the generative AI model to the server.

[0303] Step 10:

[0304] The server sends the translation result and emotion recognition result to the terminal. A response including the translation result "Hello" and the user's emotional state is generated and sent to the terminal.

[0305] Step 11:

[0306] The device receives the translation result and emotion recognition result from the server. The translation result "Hello" and the emotional state are extracted from the HTTP response.

[0307] Step 12:

[0308] The device presents the translation result to the user. Specifically, it displays the text data "Hello" on the screen or plays it as voice using a speech synthesis engine. The tone of the voice and the way it is presented are adjusted depending on the user's emotional state.

[0309] Step 13:

[0310] User B checks the translated message and continues the conversation. If User B says "How are you?", the process is repeated in the same way.

[0311] This step is not only designed to facilitate real-time conversations between users who speak different languages, but also to provide optimal communication support by taking into account the user's emotions.

[0312] Example 2

[0313] 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."

[0314] Current language translation systems support communication between users who speak different languages, but no systems provide translation results that take the user's emotions into account. Furthermore, the lack of consideration for emotional expressions in translation results can lead to a decline in the quality of communication. Therefore, when providing multilingual communication support, there is a need for a system that recognizes the user's emotions and provides optimal translation results and responses based on those emotions.

[0315] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring voice or text input from a user, means for identifying the language of the acquired input data, means for translating the identified language into a specified translation target language, means for analyzing the user's emotions, means for adjusting the translation result based on the emotion analysis result, and means for presenting the translation result to the user. This makes it possible to provide optimal translation results and responses while taking into account the user's emotions in communication between different languages.

[0316] "User" refers to a person who uses the system to provide input by voice or text.

[0317] "Speech recognition engine" refers to technology or software for converting voice data into text data.

[0318] "Input Data" refers to information provided by a user through speech or text.

[0319] "Means for identifying language" refers to a technique or method for determining the language of input data.

[0320] "Means for translating" refers to a technique or method for converting data entered in a particular language into another specified language.

[0321] "Means for adjusting translation results" refers to techniques or methods for optimizing the presentation of translated text based on the results of user sentiment analysis.

[0322] "Means for analyzing emotions" refers to a technology or method for analyzing a user's emotional state from input speech or text.

[0323] "Server" refers to the computer device that is the core of this system and that manages and executes data processing and communications.

[0324] "Audio output device" refers to a device for reproducing audio data.

[0325] A "system" refers to a collection of components that integrate a series of processes, such as obtaining user input, identifying the language of the data, translating it, analyzing emotions, and presenting the results.

[0326] Overall system overview

[0327] This invention is a language translation and communication assistance system that combines a generative AI model and an emotion engine. This system not only facilitates communication between users who speak different languages, but also recognizes the user's emotions and provides optimal communication assistance based on those emotions. This system provides multilingual real-time translation and emotion recognition functions.

[0328] Hardware and software used

[0329] Terminal: A device through which a user inputs voice or text. This can include a microphone, keyboard, screen, scanner, etc.

[0330] Server: Serves as the central processing unit, processes and manages data. The server has API endpoints that handle HTTP requests.

[0331] Speech recognition engine: Software for converting speech to text, such as the Google Cloud Speech-to-Text API.

[0332] Generative AI models: Software for performing natural language processing, such as OpenAI's GPT series.

[0333] Emotion engine: Software for analyzing user emotions, such as Microsoft® Azure® Text Analytics API.

[0334] Audio output device: Software such as Amazon Polly that plays back the translation results as audio.

[0335] System Operation and Data Processing

[0336] Initialization and getting input

[0337] The user inputs voice or text. For example, if user A says "Hello" in Japanese, the voice input is passed to the device.

[0338] Speech Recognition and Language Identification

[0339] The device converts the voice input into text data "Hello" using a speech recognition engine. The device then sends this text data and the user-specified language information "Japanese" to the server. The server receives this and reconfirms the language of the text data using a generative AI model for language identification.

[0340] Translation and Emotion Recognition

[0341] The server checks the target language and, for example, if User B is set to use English, translates it into the specified target language, English. The server requests the generative AI model to translate "hello" into English and receives the result "Hello." The server then uses an emotion engine to analyze the user's emotional state. For example, the server recognizes the user's emotion (joy, sadness, anger, etc.) from the speech features and text content seen at first sight.

[0342] Providing translation results and responding to emotions

[0343] The server sends the translation result "Hello" and the emotion recognition result to the device. The device receives this and displays it on the screen or plays it as audio using an audio output device. Depending on the user's emotion, for example, if the user is happy, the tone of the translation result is adjusted to be brighter.

[0344] Specific use cases

[0345] Conversation assistance

[0346] Let's take the example of a conversation between User A (speaking Japanese) and User B (speaking English).

[0347] 1. User A says "Hello."

[0348] 2. The device launches the speech recognition engine and receives the text "Hello."

[0349] 3. The device sends the text and language information "Japanese" to the server.

[0350] 4. The server checks the language information and requests a translation into English from the generative AI model.

[0351] 5. The server receives the translation result "Hello" and the emotion recognition result from the emotion engine.

[0352] 6. The server sends this information back to the device.

[0353] 7. The device reads "Hello" using a speech synthesis engine and conveys it to User B. If User A is happy, the voice tone will be brighter.

[0354] Prompt Sentence Examples

[0355] "Receive audio data of a user saying 'hello,' analyze its sentiment, and translate it into appropriate English."

[0356] Document Translation

[0357] Take for example the case where a user wants to translate a business letter in a foreign language.

[0358] 1. A user types or scans a business letter (in English) into a terminal.

[0359] 2. The device sends the scanned data to the server.

[0360] 3. The server requests a translation into Japanese from the generative AI model.

[0361] 4. The server receives the translation results and emotion recognition results.

[0362] 5. The server sends these results back to the device.

[0363] 6. The device displays the translated Japanese business letter on the screen, highlighting the important parts if the user is in a hurry.

[0364] Prompt Sentence Examples

[0365] "Translate an English business letter into Japanese and analyze user sentiment based on the document."

[0366] The system of the present invention not only provides real-time conversation assistance and document translation quickly and efficiently, but also takes into account the user's emotions to provide optimal communication assistance, aiming to significantly facilitate communication between different languages ​​and improve the user experience.

[0367] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0368] Step 1:

[0369] The user inputs voice or text. For example, user A says "Hello" in Japanese. At that time, the voice data from the user is input to the terminal.

[0370] Step 2:

[0371] The device converts the voice input into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). Specifically, the device's microphone captures the voice, sends it to the speech recognition engine, and obtains the text data "Hello" as output.

[0372] Step 3:

[0373] The device sends the converted text data and the user-specified language information "Japanese" to the server as the payload of an HTTP request. Specifically, the device generates an HTTP POST request and sends it to the server's API endpoint. The input is the text data "Hello" and the language information "Japanese," and the output is completion of transmission to the server.

[0374] Step 4:

[0375] The server receives the HTTP request and extracts the text data "Hello" and the language information "Japanese." Specifically, the server's API endpoint parses the request body and retrieves the required data. The input is the received HTTP request, and the output is the extracted data.

[0376] Step 5:

[0377] The server uses a generative AI model (e.g., OpenAI's GPT-3 (registered trademark)) to reconfirm the language of the text data. Specifically, the server sends a prompt to the generative AI model asking, "What language is this text in?" and receives the result. The input is the text data "Hello," and the output is the reconfirmed language information "Japanese."

[0378] Step 6:

[0379] The server checks the target language. For example, if User B is set to use English, the target language is set to "English." Specifically, the server reads User B's language setting from the database or settings file. The input is User B's language setting information, and the output is the target language, "English."

[0380] Step 7:

[0381] The server sends a translation request to the generative AI model. Specifically, the server prompts the generative AI model with "Translate 'Hello' to English" and waits for the result. The input is the text data "Hello" and the target language "English," and the output is the translation result "Hello."

[0382] Step 8:

[0383] The server receives the translation result "Hello" from the generative AI model. Specifically, the server receives the response from the generative AI model, analyzes it, and extracts the translation result. The input is the response from the generative AI model, and the output is the translation result "Hello."

[0384] Step 9:

[0385] The server analyzes the user's emotional state using an emotion engine (e.g., Microsoft Azure's Text Analytics API). Specifically, the server sends the text "Hello" to the emotion engine and receives the emotion analysis result. The input is the text data "Hello," and the output is the emotion analysis result (e.g., joy).

[0386] Step 10:

[0387] The server sends the translation result "Hello" and the emotion recognition result to the device. Specifically, the server constructs a JSON response containing the translation result and emotion information and sends it to the device via an HTTP POST request. The input is the translation result "Hello" and the emotion analysis result, and the output is completion of transmission to the device.

[0388] Step 11:

[0389] The device receives the translation result and emotion recognition result from the server. Specifically, the device parses the HTTP response to obtain the necessary data. The input is the response from the server, and the output is the translation result "Hello" and the emotion analysis result.

[0390] Step 12:

[0391] The device presents the translation result to the user. Specifically, the text data "Hello" is displayed on the screen or played as voice using a speech synthesis engine (e.g., Amazon Polly). The tone of the voice and presentation method are adjusted depending on the user's emotion. The input is the translation result "Hello" and the emotion analysis result, and the output is the translation result presented to the user.

[0392] Prompt Sentence Examples

[0393] "Receive audio data of a user saying 'hello,' analyze its sentiment, and translate it into appropriate English."

[0394] (Application example 2)

[0395] 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."

[0396] This system not only facilitates communication between users who speak different languages, but can also understand the emotions of the other person during the conversation and respond appropriately. Conventional translation systems simply convert languages ​​and are unable to fully reflect emotions and nuances, so there is a need to improve the user experience.

[0397] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0398] In this invention, the server includes means for acquiring voice or text input from a user, means for identifying the language of the acquired input data, means for translating the identified language into a specified translation language, means for presenting the translated result to the user, emotion recognition means for analyzing the emotional state of the user, and means for adjusting the presentation method of the translation result based on the emotional state of the user, thereby facilitating communication between different languages ​​and enabling responses according to the emotions of the communication partner, thereby improving the user experience.

[0399] A "speech recognition engine" is a device or software that converts a user's voice input into text.

[0400] The "language identification means" is a mechanism for identifying the language of the acquired text data.

[0401] A "translation means" is a mechanism that has the function of converting text in a specified language into another specified language.

[0402] "Emotion recognition means" is a technology for analyzing and recognizing the emotional state of a user from their voice or text.

[0403] "Translation result presentation means" refers to a device or software that displays or plays the translated text or audio to the user.

[0404] The "adjustment means based on emotional state" is a mechanism that adjusts the way in which the translation result is presented based on the recognized emotional state.

[0405] The present invention is applied as a system that supports multilingual communication in brick-and-mortar stores. This system receives voice or text input from a user, translates it in real time, and analyzes the user's emotional state to present an appropriate translation result. Each part of the system is described in detail below.

[0406] System configuration

[0407] The main components of the system are:

[0408] Terminal: User interface device such as smart glasses or smartphone

[0409] Server: Cloud-based processing server

[0410] Speech recognition engine: Software installed on the device that converts voice input into text

[0411] Generative AI model: An AI model that performs language translation

[0412] Emotion recognition engine: Software that analyzes emotions from voice and text

[0413] Program processing explanation

[0414] Device:

[0415] It captures voice input from the user and passes this voice data to a voice recognition engine. The captured voice data is converted into text data and then sent to the server. For example, if a user asks, "Could you help me find a good restaurant nearby?", the voice is converted into text.

[0416] server:

[0417] The system receives text data and language information and identifies the language of the text using a language identification means. It then sends a request to a generative AI model to translate the text into the specified language. The AI ​​model used in this case is, for example, OpenAI GPT-3. Along with the translated result, it also obtains the emotional state analyzed using an emotion recognition engine (for example, Microsoft Azure's emotion recognition engine).

[0418] Device:

[0419] The translation results and emotion recognition results sent from the server are received and presented to the user. The presentation method is adjusted according to the user's emotional state. For example, when playing back the translation results aloud, the tone of the voice can be adjusted based on the user's emotional state.

[0420] Specific examples

[0421] As a specific usage scenario, consider a case where a tourist asks, "Could you help me find a good restaurant nearby?" in a brick-and-mortar store. Using this system, the store clerk's smart glasses will display the translation result, "Can you tell me where a good restaurant is nearby?". In addition, if the tourist expresses gratitude, the translation result will be played in a more friendly tone.

[0422] Example prompt sentence:

[0423] 1. English sentence: "Could you help me find a good restaurant nearby?"

[0424] Prompt (for translation): "Translate 'Could you help me find a good restaurant nearby?' from English to Japanese"

[0425] Prompt (for emotion recognition): "Analyze the emotion in the following text and tone: 'Could you help me find a good restaurant nearby?'"

[0426] In this way, the present invention provides a system that performs language translation and emotion recognition in real time, significantly improving the user's communication experience. This embodiment of the present invention enables smooth customer service even in multilingual brick-and-mortar stores, improving user satisfaction.

[0427] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0428] Step 1:

[0429] The user inputs voice or text. For example, if the user inputs "Could you help me find a good restaurant nearby?", the device acquires this voice data. The input is voice data.

[0430] Step 2:

[0431] The device uses a speech recognition engine to convert the acquired voice data into text data. Specifically, the speech recognition engine analyzes the voice waveform and generates text data such as "Could you help me find a good restaurant nearby?" The output is text data.

[0432] Step 3:

[0433] The terminal sends the converted text data and input language information to the server. At this time, the data is passed to the server using an HTTP request. The server analyzes the request and extracts the text and language information. The input is the text data, and the output is the state in which the server has received the text and language information.

[0434] Step 4:

[0435] The server identifies the language of the received text data. The server uses a generative AI model to identify the language of the text data and confirms that the language is English. The input is text data and the output is language information.

[0436] Step 5:

[0437] The server translates the identified language into the specified target language. It sends the prompt "Translate 'Could you help me find a good restaurant nearby?' from English to Japanese" to the generative AI model and receives the translation result "Could you help me find a good restaurant nearby?" The input is English text data, and the output is the translated Japanese text data.

[0438] Step 6:

[0439] The server uses an emotion recognition engine to analyze the user's emotional state. Specifically, it analyzes emotions such as joy, worry, and gratitude based on text data and voice input. The input is voice and text data, and the output is the user's emotional state.

[0440] Step 7:

[0441] The server sends the translation results and emotion recognition results to the device. The device analyzes the translation data "Can you tell me about a good restaurant nearby?" and emotion data received from the server and prepares to present them to the user. The input is the translation results and emotion recognition results, and the output is the state in which the device received them.

[0442] Step 8:

[0443] The device presents the translation result to the user. For example, the smart glasses display the text "Can you recommend a good restaurant nearby?", and the voice output device plays back the translation result aloud. The voice tone is adjusted according to the emotion data. The input is the translation result and the emotion recognition result, and the output is the translation result provided to the user.

[0444] Through this series of processes, users can receive appropriate translation results that correspond to their own emotions in real time.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] [Second embodiment]

[0449] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0450] 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.

[0451] 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).

[0452] 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.

[0453] 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.

[0454] 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).

[0455] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0456] 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.

[0457] 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.

[0458] 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.

[0459] 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.

[0460] 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."

[0461] Overall system overview

[0462] This invention is a language translation and communication assistance system that utilizes a generative AI model. This system provides multilingual, real-time translation functionality to enable users to communicate smoothly with others who speak different languages. It automatically identifies and translates the user's voice and text input, and presents the translation results to the user, thereby eliminating language barriers.

[0463] System program processing description

[0464] 1. Initialization and getting input

[0465] The user inputs voice or text into the terminal.

[0466] For example, if user A says "hello," this voice input is passed to the terminal.

[0467] 2. Speech Recognition and Language Identification

[0468] The device converts the voice input into text data.

[0469] A speech recognition engine is used to convert the voice data into text data such as "Hello."

[0470] The terminal transmits the acquired text data to the server.

[0471] The text data "Hello" and the language (Japanese) specified by the user are sent to the server.

[0472] The server identifies the language of the received data.

[0473] A generative AI model is used to confirm that the language of the received data is Japanese.

[0474] 3. Translation

[0475] The server checks the target language.

[0476] For example, if User B speaks English, the translation language is English.

[0477] The server sends a translation request to the generative AI model.

[0478] A request to translate the text data "Hello" into English is sent to the generative AI model.

[0479] The server receives the translation results from the generative AI model.

[0480] The translation result "Hello" is received.

[0481] 4. Providing translation results

[0482] The server sends the translation results to the terminal.

[0483] The translated data "Hello" is sent to the terminal.

[0484] The terminal displays or outputs the translation result to the user.

[0485] The device displays or plays as audio the text "Hello" to User B.

[0486] Specific use cases

[0487] Conversation assistance

[0488] Let us take the example of User A (speaking Japanese) having a conversation with User B (speaking English).

[0489] 1. User A says "Hello."

[0490] 2. The device converts the speech to text and sends the text "Hello" to the server.

[0491] 3. The server recognizes "hello" and translates it into English.

[0492] 4. The server sends the translation result "Hello" to the terminal.

[0493] 5. The device plays "Hello" aloud to User B.

[0494] Document Translation

[0495] Take for example the case where a user wants to translate a business letter in a foreign language.

[0496] 1. A user types or scans a business letter (in English) into a terminal.

[0497] 2. The device sends the scanned data to the server.

[0498] 3. The server sends a request to the generative AI model to translate the received data into Japanese.

[0499] 4. The server receives the translated Japanese business letter and sends it to the terminal.

[0500] 5. The device will display the translated business letter on the screen.

[0501] The system according to the present invention can provide real-time conversation assistance and document translation quickly and efficiently, and can greatly facilitate communication between different languages.

[0502] The processing flow will be explained below.

[0503] Step 1:

[0504] The user inputs voice or text. For example, if user A says "hello" in Japanese, the voice input is passed to the device.

[0505] Step 2:

[0506] The device converts the voice input into text data, and then uses a speech recognition engine to convert the voice data into the text data "Hello."

[0507] Step 3:

[0508] The device sends the acquired text data and the language information (Japanese) specified by the user to the server. Specifically, the text data "Hello" and the language information "Japanese" are sent to the server as the payload of the HTTP request.

[0509] Step 4:

[0510] The server analyzes the received data and extracts the text data "Hello" and the language information "Japanese" from the HTTP request.

[0511] Step 5:

[0512] The server double-checks the language of the data received. It uses a generative AI model to identify the language of the text data and confirms that it is the specified language (Japanese).

[0513] Step 6:

[0514] The server checks the language to translate to. For example, if User B is set to use English, it needs to be translated to "English".

[0515] Step 7:

[0516] The server sends a translation request to the generative AI model, requesting that the generative AI model translate the text data "Hello" into "English."

[0517] Step 8:

[0518] The server receives the translation result from the generative AI model. The translation result "Hello" is returned from the generative AI model to the server.

[0519] Step 9:

[0520] The server sends the translation result to the terminal. It then generates a response including the translation result "Hello" and sends it to the terminal as an HTTP response.

[0521] Step 10:

[0522] The device receives the translation result from the server and extracts the translation result "Hello" from the HTTP response.

[0523] Step 11:

[0524] The device presents the translation result to the user. Specifically, the text data "Hello" is displayed on the screen or played back as voice using a speech synthesis engine.

[0525] Step 12:

[0526] User B checks the translated message and continues the conversation. If User B says "How are you?", the process is repeated in the same way.

[0527] This step is designed to facilitate real-time conversations between users who speak different languages.

[0528] Example 1

[0529] 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."

[0530] There is a need for a system that enables smooth real-time communication between users who speak different languages. In particular, there is a need for technology that can quickly and accurately recognize voice input and translate it into the appropriate language. Another challenge is how to efficiently provide translation results to users.

[0531] 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.

[0532] In this invention, the server includes means for identifying the language of the received data using the generative AI model, means for confirming the specified target language, and means for sending a request to the generative AI model to translate the text data into the specified target language, thereby enabling real-time translation between users who speak different languages.

[0533] - "User" is the person who operates the system and inputs voice or text.

[0534] A "means for obtaining voice or text input" means any device or software for receiving voice or text data from a user. Examples include a microphone or keyboard.

[0535] "Means of converting voice data into text using voice recognition technology" refers to technology that analyzes voice data and converts it into text. A typical example is a voice recognition engine.

[0536] "Means for sending acquired text data to the server" refers to the communication means for transferring text data from the device to the server, including internet connection and API calls.

[0537] "Means for identifying the language of incoming data using a generative AI model" refers to technology that uses an artificial intelligence model to identify the language of text data. Specifically, this applies to language identification algorithms.

[0538] "Means for determining the desired target language" refers to a method for determining which language to translate into based on user preferences and other metadata. This may include database lookups or use of user profiles.

[0539] "Means for sending a request to a generative AI model to translate text data into a specified target language" refers to a method for sending an instruction to an AI translation model to translate specific text data, such as an API call or sending a prompt.

[0540] "Means for receiving translation results from a generative AI model" refers to a method by which a server obtains translated data from an AI model. Specifically, it includes a method for receiving API responses.

[0541] "Means for presenting the translated results to the user" refers to a method for displaying or playing back the translated text or audio in a way that is easy for the user to understand. This includes displaying on a display or playing the audio through an audio output device.

[0542] MODE FOR CARRYING OUT THE INVENTION

[0543] Overall system overview

[0544] This invention is a language translation and communication assistance system that utilizes a generative AI model. This system provides multilingual, real-time translation functionality to enable users to communicate smoothly with others who speak different languages. It automatically identifies and translates the user's voice and text input, and presents the translation results to the user, thereby eliminating language barriers.

[0545] Hardware and software used

[0546] 1. Audio input device: Uses a microphone to capture the user's voice.

[0547] 2. Terminal: A computing device (including smartphones and tablets) that receives user input and performs initial processing.

[0548] 3. Speech recognition technology: Use APIs such as Google Cloud Speech-to-Text.

[0549] 4. Server: A remote computing resource for processing and interpreting data.

[0550] 5. Generative AI models: Translate text data using models such as OpenAI's GPT-4.

[0551] 6. Audio output device: A speaker to provide the translation results to the user audibly.

[0552] Specific example of system operation

[0553] Step 1: Getting input

[0554] The user speaks "Hello" into the device's microphone. This voice data is input into the device.

[0555] Step 2: Voice recognition and transmission

[0556] The device uses the Google Cloud Speech-to-Text API to convert the voice data into text data such as "Hello." The converted text data is then sent to the server.

[0557] Step 3: Server Processing

[0558] The server uses the generative AI model to verify that the language of the received data is Japanese. The server then verifies the language used by User B (e.g., English).

[0559] Step 4: Translate and receive the results

[0560] The server sends a request to the generative AI model to translate "Hello" into English. For example, it passes the prompt sentence "Please translate the following Japanese into English: Hello" to the generative AI model. It receives the translation result "Hello" from the generative AI model.

[0561] Step 5: Presenting the results

[0562] The server sends the translation result to the device, which then displays the text "Hello" to User B or plays the audio "Hello" using the Google Cloud Text-to-Speech API.

[0563] Specific use cases

[0564] Conversation assistance

[0565] A specific example of User A (speaking Japanese) assisting User B (speaking English) in a conversation is as follows.

[0566] 1. User A says "Hello."

[0567] 2. The device converts the speech to text and sends the text "Hello" to the server.

[0568] 3. The server recognizes "hello" and translates it into English.

[0569] 4. The server sends the translation result "Hello" to the terminal.

[0570] 5. The device plays "Hello" aloud to User B.

[0571] Document Translation

[0572] If a user wants to translate a business letter in a foreign language, a specific example is as follows.

[0573] 1. The user types or scans a business letter (e.g., in English) into the terminal.

[0574] 2. The device sends the scanned data to the server.

[0575] 3. The server sends a request to the generative AI model to translate the received data into Japanese.

[0576] 4. The server sends the translated Japanese business letter to the terminal.

[0577] 5. The device will display the translated business letter on the screen.

[0578] This system enables real-time conversation assistance and document translation between users who speak different languages ​​quickly and efficiently, greatly facilitating communication between different languages.

[0579] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0580] Step 1:

[0581] The user inputs voice or text into the device. The user speaks "Hello" into the microphone or types "Hello" on the keyboard. This causes the voice data or text data to be acquired by the device.

[0582] Input: User voice or text

[0583] Output: Audio or text data

[0584] Step 2:

[0585] The device converts the voice input into text data. The device uses the Google Cloud Speech-to-Text API to convert the voice data into text data such as "Hello." This allows the voice information to be stored in text format on the device.

[0586] Input: Audio data

[0587] Output: Text data "Hello"

[0588] Step 3:

[0589] The device sends the acquired text data to the server. The device then sends the text data "Hello" and the language specified by the user (Japanese in this case) to the server as an HTTP request. The server then receives the text data and the specified language.

[0590] Input: Text data "Hello"

[0591] Output: Text data sent to the server and the specified language

[0592] Step 4:

[0593] The server identifies the language of the incoming data. Using a generative AI model (e.g., OpenAI's GPT-4), the server analyzes the incoming data and confirms that the language is Japanese. This prepares the server for the next processing step.

[0594] Input: Text data sent to the server and the specified language

[0595] Output: Data confirmed to be in Japanese

[0596] Step 5:

[0597] The server checks the target language. For example, if user B's language is English, the server checks the internal database or user profile to confirm that the target language is English.

[0598] Input: User B's language setting data

[0599] Output: Confirmation of the target language (English)

[0600] Step 6:

[0601] The server sends a translation request to the generative AI model. The server sends an API request to the generative AI model to translate the text data "Hello" into English. In this case, an example prompt is sent in the form "Please translate the following Japanese into English: Hello."

[0602] Input: Text data "Hello", prompt "Please translate the following Japanese into English: Hello"

[0603] Output: The prompt text sent as an API request

[0604] Step 7:

[0605] The server receives the translation result from the generative AI model. The server receives "Hello" as the translation result from the generative AI model and stores this data on the server side. The server then checks whether the translation result was obtained correctly.

[0606] Input: Translation results from a generative AI model

[0607] Output: Translation result "Hello"

[0608] Step 8:

[0609] The server sends the translation result to the terminal. The server then sends the translated data, "Hello," to the terminal as an HTTP response. This allows the translation result to reach the terminal.

[0610] Input: Translation result "Hello"

[0611] Output: Translation results sent to the device

[0612] Step 9:

[0613] The device displays or speaks the translation result to the user. The device displays the text "Hello" to User B or uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to speak "Hello." This allows User B to understand the translation result.

[0614] Input: Translation result "Hello"

[0615] Output: "Hello" displayed to User B or spoken "Hello" played

[0616] (Application example 1)

[0617] 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."

[0618] In autonomous vehicles, there is a need to facilitate communication between passengers who speak different languages, and there is a need for a means to support real-time language translation, including navigation instructions.

[0619] 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.

[0620] In this invention, the server includes means for acquiring voice or text input from a user, means for identifying the language of the acquired input data, means for translating the identified language into a specified translation language, means for presenting the translated result to the user, means including a speech recognition engine for converting the voice input into text, means including a voice player for outputting the translated text by voice, means for supporting multilingual communication, and means implemented in the autonomous vehicle, thereby enabling smooth real-time communication between passengers who speak different languages ​​and the autonomous vehicle system.

[0621] "User" means an individual who uses this system.

[0622] A "means for obtaining voice or text input" refers to a device or software that has the function of receiving a user's voice or text data.

[0623] "Means for identifying the language of acquired input data" refers to algorithms or software for determining the language of received voice or text data.

[0624] "Means for translating into a specified target language" means any device or software capable of changing an identified language into another language.

[0625] "Means for presenting the translated results to the user" refers to devices or software that display or audibly output the translated information to the user.

[0626] A "voice recognition engine" is software or hardware that converts a user's voice input into text data.

[0627] An "audio output device" is a device that converts text data into audio and plays it back.

[0628] "Supporting multilingual communication" means enabling users who speak different languages ​​to communicate smoothly with each other.

[0629] An "autonomous vehicle" is a vehicle that can move autonomously without the need for human operation.

[0630] "Real-time" refers to immediate processing and response with minimal delay.

[0631] A "server" is a computer system that processes data and provides information.

[0632] Overall system overview

[0633] This invention is a system for facilitating multilingual communication within an autonomous vehicle. The system can take voice or text input, translate it into another language in real time, and present the translation results to the user. This enables smooth communication between passengers who speak different languages ​​and the autonomous vehicle system.

[0634] System program processing description

[0635] 1. Initialization and getting input

[0636] The server uses a microphone or text input device to obtain voice or text input from the user, and the passenger's spoken or typed voice is passed to the system.

[0637] 2. Speech Recognition and Language Identification

[0638] The server uses a speech recognition engine to convert speech input into text data, for example, when a user says, "Turn left at the next intersection," the speech recognition engine converts this speech into text data.

[0639] 3. Translation

[0640] The server translates the acquired text data using a multilingual generative AI model. For example, this model translates the text "Please turn left at the next intersection" into English as "Please turn left at the next intersection."

[0641] 4. Providing translation results

[0642] The server then presents the translated text to the user using a voice output device, which plays back the translation results as audio, facilitating communication between passengers who speak different languages.

[0643] Hardware / Software used

[0644] Hardware: Vehicle-mounted microphone, speaker, and text input device

[0645] software:

[0646] speech_recognition library: for converting speech data to text

[0647] googletrans library: for text translation

[0648] pyttsx3 library: for playing the translated text aloud

[0649] Specific examples

[0650] For example, if Japanese-speaking Passenger A says, "Please turn left at the next intersection," the system recognizes the speech, converts it to text, translates it into English, and plays it back aloud as, "Please turn left at the next intersection." This allows English-speaking Driver B to understand the instruction and for the autonomous vehicle to take the appropriate next action.

[0651] Examples of prompt statements

[0652] use speech_recognition, googletrans, and pyttsx3 libraries to implement a voice recognition, translation, and speech output system for a self-driving car application. The system needs to support real-time translation from Japanese to English and announce the translated text back to the user.

[0653] According to the embodiment of the present invention, users who speak different languages ​​can smoothly communicate with each other in real time within an autonomous vehicle.

[0654] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0655] Step 1:

[0656] The terminal receives voice or text input from the user. The input voice data or text data is temporarily saved. The input in this step is the user's voice or text, and the output is the received voice data or text data.

[0657] Step 2:

[0658] The device converts voice data into text using a voice recognition engine. To perform this process, the voice data is passed to the voice recognition engine and text data is obtained as the output. The input is voice data and the output is text data.

[0659] Step 3:

[0660] The terminal transmits the acquired text data to the server. The input is the text data converted by speech recognition, and the output is the text data transmitted to the server.

[0661] Step 4:

[0662] The server identifies the language of the received text data. To do this, it uses a generative AI model to analyze the linguistic characteristics of the text and determine what language the input is in. The input is the converted text data, and the output is the identified language information.

[0663] Step 5:

[0664] The server translates the identified language into the specified target language using a generative AI model. This process involves sending a request to translate the identified language into another specified language and receiving the translation result. The input is the identified language information and text data, and the output is the translated text data.

[0665] Step 6:

[0666] The server sends the translation result to the terminal. The input is the translated text data, and the output is the translated text data sent to the terminal.

[0667] Step 7:

[0668] The terminal presents the received translated text data to the user using a voice output device. To do this, the terminal passes the translated text data to a speech synthesis engine and plays the generated voice data as its output. The input is the translated text data, and the output is the voice data played to the user.

[0669] This process flow enables users who speak different languages ​​to communicate smoothly in real time.

[0670] 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.

[0671] Overall system overview

[0672] This invention is a language translation and communication assistance system that combines a generative AI model and an emotion engine. This system not only facilitates communication between users who speak different languages, but also recognizes the user's emotions and provides optimal communication assistance based on those emotions. This system provides multilingual real-time translation and emotion recognition functions.

[0673] System program processing description

[0674] 1. Initialization and getting input

[0675] The user inputs voice or text. For example, if user A says "hello" in Japanese, the voice input is passed to the device.

[0676] 2. Speech Recognition and Language Identification

[0677] The device converts the voice input into text data, and then uses a speech recognition engine to convert the voice data into the text data "Hello."

[0678] The device sends the acquired text data and the language information (Japanese) specified by the user to the server. Specifically, the text data "Hello" and the language information "Japanese" are sent to the server as the payload of the HTTP request.

[0679] The server analyzes the received data and extracts the text data "Hello" and the language information "Japanese" from the HTTP request.

[0680] The server double-checks the language of the data received. It uses a generative AI model to identify the language of the text data and confirms that it is the specified language (Japanese).

[0681] 3. Translation and Emotion Recognition

[0682] The server checks the language to translate to. For example, if User B is set to use English, it needs to be translated to "English".

[0683] The server sends a translation request to the generative AI model, requesting that the model translate the text data "Hello" into English.

[0684] The server receives the translation result from the generative AI model. The translation result "Hello" is returned from the generative AI model to the server.

[0685] The server uses an emotion engine to analyze the user's emotional state and recognize the user's emotions (e.g., joy, sadness, anger, etc.) from the voice features and text content.

[0686] 4. Providing translation results and responding to emotions

[0687] The server sends the translation result and emotion recognition result to the terminal. A response including the translation result "Hello" and the user's emotional state is generated and sent to the terminal.

[0688] The device receives the translation result and emotion recognition result from the server. The translation result "Hello" and the emotional state are extracted from the HTTP response.

[0689] The device presents the translation result to the user. Specifically, it displays the text data "Hello" on the screen or plays it as voice using a speech synthesis engine. The tone of the voice and the way it is presented are adjusted depending on the user's emotional state.

[0690] Specific use cases

[0691] Conversation assistance

[0692] Let us take the example of User A (speaking Japanese) having a conversation with User B (speaking English).

[0693] 1. User A says "Hello."

[0694] 2. The device converts the speech to text and sends the text "Hello" to the server.

[0695] 3. The server recognizes "hello" and translates it into English.

[0696] 4. The server recognizes User A's emotional state using the emotion engine.

[0697] 5. The server sends the translation result "Hello" and User A's emotional state to the device.

[0698] 6. The device plays "Hello" aloud to User B. If User A is happy, the audio tone is set to brighter.

[0699] Document Translation

[0700] Take for example the case where a user wants to translate a business letter in a foreign language.

[0701] 1. A user types or scans a business letter (in English) into a terminal.

[0702] 2. The device sends the scanned data to the server.

[0703] 3. The server sends a request to the generative AI model to translate the received data into Japanese.

[0704] 4. The server recognizes the user's emotions based on the content of the business letter.

[0705] 5. The server sends the translated Japanese business letter and emotional state to the terminal.

[0706] 6. The device will display the translated business letter on the screen, highlighting the important parts if the user is in a hurry.

[0707] The system of the present invention not only provides real-time conversation assistance and document translation quickly and efficiently, but also takes into account the user's emotions to provide optimal communication assistance, significantly facilitating communication between different languages ​​and improving the user experience.

[0708] The processing flow will be explained below.

[0709] Step 1:

[0710] The user inputs voice or text. For example, if user A says "hello" in Japanese, the voice input is passed to the device.

[0711] Step 2:

[0712] The device converts the voice input into text data, and then uses a speech recognition engine to convert the voice data into the text data "Hello."

[0713] Step 3:

[0714] The device sends the acquired text data and the language information (Japanese) specified by the user to the server. Specifically, the text data "Hello" and the language information "Japanese" are sent to the server as the payload of the HTTP request.

[0715] Step 4:

[0716] The server analyzes the received data and extracts the text data "Hello" and the language information "Japanese" from the HTTP request.

[0717] Step 5:

[0718] The server double-checks the language of the data received. It uses a generative AI model to identify the language of the text data and confirms that it is the specified language (Japanese).

[0719] Step 6:

[0720] The server uses an emotion engine to analyze the user's emotional state and recognize the user's emotions (e.g., joy, sadness, anger, etc.) from the voice features and text content.

[0721] Step 7:

[0722] The server checks the language to translate to. For example, if User B is set to use English, it needs to be translated to "English".

[0723] Step 8:

[0724] The server sends a translation request to the generative AI model, requesting that the model translate the text data "Hello" into English.

[0725] Step 9:

[0726] The server receives the translation result from the generative AI model. The translation result "Hello" is returned from the generative AI model to the server.

[0727] Step 10:

[0728] The server sends the translation result and emotion recognition result to the terminal. A response including the translation result "Hello" and the user's emotional state is generated and sent to the terminal.

[0729] Step 11:

[0730] The device receives the translation result and emotion recognition result from the server. The translation result "Hello" and the emotional state are extracted from the HTTP response.

[0731] Step 12:

[0732] The device presents the translation result to the user. Specifically, it displays the text data "Hello" on the screen or plays it as voice using a speech synthesis engine. The tone of the voice and the way it is presented are adjusted depending on the user's emotional state.

[0733] Step 13:

[0734] User B checks the translated message and continues the conversation. If User B says "How are you?", the process is repeated in the same way.

[0735] This step is not only designed to facilitate real-time conversations between users who speak different languages, but also to provide optimal communication support by taking into account the user's emotions.

[0736] Example 2

[0737] 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."

[0738] Current language translation systems support communication between users who speak different languages, but no systems provide translation results that take the user's emotions into account. Furthermore, the lack of consideration for emotional expressions in translation results can lead to a decline in the quality of communication. Therefore, when providing multilingual communication support, there is a need for a system that recognizes the user's emotions and provides optimal translation results and responses based on those emotions.

[0739] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring voice or text input from a user, means for identifying the language of the acquired input data, means for translating the identified language into a specified translation target language, means for analyzing the user's emotions, means for adjusting the translation result based on the emotion analysis result, and means for presenting the translation result to the user. This makes it possible to provide optimal translation results and responses while taking into account the user's emotions in communication between different languages.

[0740] "User" refers to a person who uses the system to provide input by voice or text.

[0741] "Speech recognition engine" refers to technology or software for converting voice data into text data.

[0742] "Input Data" refers to information provided by a user through speech or text.

[0743] "Means for identifying language" refers to a technique or method for determining the language of input data.

[0744] "Means for translating" refers to a technique or method for converting data entered in a particular language into another specified language.

[0745] "Means for adjusting translation results" refers to techniques or methods for optimizing the presentation of translated text based on the results of user sentiment analysis.

[0746] "Means for analyzing emotions" refers to a technology or method for analyzing a user's emotional state from input speech or text.

[0747] "Server" refers to the computer device that is the core of this system and that manages and executes data processing and communications.

[0748] "Audio output device" refers to a device for reproducing audio data.

[0749] A "system" refers to a collection of components that integrate a series of processes, such as obtaining user input, identifying the language of the data, translating it, analyzing emotions, and presenting the results.

[0750] Overall system overview

[0751] This invention is a language translation and communication assistance system that combines a generative AI model and an emotion engine. This system not only facilitates communication between users who speak different languages, but also recognizes the user's emotions and provides optimal communication assistance based on those emotions. This system provides multilingual real-time translation and emotion recognition functions.

[0752] Hardware and software used

[0753] Terminal: A device through which a user inputs voice or text. This can include a microphone, keyboard, screen, scanner, etc.

[0754] Server: Serves as the central processing unit, processes and manages data. The server has API endpoints that handle HTTP requests.

[0755] Speech recognition engine: Software for converting speech to text, such as the Google Cloud Speech-to-Text API.

[0756] Generative AI models: Software for performing natural language processing, such as OpenAI's GPT series.

[0757] Emotion engine: Software for analyzing user emotions, such as Microsoft Azure's Text Analytics API.

[0758] Audio output device: Software such as Amazon Polly that plays back the translation results as audio.

[0759] System Operation and Data Processing

[0760] Initialization and getting input

[0761] The user inputs voice or text. For example, if user A says "Hello" in Japanese, the voice input is passed to the device.

[0762] Speech Recognition and Language Identification

[0763] The device converts the voice input into text data "Hello" using a speech recognition engine. The device then sends this text data and the user-specified language information "Japanese" to the server. The server receives this and reconfirms the language of the text data using a generative AI model for language identification.

[0764] Translation and Emotion Recognition

[0765] The server checks the target language and, for example, if User B is set to use English, translates it into the specified target language, English. The server requests the generative AI model to translate "hello" into English and receives the result "Hello." The server then uses an emotion engine to analyze the user's emotional state. For example, the server recognizes the user's emotion (joy, sadness, anger, etc.) from the speech features and text content seen at first sight.

[0766] Providing translation results and responding to emotions

[0767] The server sends the translation result "Hello" and the emotion recognition result to the device. The device receives this and displays it on the screen or plays it as audio using an audio output device. Depending on the user's emotion, for example, if the user is happy, the tone of the translation result is adjusted to be brighter.

[0768] Specific use cases

[0769] Conversation assistance

[0770] Let's take the example of a conversation between User A (speaking Japanese) and User B (speaking English).

[0771] 1. User A says "Hello."

[0772] 2. The device launches the speech recognition engine and receives the text "Hello."

[0773] 3. The device sends the text and language information "Japanese" to the server.

[0774] 4. The server checks the language information and requests a translation into English from the generative AI model.

[0775] 5. The server receives the translation result "Hello" and the emotion recognition result from the emotion engine.

[0776] 6. The server sends this information back to the device.

[0777] 7. The device reads "Hello" using a speech synthesis engine and conveys it to User B. If User A is happy, the voice tone will be brighter.

[0778] Prompt Sentence Examples

[0779] "Receive audio data of a user saying 'hello,' analyze its sentiment, and translate it into appropriate English."

[0780] Document Translation

[0781] Take for example the case where a user wants to translate a business letter in a foreign language.

[0782] 1. A user types or scans a business letter (in English) into a terminal.

[0783] 2. The device sends the scanned data to the server.

[0784] 3. The server requests a translation into Japanese from the generative AI model.

[0785] 4. The server receives the translation results and emotion recognition results.

[0786] 5. The server sends these results back to the device.

[0787] 6. The device displays the translated Japanese business letter on the screen, highlighting the important parts if the user is in a hurry.

[0788] Prompt Sentence Examples

[0789] "Translate an English business letter into Japanese and analyze user sentiment based on the document."

[0790] The system of the present invention not only provides real-time conversation assistance and document translation quickly and efficiently, but also takes into account the user's emotions to provide optimal communication assistance, aiming to significantly facilitate communication between different languages ​​and improve the user experience.

[0791] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0792] Step 1:

[0793] The user inputs voice or text. For example, user A says "Hello" in Japanese. At that time, the voice data from the user is input to the terminal.

[0794] Step 2:

[0795] The device converts the voice input into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). Specifically, the device's microphone captures the voice, sends it to the speech recognition engine, and obtains the text data "Hello" as output.

[0796] Step 3:

[0797] The device sends the converted text data and the user-specified language information "Japanese" to the server as the payload of an HTTP request. Specifically, the device generates an HTTP POST request and sends it to the server's API endpoint. The input is the text data "Hello" and the language information "Japanese," and the output is completion of transmission to the server.

[0798] Step 4:

[0799] The server receives the HTTP request and extracts the text data "Hello" and the language information "Japanese." Specifically, the server's API endpoint parses the request body and retrieves the required data. The input is the received HTTP request, and the output is the extracted data.

[0800] Step 5:

[0801] The server uses a generative AI model (e.g., OpenAI's GPT-3) to reconfirm the language of the text data. Specifically, the server sends a prompt to the generative AI model asking, "What language is this text in?" and receives the result. The input is the text data "Hello," and the output is the reconfirmed language information "Japanese."

[0802] Step 6:

[0803] The server checks the target language. For example, if User B is set to use English, the target language is set to "English." Specifically, the server reads User B's language setting from the database or settings file. The input is User B's language setting information, and the output is the target language, "English."

[0804] Step 7:

[0805] The server sends a translation request to the generative AI model. Specifically, the server prompts the generative AI model with "Translate 'Hello' to English" and waits for the result. The input is the text data "Hello" and the target language "English," and the output is the translation result "Hello."

[0806] Step 8:

[0807] The server receives the translation result "Hello" from the generative AI model. Specifically, the server receives the response from the generative AI model, analyzes it, and extracts the translation result. The input is the response from the generative AI model, and the output is the translation result "Hello."

[0808] Step 9:

[0809] The server analyzes the user's emotional state using an emotion engine (e.g., Microsoft Azure's Text Analytics API). Specifically, the server sends the text "Hello" to the emotion engine and receives the emotion analysis result. The input is the text data "Hello," and the output is the emotion analysis result (e.g., joy).

[0810] Step 10:

[0811] The server sends the translation result "Hello" and the emotion recognition result to the device. Specifically, the server constructs a JSON response containing the translation result and emotion information and sends it to the device via an HTTP POST request. The input is the translation result "Hello" and the emotion analysis result, and the output is completion of transmission to the device.

[0812] Step 11:

[0813] The device receives the translation result and emotion recognition result from the server. Specifically, the device parses the HTTP response to obtain the necessary data. The input is the response from the server, and the output is the translation result "Hello" and the emotion analysis result.

[0814] Step 12:

[0815] The device presents the translation result to the user. Specifically, the text data "Hello" is displayed on the screen or played as voice using a speech synthesis engine (e.g., Amazon Polly). The tone of the voice and presentation method are adjusted depending on the user's emotion. The input is the translation result "Hello" and the emotion analysis result, and the output is the translation result presented to the user.

[0816] Prompt Sentence Examples

[0817] "Receive audio data of a user saying 'hello,' analyze its sentiment, and translate it into appropriate English."

[0818] (Application example 2)

[0819] 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."

[0820] This system not only facilitates communication between users who speak different languages, but can also understand the emotions of the other person during the conversation and respond appropriately. Conventional translation systems simply convert languages ​​and are unable to fully reflect emotions and nuances, so there is a need to improve the user experience.

[0821] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0822] In this invention, the server includes means for acquiring voice or text input from a user, means for identifying the language of the acquired input data, means for translating the identified language into a specified translation language, means for presenting the translated result to the user, emotion recognition means for analyzing the emotional state of the user, and means for adjusting the presentation method of the translation result based on the emotional state of the user, thereby facilitating communication between different languages ​​and enabling responses according to the emotions of the communication partner, thereby improving the user experience.

[0823] A "speech recognition engine" is a device or software that converts a user's voice input into text.

[0824] The "language identification means" is a mechanism for identifying the language of the acquired text data.

[0825] A "translation means" is a mechanism that has the function of converting text in a specified language into another specified language.

[0826] "Emotion recognition means" is a technology for analyzing and recognizing the emotional state of a user from their voice or text.

[0827] "Translation result presentation means" refers to a device or software that displays or plays the translated text or audio to the user.

[0828] The "adjustment means based on emotional state" is a mechanism that adjusts the way in which the translation result is presented based on the recognized emotional state.

[0829] The present invention is applied as a system that supports multilingual communication in brick-and-mortar stores. This system receives voice or text input from a user, translates it in real time, and analyzes the user's emotional state to present an appropriate translation result. Each part of the system is described in detail below.

[0830] System configuration

[0831] The main components of the system are:

[0832] Terminal: User interface device such as smart glasses or smartphone

[0833] Server: Cloud-based processing server

[0834] Speech recognition engine: Software installed on the device that converts voice input into text

[0835] Generative AI model: An AI model that performs language translation

[0836] Emotion recognition engine: Software that analyzes emotions from voice and text

[0837] Program processing explanation

[0838] Device:

[0839] It captures voice input from the user and passes this voice data to a voice recognition engine. The captured voice data is converted into text data and then sent to the server. For example, if a user asks, "Could you help me find a good restaurant nearby?", the voice is converted into text.

[0840] server:

[0841] The system receives text data and language information and identifies the language of the text using a language identification means. It then sends a request to a generative AI model to translate the text into the specified language. The AI ​​model used in this case is, for example, OpenAI GPT-3. Along with the translated result, it also obtains the emotional state analyzed using an emotion recognition engine (for example, Microsoft Azure's emotion recognition engine).

[0842] Device:

[0843] The translation results and emotion recognition results sent from the server are received and presented to the user. The presentation method is adjusted according to the user's emotional state. For example, when playing back the translation results aloud, the tone of the voice can be adjusted based on the user's emotional state.

[0844] Specific examples

[0845] As a specific usage scenario, consider a case where a tourist asks, "Could you help me find a good restaurant nearby?" in a brick-and-mortar store. Using this system, the store clerk's smart glasses will display the translation result, "Can you tell me where a good restaurant is nearby?". In addition, if the tourist expresses gratitude, the translation result will be played in a more friendly tone.

[0846] Example prompt sentence:

[0847] 1. English sentence: "Could you help me find a good restaurant nearby?"

[0848] Prompt (for translation): "Translate 'Could you help me find a good restaurant nearby?' from English to Japanese"

[0849] Prompt (for emotion recognition): "Analyze the emotion in the following text and tone: 'Could you help me find a good restaurant nearby?'"

[0850] In this way, the present invention provides a system that performs language translation and emotion recognition in real time, significantly improving the user's communication experience. This embodiment of the present invention enables smooth customer service even in multilingual brick-and-mortar stores, improving user satisfaction.

[0851] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0852] Step 1:

[0853] The user inputs voice or text. For example, if the user inputs "Could you help me find a good restaurant nearby?", the device acquires this voice data. The input is voice data.

[0854] Step 2:

[0855] The device uses a speech recognition engine to convert the acquired voice data into text data. Specifically, the speech recognition engine analyzes the voice waveform and generates text data such as "Could you help me find a good restaurant nearby?" The output is text data.

[0856] Step 3:

[0857] The terminal sends the converted text data and input language information to the server. At this time, the data is passed to the server using an HTTP request. The server analyzes the request and extracts the text and language information. The input is the text data, and the output is the state in which the server has received the text and language information.

[0858] Step 4:

[0859] The server identifies the language of the received text data. The server uses a generative AI model to identify the language of the text data and confirms that the language is English. The input is text data and the output is language information.

[0860] Step 5:

[0861] The server translates the identified language into the specified target language. It sends the prompt "Translate 'Could you help me find a good restaurant nearby?' from English to Japanese" to the generative AI model and receives the translation result "Could you help me find a good restaurant nearby?" The input is English text data, and the output is the translated Japanese text data.

[0862] Step 6:

[0863] The server uses an emotion recognition engine to analyze the user's emotional state. Specifically, it analyzes emotions such as joy, worry, and gratitude based on text data and voice input. The input is voice and text data, and the output is the user's emotional state.

[0864] Step 7:

[0865] The server sends the translation results and emotion recognition results to the device. The device analyzes the translation data "Can you tell me about a good restaurant nearby?" and emotion data received from the server and prepares to present them to the user. The input is the translation results and emotion recognition results, and the output is the state in which the device received them.

[0866] Step 8:

[0867] The device presents the translation result to the user. For example, the smart glasses display the text "Can you recommend a good restaurant nearby?", and the voice output device plays back the translation result aloud. The voice tone is adjusted according to the emotion data. The input is the translation result and the emotion recognition result, and the output is the translation result provided to the user.

[0868] Through this series of processes, users can receive appropriate translation results that correspond to their own emotions in real time.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] [Third embodiment]

[0873] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0874] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0875] 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).

[0876] 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.

[0877] 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.

[0878] 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).

[0879] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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."

[0885] Overall system overview

[0886] This invention is a language translation and communication assistance system that utilizes a generative AI model. This system provides multilingual, real-time translation functionality to enable users to communicate smoothly with others who speak different languages. It automatically identifies and translates the user's voice and text input, and presents the translation results to the user, thereby eliminating language barriers.

[0887] System program processing description

[0888] 1. Initialization and getting input

[0889] The user inputs voice or text into the terminal.

[0890] For example, if user A says "hello," this voice input is passed to the terminal.

[0891] 2. Speech Recognition and Language Identification

[0892] The device converts the voice input into text data.

[0893] A speech recognition engine is used to convert the voice data into text data such as "Hello."

[0894] The terminal transmits the acquired text data to the server.

[0895] The text data "Hello" and the language (Japanese) specified by the user are sent to the server.

[0896] The server identifies the language of the received data.

[0897] A generative AI model is used to confirm that the language of the received data is Japanese.

[0898] 3. Translation

[0899] The server checks the target language.

[0900] For example, if User B speaks English, the translation language is English.

[0901] The server sends a translation request to the generative AI model.

[0902] A request to translate the text data "Hello" into English is sent to the generative AI model.

[0903] The server receives the translation results from the generative AI model.

[0904] The translation result "Hello" is received.

[0905] 4. Providing translation results

[0906] The server sends the translation results to the terminal.

[0907] The translated data "Hello" is sent to the terminal.

[0908] The terminal displays or outputs the translation result to the user.

[0909] The device displays or plays as audio the text "Hello" to User B.

[0910] Specific use cases

[0911] Conversation assistance

[0912] Let us take the example of User A (speaking Japanese) having a conversation with User B (speaking English).

[0913] 1. User A says "Hello."

[0914] 2. The device converts the speech to text and sends the text "Hello" to the server.

[0915] 3. The server recognizes "hello" and translates it into English.

[0916] 4. The server sends the translation result "Hello" to the terminal.

[0917] 5. The device plays "Hello" aloud to User B.

[0918] Document Translation

[0919] Take for example the case where a user wants to translate a business letter in a foreign language.

[0920] 1. A user types or scans a business letter (in English) into a terminal.

[0921] 2. The device sends the scanned data to the server.

[0922] 3. The server sends a request to the generative AI model to translate the received data into Japanese.

[0923] 4. The server receives the translated Japanese business letter and sends it to the terminal.

[0924] 5. The device will display the translated business letter on the screen.

[0925] The system according to the present invention can provide real-time conversation assistance and document translation quickly and efficiently, and can greatly facilitate communication between different languages.

[0926] The processing flow will be explained below.

[0927] Step 1:

[0928] The user inputs voice or text. For example, if user A says "hello" in Japanese, the voice input is passed to the device.

[0929] Step 2:

[0930] The device converts the voice input into text data, and then uses a speech recognition engine to convert the voice data into the text data "Hello."

[0931] Step 3:

[0932] The device sends the acquired text data and the language information (Japanese) specified by the user to the server. Specifically, the text data "Hello" and the language information "Japanese" are sent to the server as the payload of the HTTP request.

[0933] Step 4:

[0934] The server analyzes the received data and extracts the text data "Hello" and the language information "Japanese" from the HTTP request.

[0935] Step 5:

[0936] The server double-checks the language of the data received. It uses a generative AI model to identify the language of the text data and confirms that it is the specified language (Japanese).

[0937] Step 6:

[0938] The server checks the language to translate to. For example, if User B is set to use English, it needs to be translated to "English".

[0939] Step 7:

[0940] The server sends a translation request to the generative AI model, requesting that the generative AI model translate the text data "Hello" into "English."

[0941] Step 8:

[0942] The server receives the translation result from the generative AI model. The translation result "Hello" is returned from the generative AI model to the server.

[0943] Step 9:

[0944] The server sends the translation result to the terminal. It then generates a response including the translation result "Hello" and sends it to the terminal as an HTTP response.

[0945] Step 10:

[0946] The device receives the translation result from the server and extracts the translation result "Hello" from the HTTP response.

[0947] Step 11:

[0948] The device presents the translation result to the user. Specifically, the text data "Hello" is displayed on the screen or played back as voice using a speech synthesis engine.

[0949] Step 12:

[0950] User B checks the translated message and continues the conversation. If User B says "How are you?", the process is repeated in the same way.

[0951] This step is designed to facilitate real-time conversations between users who speak different languages.

[0952] Example 1

[0953] 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."

[0954] There is a need for a system that enables smooth real-time communication between users who speak different languages. In particular, there is a need for technology that can quickly and accurately recognize voice input and translate it into the appropriate language. Another challenge is how to efficiently provide translation results to users.

[0955] 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.

[0956] In this invention, the server includes means for identifying the language of the received data using the generative AI model, means for confirming the specified target language, and means for sending a request to the generative AI model to translate the text data into the specified target language, thereby enabling real-time translation between users who speak different languages.

[0957] - "User" is the person who operates the system and inputs voice or text.

[0958] A "means for obtaining voice or text input" means any device or software for receiving voice or text data from a user. Examples include a microphone or keyboard.

[0959] "Means of converting voice data into text using voice recognition technology" refers to technology that analyzes voice data and converts it into text. A typical example is a voice recognition engine.

[0960] "Means for sending acquired text data to the server" refers to the communication means for transferring text data from the device to the server, including internet connection and API calls.

[0961] "Means for identifying the language of incoming data using a generative AI model" refers to technology that uses an artificial intelligence model to identify the language of text data. Specifically, this applies to language identification algorithms.

[0962] "Means for determining the desired target language" refers to a method for determining which language to translate into based on user preferences and other metadata. This may include database lookups or use of user profiles.

[0963] "Means for sending a request to a generative AI model to translate text data into a specified target language" refers to a method for sending an instruction to an AI translation model to translate specific text data, such as an API call or sending a prompt.

[0964] "Means for receiving translation results from a generative AI model" refers to a method by which a server obtains translated data from an AI model. Specifically, it includes a method for receiving API responses.

[0965] "Means for presenting the translated results to the user" refers to a method for displaying or playing back the translated text or audio in a way that is easy for the user to understand. This includes displaying on a display or playing the audio through an audio output device.

[0966] MODE FOR CARRYING OUT THE INVENTION

[0967] Overall system overview

[0968] This invention is a language translation and communication assistance system that utilizes a generative AI model. This system provides multilingual, real-time translation functionality to enable users to communicate smoothly with others who speak different languages. It automatically identifies and translates the user's voice and text input, and presents the translation results to the user, thereby eliminating language barriers.

[0969] Hardware and software used

[0970] 1. Audio input device: Uses a microphone to capture the user's voice.

[0971] 2. Terminal: A computing device (including smartphones and tablets) that receives user input and performs initial processing.

[0972] 3. Speech recognition technology: Use APIs such as Google Cloud Speech-to-Text.

[0973] 4. Server: A remote computing resource for processing and interpreting data.

[0974] 5. Generative AI models: Translate text data using models such as OpenAI's GPT-4.

[0975] 6. Audio output device: A speaker to provide the translation results to the user audibly.

[0976] Specific example of system operation

[0977] Step 1: Getting input

[0978] The user speaks "Hello" into the device's microphone. This voice data is input into the device.

[0979] Step 2: Voice recognition and transmission

[0980] The device uses the Google Cloud Speech-to-Text API to convert the voice data into text data such as "Hello." The converted text data is then sent to the server.

[0981] Step 3: Server Processing

[0982] The server uses the generative AI model to verify that the language of the received data is Japanese. The server then verifies the language used by User B (e.g., English).

[0983] Step 4: Translate and receive the results

[0984] The server sends a request to the generative AI model to translate "Hello" into English. For example, it passes the prompt sentence "Please translate the following Japanese into English: Hello" to the generative AI model. It receives the translation result "Hello" from the generative AI model.

[0985] Step 5: Presenting the results

[0986] The server sends the translation result to the device, which then displays the text "Hello" to User B or plays the audio "Hello" using the Google Cloud Text-to-Speech API.

[0987] Specific use cases

[0988] Conversation assistance

[0989] A specific example of User A (speaking Japanese) assisting User B (speaking English) in a conversation is as follows.

[0990] 1. User A says "Hello."

[0991] 2. The device converts the speech to text and sends the text "Hello" to the server.

[0992] 3. The server recognizes "hello" and translates it into English.

[0993] 4. The server sends the translation result "Hello" to the terminal.

[0994] 5. The device plays "Hello" aloud to User B.

[0995] Document Translation

[0996] If a user wants to translate a business letter in a foreign language, a specific example is as follows.

[0997] 1. The user types or scans a business letter (e.g., in English) into the terminal.

[0998] 2. The device sends the scanned data to the server.

[0999] 3. The server sends a request to the generative AI model to translate the received data into Japanese.

[1000] 4. The server sends the translated Japanese business letter to the terminal.

[1001] 5. The device will display the translated business letter on the screen.

[1002] This system enables real-time conversation assistance and document translation between users who speak different languages ​​quickly and efficiently, greatly facilitating communication between different languages.

[1003] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1004] Step 1:

[1005] The user inputs voice or text into the device. The user speaks "Hello" into the microphone or types "Hello" on the keyboard. This causes the voice data or text data to be acquired by the device.

[1006] Input: User voice or text

[1007] Output: Audio or text data

[1008] Step 2:

[1009] The device converts the voice input into text data. The device uses the Google Cloud Speech-to-Text API to convert the voice data into text data such as "Hello." This allows the voice information to be stored in text format on the device.

[1010] Input: Audio data

[1011] Output: Text data "Hello"

[1012] Step 3:

[1013] The device sends the acquired text data to the server. The device then sends the text data "Hello" and the language specified by the user (Japanese in this case) to the server as an HTTP request. The server then receives the text data and the specified language.

[1014] Input: Text data "Hello"

[1015] Output: Text data sent to the server and the specified language

[1016] Step 4:

[1017] The server identifies the language of the incoming data. Using a generative AI model (e.g., OpenAI's GPT-4), the server analyzes the incoming data and confirms that the language is Japanese. This prepares the server for the next processing step.

[1018] Input: Text data sent to the server and the specified language

[1019] Output: Data confirmed to be in Japanese

[1020] Step 5:

[1021] The server checks the target language. For example, if user B's language is English, the server checks the internal database or user profile to confirm that the target language is English.

[1022] Input: User B's language setting data

[1023] Output: Confirmation of the target language (English)

[1024] Step 6:

[1025] The server sends a translation request to the generative AI model. The server sends an API request to the generative AI model to translate the text data "Hello" into English. In this case, an example prompt is sent in the form "Please translate the following Japanese into English: Hello."

[1026] Input: Text data "Hello", prompt "Please translate the following Japanese into English: Hello"

[1027] Output: The prompt text sent as an API request

[1028] Step 7:

[1029] The server receives the translation result from the generative AI model. The server receives "Hello" as the translation result from the generative AI model and stores this data on the server side. The server then checks whether the translation result was obtained correctly.

[1030] Input: Translation results from a generative AI model

[1031] Output: Translation result "Hello"

[1032] Step 8:

[1033] The server sends the translation result to the terminal. The server then sends the translated data, "Hello," to the terminal as an HTTP response. This allows the translation result to reach the terminal.

[1034] Input: Translation result "Hello"

[1035] Output: Translation results sent to the device

[1036] Step 9:

[1037] The device displays or speaks the translation result to the user. The device displays the text "Hello" to User B or uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to speak "Hello." This allows User B to understand the translation result.

[1038] Input: Translation result "Hello"

[1039] Output: "Hello" displayed to User B or spoken "Hello" played

[1040] (Application example 1)

[1041] 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."

[1042] In autonomous vehicles, there is a need to facilitate communication between passengers who speak different languages, and there is a need for a means to support real-time language translation, including navigation instructions.

[1043] 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.

[1044] In this invention, the server includes means for acquiring voice or text input from a user, means for identifying the language of the acquired input data, means for translating the identified language into a specified translation language, means for presenting the translated result to the user, means including a speech recognition engine for converting the voice input into text, means including a voice player for outputting the translated text by voice, means for supporting multilingual communication, and means implemented in the autonomous vehicle, thereby enabling smooth real-time communication between passengers who speak different languages ​​and the autonomous vehicle system.

[1045] "User" means an individual who uses this system.

[1046] A "means for obtaining voice or text input" refers to a device or software that has the function of receiving a user's voice or text data.

[1047] "Means for identifying the language of acquired input data" refers to algorithms or software for determining the language of received voice or text data.

[1048] "Means for translating into a specified target language" means any device or software capable of changing an identified language into another language.

[1049] "Means for presenting the translated results to the user" refers to devices or software that display or audibly output the translated information to the user.

[1050] A "voice recognition engine" is software or hardware that converts a user's voice input into text data.

[1051] An "audio output device" is a device that converts text data into audio and plays it back.

[1052] "Supporting multilingual communication" means enabling users who speak different languages ​​to communicate smoothly with each other.

[1053] An "autonomous vehicle" is a vehicle that can move autonomously without the need for human operation.

[1054] "Real-time" refers to immediate processing and response with minimal delay.

[1055] A "server" is a computer system that processes data and provides information.

[1056] Overall system overview

[1057] This invention is a system for facilitating multilingual communication within an autonomous vehicle. The system can take voice or text input, translate it into another language in real time, and present the translation results to the user. This enables smooth communication between passengers who speak different languages ​​and the autonomous vehicle system.

[1058] System program processing description

[1059] 1. Initialization and getting input

[1060] The server uses a microphone or text input device to obtain voice or text input from the user, and the passenger's spoken or typed voice is passed to the system.

[1061] 2. Speech Recognition and Language Identification

[1062] The server uses a speech recognition engine to convert speech input into text data, for example, when a user says, "Turn left at the next intersection," the speech recognition engine converts this speech into text data.

[1063] 3. Translation

[1064] The server translates the acquired text data using a multilingual generative AI model. For example, this model translates the text "Please turn left at the next intersection" into English as "Please turn left at the next intersection."

[1065] 4. Providing translation results

[1066] The server then presents the translated text to the user using a voice output device, which plays back the translation results as audio, facilitating communication between passengers who speak different languages.

[1067] Hardware / Software used

[1068] Hardware: Vehicle-mounted microphone, speaker, and text input device

[1069] software:

[1070] speech_recognition library: for converting speech data to text

[1071] googletrans library: for text translation

[1072] pyttsx3 library: for playing the translated text aloud

[1073] Specific examples

[1074] For example, if Japanese-speaking Passenger A says, "Please turn left at the next intersection," the system recognizes the speech, converts it to text, translates it into English, and plays it back aloud as, "Please turn left at the next intersection." This allows English-speaking Driver B to understand the instruction and for the autonomous vehicle to take the appropriate next action.

[1075] Examples of prompt statements

[1076] use speech_recognition, googletrans, and pyttsx3 libraries to implement a voice recognition, translation, and speech output system for a self-driving car application. The system needs to support real-time translation from Japanese to English and announce the translated text back to the user.

[1077] According to the embodiment of the present invention, users who speak different languages ​​can smoothly communicate with each other in real time within an autonomous vehicle.

[1078] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1079] Step 1:

[1080] The terminal receives voice or text input from the user. The input voice data or text data is temporarily saved. The input in this step is the user's voice or text, and the output is the received voice data or text data.

[1081] Step 2:

[1082] The device converts voice data into text using a voice recognition engine. To perform this process, the voice data is passed to the voice recognition engine and text data is obtained as the output. The input is voice data and the output is text data.

[1083] Step 3:

[1084] The terminal transmits the acquired text data to the server. The input is the text data converted by speech recognition, and the output is the text data transmitted to the server.

[1085] Step 4:

[1086] The server identifies the language of the received text data. To do this, it uses a generative AI model to analyze the linguistic characteristics of the text and determine what language the input is in. The input is the converted text data, and the output is the identified language information.

[1087] Step 5:

[1088] The server translates the identified language into the specified target language using a generative AI model. This process involves sending a request to translate the identified language into another specified language and receiving the translation result. The input is the identified language information and text data, and the output is the translated text data.

[1089] Step 6:

[1090] The server sends the translation result to the terminal. The input is the translated text data, and the output is the translated text data sent to the terminal.

[1091] Step 7:

[1092] The terminal presents the received translated text data to the user using a voice output device. To do this, the terminal passes the translated text data to a speech synthesis engine and plays the generated voice data as its output. The input is the translated text data, and the output is the voice data played to the user.

[1093] This process flow enables users who speak different languages ​​to communicate smoothly in real time.

[1094] 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.

[1095] Overall system overview

[1096] This invention is a language translation and communication assistance system that combines a generative AI model and an emotion engine. This system not only facilitates communication between users who speak different languages, but also recognizes the user's emotions and provides optimal communication assistance based on those emotions. This system provides multilingual real-time translation and emotion recognition functions.

[1097] System program processing description

[1098] 1. Initialization and getting input

[1099] The user inputs voice or text. For example, if user A says "hello" in Japanese, the voice input is passed to the device.

[1100] 2. Speech Recognition and Language Identification

[1101] The device converts the voice input into text data, and then uses a speech recognition engine to convert the voice data into the text data "Hello."

[1102] The device sends the acquired text data and the language information (Japanese) specified by the user to the server. Specifically, the text data "Hello" and the language information "Japanese" are sent to the server as the payload of the HTTP request.

[1103] The server analyzes the received data and extracts the text data "Hello" and the language information "Japanese" from the HTTP request.

[1104] The server double-checks the language of the data received. It uses a generative AI model to identify the language of the text data and confirms that it is the specified language (Japanese).

[1105] 3. Translation and Emotion Recognition

[1106] The server checks the language to translate to. For example, if User B is set to use English, it needs to be translated to "English".

[1107] The server sends a translation request to the generative AI model, requesting that the model translate the text data "Hello" into English.

[1108] The server receives the translation result from the generative AI model. The translation result "Hello" is returned from the generative AI model to the server.

[1109] The server uses an emotion engine to analyze the user's emotional state and recognize the user's emotions (e.g., joy, sadness, anger, etc.) from the voice features and text content.

[1110] 4. Providing translation results and responding to emotions

[1111] The server sends the translation result and emotion recognition result to the terminal. A response including the translation result "Hello" and the user's emotional state is generated and sent to the terminal.

[1112] The device receives the translation result and emotion recognition result from the server. The translation result "Hello" and the emotional state are extracted from the HTTP response.

[1113] The device presents the translation result to the user. Specifically, it displays the text data "Hello" on the screen or plays it as voice using a speech synthesis engine. The tone of the voice and the way it is presented are adjusted depending on the user's emotional state.

[1114] Specific use cases

[1115] Conversation assistance

[1116] Let us take the example of User A (speaking Japanese) having a conversation with User B (speaking English).

[1117] 1. User A says "Hello."

[1118] 2. The device converts the speech to text and sends the text "Hello" to the server.

[1119] 3. The server recognizes "hello" and translates it into English.

[1120] 4. The server recognizes User A's emotional state using the emotion engine.

[1121] 5. The server sends the translation result "Hello" and User A's emotional state to the device.

[1122] 6. The device plays "Hello" aloud to User B. If User A is happy, the audio tone is set to brighter.

[1123] Document Translation

[1124] Take for example the case where a user wants to translate a business letter in a foreign language.

[1125] 1. A user types or scans a business letter (in English) into a terminal.

[1126] 2. The device sends the scanned data to the server.

[1127] 3. The server sends a request to the generative AI model to translate the received data into Japanese.

[1128] 4. The server recognizes the user's emotions based on the content of the business letter.

[1129] 5. The server sends the translated Japanese business letter and emotional state to the terminal.

[1130] 6. The device will display the translated business letter on the screen, highlighting the important parts if the user is in a hurry.

[1131] The system of the present invention not only provides real-time conversation assistance and document translation quickly and efficiently, but also takes into account the user's emotions to provide optimal communication assistance, significantly facilitating communication between different languages ​​and improving the user experience.

[1132] The processing flow will be explained below.

[1133] Step 1:

[1134] The user inputs voice or text. For example, if user A says "hello" in Japanese, the voice input is passed to the device.

[1135] Step 2:

[1136] The device converts the voice input into text data, and then uses a speech recognition engine to convert the voice data into the text data "Hello."

[1137] Step 3:

[1138] The device sends the acquired text data and the language information (Japanese) specified by the user to the server. Specifically, the text data "Hello" and the language information "Japanese" are sent to the server as the payload of the HTTP request.

[1139] Step 4:

[1140] The server analyzes the received data and extracts the text data "Hello" and the language information "Japanese" from the HTTP request.

[1141] Step 5:

[1142] The server double-checks the language of the data received. It uses a generative AI model to identify the language of the text data and confirms that it is the specified language (Japanese).

[1143] Step 6:

[1144] The server uses an emotion engine to analyze the user's emotional state and recognize the user's emotions (e.g., joy, sadness, anger, etc.) from the voice features and text content.

[1145] Step 7:

[1146] The server checks the language to translate to. For example, if User B is set to use English, it needs to be translated to "English".

[1147] Step 8:

[1148] The server sends a translation request to the generative AI model, requesting that the model translate the text data "Hello" into English.

[1149] Step 9:

[1150] The server receives the translation result from the generative AI model. The translation result "Hello" is returned from the generative AI model to the server.

[1151] Step 10:

[1152] The server sends the translation result and emotion recognition result to the terminal. A response including the translation result "Hello" and the user's emotional state is generated and sent to the terminal.

[1153] Step 11:

[1154] The device receives the translation result and emotion recognition result from the server. The translation result "Hello" and the emotional state are extracted from the HTTP response.

[1155] Step 12:

[1156] The device presents the translation result to the user. Specifically, it displays the text data "Hello" on the screen or plays it as voice using a speech synthesis engine. The tone of the voice and the way it is presented are adjusted depending on the user's emotional state.

[1157] Step 13:

[1158] User B checks the translated message and continues the conversation. If User B says "How are you?", the process is repeated in the same way.

[1159] This step is not only designed to facilitate real-time conversations between users who speak different languages, but also to provide optimal communication support by taking into account the user's emotions.

[1160] Example 2

[1161] 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."

[1162] Current language translation systems support communication between users who speak different languages, but no systems provide translation results that take the user's emotions into account. Furthermore, the lack of consideration for emotional expressions in translation results can lead to a decline in the quality of communication. Therefore, when providing multilingual communication support, there is a need for a system that recognizes the user's emotions and provides optimal translation results and responses based on those emotions.

[1163] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring voice or text input from a user, means for identifying the language of the acquired input data, means for translating the identified language into a specified translation target language, means for analyzing the user's emotions, means for adjusting the translation result based on the emotion analysis result, and means for presenting the translation result to the user. This makes it possible to provide optimal translation results and responses while taking into account the user's emotions in communication between different languages.

[1164] "User" refers to a person who uses the system to provide input by voice or text.

[1165] "Speech recognition engine" refers to technology or software for converting voice data into text data.

[1166] "Input Data" refers to information provided by a user through speech or text.

[1167] "Means for identifying language" refers to a technique or method for determining the language of input data.

[1168] "Means for translating" refers to a technique or method for converting data entered in a particular language into another specified language.

[1169] "Means for adjusting translation results" refers to techniques or methods for optimizing the presentation of translated text based on the results of user sentiment analysis.

[1170] "Means for analyzing emotions" refers to a technology or method for analyzing a user's emotional state from input speech or text.

[1171] "Server" refers to the computer device that is the core of this system and that manages and executes data processing and communications.

[1172] "Audio output device" refers to a device for reproducing audio data.

[1173] A "system" refers to a collection of components that integrate a series of processes, such as obtaining user input, identifying the language of the data, translating it, analyzing emotions, and presenting the results.

[1174] Overall system overview

[1175] This invention is a language translation and communication assistance system that combines a generative AI model and an emotion engine. This system not only facilitates communication between users who speak different languages, but also recognizes the user's emotions and provides optimal communication assistance based on those emotions. This system provides multilingual real-time translation and emotion recognition functions.

[1176] Hardware and software used

[1177] Terminal: A device through which a user inputs voice or text. This can include a microphone, keyboard, screen, scanner, etc.

[1178] Server: Serves as the central processing unit, processes and manages data. The server has API endpoints that handle HTTP requests.

[1179] Speech recognition engine: Software for converting speech to text, such as the Google Cloud Speech-to-Text API.

[1180] Generative AI models: Software for performing natural language processing, such as OpenAI's GPT series.

[1181] Emotion engine: Software for analyzing user emotions, such as Microsoft Azure's Text Analytics API.

[1182] Audio output device: Software such as Amazon Polly that plays back the translation results as audio.

[1183] System Operation and Data Processing

[1184] Initialization and getting input

[1185] The user inputs voice or text. For example, if user A says "Hello" in Japanese, the voice input is passed to the device.

[1186] Speech Recognition and Language Identification

[1187] The device converts the voice input into text data "Hello" using a speech recognition engine. The device then sends this text data and the user-specified language information "Japanese" to the server. The server receives this and reconfirms the language of the text data using a generative AI model for language identification.

[1188] Translation and Emotion Recognition

[1189] The server checks the target language and, for example, if User B is set to use English, translates it into the specified target language, English. The server requests the generative AI model to translate "hello" into English and receives the result "Hello." The server then uses an emotion engine to analyze the user's emotional state. For example, the server recognizes the user's emotion (joy, sadness, anger, etc.) from the speech features and text content seen at first sight.

[1190] Providing translation results and responding to emotions

[1191] The server sends the translation result "Hello" and the emotion recognition result to the device. The device receives this and displays it on the screen or plays it as audio using an audio output device. Depending on the user's emotion, for example, if the user is happy, the tone of the translation result is adjusted to be brighter.

[1192] Specific use cases

[1193] Conversation assistance

[1194] Let's take the example of a conversation between User A (speaking Japanese) and User B (speaking English).

[1195] 1. User A says "Hello."

[1196] 2. The device launches the speech recognition engine and receives the text "Hello."

[1197] 3. The device sends the text and language information "Japanese" to the server.

[1198] 4. The server checks the language information and requests a translation into English from the generative AI model.

[1199] 5. The server receives the translation result "Hello" and the emotion recognition result from the emotion engine.

[1200] 6. The server sends this information back to the device.

[1201] 7. The device reads "Hello" using a speech synthesis engine and conveys it to User B. If User A is happy, the voice tone will be brighter.

[1202] Prompt Sentence Examples

[1203] "Receive audio data of a user saying 'hello,' analyze its sentiment, and translate it into appropriate English."

[1204] Document Translation

[1205] Take for example the case where a user wants to translate a business letter in a foreign language.

[1206] 1. A user types or scans a business letter (in English) into a terminal.

[1207] 2. The device sends the scanned data to the server.

[1208] 3. The server requests a translation into Japanese from the generative AI model.

[1209] 4. The server receives the translation results and emotion recognition results.

[1210] 5. The server sends these results back to the device.

[1211] 6. The device displays the translated Japanese business letter on the screen, highlighting the important parts if the user is in a hurry.

[1212] Prompt Sentence Examples

[1213] "Translate an English business letter into Japanese and analyze user sentiment based on the document."

[1214] The system of the present invention not only provides real-time conversation assistance and document translation quickly and efficiently, but also takes into account the user's emotions to provide optimal communication assistance, aiming to significantly facilitate communication between different languages ​​and improve the user experience.

[1215] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1216] Step 1:

[1217] The user inputs voice or text. For example, user A says "Hello" in Japanese. At that time, the voice data from the user is input to the terminal.

[1218] Step 2:

[1219] The device converts the voice input into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). Specifically, the device's microphone captures the voice, sends it to the speech recognition engine, and obtains the text data "Hello" as output.

[1220] Step 3:

[1221] The device sends the converted text data and the user-specified language information "Japanese" to the server as the payload of an HTTP request. Specifically, the device generates an HTTP POST request and sends it to the server's API endpoint. The input is the text data "Hello" and the language information "Japanese," and the output is completion of transmission to the server.

[1222] Step 4:

[1223] The server receives the HTTP request and extracts the text data "Hello" and the language information "Japanese." Specifically, the server's API endpoint parses the request body and retrieves the required data. The input is the received HTTP request, and the output is the extracted data.

[1224] Step 5:

[1225] The server uses a generative AI model (e.g., OpenAI's GPT-3) to reconfirm the language of the text data. Specifically, the server sends a prompt to the generative AI model asking, "What language is this text in?" and receives the result. The input is the text data "Hello," and the output is the reconfirmed language information "Japanese."

[1226] Step 6:

[1227] The server checks the target language. For example, if User B is set to use English, the target language is set to "English." Specifically, the server reads User B's language setting from the database or settings file. The input is User B's language setting information, and the output is the target language, "English."

[1228] Step 7:

[1229] The server sends a translation request to the generative AI model. Specifically, the server prompts the generative AI model with "Translate 'Hello' to English" and waits for the result. The input is the text data "Hello" and the target language "English," and the output is the translation result "Hello."

[1230] Step 8:

[1231] The server receives the translation result "Hello" from the generative AI model. Specifically, the server receives the response from the generative AI model, analyzes it, and extracts the translation result. The input is the response from the generative AI model, and the output is the translation result "Hello."

[1232] Step 9:

[1233] The server analyzes the user's emotional state using an emotion engine (e.g., Microsoft Azure's Text Analytics API). Specifically, the server sends the text "Hello" to the emotion engine and receives the emotion analysis result. The input is the text data "Hello," and the output is the emotion analysis result (e.g., joy).

[1234] Step 10:

[1235] The server sends the translation result "Hello" and the emotion recognition result to the device. Specifically, the server constructs a JSON response containing the translation result and emotion information and sends it to the device via an HTTP POST request. The input is the translation result "Hello" and the emotion analysis result, and the output is completion of transmission to the device.

[1236] Step 11:

[1237] The device receives the translation result and emotion recognition result from the server. Specifically, the device parses the HTTP response to obtain the necessary data. The input is the response from the server, and the output is the translation result "Hello" and the emotion analysis result.

[1238] Step 12:

[1239] The device presents the translation result to the user. Specifically, the text data "Hello" is displayed on the screen or played as voice using a speech synthesis engine (e.g., Amazon Polly). The tone of the voice and presentation method are adjusted depending on the user's emotion. The input is the translation result "Hello" and the emotion analysis result, and the output is the translation result presented to the user.

[1240] Prompt Sentence Examples

[1241] "Receive audio data of a user saying 'hello,' analyze its sentiment, and translate it into appropriate English."

[1242] (Application example 2)

[1243] 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."

[1244] This system not only facilitates communication between users who speak different languages, but can also understand the emotions of the other person during the conversation and respond appropriately. Conventional translation systems simply convert languages ​​and are unable to fully reflect emotions and nuances, so there is a need to improve the user experience.

[1245] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1246] In this invention, the server includes means for acquiring voice or text input from a user, means for identifying the language of the acquired input data, means for translating the identified language into a specified translation language, means for presenting the translated result to the user, emotion recognition means for analyzing the emotional state of the user, and means for adjusting the presentation method of the translation result based on the emotional state of the user, thereby facilitating communication between different languages ​​and enabling responses according to the emotions of the communication partner, thereby improving the user experience.

[1247] A "speech recognition engine" is a device or software that converts a user's voice input into text.

[1248] The "language identification means" is a mechanism for identifying the language of the acquired text data.

[1249] A "translation means" is a mechanism that has the function of converting text in a specified language into another specified language.

[1250] "Emotion recognition means" is a technology for analyzing and recognizing the emotional state of a user from their voice or text.

[1251] "Translation result presentation means" refers to a device or software that displays or plays the translated text or audio to the user.

[1252] The "adjustment means based on emotional state" is a mechanism that adjusts the way in which the translation result is presented based on the recognized emotional state.

[1253] The present invention is applied as a system that supports multilingual communication in brick-and-mortar stores. This system receives voice or text input from a user, translates it in real time, and analyzes the user's emotional state to present an appropriate translation result. Each part of the system is described in detail below.

[1254] System configuration

[1255] The main components of the system are:

[1256] Terminal: User interface device such as smart glasses or smartphone

[1257] Server: Cloud-based processing server

[1258] Speech recognition engine: Software installed on the device that converts voice input into text

[1259] Generative AI model: An AI model that performs language translation

[1260] Emotion recognition engine: Software that analyzes emotions from voice and text

[1261] Program processing explanation

[1262] Device:

[1263] It captures voice input from the user and passes this voice data to a voice recognition engine. The captured voice data is converted into text data and then sent to the server. For example, if a user asks, "Could you help me find a good restaurant nearby?", the voice is converted into text.

[1264] server:

[1265] The system receives text data and language information and identifies the language of the text using a language identification means. It then sends a request to a generative AI model to translate the text into the specified language. The AI ​​model used in this case is, for example, OpenAI GPT-3. Along with the translated result, it also obtains the emotional state analyzed using an emotion recognition engine (for example, Microsoft Azure's emotion recognition engine).

[1266] Device:

[1267] The translation results and emotion recognition results sent from the server are received and presented to the user. The presentation method is adjusted according to the user's emotional state. For example, when playing back the translation results aloud, the tone of the voice can be adjusted based on the user's emotional state.

[1268] Specific examples

[1269] As a specific usage scenario, consider a case where a tourist asks, "Could you help me find a good restaurant nearby?" in a brick-and-mortar store. Using this system, the store clerk's smart glasses will display the translation result, "Can you tell me where a good restaurant is nearby?". In addition, if the tourist expresses gratitude, the translation result will be played in a more friendly tone.

[1270] Example prompt sentence:

[1271] 1. English sentence: "Could you help me find a good restaurant nearby?"

[1272] Prompt (for translation): "Translate 'Could you help me find a good restaurant nearby?' from English to Japanese"

[1273] Prompt (for emotion recognition): "Analyze the emotion in the following text and tone: 'Could you help me find a good restaurant nearby?'"

[1274] In this way, the present invention provides a system that performs language translation and emotion recognition in real time, significantly improving the user's communication experience. This embodiment of the present invention enables smooth customer service even in multilingual brick-and-mortar stores, improving user satisfaction.

[1275] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1276] Step 1:

[1277] The user inputs voice or text. For example, if the user inputs "Could you help me find a good restaurant nearby?", the device acquires this voice data. The input is voice data.

[1278] Step 2:

[1279] The device uses a speech recognition engine to convert the acquired voice data into text data. Specifically, the speech recognition engine analyzes the voice waveform and generates text data such as "Could you help me find a good restaurant nearby?" The output is text data.

[1280] Step 3:

[1281] The terminal sends the converted text data and input language information to the server. At this time, the data is passed to the server using an HTTP request. The server analyzes the request and extracts the text and language information. The input is the text data, and the output is the state in which the server has received the text and language information.

[1282] Step 4:

[1283] The server identifies the language of the received text data. The server uses a generative AI model to identify the language of the text data and confirms that the language is English. The input is text data and the output is language information.

[1284] Step 5:

[1285] The server translates the identified language into the specified target language. It sends the prompt "Translate 'Could you help me find a good restaurant nearby?' from English to Japanese" to the generative AI model and receives the translation result "Could you help me find a good restaurant nearby?" The input is English text data, and the output is the translated Japanese text data.

[1286] Step 6:

[1287] The server uses an emotion recognition engine to analyze the user's emotional state. Specifically, it analyzes emotions such as joy, worry, and gratitude based on text data and voice input. The input is voice and text data, and the output is the user's emotional state.

[1288] Step 7:

[1289] The server sends the translation results and emotion recognition results to the device. The device analyzes the translation data "Can you tell me about a good restaurant nearby?" and emotion data received from the server and prepares to present them to the user. The input is the translation results and emotion recognition results, and the output is the state in which the device received them.

[1290] Step 8:

[1291] The device presents the translation result to the user. For example, the smart glasses display the text "Can you recommend a good restaurant nearby?", and the voice output device plays back the translation result aloud. The voice tone is adjusted according to the emotion data. The input is the translation result and the emotion recognition result, and the output is the translation result provided to the user.

[1292] Through this series of processes, users can receive appropriate translation results that correspond to their own emotions in real time.

[1293] 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.

[1294] 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.

[1295] 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.

[1296] [Fourth embodiment]

[1297] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1298] 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.

[1299] 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).

[1300] 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.

[1301] 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.

[1302] 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).

[1303] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1304] 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.

[1305] 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.

[1306] 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.

[1307] 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.

[1308] 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.

[1309] 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."

[1310] Overall system overview

[1311] This invention is a language translation and communication assistance system that utilizes a generative AI model. This system provides multilingual, real-time translation functionality to enable users to communicate smoothly with others who speak different languages. It automatically identifies and translates the user's voice and text input, and presents the translation results to the user, thereby eliminating language barriers.

[1312] System program processing description

[1313] 1. Initialization and getting input

[1314] The user inputs voice or text into the terminal.

[1315] For example, if user A says "hello," this voice input is passed to the terminal.

[1316] 2. Speech Recognition and Language Identification

[1317] The device converts the voice input into text data.

[1318] A speech recognition engine is used to convert the voice data into text data such as "Hello."

[1319] The terminal transmits the acquired text data to the server.

[1320] The text data "Hello" and the language (Japanese) specified by the user are sent to the server.

[1321] The server identifies the language of the received data.

[1322] A generative AI model is used to confirm that the language of the received data is Japanese.

[1323] 3. Translation

[1324] The server checks the target language.

[1325] For example, if User B speaks English, the translation language is English.

[1326] The server sends a translation request to the generative AI model.

[1327] A request to translate the text data "Hello" into English is sent to the generative AI model.

[1328] The server receives the translation results from the generative AI model.

[1329] The translation result "Hello" is received.

[1330] 4. Providing translation results

[1331] The server sends the translation results to the terminal.

[1332] The translated data "Hello" is sent to the terminal.

[1333] The terminal displays or outputs the translation result to the user.

[1334] The device displays or plays as audio the text "Hello" to User B.

[1335] Specific use cases

[1336] Conversation assistance

[1337] Let us take the example of User A (speaking Japanese) having a conversation with User B (speaking English).

[1338] 1. User A says "Hello."

[1339] 2. The device converts the speech to text and sends the text "Hello" to the server.

[1340] 3. The server recognizes "hello" and translates it into English.

[1341] 4. The server sends the translation result "Hello" to the terminal.

[1342] 5. The device plays "Hello" aloud to User B.

[1343] Document Translation

[1344] Take for example the case where a user wants to translate a business letter in a foreign language.

[1345] 1. A user types or scans a business letter (in English) into a terminal.

[1346] 2. The device sends the scanned data to the server.

[1347] 3. The server sends a request to the generative AI model to translate the received data into Japanese.

[1348] 4. The server receives the translated Japanese business letter and sends it to the terminal.

[1349] 5. The device will display the translated business letter on the screen.

[1350] The system according to the present invention can provide real-time conversation assistance and document translation quickly and efficiently, and can greatly facilitate communication between different languages.

[1351] The processing flow will be explained below.

[1352] Step 1:

[1353] The user inputs voice or text. For example, if user A says "hello" in Japanese, the voice input is passed to the device.

[1354] Step 2:

[1355] The device converts the voice input into text data, and then uses a speech recognition engine to convert the voice data into the text data "Hello."

[1356] Step 3:

[1357] The device sends the acquired text data and the language information (Japanese) specified by the user to the server. Specifically, the text data "Hello" and the language information "Japanese" are sent to the server as the payload of the HTTP request.

[1358] Step 4:

[1359] The server analyzes the received data and extracts the text data "Hello" and the language information "Japanese" from the HTTP request.

[1360] Step 5:

[1361] The server double-checks the language of the data received. It uses a generative AI model to identify the language of the text data and confirms that it is the specified language (Japanese).

[1362] Step 6:

[1363] The server checks the language to translate to. For example, if User B is set to use English, it needs to be translated to "English".

[1364] Step 7:

[1365] The server sends a translation request to the generative AI model, requesting that the generative AI model translate the text data "Hello" into "English."

[1366] Step 8:

[1367] The server receives the translation result from the generative AI model. The translation result "Hello" is returned from the generative AI model to the server.

[1368] Step 9:

[1369] The server sends the translation result to the terminal. It then generates a response including the translation result "Hello" and sends it to the terminal as an HTTP response.

[1370] Step 10:

[1371] The device receives the translation result from the server and extracts the translation result "Hello" from the HTTP response.

[1372] Step 11:

[1373] The device presents the translation result to the user. Specifically, the text data "Hello" is displayed on the screen or played back as voice using a speech synthesis engine.

[1374] Step 12:

[1375] User B checks the translated message and continues the conversation. If User B says "How are you?", the process is repeated in the same way.

[1376] This step is designed to facilitate real-time conversations between users who speak different languages.

[1377] Example 1

[1378] 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."

[1379] There is a need for a system that enables smooth real-time communication between users who speak different languages. In particular, there is a need for technology that can quickly and accurately recognize voice input and translate it into the appropriate language. Another challenge is how to efficiently provide translation results to users.

[1380] 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.

[1381] In this invention, the server includes means for identifying the language of the received data using the generative AI model, means for confirming the specified target language, and means for sending a request to the generative AI model to translate the text data into the specified target language, thereby enabling real-time translation between users who speak different languages.

[1382] - "User" is the person who operates the system and inputs voice or text.

[1383] A "means for obtaining voice or text input" means any device or software for receiving voice or text data from a user. Examples include a microphone or keyboard.

[1384] "Means of converting voice data into text using voice recognition technology" refers to technology that analyzes voice data and converts it into text. A typical example is a voice recognition engine.

[1385] "Means for sending acquired text data to the server" refers to the communication means for transferring text data from the device to the server, including internet connection and API calls.

[1386] "Means for identifying the language of incoming data using a generative AI model" refers to technology that uses an artificial intelligence model to identify the language of text data. Specifically, this applies to language identification algorithms.

[1387] "Means for determining the desired target language" refers to a method for determining which language to translate into based on user preferences and other metadata. This may include database lookups or use of user profiles.

[1388] "Means for sending a request to a generative AI model to translate text data into a specified target language" refers to a method for sending an instruction to an AI translation model to translate specific text data, such as an API call or sending a prompt.

[1389] "Means for receiving translation results from a generative AI model" refers to a method by which a server obtains translated data from an AI model. Specifically, it includes a method for receiving API responses.

[1390] "Means for presenting the translated results to the user" refers to a method for displaying or playing back the translated text or audio in a way that is easy for the user to understand. This includes displaying on a display or playing the audio through an audio output device.

[1391] MODE FOR CARRYING OUT THE INVENTION

[1392] Overall system overview

[1393] This invention is a language translation and communication assistance system that utilizes a generative AI model. This system provides multilingual, real-time translation functionality to enable users to communicate smoothly with others who speak different languages. It automatically identifies and translates the user's voice and text input, and presents the translation results to the user, thereby eliminating language barriers.

[1394] Hardware and software used

[1395] 1. Audio input device: Uses a microphone to capture the user's voice.

[1396] 2. Terminal: A computing device (including smartphones and tablets) that receives user input and performs initial processing.

[1397] 3. Speech recognition technology: Use APIs such as Google Cloud Speech-to-Text.

[1398] 4. Server: A remote computing resource for processing and interpreting data.

[1399] 5. Generative AI models: Translate text data using models such as OpenAI's GPT-4.

[1400] 6. Audio output device: A speaker to provide the translation results to the user audibly.

[1401] Specific example of system operation

[1402] Step 1: Getting input

[1403] The user speaks "Hello" into the device's microphone. This voice data is input into the device.

[1404] Step 2: Voice recognition and transmission

[1405] The device uses the Google Cloud Speech-to-Text API to convert the voice data into text data such as "Hello." The converted text data is then sent to the server.

[1406] Step 3: Server Processing

[1407] The server uses the generative AI model to verify that the language of the received data is Japanese. The server then verifies the language used by User B (e.g., English).

[1408] Step 4: Translate and receive the results

[1409] The server sends a request to the generative AI model to translate "Hello" into English. For example, it passes the prompt sentence "Please translate the following Japanese into English: Hello" to the generative AI model. It receives the translation result "Hello" from the generative AI model.

[1410] Step 5: Presenting the results

[1411] The server sends the translation result to the device, which then displays the text "Hello" to User B or plays the audio "Hello" using the Google Cloud Text-to-Speech API.

[1412] Specific use cases

[1413] Conversation assistance

[1414] A specific example of User A (speaking Japanese) assisting User B (speaking English) in a conversation is as follows.

[1415] 1. User A says "Hello."

[1416] 2. The device converts the speech to text and sends the text "Hello" to the server.

[1417] 3. The server recognizes "hello" and translates it into English.

[1418] 4. The server sends the translation result "Hello" to the terminal.

[1419] 5. The device plays "Hello" aloud to User B.

[1420] Document Translation

[1421] If a user wants to translate a business letter in a foreign language, a specific example is as follows.

[1422] 1. The user types or scans a business letter (e.g., in English) into the terminal.

[1423] 2. The device sends the scanned data to the server.

[1424] 3. The server sends a request to the generative AI model to translate the received data into Japanese.

[1425] 4. The server sends the translated Japanese business letter to the terminal.

[1426] 5. The device will display the translated business letter on the screen.

[1427] This system enables real-time conversation assistance and document translation between users who speak different languages ​​quickly and efficiently, greatly facilitating communication between different languages.

[1428] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1429] Step 1:

[1430] The user inputs voice or text into the device. The user speaks "Hello" into the microphone or types "Hello" on the keyboard. This causes the voice data or text data to be acquired by the device.

[1431] Input: User voice or text

[1432] Output: Audio or text data

[1433] Step 2:

[1434] The device converts the voice input into text data. The device uses the Google Cloud Speech-to-Text API to convert the voice data into text data such as "Hello." This allows the voice information to be stored in text format on the device.

[1435] Input: Audio data

[1436] Output: Text data "Hello"

[1437] Step 3:

[1438] The device sends the acquired text data to the server. The device then sends the text data "Hello" and the language specified by the user (Japanese in this case) to the server as an HTTP request. The server then receives the text data and the specified language.

[1439] Input: Text data "Hello"

[1440] Output: Text data sent to the server and the specified language

[1441] Step 4:

[1442] The server identifies the language of the incoming data. Using a generative AI model (e.g., OpenAI's GPT-4), the server analyzes the incoming data and confirms that the language is Japanese. This prepares the server for the next processing step.

[1443] Input: Text data sent to the server and the specified language

[1444] Output: Data confirmed to be in Japanese

[1445] Step 5:

[1446] The server checks the target language. For example, if user B's language is English, the server checks the internal database or user profile to confirm that the target language is English.

[1447] Input: User B's language setting data

[1448] Output: Confirmation of the target language (English)

[1449] Step 6:

[1450] The server sends a translation request to the generative AI model. The server sends an API request to the generative AI model to translate the text data "Hello" into English. In this case, an example prompt is sent in the form "Please translate the following Japanese into English: Hello."

[1451] Input: Text data "Hello", prompt "Please translate the following Japanese into English: Hello"

[1452] Output: The prompt text sent as an API request

[1453] Step 7:

[1454] The server receives the translation result from the generative AI model. The server receives "Hello" as the translation result from the generative AI model and stores this data on the server side. The server then checks whether the translation result was obtained correctly.

[1455] Input: Translation results from a generative AI model

[1456] Output: Translation result "Hello"

[1457] Step 8:

[1458] The server sends the translation result to the terminal. The server then sends the translated data, "Hello," to the terminal as an HTTP response. This allows the translation result to reach the terminal.

[1459] Input: Translation result "Hello"

[1460] Output: Translation results sent to the device

[1461] Step 9:

[1462] The device displays or speaks the translation result to the user. The device displays the text "Hello" to User B or uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to speak "Hello." This allows User B to understand the translation result.

[1463] Input: Translation result "Hello"

[1464] Output: "Hello" displayed to User B or spoken "Hello" played

[1465] (Application example 1)

[1466] 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."

[1467] In autonomous vehicles, there is a need to facilitate communication between passengers who speak different languages, and there is a need for a means to support real-time language translation, including navigation instructions.

[1468] 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.

[1469] In this invention, the server includes means for acquiring voice or text input from a user, means for identifying the language of the acquired input data, means for translating the identified language into a specified translation language, means for presenting the translated result to the user, means including a speech recognition engine for converting the voice input into text, means including a voice player for outputting the translated text by voice, means for supporting multilingual communication, and means implemented in the autonomous vehicle, thereby enabling smooth real-time communication between passengers who speak different languages ​​and the autonomous vehicle system.

[1470] "User" means an individual who uses this system.

[1471] A "means for obtaining voice or text input" refers to a device or software that has the function of receiving a user's voice or text data.

[1472] "Means for identifying the language of acquired input data" refers to algorithms or software for determining the language of received voice or text data.

[1473] "Means for translating into a specified target language" means any device or software capable of changing an identified language into another language.

[1474] "Means for presenting the translated results to the user" refers to devices or software that display or audibly output the translated information to the user.

[1475] A "voice recognition engine" is software or hardware that converts a user's voice input into text data.

[1476] An "audio output device" is a device that converts text data into audio and plays it back.

[1477] "Supporting multilingual communication" means enabling users who speak different languages ​​to communicate smoothly with each other.

[1478] An "autonomous vehicle" is a vehicle that can move autonomously without the need for human operation.

[1479] "Real-time" refers to immediate processing and response with minimal delay.

[1480] A "server" is a computer system that processes data and provides information.

[1481] Overall system overview

[1482] This invention is a system for facilitating multilingual communication within an autonomous vehicle. The system can take voice or text input, translate it into another language in real time, and present the translation results to the user. This enables smooth communication between passengers who speak different languages ​​and the autonomous vehicle system.

[1483] System program processing description

[1484] 1. Initialization and getting input

[1485] The server uses a microphone or text input device to obtain voice or text input from the user, and the passenger's spoken or typed voice is passed to the system.

[1486] 2. Speech Recognition and Language Identification

[1487] The server uses a speech recognition engine to convert speech input into text data, for example, when a user says, "Turn left at the next intersection," the speech recognition engine converts this speech into text data.

[1488] 3. Translation

[1489] The server translates the acquired text data using a multilingual generative AI model. For example, this model translates the text "Please turn left at the next intersection" into English as "Please turn left at the next intersection."

[1490] 4. Providing translation results

[1491] The server then presents the translated text to the user using a voice output device, which plays back the translation results as audio, facilitating communication between passengers who speak different languages.

[1492] Hardware / Software used

[1493] Hardware: Vehicle-mounted microphone, speaker, and text input device

[1494] software:

[1495] speech_recognition library: for converting speech data to text

[1496] googletrans library: for text translation

[1497] pyttsx3 library: for playing the translated text aloud

[1498] Specific examples

[1499] For example, if Japanese-speaking Passenger A says, "Please turn left at the next intersection," the system recognizes the speech, converts it to text, translates it into English, and plays it back aloud as, "Please turn left at the next intersection." This allows English-speaking Driver B to understand the instruction and for the autonomous vehicle to take the appropriate next action.

[1500] Examples of prompt statements

[1501] use speech_recognition, googletrans, and pyttsx3 libraries to implement a voice recognition, translation, and speech output system for a self-driving car application. The system needs to support real-time translation from Japanese to English and announce the translated text back to the user.

[1502] According to the embodiment of the present invention, users who speak different languages ​​can smoothly communicate with each other in real time within an autonomous vehicle.

[1503] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1504] Step 1:

[1505] The terminal receives voice or text input from the user. The input voice data or text data is temporarily saved. The input in this step is the user's voice or text, and the output is the received voice data or text data.

[1506] Step 2:

[1507] The device converts voice data into text using a voice recognition engine. To perform this process, the voice data is passed to the voice recognition engine and text data is obtained as the output. The input is voice data and the output is text data.

[1508] Step 3:

[1509] The terminal transmits the acquired text data to the server. The input is the text data converted by speech recognition, and the output is the text data transmitted to the server.

[1510] Step 4:

[1511] The server identifies the language of the received text data. To do this, it uses a generative AI model to analyze the linguistic characteristics of the text and determine what language the input is in. The input is the converted text data, and the output is the identified language information.

[1512] Step 5:

[1513] The server translates the identified language into the specified target language using a generative AI model. This process involves sending a request to translate the identified language into another specified language and receiving the translation result. The input is the identified language information and text data, and the output is the translated text data.

[1514] Step 6:

[1515] The server sends the translation result to the terminal. The input is the translated text data, and the output is the translated text data sent to the terminal.

[1516] Step 7:

[1517] The terminal presents the received translated text data to the user using a voice output device. To do this, the terminal passes the translated text data to a speech synthesis engine and plays the generated voice data as its output. The input is the translated text data, and the output is the voice data played to the user.

[1518] This process flow enables users who speak different languages ​​to communicate smoothly in real time.

[1519] 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.

[1520] Overall system overview

[1521] This invention is a language translation and communication assistance system that combines a generative AI model and an emotion engine. This system not only facilitates communication between users who speak different languages, but also recognizes the user's emotions and provides optimal communication assistance based on those emotions. This system provides multilingual real-time translation and emotion recognition functions.

[1522] System program processing description

[1523] 1. Initialization and getting input

[1524] The user inputs voice or text. For example, if user A says "hello" in Japanese, the voice input is passed to the device.

[1525] 2. Speech Recognition and Language Identification

[1526] The device converts the voice input into text data, and then uses a speech recognition engine to convert the voice data into the text data "Hello."

[1527] The device sends the acquired text data and the language information (Japanese) specified by the user to the server. Specifically, the text data "Hello" and the language information "Japanese" are sent to the server as the payload of the HTTP request.

[1528] The server analyzes the received data and extracts the text data "Hello" and the language information "Japanese" from the HTTP request.

[1529] The server double-checks the language of the data received. It uses a generative AI model to identify the language of the text data and confirms that it is the specified language (Japanese).

[1530] 3. Translation and Emotion Recognition

[1531] The server checks the language to translate to. For example, if User B is set to use English, it needs to be translated to "English".

[1532] The server sends a translation request to the generative AI model, requesting that the model translate the text data "Hello" into English.

[1533] The server receives the translation result from the generative AI model. The translation result "Hello" is returned from the generative AI model to the server.

[1534] The server uses an emotion engine to analyze the user's emotional state and recognize the user's emotions (e.g., joy, sadness, anger, etc.) from the voice features and text content.

[1535] 4. Providing translation results and responding to emotions

[1536] The server sends the translation result and emotion recognition result to the terminal. A response including the translation result "Hello" and the user's emotional state is generated and sent to the terminal.

[1537] The device receives the translation result and emotion recognition result from the server. The translation result "Hello" and the emotional state are extracted from the HTTP response.

[1538] The device presents the translation result to the user. Specifically, it displays the text data "Hello" on the screen or plays it as voice using a speech synthesis engine. The tone of the voice and the way it is presented are adjusted depending on the user's emotional state.

[1539] Specific use cases

[1540] Conversation assistance

[1541] Let us take the example of User A (speaking Japanese) having a conversation with User B (speaking English).

[1542] 1. User A says "Hello."

[1543] 2. The device converts the speech to text and sends the text "Hello" to the server.

[1544] 3. The server recognizes "hello" and translates it into English.

[1545] 4. The server recognizes User A's emotional state using the emotion engine.

[1546] 5. The server sends the translation result "Hello" and User A's emotional state to the device.

[1547] 6. The device plays "Hello" aloud to User B. If User A is happy, the audio tone is set to brighter.

[1548] Document Translation

[1549] Take for example the case where a user wants to translate a business letter in a foreign language.

[1550] 1. A user types or scans a business letter (in English) into a terminal.

[1551] 2. The device sends the scanned data to the server.

[1552] 3. The server sends a request to the generative AI model to translate the received data into Japanese.

[1553] 4. The server recognizes the user's emotions based on the content of the business letter.

[1554] 5. The server sends the translated Japanese business letter and emotional state to the terminal.

[1555] 6. The device will display the translated business letter on the screen, highlighting the important parts if the user is in a hurry.

[1556] The system of the present invention not only provides real-time conversation assistance and document translation quickly and efficiently, but also takes into account the user's emotions to provide optimal communication assistance, significantly facilitating communication between different languages ​​and improving the user experience.

[1557] The processing flow will be explained below.

[1558] Step 1:

[1559] The user inputs voice or text. For example, if user A says "hello" in Japanese, the voice input is passed to the device.

[1560] Step 2:

[1561] The device converts the voice input into text data, and then uses a speech recognition engine to convert the voice data into the text data "Hello."

[1562] Step 3:

[1563] The device sends the acquired text data and the language information (Japanese) specified by the user to the server. Specifically, the text data "Hello" and the language information "Japanese" are sent to the server as the payload of the HTTP request.

[1564] Step 4:

[1565] The server analyzes the received data and extracts the text data "Hello" and the language information "Japanese" from the HTTP request.

[1566] Step 5:

[1567] The server double-checks the language of the data received. It uses a generative AI model to identify the language of the text data and confirms that it is the specified language (Japanese).

[1568] Step 6:

[1569] The server uses an emotion engine to analyze the user's emotional state and recognize the user's emotions (e.g., joy, sadness, anger, etc.) from the voice features and text content.

[1570] Step 7:

[1571] The server checks the language to translate to. For example, if User B is set to use English, it needs to be translated to "English".

[1572] Step 8:

[1573] The server sends a translation request to the generative AI model, requesting that the model translate the text data "Hello" into English.

[1574] Step 9:

[1575] The server receives the translation result from the generative AI model. The translation result "Hello" is returned from the generative AI model to the server.

[1576] Step 10:

[1577] The server sends the translation result and emotion recognition result to the terminal. A response including the translation result "Hello" and the user's emotional state is generated and sent to the terminal.

[1578] Step 11:

[1579] The device receives the translation result and emotion recognition result from the server. The translation result "Hello" and the emotional state are extracted from the HTTP response.

[1580] Step 12:

[1581] The device presents the translation result to the user. Specifically, it displays the text data "Hello" on the screen or plays it as voice using a speech synthesis engine. The tone of the voice and the way it is presented are adjusted depending on the user's emotional state.

[1582] Step 13:

[1583] User B checks the translated message and continues the conversation. If User B says "How are you?", the process is repeated in the same way.

[1584] This step is not only designed to facilitate real-time conversations between users who speak different languages, but also to provide optimal communication support by taking into account the user's emotions.

[1585] Example 2

[1586] 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."

[1587] Current language translation systems support communication between users who speak different languages, but no systems provide translation results that take the user's emotions into account. Furthermore, the lack of consideration for emotional expressions in translation results can lead to a decline in the quality of communication. Therefore, when providing multilingual communication support, there is a need for a system that recognizes the user's emotions and provides optimal translation results and responses based on those emotions.

[1588] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for acquiring voice or text input from a user, means for identifying the language of the acquired input data, means for translating the identified language into a specified translation target language, means for analyzing the user's emotions, means for adjusting the translation result based on the emotion analysis result, and means for presenting the translation result to the user. This makes it possible to provide optimal translation results and responses while taking into account the user's emotions in communication between different languages.

[1589] "User" refers to a person who uses the system to provide input by voice or text.

[1590] "Speech recognition engine" refers to technology or software for converting voice data into text data.

[1591] "Input Data" refers to information provided by a user through speech or text.

[1592] "Means for identifying language" refers to a technique or method for determining the language of input data.

[1593] "Means for translating" refers to a technique or method for converting data entered in a particular language into another specified language.

[1594] "Means for adjusting translation results" refers to techniques or methods for optimizing the presentation of translated text based on the results of user sentiment analysis.

[1595] "Means for analyzing emotions" refers to a technology or method for analyzing a user's emotional state from input speech or text.

[1596] "Server" refers to the computer device that is the core of this system and that manages and executes data processing and communications.

[1597] "Audio output device" refers to a device for reproducing audio data.

[1598] A "system" refers to a collection of components that integrate a series of processes, such as obtaining user input, identifying the language of the data, translating it, analyzing emotions, and presenting the results.

[1599] Overall system overview

[1600] This invention is a language translation and communication assistance system that combines a generative AI model and an emotion engine. This system not only facilitates communication between users who speak different languages, but also recognizes the user's emotions and provides optimal communication assistance based on those emotions. This system provides multilingual real-time translation and emotion recognition functions.

[1601] Hardware and software used

[1602] Terminal: A device through which a user inputs voice or text. This can include a microphone, keyboard, screen, scanner, etc.

[1603] Server: Serves as the central processing unit, processes and manages data. The server has API endpoints that handle HTTP requests.

[1604] Speech recognition engine: Software for converting speech to text, such as the Google Cloud Speech-to-Text API.

[1605] Generative AI models: Software for performing natural language processing, such as OpenAI's GPT series.

[1606] Emotion engine: Software for analyzing user emotions, such as Microsoft Azure's Text Analytics API.

[1607] Audio output device: Software such as Amazon Polly that plays back the translation results as audio.

[1608] System Operation and Data Processing

[1609] Initialization and getting input

[1610] The user inputs voice or text. For example, if user A says "Hello" in Japanese, the voice input is passed to the device.

[1611] Speech Recognition and Language Identification

[1612] The device converts the voice input into text data "Hello" using a speech recognition engine. The device then sends this text data and the user-specified language information "Japanese" to the server. The server receives this and reconfirms the language of the text data using a generative AI model for language identification.

[1613] Translation and Emotion Recognition

[1614] The server checks the target language and, for example, if User B is set to use English, translates it into the specified target language, English. The server requests the generative AI model to translate "hello" into English and receives the result "Hello." The server then uses an emotion engine to analyze the user's emotional state. For example, the server recognizes the user's emotion (joy, sadness, anger, etc.) from the speech features and text content seen at first sight.

[1615] Providing translation results and responding to emotions

[1616] The server sends the translation result "Hello" and the emotion recognition result to the device. The device receives this and displays it on the screen or plays it as audio using an audio output device. Depending on the user's emotion, for example, if the user is happy, the tone of the translation result is adjusted to be brighter.

[1617] Specific use cases

[1618] Conversation assistance

[1619] Let's take the example of a conversation between User A (speaking Japanese) and User B (speaking English).

[1620] 1. User A says "Hello."

[1621] 2. The device launches the speech recognition engine and receives the text "Hello."

[1622] 3. The device sends the text and language information "Japanese" to the server.

[1623] 4. The server checks the language information and requests a translation into English from the generative AI model.

[1624] 5. The server receives the translation result "Hello" and the emotion recognition result from the emotion engine.

[1625] 6. The server sends this information back to the device.

[1626] 7. The device reads "Hello" using a speech synthesis engine and conveys it to User B. If User A is happy, the voice tone will be brighter.

[1627] Prompt Sentence Examples

[1628] "Receive audio data of a user saying 'hello,' analyze its sentiment, and translate it into appropriate English."

[1629] Document Translation

[1630] Take for example the case where a user wants to translate a business letter in a foreign language.

[1631] 1. A user types or scans a business letter (in English) into a terminal.

[1632] 2. The device sends the scanned data to the server.

[1633] 3. The server requests a translation into Japanese from the generative AI model.

[1634] 4. The server receives the translation results and emotion recognition results.

[1635] 5. The server sends these results back to the device.

[1636] 6. The device displays the translated Japanese business letter on the screen, highlighting the important parts if the user is in a hurry.

[1637] Prompt Sentence Examples

[1638] "Translate an English business letter into Japanese and analyze user sentiment based on the document."

[1639] The system of the present invention not only provides real-time conversation assistance and document translation quickly and efficiently, but also takes into account the user's emotions to provide optimal communication assistance, aiming to significantly facilitate communication between different languages ​​and improve the user experience.

[1640] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1641] Step 1:

[1642] The user inputs voice or text. For example, user A says "Hello" in Japanese. At that time, the voice data from the user is input to the terminal.

[1643] Step 2:

[1644] The device converts the voice input into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). Specifically, the device's microphone captures the voice, sends it to the speech recognition engine, and obtains the text data "Hello" as output.

[1645] Step 3:

[1646] The device sends the converted text data and the user-specified language information "Japanese" to the server as the payload of an HTTP request. Specifically, the device generates an HTTP POST request and sends it to the server's API endpoint. The input is the text data "Hello" and the language information "Japanese," and the output is completion of transmission to the server.

[1647] Step 4:

[1648] The server receives the HTTP request and extracts the text data "Hello" and the language information "Japanese." Specifically, the server's API endpoint parses the request body and retrieves the required data. The input is the received HTTP request, and the output is the extracted data.

[1649] Step 5:

[1650] The server uses a generative AI model (e.g., OpenAI's GPT-3) to reconfirm the language of the text data. Specifically, the server sends a prompt to the generative AI model asking, "What language is this text in?" and receives the result. The input is the text data "Hello," and the output is the reconfirmed language information "Japanese."

[1651] Step 6:

[1652] The server checks the target language. For example, if User B is set to use English, the target language is set to "English." Specifically, the server reads User B's language setting from the database or settings file. The input is User B's language setting information, and the output is the target language, "English."

[1653] Step 7:

[1654] The server sends a translation request to the generative AI model. Specifically, the server prompts the generative AI model with "Translate 'Hello' to English" and waits for the result. The input is the text data "Hello" and the target language "English," and the output is the translation result "Hello."

[1655] Step 8:

[1656] The server receives the translation result "Hello" from the generative AI model. Specifically, the server receives the response from the generative AI model, analyzes it, and extracts the translation result. The input is the response from the generative AI model, and the output is the translation result "Hello."

[1657] Step 9:

[1658] The server analyzes the user's emotional state using an emotion engine (e.g., Microsoft Azure's Text Analytics API). Specifically, the server sends the text "Hello" to the emotion engine and receives the emotion analysis result. The input is the text data "Hello," and the output is the emotion analysis result (e.g., joy).

[1659] Step 10:

[1660] The server sends the translation result "Hello" and the emotion recognition result to the device. Specifically, the server constructs a JSON response containing the translation result and emotion information and sends it to the device via an HTTP POST request. The input is the translation result "Hello" and the emotion analysis result, and the output is completion of transmission to the device.

[1661] Step 11:

[1662] The device receives the translation result and emotion recognition result from the server. Specifically, the device parses the HTTP response to obtain the necessary data. The input is the response from the server, and the output is the translation result "Hello" and the emotion analysis result.

[1663] Step 12:

[1664] The device presents the translation result to the user. Specifically, the text data "Hello" is displayed on the screen or played as voice using a speech synthesis engine (e.g., Amazon Polly). The tone of the voice and presentation method are adjusted depending on the user's emotion. The input is the translation result "Hello" and the emotion analysis result, and the output is the translation result presented to the user.

[1665] Prompt Sentence Examples

[1666] "Receive audio data of a user saying 'hello,' analyze its sentiment, and translate it into appropriate English."

[1667] (Application example 2)

[1668] 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."

[1669] This system not only facilitates communication between users who speak different languages, but can also understand the emotions of the other person during the conversation and respond appropriately. Conventional translation systems simply convert languages ​​and are unable to fully reflect emotions and nuances, so there is a need to improve the user experience.

[1670] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1671] In this invention, the server includes means for acquiring voice or text input from a user, means for identifying the language of the acquired input data, means for translating the identified language into a specified translation language, means for presenting the translated result to the user, emotion recognition means for analyzing the emotional state of the user, and means for adjusting the presentation method of the translation result based on the emotional state of the user, thereby facilitating communication between different languages ​​and enabling responses according to the emotions of the communication partner, thereby improving the user experience.

[1672] A "speech recognition engine" is a device or software that converts a user's voice input into text.

[1673] The "language identification means" is a mechanism for identifying the language of the acquired text data.

[1674] A "translation means" is a mechanism that has the function of converting text in a specified language into another specified language.

[1675] "Emotion recognition means" is a technology for analyzing and recognizing the emotional state of a user from their voice or text.

[1676] "Translation result presentation means" refers to a device or software that displays or plays the translated text or audio to the user.

[1677] The "adjustment means based on emotional state" is a mechanism that adjusts the way in which the translation result is presented based on the recognized emotional state.

[1678] The present invention is applied as a system that supports multilingual communication in brick-and-mortar stores. This system receives voice or text input from a user, translates it in real time, and analyzes the user's emotional state to present an appropriate translation result. Each part of the system is described in detail below.

[1679] System configuration

[1680] The main components of the system are:

[1681] Terminal: User interface device such as smart glasses or smartphone

[1682] Server: Cloud-based processing server

[1683] Speech recognition engine: Software installed on the device that converts voice input into text

[1684] Generative AI model: An AI model that performs language translation

[1685] Emotion recognition engine: Software that analyzes emotions from voice and text

[1686] Program processing explanation

[1687] Device:

[1688] It captures voice input from the user and passes this voice data to a voice recognition engine. The captured voice data is converted into text data and then sent to the server. For example, if a user asks, "Could you help me find a good restaurant nearby?", the voice is converted into text.

[1689] server:

[1690] The system receives text data and language information and identifies the language of the text using a language identification means. It then sends a request to a generative AI model to translate the text into the specified language. The AI ​​model used in this case is, for example, OpenAI GPT-3. Along with the translated result, it also obtains the emotional state analyzed using an emotion recognition engine (for example, Microsoft Azure's emotion recognition engine).

[1691] Device:

[1692] The translation results and emotion recognition results sent from the server are received and presented to the user. The presentation method is adjusted according to the user's emotional state. For example, when playing back the translation results aloud, the tone of the voice can be adjusted based on the user's emotional state.

[1693] Specific examples

[1694] As a specific usage scenario, consider a case where a tourist asks, "Could you help me find a good restaurant nearby?" in a brick-and-mortar store. Using this system, the store clerk's smart glasses will display the translation result, "Can you tell me where a good restaurant is nearby?". In addition, if the tourist expresses gratitude, the translation result will be played in a more friendly tone.

[1695] Example prompt sentence:

[1696] 1. English sentence: "Could you help me find a good restaurant nearby?"

[1697] Prompt (for translation): "Translate 'Could you help me find a good restaurant nearby?' from English to Japanese"

[1698] Prompt (for emotion recognition): "Analyze the emotion in the following text and tone: 'Could you help me find a good restaurant nearby?'"

[1699] In this way, the present invention provides a system that performs language translation and emotion recognition in real time, significantly improving the user's communication experience. This embodiment of the present invention enables smooth customer service even in multilingual brick-and-mortar stores, improving user satisfaction.

[1700] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1701] Step 1:

[1702] The user inputs voice or text. For example, if the user inputs "Could you help me find a good restaurant nearby?", the device acquires this voice data. The input is voice data.

[1703] Step 2:

[1704] The device uses a speech recognition engine to convert the acquired voice data into text data. Specifically, the speech recognition engine analyzes the voice waveform and generates text data such as "Could you help me find a good restaurant nearby?" The output is text data.

[1705] Step 3:

[1706] The terminal sends the converted text data and input language information to the server. At this time, the data is passed to the server using an HTTP request. The server analyzes the request and extracts the text and language information. The input is the text data, and the output is the state in which the server has received the text and language information.

[1707] Step 4:

[1708] The server identifies the language of the received text data. The server uses a generative AI model to identify the language of the text data and confirms that the language is English. The input is text data and the output is language information.

[1709] Step 5:

[1710] The server translates the identified language into the specified target language. It sends the prompt "Translate 'Could you help me find a good restaurant nearby?' from English to Japanese" to the generative AI model and receives the translation result "Could you help me find a good restaurant nearby?" The input is English text data, and the output is the translated Japanese text data.

[1711] Step 6:

[1712] The server uses an emotion recognition engine to analyze the user's emotional state. Specifically, it analyzes emotions such as joy, worry, and gratitude based on text data and voice input. The input is voice and text data, and the output is the user's emotional state.

[1713] Step 7:

[1714] The server sends the translation results and emotion recognition results to the device. The device analyzes the translation data "Can you tell me about a good restaurant nearby?" and emotion data received from the server and prepares to present them to the user. The input is the translation results and emotion recognition results, and the output is the state in which the device received them.

[1715] Step 8:

[1716] The device presents the translation result to the user. For example, the smart glasses display the text "Can you recommend a good restaurant nearby?", and the voice output device plays back the translation result aloud. The voice tone is adjusted according to the emotion data. The input is the translation result and the emotion recognition result, and the output is the translation result provided to the user.

[1717] Through this series of processes, users can receive appropriate translation results that correspond to their own emotions in real time.

[1718] 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.

[1719] 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.

[1720] 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.

[1721] 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.

[1722] 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.

[1723] 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.

[1724] 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).

[1725] 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.

[1726] 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."

[1727] 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.

[1728] 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).

[1729] 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.

[1730] 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.

[1731] 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.

[1732] 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.

[1733] 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.

[1734] 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.

[1735] 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.

[1736] 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.

[1737] 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.

[1738] 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.

[1739] The following is further disclosed regarding the above embodiment.

[1740] (Claim 1)

[1741] means for obtaining voice or text input from a user;

[1742] means for identifying the language of the acquired input data;

[1743] means for translating the identified language into a specified target language;

[1744] means for presenting the translated results to a user;

[1745] A system including:

[1746] (Claim 2)

[1747] 2. The system according to claim 1, wherein the means for acquiring the voice or text input has a function of converting voice into text using a voice recognition engine.

[1748] (Claim 3)

[1749] 2. The system according to claim 1, wherein the means for presenting the translation result to the user includes an audio output device and has a function of playing back the translation result by voice.

[1750] "Example 1"

[1751] (Claim 1)

[1752] means for obtaining voice or text input from a user;

[1753] A means for converting the acquired input data into text data using voice recognition technology;

[1754] means for transmitting the acquired text data to a server;

[1755] means for identifying the language of the received data using a generative AI model;

[1756] A means of verifying the specified target language;

[1757] means for sending a request to a generative AI model to translate the text data into a specified target language;

[1758] means for receiving translation results from the generative AI model;

[1759] means for presenting the translated results to a user;

[1760] A system including:

[1761] (Claim 2)

[1762] 2. The system of claim 1, wherein the means for obtaining voice or text input has the ability to convert voice to text using voice recognition technology.

[1763] (Claim 3)

[1764] 2. The system according to claim 1, wherein the means for presenting the translation result to the user includes an audio output device and has a function of playing back the translation result by voice.

[1765] "Application Example 1"

[1766] (Claim 1)

[1767] means for obtaining voice or text input from a user;

[1768] means for identifying the language of the acquired input data;

[1769] means for translating the identified language into a specified target language;

[1770] means for presenting the translated results to a user;

[1771] means including a speech recognition engine for converting speech input into text;

[1772] means including a voice player for audibly outputting the translated text;

[1773] means including supporting multilingual communication;

[1774] a means implemented in an autonomous vehicle;

[1775] A system including:

[1776] (Claim 2)

[1777] 2. The system according to claim 1, wherein the means for acquiring the voice or text input has a function of converting voice into text using a voice recognition engine.

[1778] (Claim 3)

[1779] 2. The system according to claim 1, wherein the means for presenting the translation result to the user includes an audio output device and has a function of playing back the translation result by voice.

[1780] "Example 2: Combining Emotion Engines"

[1781] (Claim 1)

[1782] means for obtaining voice or text input from a user;

[1783] means for identifying the language of the acquired input data;

[1784] means for translating the identified language into a specified target language;

[1785] means for presenting the translated results to a user;

[1786] means for analyzing user emotions;

[1787] means for adjusting the translation result based on the sentiment analysis result;

[1788] A system including:

[1789] (Claim 2)

[1790] 2. The system according to claim 1, wherein the means for acquiring the voice or text input has a function of converting voice into text using a voice recognition engine.

[1791] (Claim 3)

[1792] 2. The system according to claim 1, wherein the means for presenting the translation result to the user includes an audio output device and has a function of playing back the translation result by voice.

[1793] "Application example 2 when combining emotion engines"

[1794] (Claim 1)

[1795] means for obtaining voice or text input from a user;

[1796] means for identifying the language of the acquired input data;

[1797] means for translating the identified language into a specified target language;

[1798] means for presenting the translated results to a user;

[1799] emotion recognition means for analyzing the emotional state of a user;

[1800] means for adjusting the presentation of the translation result based on the emotional state of the user;

[1801] A system including:

[1802] (Claim 2)

[1803] 2. The system according to claim 1, wherein the means for acquiring the voice or text input has a function of converting voice into text using a voice recognition engine.

[1804] (Claim 3)

[1805] The system of claim 1, wherein the means for presenting the translated result to the user includes an audio output device, has the function of playing back the translation result aloud, and further adjusts the tone of the voice according to the user's emotional state. [Explanation of symbols]

[1806] 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. means for obtaining voice or text input from a user; means for identifying the language of the acquired input data; means for translating the identified language into a specified target language; means for presenting the translated results to a user; A system including:

2. 2. The system of claim 1, wherein the means for obtaining voice or text input has a function of converting voice to text using a voice recognition engine.

3. 2. The system according to claim 1, wherein the means for presenting the translation result to the user includes an audio output device and has the function of playing back the translation result by voice.

Images