system

Abstract

Telephone communication between users who speak different languages ​​requires real-time, low-latency translation. The method includes: acquiring an IP address of a connecting device and determining the country and language of the connecting device from the IP address; a means for obtaining a caller ID and identifying the language used by an individual user based on the caller's past call history; A means of integrating the acquired IP address information and caller ID information to perform real-time multilingual translation; The system includes means for transmitting the translated speech data to a receiving terminal.

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] In today's increasingly globalized world, multinational corporations and international communication are becoming increasingly important. However, real-time, low-latency translation is required for telephone communication between users who speak different languages, but current technology makes this difficult to achieve. Specifically, there are issues with the accuracy of language identification, the speed of translation, and the integration of each process. To solve these issues, a more efficient and effective multilingual translation system is needed. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including: means for acquiring the IP address of a connecting party and determining the country and language of the connecting party from the IP address; means for acquiring a caller's number and identifying the language used by each user based on the caller's past call history; means for integrating the acquired IP address information and caller number information to perform real-time multilingual translation; and means for transmitting translated voice data to a receiving terminal. The system also includes means for statistically analyzing communication history data and optimizing to improve the speed and accuracy of real-time translation, thereby improving translation accuracy. Furthermore, by transmitting the real-time translated voice data to a receiving terminal and playing the voice on the receiving terminal, the user can instantly use the translation results.

[0006] An "IP address" is a unique identifier assigned to each device connected to the Internet, and is a combination of numbers used to identify the source of the connection and location information.

[0007] A "caller ID" is a number used to identify the caller and is information that is linked to a specific user or terminal.

[0008] A "call history" is a record of past phone calls, including details such as the date and time of the call, the caller, the recipient, and the language used.

[0009] "Real-time translation" is a process in which a user's speech is instantly converted into another language and transmitted to another user, and is a technology that aims to minimize delays.

[0010] A "translation engine" is a set of algorithms or programs that converts given text or audio data into another language.

[0011] A "server" is a high-performance computer that processes data and provides services over a network, and is the device that handles the core processing of this system.

[0012] A "terminal" is a device used by a user, such as a smartphone, tablet, or computer.

[0013] "Communication history data" is a collection of data collected during the course of communication, and is a data set that includes information such as the number of calls, duration, and language used.

[0014] "Statistical analysis" is the process of analyzing data using mathematical methods to extract useful information from the data. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention is a system that identifies the user's language based on information such as the IP address and caller ID, and provides real-time multilingual translation. As a specific example of how to implement this invention, the following configuration and program processing will be described.

[0037] System configuration

[0038] This system is mainly composed of three elements: the server, the terminal, and the user. The server is the core of the system and is responsible for analyzing and processing various data. The terminal is used by the user and communicates with the server and sends and receives voice data. The user is the individual who uses the system, initiates calls, and receives translation services.

[0039] Program processing flow

[0040] 1. The user initiates a call

[0041] When a user makes a call, the terminal detects the call and acquires the caller ID.

[0042] 2. The device obtains the IP address and caller ID

[0043] The terminal sends the caller ID to the server, and at the same time connects to the Internet and obtains an IP address, which is also sent to the server.

[0044] 3. The server determines the country and primary language from which you are connecting

[0045] The server uses the IP address it receives to determine the geographic location of the connection, which allows it to determine the language that is primarily spoken in that region.

[0046] 4. The server identifies personal language information based on the caller ID.

[0047] The server references past call history linked to the caller ID and identifies the user's language patterns and preferred languages.

[0048] 5. The server selects the optimal language pair based on the integrated data

[0049] The acquired IP address information and caller ID information are integrated to determine the most appropriate language pair for real-time translation, where statistical analysis technology is used to enable high-speed, highly accurate translation.

[0050] 6. Real-time translation

[0051] When the user starts speaking, the device transmits the voice data in real time to the server, which instantly translates the received voice into the specified language.

[0052] 7. Delivery and playback of translation results

[0053] The translated voice data is sent to the receiving device, which plays the voice back, allowing the receiving user to understand the conversation in their own language.

[0054] Specific scenario example

[0055] A specific scenario is shown below.

[0056] User A (living in Japan) calls User B (living in the US).

[0057] Terminal A sends User A's caller number and IP address information to the server.

[0058] The server recognizes the connection from Japan and identifies Japanese as the primary language.

[0059] Terminal B is in the United States, and the server identifies User B's primary language as English.

[0060] When user A speaks in Japanese, terminal A sends the speech to the server.

[0061] The server translates the Japanese speech into English and sends the translated speech data to terminal B.

[0062] Terminal B plays the English audio and lets User B listen to it.

[0063] In this way, the system can provide low-latency, highly accurate translation in calls between users who speak different languages.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] The user initiates a call.

[0067] The user performs an operation to make a call and gives an instruction to start a call.

[0068] Step 2:

[0069] The device detects the call.

[0070] The terminal detects the user's call initiation operation and captures the caller number.

[0071] At the same time, an IP address is obtained through the Internet connection.

[0072] Step 3:

[0073] The terminal sends the caller number and IP address to the server.

[0074] The terminal sends the acquired caller ID and IP address information to the server, completing preparations for connecting the call.

[0075] Step 4:

[0076] The server analyzes the IP address.

[0077] The server compares the received IP address with a database to identify the country or region from which the connection originates.

[0078] Determine the primary language spoken based on the identified country or region.

[0079] Step 5:

[0080] The server parses the caller ID.

[0081] The server uses the received caller ID to look up past call history.

[0082] Extracts caller's past language usage from call history to create an individual language profile.

[0083] Step 6:

[0084] The server combines the IP address information with the caller ID information.

[0085] The server combines the IP address information and caller ID information it has acquired to determine the optimal language pair.

[0086] If necessary, the results of statistical analysis of communication history data will be used to optimize real-time translation algorithms.

[0087] Step 7:

[0088] When the user starts speaking, the terminal transmits the voice data to the server.

[0089] The device captures the user's voice and transmits the voice data to the server in real time.

[0090] Step 8:

[0091] The server translates the received audio data.

[0092] The server uses a translation engine to translate the received voice data into the specified language in real time.

[0093] The translated text is converted into audio data using a speech synthesis engine.

[0094] Step 9:

[0095] The server sends the translated voice data to the receiving terminal.

[0096] The server sends the translated voice data to the receiving terminal.

[0097] Step 10:

[0098] The receiving terminal plays the audio data.

[0099] The receiving terminal plays the received translated voice data through a speaker and conveys it to the user.

[0100] Step 11:

[0101] The user ends the call.

[0102] End the call, and the system will save the call record and end the session.

[0103] Example 1

[0104] 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."

[0105] There has long been a demand for a system that provides high-precision, low-latency real-time translation for calls between users who speak different languages, but current technology has not been able to fully achieve this. Furthermore, conventional systems are unable to accurately and quickly identify the user's language or region information, resulting in insufficient translation accuracy and speed.

[0106] 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.

[0107] In this invention, the server includes means for acquiring the Internet Protocol address of the connecting party and determining the region and primary language of the connecting party from the Internet Protocol address, means for acquiring the caller's number and identifying the language used by an individual user based on the caller's past communication records, and means for integrating the acquired Internet Protocol address information and caller number information to perform real-time multilingual translation, thereby enabling real-time and highly accurate translation in calls between users who speak different languages.

[0108] The "Internet Protocol address of the connecting device" is a number that uniquely identifies the connecting device on the Internet.

[0109] The "region of origin" refers to geographical location information identified based on the Internet Protocol address of the origin.

[0110] A "primary language" is a language that is primarily used in a particular region or by a particular user.

[0111] A "caller number" is a telephone number that identifies the user making a call.

[0112] "Past communication records" refers to historical data relating to communications such as phone calls that the user has made in the past.

[0113] The "language used by an individual user" refers to the language that a particular user primarily uses.

[0114] "Means for real-time multilingual translation" refers to technology that instantly translates spoken content and converts it into the next language.

[0115] "Translated speech data" refers to speech data that has been translated from a source language into a target language.

[0116] "Receiving terminal" means the device that receives the call.

[0117] "Statistical analysis" means analyzing large amounts of data using statistical methods.

[0118] "Optimization methods" refer to techniques and processes for optimizing system performance.

[0119] "Real-time translated voice data" refers to voice data after it has been instantly translated.

[0120] "Receiving terminal" means the device that receives the call.

[0121] "Means for reproducing audio" refers to the technology or device for outputting audio signals as sound.

[0122] The present invention is a system that identifies the user's language based on the connection source's Internet Protocol address and caller ID, and provides real-time multilingual translation. This system is primarily composed of three elements: a server, a terminal, and a user. The following describes specific embodiments of the present invention.

[0123] System Hardware and Software

[0124] Hardware

[0125] Server: Responsible for data analysis and processing. For example, a cloud-based server (e.g., a virtual server on a general cloud platform) is used.

[0126] Terminal: A device used by a user to communicate with a server and send and receive voice data. Examples include smartphones and personal computers.

[0127] software

[0128] Speech recognition engine (e.g., a speech recognition API for a general cloud service): Converts the user's speech into text data.

[0129] Translation engine (e.g., a translation API for a general cloud service): Translates recognized text data into different languages.

[0130] Speech synthesis engine (e.g., speech synthesis API of a general cloud service): Converts translated text data into speech data.

[0131] Specific operation of the system

[0132] First, a user starts a call using a terminal. At the start of the call, the terminal acquires the caller ID and sends it to the server. At the same time, the terminal connects to the Internet, acquires the Internet Protocol address, and sends this to the server.

[0133] The server uses the received Internet Protocol address to identify the region from which the connection originates through a GeoIP service (e.g., a common geolocation service) and determines the primary language spoken in that region. It also references past communication records based on the caller ID to identify the language spoken by the user.

[0134] The server then integrates this information and selects the optimal language pair in real time, using statistical analysis techniques and machine learning models (e.g., common machine learning libraries) to achieve highly accurate results.

[0135] When a user speaks during a call, the device sends the voice data to the server in real time. The server converts the voice data into text using a speech recognition engine, and then translates it into the target language using a translation engine. The translated text is then converted back into voice data using a speech synthesis engine and sent to the receiving device. The receiving device then plays back this voice data for the user to listen to.

[0136] Specific examples

[0137] For example, when user A in Japan calls user B in the United States, the following steps are taken:

[0138] Terminal A sends User A's caller number and Internet Protocol address to the server.

[0139] The server identifies the Internet Protocol address as being in Japan and has Japanese as the primary language.

[0140] The server determines from past communication records that User A uses Japanese.

[0141] When user A speaks in Japanese, terminal A sends the speech to the server.

[0142] The server converts the speech to text, which is then translated into English.

[0143] The translated English audio data is sent to terminal B, where user B listens to it.

[0144] Prompt Sentence Examples

[0145] Person A, who lives in Japan, calls Person B, who lives in the U.S. During the call, what Person A says in Japanese is translated into English in real time and sent to Person B's device. Please tell me the process.

[0146] In this way, the system can provide real-time, highly accurate translation for calls between users who speak different languages.

[0147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0148] Step 1:

[0149] The user initiates a call.

[0150] When a user uses a terminal to initiate a call, the terminal obtains the caller ID when the user presses the "Start Call" button in a specific application. The input is the user's operation, and the output is the caller ID obtained by the terminal.

[0151] Step 2:

[0152] The device obtains the IP address and caller ID.

[0153] The terminal sends the caller ID to the server. The terminal also connects to the Internet and obtains an Internet Protocol address. The obtained IP address is also sent to the server. The input is the caller ID and connection process, and the output is the IP address and caller ID sent to the server.

[0154] Step 3:

[0155] The server determines the country and primary language from which you are connecting.

[0156] The server analyzes the received Internet Protocol address using the GeoIP service to identify the region of the connecting user. It then determines the primary language used in that region. The input is the Internet Protocol address, and the output is the region of the connecting user and the primary language. Specifically, the server calls the GeoIP API to obtain location information from the IP address.

[0157] Step 4:

[0158] The server identifies the personal language information based on the caller number.

[0159] The server references a database of past communication records based on the caller ID to identify the user's preferred language. The input is the caller ID, and the output is the preferred language of the user. Specifically, the server executes an SQL query to retrieve the language information from the database.

[0160] Step 5:

[0161] The server selects the optimal language pair based on the integrated data.

[0162] The server integrates the regional information, primary language, and personal language information acquired in the previous step to select a highly accurate language pair. The input is regional information and personal language information, and the optimal language pair is determined as the output. Specifically, the server analyzes this information using statistical analysis methods and machine learning models to select the optimal language pair.

[0163] Step 6:

[0164] Perform real-time translation.

[0165] When a user speaks during a call, the device immediately sends the voice data to the server. The server then runs the voice data through a voice recognition engine in real time to convert it into text. The text is then translated into the target language using a translation engine. The input is the voice data, and the output is the translated text. Specifically, the server calls the voice recognition API to convert the voice data into text data.

[0166] Step 7:

[0167] Delivery and playback of translation results.

[0168] The translated text is converted into audio data using a speech synthesis engine and sent to the receiving device. The receiving device then plays this audio data and lets the user listen to it. The input is the translated text and the output is audio data. Specifically, the server uses a speech synthesis API to convert the text into audio and sends it to the receiving device.

[0169] Through the above steps, the system can provide real-time, highly accurate translation in calls between users who speak different languages.

[0170] (Application example 1)

[0171] 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."

[0172] To achieve smooth communication between multinational passengers and between passengers and the autonomous driving system in autonomous vehicles, real-time translation that overcomes language barriers is essential. However, conventional translation systems are not designed for use in vehicles, and it is difficult to achieve low-latency, high-precision translation. Furthermore, they lack the ability to automatically determine the language used by passengers or their location, making them impractical. Therefore, it is necessary to solve this problem.

[0173] 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.

[0174] In this invention, the server includes means for acquiring the IP address of the connecting source and determining the region and primary language of the connecting source from the IP address, means for acquiring the caller ID and identifying the language used by each user based on the caller's past call history, means for integrating the acquired IP address information and caller ID information and performing real-time multilingual translation on a device installed in the autonomous vehicle, and means for transmitting the translated audio data to an output device such as an in-vehicle speaker or an in-vehicle display for playback, thereby enabling smooth communication between passengers who speak different languages ​​in the autonomous vehicle and between passengers and the system.

[0175] The "source IP address" is a unique number that identifies the device connecting to the Internet.

[0176] "Region" refers to a specific geographical location or area.

[0177] A "dominant language" is the language that is primarily used in a region or country.

[0178] The "caller number" is identification information such as a telephone number for identifying the caller in a communication.

[0179] "Past call history" refers to recorded information about calls made by the user in the past.

[0180] "Real-time multilingual translation" refers to translation between multiple languages ​​in real time.

[0181] An "autonomous vehicle" is a vehicle that drives itself based on its own judgment without any driver intervention.

[0182] A "device" refers to an electronic device with a specific function, and in the present invention refers to a smartphone or an in-vehicle display.

[0183] "Translated speech data" refers to speech data that has been translated from an original language into another language.

[0184] An "output device" is a device for conveying information such as audio and video to a user, and in the present invention refers to a speaker or a display.

[0185] The present invention provides a system that performs real-time multilingual translation within an autonomous vehicle, enabling smooth communication between passengers who speak different languages ​​and between passengers and the system. Specific embodiments and program processing for implementing the present invention are described below.

[0186] System configuration

[0187] This system mainly consists of three elements: a server, an in-vehicle terminal, and a user. The server is the core of the system and is responsible for analyzing and translating voice data. The in-vehicle terminal is used by the user and communicates with the server and sends and receives voice data. The user is an individual who uses the system.

[0188] Program processing

[0189] 1. Acquiring voice input

[0190] When a user speaks in the car, the microphone built into the smartphone or in-car display picks up the voice data.

[0191] 2. Obtaining IP addresses and vehicle IDs

[0192] The in-vehicle terminal connects to the Internet, obtains the IP address and vehicle ID of the connection source, and sends them to the server.

[0193] 3. Language-specific processing

[0194] The server identifies geographic information based on the IP address and determines the predominant language used in that area.

[0195] Additionally, the language used by the speaker is identified by referring to past call history data.

[0196] 4. Selecting the best language pair

[0197] The acquired IP address information and caller ID information are integrated to determine the optimal translation language pair.

[0198] 5. Real-time speech translation

[0199] The server translates the acquired voice data in real time using multilingual translation APIs such as Google (registered trademark) Cloud Speech-to-Text, DeepL, and Google Translate.

[0200] 6. Playback of translation results

[0201] The translated voice data is sent to an in-car terminal and played back through the car's speakers and display.

[0202] Hardware and software used

[0203] Hardware

[0204] Smartphones, in-vehicle displays, microphones, speakers

[0205] software

[0206] Speech recognition system (Google Cloud Speech-to-Text, etc.)

[0207] Multilingual translation API (DeepL, Google Translate)

[0208] Data processing server (AWS (registered trademark) Lambda, etc.)

[0209] Geographical information analysis system (MaxMind GeoIP2, etc.)

[0210] Specific examples

[0211] When User A says in Japanese, "Where is the next stop?" in an autonomous vehicle, the system inside the autonomous vehicle immediately detects this speech, translates it into English, and tells the driver, "Where is the next stop?"

[0212] Prompt Sentence Examples

[0213] Prompt: "A passenger speaks in Japanese in a self-driving vehicle. Please translate what they said into English and convey it to the driver."

[0214] The system configured as described above enables smooth communication between passengers of various nationalities and between passengers and the automated driving system.

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

[0216] Step 1:

[0217] Processing description: When a user starts speaking in the car, the terminal uses the microphone to capture voice data.

[0218] Specific operation: When passenger A says, "Where is the next stop?", the microphone on the device picks up the voice.

[0219] Input: Passenger voice data

[0220] Output: Digitized signal of audio data

[0221] Step 2:

[0222] Processing description: The terminal connects to the Internet, obtains the IP address and vehicle ID of the connection source, and sends them to the server.

[0223] Specific operation: The terminal automatically obtains the vehicle's IP address and ID and sends that information to the server.

[0224] Input: Vehicle network connection information

[0225] Output: IP address and vehicle ID sent to the server

[0226] Step 3:

[0227] Process Description: The server determines geographic information based on the IP address and determines the predominant language used in that region.

[0228] How it works: Using a geographic information analysis system such as MaxMind GeoIP2, the server identifies the geographic location from the IP address, then determines the primary language of the specified region.

[0229] Input: IP address

[0230] Output: Region of origin and primary language

[0231] Step 4:

[0232] Process description: The server refers to past call history data to identify the language used by the speaker.

[0233] What it does: The server accesses a database and looks up past call history associated with the caller's number to identify the most commonly used language.

[0234] Input: Caller ID, past call history data

[0235] Output: Caller's preferred language information

[0236] Step 5:

[0237] Process description: The server integrates the acquired IP address information and caller ID information to determine the optimal translation language pair.

[0238] Specific operation: Using statistical analysis techniques, the acquired regional information is combined with the sender's language data to determine the language pair to be translated.

[0239] Input: IP address information, caller ID information

[0240] Output: Best translation language pair

[0241] Step 6:

[0242] Process description: The server translates the acquired voice data in real time using multilingual translation APIs such as Google Cloud Speech-to-Text, DeepL, and Google Translate.

[0243] Specific operation: The speech is converted into text using a speech recognition system, and the text is translated into the specified language using a multilingual translation API.

[0244] Input: Audio data, translation language pair

[0245] Output: Translated audio data

[0246] Step 7:

[0247] Process description: The server sends the translated voice data to the in-vehicle terminal, which then plays it through the car's speakers and display.

[0248] Specific operation: The device receives the translation results from the server and plays the audio data on the speaker.

[0249] Input: Translation audio data

[0250] Output: Translated speech played through the vehicle's speakers

[0251] 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.

[0252] The present invention is a system that identifies the user's language based on information such as the IP address and caller ID, provides real-time multilingual translation, and analyzes and recognizes the user's emotions to improve the naturalness and accuracy of the translation. The following configuration and program processing will be described as a specific example of how to implement the present invention.

[0253] System configuration

[0254] This system is mainly composed of three elements: the server, the terminal, and the user. The server is the core of the system and is responsible for analyzing and processing various data. The terminal is used by the user and communicates with the server and sends and receives voice data. It also has an emotion engine that recognizes emotions from the user's voice.

[0255] Program processing flow

[0256] 1. The user initiates a call

[0257] The user performs an operation to make a call and instructs the start of a call.

[0258] 2. The device detects the call

[0259] The device detects when the user initiates a call and captures the caller ID, while also obtaining the IP address via the internet connection.

[0260] 3. The device sends the caller ID and IP address to the server.

[0261] The terminal sends the acquired caller ID and IP address information to the server, completing preparations for connecting the call.

[0262] 4. The server analyzes the IP address

[0263] The server checks the IP address against a database to determine the country or region from which the connection originates, and then determines the primary language used.

[0264] 5. The server parses the caller ID

[0265] The server uses the received caller ID to look up past call history, extracting the caller's past language usage from the call history and creating an individual language profile.

[0266] 6. The server combines the IP address information with the caller ID information

[0267] The server combines the IP address and caller ID information it has acquired to determine the optimal language pair. If necessary, it also utilizes the results of statistical analysis of communication history data to optimize the real-time translation algorithm.

[0268] 7. Emotion Analysis Using an Emotion Engine

[0269] The server analyzes the user's voice data in real time and recognizes the user's emotions using an emotion engine, which then feeds the recognized emotion information back to the translation engine.

[0270] 8. Real-time translation by translation engine

[0271] The server translates the user's speech into the specified language in real time using a translation engine. At the same time, the tone and expression of the translation results are adjusted based on the emotional information obtained from the emotion engine. For example, if the user is angry, the translation will be stronger.

[0272] 9. Delivery and playback of translation results

[0273] The translated voice data is sent to the receiving device, which plays the voice back, allowing the receiving user to understand the conversation in their own language.

[0274] Specific scenario example

[0275] A specific scenario is shown below.

[0276] User A (living in Japan) calls User B (living in the US).

[0277] Terminal A sends User A's caller number and IP address information to the server.

[0278] The server recognizes the connection from Japan and identifies Japanese as the primary language.

[0279] Terminal B is in the United States, and the server identifies User B's primary language as English.

[0280] When user A speaks in Japanese, terminal A sends the speech to the server.

[0281] The server translates the Japanese speech into English and analyzes User A's emotions using an emotion engine.

[0282] The translation engine translates based on emotional information, using a stronger tone if the person is angry and a softer tone if the person is happy.

[0283] The server sends the translated voice data to terminal B.

[0284] Device B plays the English audio and lets User B listen to it. User B's voice is also subjected to real-time emotion analysis and translation.

[0285] In this way, the system provides low-latency, highly accurate translation in calls between users who speak different languages, while also realizing natural communication that reflects the user's emotions.

[0286] The processing flow will be explained below.

[0287] Step 1:

[0288] The user initiates a call.

[0289] The user performs an operation to make a call and gives an instruction to start a call.

[0290] Step 2:

[0291] The device detects the call.

[0292] The terminal detects the user's call initiation operation and captures the caller number.

[0293] At the same time, an IP address is obtained through the Internet connection.

[0294] Step 3:

[0295] The terminal sends the caller number and IP address to the server.

[0296] The terminal sends the acquired caller ID and IP address information to the server, completing preparations for connecting the call.

[0297] Step 4:

[0298] The server analyzes the IP address.

[0299] The server compares the received IP address with a database to identify the country or region from which the connection originates.

[0300] Determine the primary language spoken based on the identified country or region.

[0301] Step 5:

[0302] The server parses the caller ID.

[0303] The server uses the received caller ID to look up past call history.

[0304] Extracts caller's past language usage from call history to create an individual language profile.

[0305] Step 6:

[0306] The server combines the IP address information with the caller ID information.

[0307] The server combines the IP address information and caller ID information it has acquired to determine the optimal language pair.

[0308] The results of statistical analysis of communication history data are used to optimize real-time translation algorithms.

[0309] Step 7:

[0310] The server starts the emotion engine.

[0311] The server activates the emotion engine to analyze the user's voice data in real time.

[0312] Step 8:

[0313] The emotion engine analyzes the user's emotions.

[0314] The emotion engine uses an algorithm to recognize the user's emotions from the voice data and extracts emotion information.

[0315] The extracted emotion information is sent to the server.

[0316] Step 9:

[0317] The user begins speaking.

[0318] The user initiates a call with voice, which the terminal captures.

[0319] Step 10:

[0320] The terminal transmits the voice data to the server.

[0321] The terminal transmits the user's voice data to the server in real time.

[0322] Step 11:

[0323] The server translates the audio data.

[0324] The server uses a translation engine to translate the received voice data into the specified language in real time.

[0325] When translating, the tone and expression of the translation results are adjusted based on the emotional information recognized by the emotion engine.

[0326] Step 12:

[0327] The server sends the translated voice data to the receiving terminal.

[0328] The server sends the translated voice data to the receiving terminal.

[0329] Step 13:

[0330] The receiving terminal plays the audio data.

[0331] The receiving terminal plays the received translated voice data through a speaker and conveys it to the user.

[0332] Step 14:

[0333] The user ends the call.

[0334] The user then performs an operation to end the call, and the system saves the call record and ends the session.

[0335] Example 2

[0336] 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."

[0337] In today's global communication environment, it is difficult to provide low-latency, highly accurate translation for real-time conversations between users who speak different languages. Furthermore, there is a demand for systems that can accurately convey emotions, rather than simply translating words. While conventional translation systems can resolve language differences, they are unable to reflect emotional nuances, resulting in a decline in the quality of communication.

[0338] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring the IP address of the connection source and determining the country and language used by the connection source from the IP address; means for acquiring the caller number and identifying the language used by each user based on the caller's past communication record; means for integrating the acquired IP address information and caller number information and performing multilingual translation in real time; emotion analysis means for analyzing the user's voice data in real time and performing emotion analysis; means for feeding back the emotion analysis results and reflecting them in the translation content; and means for transmitting the translated voice data to the receiving terminal. This makes it possible to accurately translate in real time and accurately convey emotions even in calls between users speaking different languages.

[0339] The "IP address of the connecting device" is an identifier for a device connected to the Internet, and is a numerical address used to identify the location of a device on a network.

[0340] The "caller number" is an identification number for identifying the terminal of the caller in telephone communication, and usually means the telephone number of the caller.

[0341] "Country and language determination means" refers to methods or systems that analyze IP addresses or other geographic information to identify the primary language associated with a particular country or region.

[0342] "Past communication records" are historical data of the user's past communications, and are a collection of information including the contents of calls and messages, the language used, and so on.

[0343] "Integration means" refers to methods or systems that combine data from multiple sources into a single dataset that can be further analyzed and processed.

[0344] "Real-time multilingual translation means" refers to software or algorithms that translate speech or text into different languages ​​in real time.

[0345] "Emotion analysis means" refers to technology or systems that automatically identify a user's emotional state (e.g., joy, sadness, anger) from speech or text.

[0346] "Means of feeding back the results of emotion analysis and reflecting them in the translation content" refers to a method or system for incorporating the emotional information obtained through emotion analysis into the translation process and adjusting the translation results to an appropriate tone and expression according to the emotion.

[0347] "Means for transmitting translated speech data to a receiving terminal" refers to a method or system for quickly and accurately delivering real-time translated speech data to a receiving terminal.

[0348] MODE FOR CARRYING OUT THE INVENTION

[0349] This invention is a system that identifies the user's language based on information such as the IP address and caller ID, provides real-time multilingual translation, and improves the naturalness and accuracy of the translation content by analyzing and recognizing the user's emotions. As a concrete example for implementing this invention, the configuration and operation of the system will be described.

[0350] System configuration

[0351] This system mainly consists of three elements: a server, a terminal, and a user.

[0352] Server: The core part of the system, responsible for analyzing and processing various data. Specifically, it uses a cloud-based server (e.g., AWS EC2 instance).

[0353] Device: A device used by a user to communicate with a server and send and receive voice data. For example, a smartphone or VoIP device.

[0354] Emotion engine: Uses software (e.g., IBM Watson® Tone Analyzer) to recognize emotions from the user's voice.

[0355] Translation engine: Uses software (e.g. Google Cloud Translation API) to translate speech in real time.

[0356] How it works

[0357] server

[0358] The server receives the IP address and caller ID of the connecting user and analyzes the data. Using the IP address, it uses an IP geolocation database (e.g., MaxMind GeoIP) to identify the country and primary language of the connecting user. Based on the caller ID, it examines past communication history and extracts a language profile used by each individual user.

[0359] Furthermore, the server receives voice data in real time and sends it to the emotion engine. The emotion engine recognizes the user's emotion based on the analysis results and feeds the results back to the translation engine. The translation engine then adjusts the tone and expression of the translation based on the emotional information.

[0360] Terminal

[0361] When a user initiates a call, the device sends the caller ID and IP address to the server. During the call, the device captures the user's voice data and sends it to the server in real time. It also plays back the translated voice data sent from the server for the user to listen to.

[0362] Specific scenario example

[0363] A specific scenario is shown below.

[0364] User A (living in Japan) calls User B (living in the US).

[0365] Terminal A sends User A's caller number and IP address information to the server.

[0366] The server recognizes the connection from Japan and identifies Japanese as the primary language.

[0367] Terminal B is in the United States, and the server identifies User B's primary language as English.

[0368] When user A speaks in Japanese, terminal A sends the speech to the server.

[0369] The server translates the Japanese speech into English and analyzes User A's emotions using an emotion engine.

[0370] The translation engine translates based on emotional information, using a stronger tone if the person is angry and a softer tone if the person is happy.

[0371] The server sends the translated voice data to terminal B.

[0372] Device B plays the English audio and lets User B listen to it. User B's voice is also subjected to real-time emotion analysis and translation.

[0373] Examples of prompt statements

[0374] Below is an example of a prompt sentence to input to the AI ​​model.

[0375] "User A, who speaks Japanese, calls User B, who speaks English and lives in the United States. Please translate the conversation in real time and adjust the translation result to a natural tone based on emotional information."

[0376] By inputting this prompt into a generative AI model, appropriate and natural translation results can be obtained. This system enables real-time, highly accurate translation and emotional conveyance in calls between users who speak different languages.

[0377] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0378] Processing Steps

[0379] Step 1:

[0380] A user initiates a call

[0381] The user launches the phone app on their smartphone or VoIP device, enters the phone number of the person they want to call, and presses the call button.

[0382] Input: Phone number of the person you want to call

[0383] Output: Trigger signal to start a call

[0384] Step 2:

[0385] The device detects the call

[0386] The device detects the user's call start operation and recognizes the call using internal sensors and software.

[0387] The device temporarily stores the caller's phone number in memory and obtains the current IP address through the internet connection.

[0388] Input: User's call operation

[0389] Output: Get caller ID and IP address

[0390] Step 3:

[0391] The device sends the caller ID and IP address to the server.

[0392] The terminal collects the caller ID and IP address and assembles them into a data packet, which is then sent to the server using a communication protocol (e.g., TCP / IP).

[0393] Input: Caller ID and IP address

[0394] Output: Sending data packets to the server

[0395] Step 4:

[0396] The server analyzes the IP address

[0397] The server compares the received IP address with a database (e.g., MaxMind GeoIP) to identify the country or region from which the connection originates.

[0398] The server determines the primary language based on the identified country or region.

[0399] Input: IP address

[0400] Output: Identified country / region and primary language

[0401] Step 5:

[0402] The server parses the caller ID

[0403] The server uses the received caller ID to query a communication history database to reference past communication history.

[0404] The server extracts the languages ​​the user has used in the past from historical data and creates an individual language profile.

[0405] Input: Caller ID

[0406] Output: Language profile

[0407] Step 6:

[0408] The server combines the IP address information with the caller ID information.

[0409] The server combines the IP address information and caller ID information to determine the optimal language pair.

[0410] If necessary, the results of statistical analysis of communication history data will be used to optimize real-time translation algorithms.

[0411] Input: IP address information and caller ID information

[0412] Output: Best language pair

[0413] Step 7:

[0414] Emotion analysis using an emotion engine

[0415] The server captures the user's voice data in real time and sends it to an emotion engine (e.g., IBM Watson Tone Analyzer).

[0416] The emotion engine analyzes voice tone, speed, pitch, etc. to recognize the user's emotional state.

[0417] Input: User's voice data

[0418] Output: Emotion analysis results

[0419] Step 8:

[0420] Real-time translation by translation engine

[0421] The server's translation engine (e.g., Google Cloud Translation API) receives the sentiment analysis results as feedback and translates the speech in real time.

[0422] The translation engine adjusts the tone and expression of the translation based on emotional information.

[0423] Input: User's voice data, emotion analysis results

[0424] Output: Translated audio data

[0425] Step 9:

[0426] Delivery and playback of translation results

[0427] The server sends the translated voice data to the receiving terminal.

[0428] The receiving device receives the translated voice data and plays it back on a speaker.

[0429] Input: Translated audio data

[0430] Output: Played audio

[0431] In this way, through each step, the system translates real-time conversations between users with low latency and high accuracy, enabling natural communication including emotional information.

[0432] (Application example 2)

[0433] 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."

[0434] In the food delivery industry, where smooth communication between users who speak different languages ​​is required, natural conversation that reflects the user's emotions is important in addition to real-time multilingual translation. However, current food delivery systems lack the technology to achieve this, which can lead to misunderstandings and frustration between customers and delivery personnel. This issue needs to be resolved.

[0435] 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.

[0436] In this invention, the server includes means for acquiring the IP address of the connecting party and determining the country and language used from the IP address, means for acquiring the caller's number and identifying the language used by each user based on the caller's past call history, means for integrating the acquired IP address information and caller number information to perform real-time multilingual translation, means for analyzing the user's voice data in real time and recognizing the user's emotion using an emotion engine, means for adjusting the tone and expression of the translation result based on the recognized emotion information, and means for transmitting the translated voice data to the receiving terminal, thereby enabling real-time, natural multilingual communication between the orderer and the delivery person.

[0437] The "source IP address" is a unique number assigned when connecting to the Internet, and is used to identify the location or region from which the connection is made.

[0438] "Caller ID" refers to the caller's telephone number or communication identifier when initiating a call or communication, and is used to identify the caller and to refer to past call history.

[0439] The "means for real-time multilingual translation" refers to a process for instantly translating a user's speech into another language based on the acquired language information.

[0440] An "emotion engine" is software or a system that analyzes a user's voice data and recognizes emotions such as joy or anger.

[0441] "Emotion information" refers to data on the user's emotional state obtained as a result of analysis by the emotion engine, and is reflected in the translation results.

[0442] "Tone and expression adjustment" refers to the process of appropriately changing the nuances and phrasing of the translated language based on the recognized emotional information.

[0443] "Translated audio data" refers to audio files or audio data that have been translated from an original language into another specified language.

[0444] The "receiving terminal" is a device that receives and plays back translated audio data, and includes, for example, a smartphone or tablet.

[0445] System configuration

[0446] This invention is mainly composed of three elements: a server, a terminal, and a user. The server is the core of the system and is responsible for analyzing and processing various data. The terminal is used by the user and communicates with the server and sends and receives voice data. It also has an emotion engine that recognizes emotions from the user's voice.

[0447] Program processing flow

[0448] Hardware and Software

[0449] Hardware:

[0450] Smartphone (iOS or ANDROID (registered trademark))

[0451] Server (cloud server with high-performance processing capabilities)

[0452] software:

[0453] Real-time translation: Google Cloud Translation API, Microsoft(R) Translator

[0454] Emotion analysis: IBM Watson Tone Analyzer, Azure(R) Emotion API

[0455] Communication: Firebase, RESTful API

[0456] Processing Description

[0457] 1. User authentication and initialization:

[0458] When a user launches the app, their IP address is automatically acquired. The acquired IP address and caller ID are sent to the server, which then uses this information to identify the country or region from which the connection originates and determine the language being used.

[0459] 2. Sending IP address and caller ID:

[0460] Based on IP addresses and caller IDs, past call history is used to identify the language used by each individual user.

[0461] 3. Real-time translation:

[0462] When an orderer sends a message to a delivery person, the voice data is sent in real time to the server, which instantly translates it into the specified language.

[0463] 4. Sentiment analysis and tone adjustment:

[0464] The server analyzes the user's voice data using an emotion engine to recognize the user's emotions. Based on the recognized emotion information, the tone and expression of the translation results are adjusted. For example, if the user is angry, the translation will be stronger.

[0465] 5. Send and play translation results:

[0466] The translated voice data is sent to the receiving device, where the voice is played back. The delivery person understands the message in their own language. The voice from the delivery person is also translated in real time.

[0467] Specific examples

[0468] For example, if a Japanese customer says, "Please deliver the pizza quickly," the app will not only translate it as "Please deliver the pizza quickly," but if it detects a strong emotion (anger), it will convert it into a stronger message such as "Could you please hurry up with the pizza delivery?"

[0469] Prompt Sentence Examples

[0470] Example prompt for a generative AI model:

[0471] User types message: "Please deliver the pizza quickly"

[0472] The system identifies Japanese from the user's IP address and caller ID.

[0473] The voice data is analyzed using an emotion engine, and the emotion is recognized as anger.

[0474] Translation result: "Please deliver the pizza quickly"

[0475] Adjust based on emotional information: "Could you please hurry up with the pizza delivery?"

[0476] The tailored message is delivered to the delivery person, who plays the audio in English through the app.

[0477] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0478] Step 1:

[0479] When a user launches the app, the IP address and caller ID are automatically acquired. This information is sent to the server as the initial setting. The input is the user's operation, IP address, and caller ID, and data is sent based on this. The output is the IP address and caller ID sent to the server.

[0480] Step 2:

[0481] The server analyzes the received IP address to determine the country and language used by the connection. It also uses the caller ID to look up past call history and identify the language used by the user. The input is the IP address and caller ID sent to the server, and a database search is performed based on this. The output is the identified language information.

[0482] Step 3:

[0483] The user inputs a message and sends the voice data from the terminal to the server. The input is the user's voice data, which is received by the server. The output is the received voice data.

[0484] Step 4:

[0485] The server analyzes the voice data in real time and translates it into the specified language. The input is the voice data and the specified language information, and the translation engine operates based on this. The output is the translated voice data.

[0486] Step 5:

[0487] The server then runs the translated voice data through an emotion engine to recognize the user's emotions. The input is the translated voice data, which the emotion engine analyzes based on. The output is the recognized emotion information.

[0488] Step 6:

[0489] The server adjusts the tone and expression of the translation result based on the recognized emotional information. The input is the emotional information and translated speech data, and the tone and expression are adjusted based on this. The output is the adjusted translated speech data.

[0490] Step 7:

[0491] The server sends the adjusted translated audio data to the receiving terminal, which then plays it back. The input is the adjusted translated audio data that is sent to the terminal. The output is the played audio.

[0492] 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.

[0493] 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.

[0494] 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.

[0495] [Second embodiment]

[0496] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0497] 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.

[0498] 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).

[0499] 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.

[0500] 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.

[0501] 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).

[0502] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0503] 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.

[0504] 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.

[0505] 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.

[0506] 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.

[0507] 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."

[0508] The present invention is a system that identifies the user's language based on information such as the IP address and caller ID, and provides real-time multilingual translation. As a specific example of how to implement this invention, the following configuration and program processing will be described.

[0509] System configuration

[0510] This system is mainly composed of three elements: the server, the terminal, and the user. The server is the core of the system and is responsible for analyzing and processing various data. The terminal is used by the user and communicates with the server and sends and receives voice data. The user is the individual who uses the system, initiates calls, and receives translation services.

[0511] Program processing flow

[0512] 1. The user initiates a call

[0513] When a user makes a call, the terminal detects the call and acquires the caller ID.

[0514] 2. The device obtains the IP address and caller ID

[0515] The terminal sends the caller ID to the server, and at the same time connects to the Internet and obtains an IP address, which is also sent to the server.

[0516] 3. The server determines the country and primary language from which you are connecting

[0517] The server uses the IP address it receives to determine the geographic location of the connection, which allows it to determine the language that is primarily spoken in that region.

[0518] 4. The server identifies personal language information based on the caller ID.

[0519] The server references past call history linked to the caller ID and identifies the user's language patterns and preferred languages.

[0520] 5. The server selects the optimal language pair based on the integrated data

[0521] The acquired IP address information and caller ID information are integrated to determine the most appropriate language pair for real-time translation, where statistical analysis technology is used to enable high-speed, highly accurate translation.

[0522] 6. Real-time translation

[0523] When the user starts speaking, the device transmits the voice data in real time to the server, which instantly translates the received voice into the specified language.

[0524] 7. Delivery and playback of translation results

[0525] The translated voice data is sent to the receiving device, which plays the voice back, allowing the receiving user to understand the conversation in their own language.

[0526] Specific scenario example

[0527] A specific scenario is shown below.

[0528] User A (living in Japan) calls User B (living in the US).

[0529] Terminal A sends User A's caller number and IP address information to the server.

[0530] The server recognizes the connection from Japan and identifies Japanese as the primary language.

[0531] Terminal B is in the United States, and the server identifies User B's primary language as English.

[0532] When user A speaks in Japanese, terminal A sends the speech to the server.

[0533] The server translates the Japanese speech into English and sends the translated speech data to terminal B.

[0534] Terminal B plays the English audio and lets User B listen to it.

[0535] In this way, the system can provide low-latency, highly accurate translation in calls between users who speak different languages.

[0536] The processing flow will be explained below.

[0537] Step 1:

[0538] The user initiates a call.

[0539] The user performs an operation to make a call and gives an instruction to start a call.

[0540] Step 2:

[0541] The device detects the call.

[0542] The terminal detects the user's call initiation operation and captures the caller number.

[0543] At the same time, an IP address is obtained through the Internet connection.

[0544] Step 3:

[0545] The terminal sends the caller number and IP address to the server.

[0546] The terminal sends the acquired caller ID and IP address information to the server, completing preparations for connecting the call.

[0547] Step 4:

[0548] The server analyzes the IP address.

[0549] The server compares the received IP address with a database to identify the country or region from which the connection originates.

[0550] Determine the primary language spoken based on the identified country or region.

[0551] Step 5:

[0552] The server parses the caller ID.

[0553] The server uses the received caller ID to look up past call history.

[0554] Extracts caller's past language usage from call history to create an individual language profile.

[0555] Step 6:

[0556] The server combines the IP address information with the caller ID information.

[0557] The server combines the IP address information and caller ID information it has acquired to determine the optimal language pair.

[0558] If necessary, the results of statistical analysis of communication history data will be used to optimize real-time translation algorithms.

[0559] Step 7:

[0560] When the user starts speaking, the terminal transmits the voice data to the server.

[0561] The device captures the user's voice and transmits the voice data to the server in real time.

[0562] Step 8:

[0563] The server translates the received audio data.

[0564] The server uses a translation engine to translate the received voice data into the specified language in real time.

[0565] The translated text is converted into audio data using a speech synthesis engine.

[0566] Step 9:

[0567] The server sends the translated voice data to the receiving terminal.

[0568] The server sends the translated voice data to the receiving terminal.

[0569] Step 10:

[0570] The receiving terminal plays the audio data.

[0571] The receiving terminal plays the received translated voice data through a speaker and conveys it to the user.

[0572] Step 11:

[0573] The user ends the call.

[0574] End the call, and the system will save the call record and end the session.

[0575] Example 1

[0576] 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."

[0577] There has long been a demand for a system that provides high-precision, low-latency real-time translation for calls between users who speak different languages, but current technology has not been able to fully achieve this. Furthermore, conventional systems are unable to accurately and quickly identify the user's language or region information, resulting in insufficient translation accuracy and speed.

[0578] 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.

[0579] In this invention, the server includes means for acquiring the Internet Protocol address of the connecting party and determining the region and primary language of the connecting party from the Internet Protocol address, means for acquiring the caller's number and identifying the language used by an individual user based on the caller's past communication records, and means for integrating the acquired Internet Protocol address information and caller number information to perform real-time multilingual translation, thereby enabling real-time and highly accurate translation in calls between users who speak different languages.

[0580] The "Internet Protocol address of the connecting device" is a number that uniquely identifies the connecting device on the Internet.

[0581] The "region of origin" refers to geographical location information identified based on the Internet Protocol address of the origin.

[0582] A "primary language" is a language that is primarily used in a particular region or by a particular user.

[0583] A "caller number" is a telephone number that identifies the user making a call.

[0584] "Past communication records" refers to historical data relating to communications such as phone calls that the user has made in the past.

[0585] The "language used by an individual user" refers to the language that a particular user primarily uses.

[0586] "Means for real-time multilingual translation" refers to technology that instantly translates spoken content and converts it into the next language.

[0587] "Translated speech data" refers to speech data that has been translated from a source language into a target language.

[0588] "Receiving terminal" means the device that receives the call.

[0589] "Statistical analysis" means analyzing large amounts of data using statistical methods.

[0590] "Optimization methods" refer to techniques and processes for optimizing system performance.

[0591] "Real-time translated voice data" refers to voice data after it has been instantly translated.

[0592] "Receiving terminal" means the device that receives the call.

[0593] "Means for reproducing audio" refers to the technology or device for outputting audio signals as sound.

[0594] The present invention is a system that identifies the user's language based on the connection source's Internet Protocol address and caller ID, and provides real-time multilingual translation. This system is primarily composed of three elements: a server, a terminal, and a user. The following describes specific embodiments of the present invention.

[0595] System Hardware and Software

[0596] Hardware

[0597] Server: Responsible for data analysis and processing. For example, a cloud-based server (e.g., a virtual server on a general cloud platform) is used.

[0598] Terminal: A device used by a user to communicate with a server and send and receive voice data. Examples include smartphones and personal computers.

[0599] software

[0600] Speech recognition engine (e.g., a speech recognition API for a general cloud service): Converts the user's speech into text data.

[0601] Translation engine (e.g., a translation API for a general cloud service): Translates recognized text data into different languages.

[0602] Speech synthesis engine (e.g., speech synthesis API of a general cloud service): Converts translated text data into speech data.

[0603] Specific operation of the system

[0604] First, a user starts a call using a terminal. At the start of the call, the terminal acquires the caller ID and sends it to the server. At the same time, the terminal connects to the Internet, acquires the Internet Protocol address, and sends this to the server.

[0605] The server uses the received Internet Protocol address to identify the region from which the connection originates through a GeoIP service (e.g., a common geolocation service) and determines the primary language spoken in that region. It also references past communication records based on the caller ID to identify the language spoken by the user.

[0606] The server then integrates this information and selects the optimal language pair in real time, using statistical analysis techniques and machine learning models (e.g., common machine learning libraries) to achieve highly accurate results.

[0607] When a user speaks during a call, the device sends the voice data to the server in real time. The server converts the voice data into text using a speech recognition engine, and then translates it into the target language using a translation engine. The translated text is then converted back into voice data using a speech synthesis engine and sent to the receiving device. The receiving device then plays back this voice data for the user to listen to.

[0608] Specific examples

[0609] For example, when user A in Japan calls user B in the United States, the following steps are taken:

[0610] Terminal A sends User A's caller number and Internet Protocol address to the server.

[0611] The server identifies the Internet Protocol address as being in Japan and has Japanese as the primary language.

[0612] The server determines from past communication records that User A uses Japanese.

[0613] When user A speaks in Japanese, terminal A sends the speech to the server.

[0614] The server converts the speech to text, which is then translated into English.

[0615] The translated English audio data is sent to terminal B, where user B listens to it.

[0616] Prompt Sentence Examples

[0617] Person A, who lives in Japan, calls Person B, who lives in the U.S. During the call, what Person A says in Japanese is translated into English in real time and sent to Person B's device. Please tell me the process.

[0618] In this way, the system can provide real-time, highly accurate translation for calls between users who speak different languages.

[0619] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0620] Step 1:

[0621] The user initiates a call.

[0622] When a user uses a terminal to initiate a call, the terminal obtains the caller ID when the user presses the "Start Call" button in a specific application. The input is the user's operation, and the output is the caller ID obtained by the terminal.

[0623] Step 2:

[0624] The device obtains the IP address and caller ID.

[0625] The terminal sends the caller ID to the server. The terminal also connects to the Internet and obtains an Internet Protocol address. The obtained IP address is also sent to the server. The input is the caller ID and connection process, and the output is the IP address and caller ID sent to the server.

[0626] Step 3:

[0627] The server determines the country and primary language from which you are connecting.

[0628] The server analyzes the received Internet Protocol address using the GeoIP service to identify the region of the connecting user. It then determines the primary language used in that region. The input is the Internet Protocol address, and the output is the region of the connecting user and the primary language. Specifically, the server calls the GeoIP API to obtain location information from the IP address.

[0629] Step 4:

[0630] The server identifies the personal language information based on the caller number.

[0631] The server references a database of past communication records based on the caller ID to identify the user's preferred language. The input is the caller ID, and the output is the preferred language of the user. Specifically, the server executes an SQL query to retrieve the language information from the database.

[0632] Step 5:

[0633] The server selects the optimal language pair based on the integrated data.

[0634] The server integrates the regional information, primary language, and personal language information acquired in the previous step to select a highly accurate language pair. The input is regional information and personal language information, and the optimal language pair is determined as the output. Specifically, the server analyzes this information using statistical analysis methods and machine learning models to select the optimal language pair.

[0635] Step 6:

[0636] Perform real-time translation.

[0637] When a user speaks during a call, the device immediately sends the voice data to the server. The server then runs the voice data through a voice recognition engine in real time to convert it into text. The text is then translated into the target language using a translation engine. The input is the voice data, and the output is the translated text. Specifically, the server calls the voice recognition API to convert the voice data into text data.

[0638] Step 7:

[0639] Delivery and playback of translation results.

[0640] The translated text is converted into audio data using a speech synthesis engine and sent to the receiving device. The receiving device then plays this audio data and lets the user listen to it. The input is the translated text and the output is audio data. Specifically, the server uses a speech synthesis API to convert the text into audio and sends it to the receiving device.

[0641] Through the above steps, the system can provide real-time, highly accurate translation in calls between users who speak different languages.

[0642] (Application example 1)

[0643] 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."

[0644] To achieve smooth communication between multinational passengers and between passengers and the autonomous driving system in autonomous vehicles, real-time translation that overcomes language barriers is essential. However, conventional translation systems are not designed for use in vehicles, and it is difficult to achieve low-latency, high-precision translation. Furthermore, they lack the ability to automatically determine the language used by passengers or their location, making them impractical. Therefore, it is necessary to solve this problem.

[0645] 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.

[0646] In this invention, the server includes means for acquiring the IP address of the connecting source and determining the region and primary language of the connecting source from the IP address, means for acquiring the caller ID and identifying the language used by each user based on the caller's past call history, means for integrating the acquired IP address information and caller ID information and performing real-time multilingual translation on a device installed in the autonomous vehicle, and means for transmitting the translated audio data to an output device such as an in-vehicle speaker or an in-vehicle display for playback, thereby enabling smooth communication between passengers who speak different languages ​​in the autonomous vehicle and between passengers and the system.

[0647] The "source IP address" is a unique number that identifies the device connecting to the Internet.

[0648] "Region" refers to a specific geographical location or area.

[0649] A "dominant language" is the language that is primarily used in a region or country.

[0650] The "caller number" is identification information such as a telephone number for identifying the caller in a communication.

[0651] "Past call history" refers to recorded information about calls made by the user in the past.

[0652] "Real-time multilingual translation" refers to translation between multiple languages ​​in real time.

[0653] An "autonomous vehicle" is a vehicle that drives itself based on its own judgment without any driver intervention.

[0654] A "device" refers to an electronic device with a specific function, and in the present invention refers to a smartphone or an in-vehicle display.

[0655] "Translated speech data" refers to speech data that has been translated from an original language into another language.

[0656] An "output device" is a device for conveying information such as audio and video to a user, and in the present invention refers to a speaker or a display.

[0657] The present invention provides a system that performs real-time multilingual translation within an autonomous vehicle, enabling smooth communication between passengers who speak different languages ​​and between passengers and the system. Specific embodiments and program processing for implementing the present invention are described below.

[0658] System configuration

[0659] This system mainly consists of three elements: a server, an in-vehicle terminal, and a user. The server is the core of the system and is responsible for analyzing and translating voice data. The in-vehicle terminal is used by the user and communicates with the server and sends and receives voice data. The user is an individual who uses the system.

[0660] Program processing

[0661] 1. Acquiring voice input

[0662] When a user speaks in the car, the microphone built into the smartphone or in-car display picks up the voice data.

[0663] 2. Obtaining IP addresses and vehicle IDs

[0664] The in-vehicle terminal connects to the Internet, obtains the IP address and vehicle ID of the connection source, and sends them to the server.

[0665] 3. Language-specific processing

[0666] The server identifies geographic information based on the IP address and determines the predominant language used in that area.

[0667] Additionally, the language used by the speaker is identified by referring to past call history data.

[0668] 4. Selecting the best language pair

[0669] The acquired IP address information and caller ID information are integrated to determine the optimal translation language pair.

[0670] 5. Real-time speech translation

[0671] The server translates the acquired voice data in real time using multilingual translation APIs such as Google Cloud Speech-to-Text, DeepL, and Google Translate.

[0672] 6. Playback of translation results

[0673] The translated voice data is sent to an in-car terminal and played back through the car's speakers and display.

[0674] Hardware and software used

[0675] Hardware

[0676] Smartphones, in-vehicle displays, microphones, speakers

[0677] software

[0678] Speech recognition system (Google Cloud Speech-to-Text, etc.)

[0679] Multilingual translation API (DeepL, Google Translate)

[0680] Data processing server (AWS Lambda, etc.)

[0681] Geographical information analysis system (MaxMind GeoIP2, etc.)

[0682] Specific examples

[0683] When User A says in Japanese, "Where is the next stop?" in an autonomous vehicle, the system inside the autonomous vehicle immediately detects this speech, translates it into English, and tells the driver, "Where is the next stop?"

[0684] Prompt Sentence Examples

[0685] Prompt: "A passenger speaks in Japanese in a self-driving vehicle. Please translate what they said into English and convey it to the driver."

[0686] The system configured as described above enables smooth communication between passengers of various nationalities and between passengers and the automated driving system.

[0687] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0688] Step 1:

[0689] Processing description: When a user starts speaking in the car, the terminal uses the microphone to capture voice data.

[0690] Specific operation: When passenger A says, "Where is the next stop?", the microphone on the device picks up the voice.

[0691] Input: Passenger voice data

[0692] Output: Digitized signal of audio data

[0693] Step 2:

[0694] Processing description: The terminal connects to the Internet, obtains the IP address and vehicle ID of the connection source, and sends them to the server.

[0695] Specific operation: The terminal automatically obtains the vehicle's IP address and ID and sends that information to the server.

[0696] Input: Vehicle network connection information

[0697] Output: IP address and vehicle ID sent to the server

[0698] Step 3:

[0699] Process Description: The server determines geographic information based on the IP address and determines the predominant language used in that region.

[0700] How it works: Using a geographic information analysis system such as MaxMind GeoIP2, the server identifies the geographic location from the IP address, then determines the primary language of the specified region.

[0701] Input: IP address

[0702] Output: Region of origin and primary language

[0703] Step 4:

[0704] Process description: The server refers to past call history data to identify the language used by the speaker.

[0705] What it does: The server accesses a database and looks up past call history associated with the caller's number to identify the most commonly used language.

[0706] Input: Caller ID, past call history data

[0707] Output: Caller's preferred language information

[0708] Step 5:

[0709] Process description: The server integrates the acquired IP address information and caller ID information to determine the optimal translation language pair.

[0710] Specific operation: Using statistical analysis techniques, the acquired regional information is combined with the sender's language data to determine the language pair to be translated.

[0711] Input: IP address information, caller ID information

[0712] Output: Best translation language pair

[0713] Step 6:

[0714] Process description: The server translates the acquired voice data in real time using multilingual translation APIs such as Google Cloud Speech-to-Text, DeepL, and Google Translate.

[0715] Specific operation: The speech is converted into text using a speech recognition system, and the text is translated into the specified language using a multilingual translation API.

[0716] Input: Audio data, translation language pair

[0717] Output: Translated audio data

[0718] Step 7:

[0719] Process description: The server sends the translated voice data to the in-vehicle terminal, which then plays it through the car's speakers and display.

[0720] Specific operation: The device receives the translation results from the server and plays the audio data on the speaker.

[0721] Input: Translation audio data

[0722] Output: Translated speech played through the vehicle's speakers

[0723] 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.

[0724] The present invention is a system that identifies the user's language based on information such as the IP address and caller ID, provides real-time multilingual translation, and analyzes and recognizes the user's emotions to improve the naturalness and accuracy of the translation. The following configuration and program processing will be described as a specific example of how to implement the present invention.

[0725] System configuration

[0726] This system is mainly composed of three elements: the server, the terminal, and the user. The server is the core of the system and is responsible for analyzing and processing various data. The terminal is used by the user and communicates with the server and sends and receives voice data. It also has an emotion engine that recognizes emotions from the user's voice.

[0727] Program processing flow

[0728] 1. The user initiates a call

[0729] The user performs an operation to make a call and instructs the start of a call.

[0730] 2. The device detects the call

[0731] The device detects when the user initiates a call and captures the caller ID, while also obtaining the IP address via the internet connection.

[0732] 3. The device sends the caller ID and IP address to the server.

[0733] The terminal sends the acquired caller ID and IP address information to the server, completing preparations for connecting the call.

[0734] 4. The server analyzes the IP address

[0735] The server checks the IP address against a database to determine the country or region from which the connection originates, and then determines the primary language used.

[0736] 5. The server parses the caller ID

[0737] The server uses the received caller ID to look up past call history, extracting the caller's past language usage from the call history and creating an individual language profile.

[0738] 6. The server combines the IP address information with the caller ID information

[0739] The server combines the IP address and caller ID information it has acquired to determine the optimal language pair. If necessary, it also utilizes the results of statistical analysis of communication history data to optimize the real-time translation algorithm.

[0740] 7. Emotion Analysis Using an Emotion Engine

[0741] The server analyzes the user's voice data in real time and recognizes the user's emotions using an emotion engine, which then feeds the recognized emotion information back to the translation engine.

[0742] 8. Real-time translation by translation engine

[0743] The server translates the user's speech into the specified language in real time using a translation engine. At the same time, the tone and expression of the translation results are adjusted based on the emotional information obtained from the emotion engine. For example, if the user is angry, the translation will be stronger.

[0744] 9. Delivery and playback of translation results

[0745] The translated voice data is sent to the receiving device, which plays the voice back, allowing the receiving user to understand the conversation in their own language.

[0746] Specific scenario example

[0747] A specific scenario is shown below.

[0748] User A (living in Japan) calls User B (living in the US).

[0749] Terminal A sends User A's caller number and IP address information to the server.

[0750] The server recognizes the connection from Japan and identifies Japanese as the primary language.

[0751] Terminal B is in the United States, and the server identifies User B's primary language as English.

[0752] When user A speaks in Japanese, terminal A sends the speech to the server.

[0753] The server translates the Japanese speech into English and analyzes User A's emotions using an emotion engine.

[0754] The translation engine translates based on emotional information, using a stronger tone if the person is angry and a softer tone if the person is happy.

[0755] The server sends the translated voice data to terminal B.

[0756] Device B plays the English audio and lets User B listen to it. User B's voice is also subjected to real-time emotion analysis and translation.

[0757] In this way, the system provides low-latency, highly accurate translation in calls between users who speak different languages, while also realizing natural communication that reflects the user's emotions.

[0758] The processing flow will be explained below.

[0759] Step 1:

[0760] The user initiates a call.

[0761] The user performs an operation to make a call and gives an instruction to start a call.

[0762] Step 2:

[0763] The device detects the call.

[0764] The terminal detects the user's call initiation operation and captures the caller number.

[0765] At the same time, an IP address is obtained through the Internet connection.

[0766] Step 3:

[0767] The terminal sends the caller number and IP address to the server.

[0768] The terminal sends the acquired caller ID and IP address information to the server, completing preparations for connecting the call.

[0769] Step 4:

[0770] The server analyzes the IP address.

[0771] The server compares the received IP address with a database to identify the country or region from which the connection originates.

[0772] Determine the primary language spoken based on the identified country or region.

[0773] Step 5:

[0774] The server parses the caller ID.

[0775] The server uses the received caller ID to look up past call history.

[0776] Extracts caller's past language usage from call history to create an individual language profile.

[0777] Step 6:

[0778] The server combines the IP address information with the caller ID information.

[0779] The server combines the IP address information and caller ID information it has acquired to determine the optimal language pair.

[0780] The results of statistical analysis of communication history data are used to optimize real-time translation algorithms.

[0781] Step 7:

[0782] The server starts the emotion engine.

[0783] The server activates the emotion engine to analyze the user's voice data in real time.

[0784] Step 8:

[0785] The emotion engine analyzes the user's emotions.

[0786] The emotion engine uses an algorithm to recognize the user's emotions from the voice data and extracts emotion information.

[0787] The extracted emotion information is sent to the server.

[0788] Step 9:

[0789] The user begins speaking.

[0790] The user initiates a call with voice, which the terminal captures.

[0791] Step 10:

[0792] The terminal transmits the voice data to the server.

[0793] The terminal transmits the user's voice data to the server in real time.

[0794] Step 11:

[0795] The server translates the audio data.

[0796] The server uses a translation engine to translate the received voice data into the specified language in real time.

[0797] When translating, the tone and expression of the translation results are adjusted based on the emotional information recognized by the emotion engine.

[0798] Step 12:

[0799] The server sends the translated voice data to the receiving terminal.

[0800] The server sends the translated voice data to the receiving terminal.

[0801] Step 13:

[0802] The receiving terminal plays the audio data.

[0803] The receiving terminal plays the received translated voice data through a speaker and conveys it to the user.

[0804] Step 14:

[0805] The user ends the call.

[0806] The user then performs an operation to end the call, and the system saves the call record and ends the session.

[0807] Example 2

[0808] 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."

[0809] In today's global communication environment, it is difficult to provide low-latency, highly accurate translation for real-time conversations between users who speak different languages. Furthermore, there is a demand for systems that can accurately convey emotions, rather than simply translating words. While conventional translation systems can resolve language differences, they are unable to reflect emotional nuances, resulting in a decline in the quality of communication.

[0810] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring the IP address of the connection source and determining the country and language used by the connection source from the IP address; means for acquiring the caller number and identifying the language used by each user based on the caller's past communication record; means for integrating the acquired IP address information and caller number information and performing multilingual translation in real time; emotion analysis means for analyzing the user's voice data in real time and performing emotion analysis; means for feeding back the emotion analysis results and reflecting them in the translation content; and means for transmitting the translated voice data to the receiving terminal. This makes it possible to accurately translate in real time and accurately convey emotions even in calls between users speaking different languages.

[0811] The "IP address of the connecting device" is an identifier for a device connected to the Internet, and is a numerical address used to identify the location of a device on a network.

[0812] The "caller number" is an identification number for identifying the terminal of the caller in telephone communication, and usually means the telephone number of the caller.

[0813] "Country and language determination means" refers to methods or systems that analyze IP addresses or other geographic information to identify the primary language associated with a particular country or region.

[0814] "Past communication records" are historical data of the user's past communications, and are a collection of information including the contents of calls and messages, the language used, and so on.

[0815] "Integration means" refers to methods or systems that combine data from multiple sources into a single dataset that can be further analyzed and processed.

[0816] "Real-time multilingual translation means" refers to software or algorithms that translate speech or text into different languages ​​in real time.

[0817] "Emotion analysis means" refers to technology or systems that automatically identify a user's emotional state (e.g., joy, sadness, anger) from speech or text.

[0818] "Means of feeding back the results of emotion analysis and reflecting them in the translation content" refers to a method or system for incorporating the emotional information obtained through emotion analysis into the translation process and adjusting the translation results to an appropriate tone and expression according to the emotion.

[0819] "Means for transmitting translated speech data to a receiving terminal" refers to a method or system for quickly and accurately delivering real-time translated speech data to a receiving terminal.

[0820] MODE FOR CARRYING OUT THE INVENTION

[0821] This invention is a system that identifies the user's language based on information such as the IP address and caller ID, provides real-time multilingual translation, and improves the naturalness and accuracy of the translation content by analyzing and recognizing the user's emotions. As a concrete example for implementing this invention, the configuration and operation of the system will be described.

[0822] System configuration

[0823] This system mainly consists of three elements: a server, a terminal, and a user.

[0824] Server: The core part of the system, responsible for analyzing and processing various data. Specifically, it uses a cloud-based server (e.g., AWS EC2 instance).

[0825] Device: A device used by a user to communicate with a server and send and receive voice data. For example, a smartphone or VoIP device.

[0826] Emotion engine: Uses software (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice.

[0827] Translation engine: Uses software (e.g. Google Cloud Translation API) to translate speech in real time.

[0828] How it works

[0829] server

[0830] The server receives the IP address and caller ID of the connecting user and analyzes the data. Using the IP address, it uses an IP geolocation database (e.g., MaxMind GeoIP) to identify the country and primary language of the connecting user. Based on the caller ID, it examines past communication history and extracts a language profile used by each individual user.

[0831] Furthermore, the server receives voice data in real time and sends it to the emotion engine. The emotion engine recognizes the user's emotion based on the analysis results and feeds the results back to the translation engine. The translation engine then adjusts the tone and expression of the translation based on the emotional information.

[0832] Terminal

[0833] When a user initiates a call, the device sends the caller ID and IP address to the server. During the call, the device captures the user's voice data and sends it to the server in real time. It also plays back the translated voice data sent from the server for the user to listen to.

[0834] Specific scenario example

[0835] A specific scenario is shown below.

[0836] User A (living in Japan) calls User B (living in the US).

[0837] Terminal A sends User A's caller number and IP address information to the server.

[0838] The server recognizes the connection from Japan and identifies Japanese as the primary language.

[0839] Terminal B is in the United States, and the server identifies User B's primary language as English.

[0840] When user A speaks in Japanese, terminal A sends the speech to the server.

[0841] The server translates the Japanese speech into English and analyzes User A's emotions using an emotion engine.

[0842] The translation engine translates based on emotional information, using a stronger tone if the person is angry and a softer tone if the person is happy.

[0843] The server sends the translated voice data to terminal B.

[0844] Device B plays the English audio and lets User B listen to it. User B's voice is also subjected to real-time emotion analysis and translation.

[0845] Examples of prompt statements

[0846] Below is an example of a prompt sentence to input to the AI ​​model.

[0847] "User A, who speaks Japanese, calls User B, who speaks English and lives in the United States. Please translate the conversation in real time and adjust the translation result to a natural tone based on emotional information."

[0848] By inputting this prompt into a generative AI model, appropriate and natural translation results can be obtained. This system enables real-time, highly accurate translation and emotional conveyance in calls between users who speak different languages.

[0849] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0850] Processing Steps

[0851] Step 1:

[0852] A user initiates a call

[0853] The user launches the phone app on their smartphone or VoIP device, enters the phone number of the person they want to call, and presses the call button.

[0854] Input: Phone number of the person you want to call

[0855] Output: Trigger signal to start a call

[0856] Step 2:

[0857] The device detects the call

[0858] The device detects the user's call start operation and recognizes the call using internal sensors and software.

[0859] The device temporarily stores the caller's phone number in memory and obtains the current IP address through the internet connection.

[0860] Input: User's call operation

[0861] Output: Get caller ID and IP address

[0862] Step 3:

[0863] The device sends the caller ID and IP address to the server.

[0864] The terminal collects the caller ID and IP address and assembles them into a data packet, which is then sent to the server using a communication protocol (e.g., TCP / IP).

[0865] Input: Caller ID and IP address

[0866] Output: Sending data packets to the server

[0867] Step 4:

[0868] The server analyzes the IP address

[0869] The server compares the received IP address with a database (e.g., MaxMind GeoIP) to identify the country or region from which the connection originates.

[0870] The server determines the primary language based on the identified country or region.

[0871] Input: IP address

[0872] Output: Identified country / region and primary language

[0873] Step 5:

[0874] The server parses the caller ID

[0875] The server uses the received caller ID to query a communication history database to reference past communication history.

[0876] The server extracts the languages ​​the user has used in the past from historical data and creates an individual language profile.

[0877] Input: Caller ID

[0878] Output: Language profile

[0879] Step 6:

[0880] The server combines the IP address information with the caller ID information.

[0881] The server combines the IP address information and caller ID information to determine the optimal language pair.

[0882] If necessary, the results of statistical analysis of communication history data will be used to optimize real-time translation algorithms.

[0883] Input: IP address information and caller ID information

[0884] Output: Best language pair

[0885] Step 7:

[0886] Emotion analysis using an emotion engine

[0887] The server captures the user's voice data in real time and sends it to an emotion engine (e.g., IBM Watson Tone Analyzer).

[0888] The emotion engine analyzes voice tone, speed, pitch, etc. to recognize the user's emotional state.

[0889] Input: User's voice data

[0890] Output: Emotion analysis results

[0891] Step 8:

[0892] Real-time translation by translation engine

[0893] The server's translation engine (e.g., Google Cloud Translation API) receives the sentiment analysis results as feedback and translates the speech in real time.

[0894] The translation engine adjusts the tone and expression of the translation based on emotional information.

[0895] Input: User's voice data, emotion analysis results

[0896] Output: Translated audio data

[0897] Step 9:

[0898] Delivery and playback of translation results

[0899] The server sends the translated voice data to the receiving terminal.

[0900] The receiving device receives the translated voice data and plays it back on a speaker.

[0901] Input: Translated audio data

[0902] Output: Played audio

[0903] In this way, through each step, the system translates real-time conversations between users with low latency and high accuracy, enabling natural communication including emotional information.

[0904] (Application example 2)

[0905] 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."

[0906] In the food delivery industry, where smooth communication between users who speak different languages ​​is required, natural conversation that reflects the user's emotions is important in addition to real-time multilingual translation. However, current food delivery systems lack the technology to achieve this, which can lead to misunderstandings and frustration between customers and delivery personnel. This issue needs to be resolved.

[0907] 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.

[0908] In this invention, the server includes means for acquiring the IP address of the connecting party and determining the country and language used from the IP address, means for acquiring the caller's number and identifying the language used by each user based on the caller's past call history, means for integrating the acquired IP address information and caller number information to perform real-time multilingual translation, means for analyzing the user's voice data in real time and recognizing the user's emotion using an emotion engine, means for adjusting the tone and expression of the translation result based on the recognized emotion information, and means for transmitting the translated voice data to the receiving terminal, thereby enabling real-time, natural multilingual communication between the orderer and the delivery person.

[0909] The "source IP address" is a unique number assigned when connecting to the Internet, and is used to identify the location or region from which the connection is made.

[0910] "Caller ID" refers to the caller's telephone number or communication identifier when initiating a call or communication, and is used to identify the caller and to refer to past call history.

[0911] The "means for real-time multilingual translation" refers to a process for instantly translating a user's speech into another language based on the acquired language information.

[0912] An "emotion engine" is software or a system that analyzes a user's voice data and recognizes emotions such as joy or anger.

[0913] "Emotion information" refers to data on the user's emotional state obtained as a result of analysis by the emotion engine, and is reflected in the translation results.

[0914] "Tone and expression adjustment" refers to the process of appropriately changing the nuances and phrasing of the translated language based on the recognized emotional information.

[0915] "Translated audio data" refers to audio files or audio data that have been translated from an original language into another specified language.

[0916] The "receiving terminal" is a device that receives and plays back translated audio data, and includes, for example, a smartphone or tablet.

[0917] System configuration

[0918] This invention is mainly composed of three elements: a server, a terminal, and a user. The server is the core of the system and is responsible for analyzing and processing various data. The terminal is used by the user and communicates with the server and sends and receives voice data. It also has an emotion engine that recognizes emotions from the user's voice.

[0919] Program processing flow

[0920] Hardware and Software

[0921] Hardware:

[0922] Smartphone (iOS or Android)

[0923] Server (cloud server with high-performance processing capabilities)

[0924] software:

[0925] Real-time translation: Google Cloud Translation API, Microsoft Translator

[0926] Emotion analysis: IBM Watson Tone Analyzer, Azure Emotion API

[0927] Communication: Firebase, RESTful API

[0928] Processing Description

[0929] 1. User authentication and initialization:

[0930] When a user launches the app, their IP address is automatically acquired. The acquired IP address and caller ID are sent to the server, which then uses this information to identify the country or region from which the connection originates and determine the language being used.

[0931] 2. Sending IP address and caller ID:

[0932] Based on IP addresses and caller IDs, past call history is used to identify the language used by each individual user.

[0933] 3. Real-time translation:

[0934] When an orderer sends a message to a delivery person, the voice data is sent in real time to the server, which instantly translates it into the specified language.

[0935] 4. Sentiment analysis and tone adjustment:

[0936] The server analyzes the user's voice data using an emotion engine to recognize the user's emotions. Based on the recognized emotion information, the tone and expression of the translation results are adjusted. For example, if the user is angry, the translation will be stronger.

[0937] 5. Send and play translation results:

[0938] The translated voice data is sent to the receiving device, where the voice is played back. The delivery person understands the message in their own language. The voice from the delivery person is also translated in real time.

[0939] Specific examples

[0940] For example, if a Japanese customer says, "Please deliver the pizza quickly," the app will not only translate it as "Please deliver the pizza quickly," but if it detects a strong emotion (anger), it will convert it into a stronger message such as "Could you please hurry up with the pizza delivery?"

[0941] Prompt Sentence Examples

[0942] Example prompt for a generative AI model:

[0943] User types message: "Please deliver the pizza quickly"

[0944] The system identifies Japanese from the user's IP address and caller ID.

[0945] The voice data is analyzed using an emotion engine, and the emotion is recognized as anger.

[0946] Translation result: "Please deliver the pizza quickly"

[0947] Adjust based on emotional information: "Could you please hurry up with the pizza delivery?"

[0948] The tailored message is delivered to the delivery person, who plays the audio in English through the app.

[0949] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0950] Step 1:

[0951] When a user launches the app, the IP address and caller ID are automatically acquired. This information is sent to the server as the initial setting. The input is the user's operation, IP address, and caller ID, and data is sent based on this. The output is the IP address and caller ID sent to the server.

[0952] Step 2:

[0953] The server analyzes the received IP address to determine the country and language used by the connection. It also uses the caller ID to look up past call history and identify the language used by the user. The input is the IP address and caller ID sent to the server, and a database search is performed based on this. The output is the identified language information.

[0954] Step 3:

[0955] The user inputs a message and sends the voice data from the terminal to the server. The input is the user's voice data, which is received by the server. The output is the received voice data.

[0956] Step 4:

[0957] The server analyzes the voice data in real time and translates it into the specified language. The input is the voice data and the specified language information, and the translation engine operates based on this. The output is the translated voice data.

[0958] Step 5:

[0959] The server then runs the translated voice data through an emotion engine to recognize the user's emotions. The input is the translated voice data, which the emotion engine analyzes based on. The output is the recognized emotion information.

[0960] Step 6:

[0961] The server adjusts the tone and expression of the translation result based on the recognized emotional information. The input is the emotional information and translated speech data, and the tone and expression are adjusted based on this. The output is the adjusted translated speech data.

[0962] Step 7:

[0963] The server sends the adjusted translated audio data to the receiving terminal, which then plays it back. The input is the adjusted translated audio data that is sent to the terminal. The output is the played audio.

[0964] 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.

[0965] 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.

[0966] 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.

[0967] [Third embodiment]

[0968] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0969] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0970] 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).

[0971] 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.

[0972] 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.

[0973] 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).

[0974] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0975] 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.

[0976] 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.

[0977] 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.

[0978] 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.

[0979] 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."

[0980] The present invention is a system that identifies the user's language based on information such as the IP address and caller ID, and provides real-time multilingual translation. As a specific example of how to implement this invention, the following configuration and program processing will be described.

[0981] System configuration

[0982] This system is mainly composed of three elements: the server, the terminal, and the user. The server is the core of the system and is responsible for analyzing and processing various data. The terminal is used by the user and communicates with the server and sends and receives voice data. The user is the individual who uses the system, initiates calls, and receives translation services.

[0983] Program processing flow

[0984] 1. The user initiates a call

[0985] When a user makes a call, the terminal detects the call and acquires the caller ID.

[0986] 2. The device obtains the IP address and caller ID

[0987] The terminal sends the caller ID to the server, and at the same time connects to the Internet and obtains an IP address, which is also sent to the server.

[0988] 3. The server determines the country and primary language from which you are connecting

[0989] The server uses the IP address it receives to determine the geographic location of the connection, which allows it to determine the language that is primarily spoken in that region.

[0990] 4. The server identifies personal language information based on the caller ID.

[0991] The server references past call history linked to the caller ID and identifies the user's language patterns and preferred languages.

[0992] 5. The server selects the optimal language pair based on the integrated data

[0993] The acquired IP address information and caller ID information are integrated to determine the most appropriate language pair for real-time translation, where statistical analysis technology is used to enable high-speed, highly accurate translation.

[0994] 6. Real-time translation

[0995] When the user starts speaking, the device transmits the voice data in real time to the server, which instantly translates the received voice into the specified language.

[0996] 7. Delivery and playback of translation results

[0997] The translated voice data is sent to the receiving device, which plays the voice back, allowing the receiving user to understand the conversation in their own language.

[0998] Specific scenario example

[0999] A specific scenario is shown below.

[1000] User A (living in Japan) calls User B (living in the US).

[1001] Terminal A sends User A's caller number and IP address information to the server.

[1002] The server recognizes the connection from Japan and identifies Japanese as the primary language.

[1003] Terminal B is in the United States, and the server identifies User B's primary language as English.

[1004] When user A speaks in Japanese, terminal A sends the speech to the server.

[1005] The server translates the Japanese speech into English and sends the translated speech data to terminal B.

[1006] Terminal B plays the English audio and lets User B listen to it.

[1007] In this way, the system can provide low-latency, highly accurate translation in calls between users who speak different languages.

[1008] The processing flow will be explained below.

[1009] Step 1:

[1010] The user initiates a call.

[1011] The user performs an operation to make a call and gives an instruction to start a call.

[1012] Step 2:

[1013] The device detects the call.

[1014] The terminal detects the user's call initiation operation and captures the caller number.

[1015] At the same time, an IP address is obtained through the Internet connection.

[1016] Step 3:

[1017] The terminal sends the caller number and IP address to the server.

[1018] The terminal sends the acquired caller ID and IP address information to the server, completing preparations for connecting the call.

[1019] Step 4:

[1020] The server analyzes the IP address.

[1021] The server compares the received IP address with a database to identify the country or region from which the connection originates.

[1022] Determine the primary language spoken based on the identified country or region.

[1023] Step 5:

[1024] The server parses the caller ID.

[1025] The server uses the received caller ID to look up past call history.

[1026] Extracts caller's past language usage from call history to create an individual language profile.

[1027] Step 6:

[1028] The server combines the IP address information with the caller ID information.

[1029] The server combines the IP address information and caller ID information it has acquired to determine the optimal language pair.

[1030] If necessary, the results of statistical analysis of communication history data will be used to optimize real-time translation algorithms.

[1031] Step 7:

[1032] When the user starts speaking, the terminal transmits the voice data to the server.

[1033] The device captures the user's voice and transmits the voice data to the server in real time.

[1034] Step 8:

[1035] The server translates the received audio data.

[1036] The server uses a translation engine to translate the received voice data into the specified language in real time.

[1037] The translated text is converted into audio data using a speech synthesis engine.

[1038] Step 9:

[1039] The server sends the translated voice data to the receiving terminal.

[1040] The server sends the translated voice data to the receiving terminal.

[1041] Step 10:

[1042] The receiving terminal plays the audio data.

[1043] The receiving terminal plays the received translated voice data through a speaker and conveys it to the user.

[1044] Step 11:

[1045] The user ends the call.

[1046] End the call, and the system will save the call record and end the session.

[1047] Example 1

[1048] 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."

[1049] There has long been a demand for a system that provides high-precision, low-latency real-time translation for calls between users who speak different languages, but current technology has not been able to fully achieve this. Furthermore, conventional systems are unable to accurately and quickly identify the user's language or region information, resulting in insufficient translation accuracy and speed.

[1050] 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.

[1051] In this invention, the server includes means for acquiring the Internet Protocol address of the connecting party and determining the region and primary language of the connecting party from the Internet Protocol address, means for acquiring the caller's number and identifying the language used by an individual user based on the caller's past communication records, and means for integrating the acquired Internet Protocol address information and caller number information to perform real-time multilingual translation, thereby enabling real-time and highly accurate translation in calls between users who speak different languages.

[1052] The "Internet Protocol address of the connecting device" is a number that uniquely identifies the connecting device on the Internet.

[1053] The "region of origin" refers to geographical location information identified based on the Internet Protocol address of the origin.

[1054] A "primary language" is a language that is primarily used in a particular region or by a particular user.

[1055] A "caller number" is a telephone number that identifies the user making a call.

[1056] "Past communication records" refers to historical data relating to communications such as phone calls that the user has made in the past.

[1057] The "language used by an individual user" refers to the language that a particular user primarily uses.

[1058] "Means for real-time multilingual translation" refers to technology that instantly translates spoken content and converts it into the next language.

[1059] "Translated speech data" refers to speech data that has been translated from a source language into a target language.

[1060] "Receiving terminal" means the device that receives the call.

[1061] "Statistical analysis" means analyzing large amounts of data using statistical methods.

[1062] "Optimization methods" refer to techniques and processes for optimizing system performance.

[1063] "Real-time translated voice data" refers to voice data after it has been instantly translated.

[1064] "Receiving terminal" means the device that receives the call.

[1065] "Means for reproducing audio" refers to the technology or device for outputting audio signals as sound.

[1066] The present invention is a system that identifies the user's language based on the connection source's Internet Protocol address and caller ID, and provides real-time multilingual translation. This system is primarily composed of three elements: a server, a terminal, and a user. The following describes specific embodiments of the present invention.

[1067] System Hardware and Software

[1068] Hardware

[1069] Server: Responsible for data analysis and processing. For example, a cloud-based server (e.g., a virtual server on a general cloud platform) is used.

[1070] Terminal: A device used by a user to communicate with a server and send and receive voice data. Examples include smartphones and personal computers.

[1071] software

[1072] Speech recognition engine (e.g., a speech recognition API for a general cloud service): Converts the user's speech into text data.

[1073] Translation engine (e.g., a translation API for a general cloud service): Translates recognized text data into different languages.

[1074] Speech synthesis engine (e.g., speech synthesis API of a general cloud service): Converts translated text data into speech data.

[1075] Specific operation of the system

[1076] First, a user starts a call using a terminal. At the start of the call, the terminal acquires the caller ID and sends it to the server. At the same time, the terminal connects to the Internet, acquires the Internet Protocol address, and sends this to the server.

[1077] The server uses the received Internet Protocol address to identify the region from which the connection originates through a GeoIP service (e.g., a common geolocation service) and determines the primary language spoken in that region. It also references past communication records based on the caller ID to identify the language spoken by the user.

[1078] The server then integrates this information and selects the optimal language pair in real time, using statistical analysis techniques and machine learning models (e.g., common machine learning libraries) to achieve highly accurate results.

[1079] When a user speaks during a call, the device sends the voice data to the server in real time. The server converts the voice data into text using a speech recognition engine, and then translates it into the target language using a translation engine. The translated text is then converted back into voice data using a speech synthesis engine and sent to the receiving device. The receiving device then plays back this voice data for the user to listen to.

[1080] Specific examples

[1081] For example, when user A in Japan calls user B in the United States, the following steps are taken:

[1082] Terminal A sends User A's caller number and Internet Protocol address to the server.

[1083] The server identifies the Internet Protocol address as being in Japan and has Japanese as the primary language.

[1084] The server determines from past communication records that User A uses Japanese.

[1085] When user A speaks in Japanese, terminal A sends the speech to the server.

[1086] The server converts the speech to text, which is then translated into English.

[1087] The translated English audio data is sent to terminal B, where user B listens to it.

[1088] Prompt Sentence Examples

[1089] Person A, who lives in Japan, calls Person B, who lives in the U.S. During the call, what Person A says in Japanese is translated into English in real time and sent to Person B's device. Please tell me the process.

[1090] In this way, the system can provide real-time, highly accurate translation for calls between users who speak different languages.

[1091] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1092] Step 1:

[1093] The user initiates a call.

[1094] When a user uses a terminal to initiate a call, the terminal obtains the caller ID when the user presses the "Start Call" button in a specific application. The input is the user's operation, and the output is the caller ID obtained by the terminal.

[1095] Step 2:

[1096] The device obtains the IP address and caller ID.

[1097] The terminal sends the caller ID to the server. The terminal also connects to the Internet and obtains an Internet Protocol address. The obtained IP address is also sent to the server. The input is the caller ID and connection process, and the output is the IP address and caller ID sent to the server.

[1098] Step 3:

[1099] The server determines the country and primary language from which you are connecting.

[1100] The server analyzes the received Internet Protocol address using the GeoIP service to identify the region of the connecting user. It then determines the primary language used in that region. The input is the Internet Protocol address, and the output is the region of the connecting user and the primary language. Specifically, the server calls the GeoIP API to obtain location information from the IP address.

[1101] Step 4:

[1102] The server identifies the personal language information based on the caller number.

[1103] The server references a database of past communication records based on the caller ID to identify the user's preferred language. The input is the caller ID, and the output is the preferred language of the user. Specifically, the server executes an SQL query to retrieve the language information from the database.

[1104] Step 5:

[1105] The server selects the optimal language pair based on the integrated data.

[1106] The server integrates the regional information, primary language, and personal language information acquired in the previous step to select a highly accurate language pair. The input is regional information and personal language information, and the optimal language pair is determined as the output. Specifically, the server analyzes this information using statistical analysis methods and machine learning models to select the optimal language pair.

[1107] Step 6:

[1108] Perform real-time translation.

[1109] When a user speaks during a call, the device immediately sends the voice data to the server. The server then runs the voice data through a voice recognition engine in real time to convert it into text. The text is then translated into the target language using a translation engine. The input is the voice data, and the output is the translated text. Specifically, the server calls the voice recognition API to convert the voice data into text data.

[1110] Step 7:

[1111] Delivery and playback of translation results.

[1112] The translated text is converted into audio data using a speech synthesis engine and sent to the receiving device. The receiving device then plays this audio data and lets the user listen to it. The input is the translated text and the output is audio data. Specifically, the server uses a speech synthesis API to convert the text into audio and sends it to the receiving device.

[1113] Through the above steps, the system can provide real-time, highly accurate translation in calls between users who speak different languages.

[1114] (Application example 1)

[1115] 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."

[1116] To achieve smooth communication between multinational passengers and between passengers and the autonomous driving system in autonomous vehicles, real-time translation that overcomes language barriers is essential. However, conventional translation systems are not designed for use in vehicles, and it is difficult to achieve low-latency, high-precision translation. Furthermore, they lack the ability to automatically determine the language used by passengers or their location, making them impractical. Therefore, it is necessary to solve this problem.

[1117] 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.

[1118] In this invention, the server includes means for acquiring the IP address of the connecting source and determining the region and primary language of the connecting source from the IP address, means for acquiring the caller ID and identifying the language used by each user based on the caller's past call history, means for integrating the acquired IP address information and caller ID information and performing real-time multilingual translation on a device installed in the autonomous vehicle, and means for transmitting the translated audio data to an output device such as an in-vehicle speaker or an in-vehicle display for playback, thereby enabling smooth communication between passengers who speak different languages ​​in the autonomous vehicle and between passengers and the system.

[1119] The "source IP address" is a unique number that identifies the device connecting to the Internet.

[1120] "Region" refers to a specific geographical location or area.

[1121] A "dominant language" is the language that is primarily used in a region or country.

[1122] The "caller number" is identification information such as a telephone number for identifying the caller in a communication.

[1123] "Past call history" refers to recorded information about calls made by the user in the past.

[1124] "Real-time multilingual translation" refers to translation between multiple languages ​​in real time.

[1125] An "autonomous vehicle" is a vehicle that drives itself based on its own judgment without any driver intervention.

[1126] A "device" refers to an electronic device with a specific function, and in the present invention refers to a smartphone or an in-vehicle display.

[1127] "Translated speech data" refers to speech data that has been translated from an original language into another language.

[1128] An "output device" is a device for conveying information such as audio and video to a user, and in the present invention refers to a speaker or a display.

[1129] The present invention provides a system that performs real-time multilingual translation within an autonomous vehicle, enabling smooth communication between passengers who speak different languages ​​and between passengers and the system. Specific embodiments and program processing for implementing the present invention are described below.

[1130] System configuration

[1131] This system mainly consists of three elements: a server, an in-vehicle terminal, and a user. The server is the core of the system and is responsible for analyzing and translating voice data. The in-vehicle terminal is used by the user and communicates with the server and sends and receives voice data. The user is an individual who uses the system.

[1132] Program processing

[1133] 1. Acquiring voice input

[1134] When a user speaks in the car, the microphone built into the smartphone or in-car display picks up the voice data.

[1135] 2. Obtaining IP addresses and vehicle IDs

[1136] The in-vehicle terminal connects to the Internet, obtains the IP address and vehicle ID of the connection source, and sends them to the server.

[1137] 3. Language-specific processing

[1138] The server identifies geographic information based on the IP address and determines the predominant language used in that area.

[1139] Additionally, the language used by the speaker is identified by referring to past call history data.

[1140] 4. Selecting the best language pair

[1141] The acquired IP address information and caller ID information are integrated to determine the optimal translation language pair.

[1142] 5. Real-time speech translation

[1143] The server translates the acquired voice data in real time using multilingual translation APIs such as Google Cloud Speech-to-Text, DeepL, and Google Translate.

[1144] 6. Playback of translation results

[1145] The translated voice data is sent to an in-car terminal and played back through the car's speakers and display.

[1146] Hardware and software used

[1147] Hardware

[1148] Smartphones, in-vehicle displays, microphones, speakers

[1149] software

[1150] Speech recognition system (Google Cloud Speech-to-Text, etc.)

[1151] Multilingual translation API (DeepL, Google Translate)

[1152] Data processing server (AWS Lambda, etc.)

[1153] Geographical information analysis system (MaxMind GeoIP2, etc.)

[1154] Specific examples

[1155] When User A says in Japanese, "Where is the next stop?" in an autonomous vehicle, the system inside the autonomous vehicle immediately detects this speech, translates it into English, and tells the driver, "Where is the next stop?"

[1156] Prompt Sentence Examples

[1157] Prompt: "A passenger speaks in Japanese in a self-driving vehicle. Please translate what they said into English and convey it to the driver."

[1158] The system configured as described above enables smooth communication between passengers of various nationalities and between passengers and the automated driving system.

[1159] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1160] Step 1:

[1161] Processing description: When a user starts speaking in the car, the terminal uses the microphone to capture voice data.

[1162] Specific operation: When passenger A says, "Where is the next stop?", the microphone on the device picks up the voice.

[1163] Input: Passenger voice data

[1164] Output: Digitized signal of audio data

[1165] Step 2:

[1166] Processing description: The terminal connects to the Internet, obtains the IP address and vehicle ID of the connection source, and sends them to the server.

[1167] Specific operation: The terminal automatically obtains the vehicle's IP address and ID and sends that information to the server.

[1168] Input: Vehicle network connection information

[1169] Output: IP address and vehicle ID sent to the server

[1170] Step 3:

[1171] Process Description: The server determines geographic information based on the IP address and determines the predominant language used in that region.

[1172] How it works: Using a geographic information analysis system such as MaxMind GeoIP2, the server identifies the geographic location from the IP address, then determines the primary language of the specified region.

[1173] Input: IP address

[1174] Output: Region of origin and primary language

[1175] Step 4:

[1176] Process description: The server refers to past call history data to identify the language used by the speaker.

[1177] What it does: The server accesses a database and looks up past call history associated with the caller's number to identify the most commonly used language.

[1178] Input: Caller ID, past call history data

[1179] Output: Caller's preferred language information

[1180] Step 5:

[1181] Process description: The server integrates the acquired IP address information and caller ID information to determine the optimal translation language pair.

[1182] Specific operation: Using statistical analysis techniques, the acquired regional information is combined with the sender's language data to determine the language pair to be translated.

[1183] Input: IP address information, caller ID information

[1184] Output: Best translation language pair

[1185] Step 6:

[1186] Process description: The server translates the acquired voice data in real time using multilingual translation APIs such as Google Cloud Speech-to-Text, DeepL, and Google Translate.

[1187] Specific operation: The speech is converted into text using a speech recognition system, and the text is translated into the specified language using a multilingual translation API.

[1188] Input: Audio data, translation language pair

[1189] Output: Translated audio data

[1190] Step 7:

[1191] Process description: The server sends the translated voice data to the in-vehicle terminal, which then plays it through the car's speakers and display.

[1192] Specific operation: The device receives the translation results from the server and plays the audio data on the speaker.

[1193] Input: Translation audio data

[1194] Output: Translated speech played through the vehicle's speakers

[1195] 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.

[1196] The present invention is a system that identifies the user's language based on information such as the IP address and caller ID, provides real-time multilingual translation, and analyzes and recognizes the user's emotions to improve the naturalness and accuracy of the translation. The following configuration and program processing will be described as a specific example of how to implement the present invention.

[1197] System configuration

[1198] This system is mainly composed of three elements: the server, the terminal, and the user. The server is the core of the system and is responsible for analyzing and processing various data. The terminal is used by the user and communicates with the server and sends and receives voice data. It also has an emotion engine that recognizes emotions from the user's voice.

[1199] Program processing flow

[1200] 1. The user initiates a call

[1201] The user performs an operation to make a call and instructs the start of a call.

[1202] 2. The device detects the call

[1203] The device detects when the user initiates a call and captures the caller ID, while also obtaining the IP address via the internet connection.

[1204] 3. The device sends the caller ID and IP address to the server.

[1205] The terminal sends the acquired caller ID and IP address information to the server, completing preparations for connecting the call.

[1206] 4. The server analyzes the IP address

[1207] The server checks the IP address against a database to determine the country or region from which the connection originates, and then determines the primary language used.

[1208] 5. The server parses the caller ID

[1209] The server uses the received caller ID to look up past call history, extracting the caller's past language usage from the call history and creating an individual language profile.

[1210] 6. The server combines the IP address information with the caller ID information

[1211] The server combines the IP address and caller ID information it has acquired to determine the optimal language pair. If necessary, it also utilizes the results of statistical analysis of communication history data to optimize the real-time translation algorithm.

[1212] 7. Emotion Analysis Using an Emotion Engine

[1213] The server analyzes the user's voice data in real time and recognizes the user's emotions using an emotion engine, which then feeds the recognized emotion information back to the translation engine.

[1214] 8. Real-time translation by translation engine

[1215] The server translates the user's speech into the specified language in real time using a translation engine. At the same time, the tone and expression of the translation results are adjusted based on the emotional information obtained from the emotion engine. For example, if the user is angry, the translation will be stronger.

[1216] 9. Delivery and playback of translation results

[1217] The translated voice data is sent to the receiving device, which plays the voice back, allowing the receiving user to understand the conversation in their own language.

[1218] Specific scenario example

[1219] A specific scenario is shown below.

[1220] User A (living in Japan) calls User B (living in the US).

[1221] Terminal A sends User A's caller number and IP address information to the server.

[1222] The server recognizes the connection from Japan and identifies Japanese as the primary language.

[1223] Terminal B is in the United States, and the server identifies User B's primary language as English.

[1224] When user A speaks in Japanese, terminal A sends the speech to the server.

[1225] The server translates the Japanese speech into English and analyzes User A's emotions using an emotion engine.

[1226] The translation engine translates based on emotional information, using a stronger tone if the person is angry and a softer tone if the person is happy.

[1227] The server sends the translated voice data to terminal B.

[1228] Device B plays the English audio and lets User B listen to it. User B's voice is also subjected to real-time emotion analysis and translation.

[1229] In this way, the system provides low-latency, highly accurate translation in calls between users who speak different languages, while also realizing natural communication that reflects the user's emotions.

[1230] The processing flow will be explained below.

[1231] Step 1:

[1232] The user initiates a call.

[1233] The user performs an operation to make a call and gives an instruction to start a call.

[1234] Step 2:

[1235] The device detects the call.

[1236] The terminal detects the user's call initiation operation and captures the caller number.

[1237] At the same time, an IP address is obtained through the Internet connection.

[1238] Step 3:

[1239] The terminal sends the caller number and IP address to the server.

[1240] The terminal sends the acquired caller ID and IP address information to the server, completing preparations for connecting the call.

[1241] Step 4:

[1242] The server analyzes the IP address.

[1243] The server compares the received IP address with a database to identify the country or region from which the connection originates.

[1244] Determine the primary language spoken based on the identified country or region.

[1245] Step 5:

[1246] The server parses the caller ID.

[1247] The server uses the received caller ID to look up past call history.

[1248] Extracts caller's past language usage from call history to create an individual language profile.

[1249] Step 6:

[1250] The server combines the IP address information with the caller ID information.

[1251] The server combines the IP address information and caller ID information it has acquired to determine the optimal language pair.

[1252] The results of statistical analysis of communication history data are used to optimize real-time translation algorithms.

[1253] Step 7:

[1254] The server starts the emotion engine.

[1255] The server activates the emotion engine to analyze the user's voice data in real time.

[1256] Step 8:

[1257] The emotion engine analyzes the user's emotions.

[1258] The emotion engine uses an algorithm to recognize the user's emotions from the voice data and extracts emotion information.

[1259] The extracted emotion information is sent to the server.

[1260] Step 9:

[1261] The user begins speaking.

[1262] The user initiates a call with voice, which the terminal captures.

[1263] Step 10:

[1264] The terminal transmits the voice data to the server.

[1265] The terminal transmits the user's voice data to the server in real time.

[1266] Step 11:

[1267] The server translates the audio data.

[1268] The server uses a translation engine to translate the received voice data into the specified language in real time.

[1269] When translating, the tone and expression of the translation results are adjusted based on the emotional information recognized by the emotion engine.

[1270] Step 12:

[1271] The server sends the translated voice data to the receiving terminal.

[1272] The server sends the translated voice data to the receiving terminal.

[1273] Step 13:

[1274] The receiving terminal plays the audio data.

[1275] The receiving terminal plays the received translated voice data through a speaker and conveys it to the user.

[1276] Step 14:

[1277] The user ends the call.

[1278] The user then performs an operation to end the call, and the system saves the call record and ends the session.

[1279] Example 2

[1280] 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."

[1281] In today's global communication environment, it is difficult to provide low-latency, highly accurate translation for real-time conversations between users who speak different languages. Furthermore, there is a demand for systems that can accurately convey emotions, rather than simply translating words. While conventional translation systems can resolve language differences, they are unable to reflect emotional nuances, resulting in a decline in the quality of communication.

[1282] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring the IP address of the connection source and determining the country and language used by the connection source from the IP address; means for acquiring the caller number and identifying the language used by each user based on the caller's past communication record; means for integrating the acquired IP address information and caller number information and performing multilingual translation in real time; emotion analysis means for analyzing the user's voice data in real time and performing emotion analysis; means for feeding back the emotion analysis results and reflecting them in the translation content; and means for transmitting the translated voice data to the receiving terminal. This makes it possible to accurately translate in real time and accurately convey emotions even in calls between users speaking different languages.

[1283] The "IP address of the connecting device" is an identifier for a device connected to the Internet, and is a numerical address used to identify the location of a device on a network.

[1284] The "caller number" is an identification number for identifying the terminal of the caller in telephone communication, and usually means the telephone number of the caller.

[1285] "Country and language determination means" refers to methods or systems that analyze IP addresses or other geographic information to identify the primary language associated with a particular country or region.

[1286] "Past communication records" are historical data of the user's past communications, and are a collection of information including the contents of calls and messages, the language used, and so on.

[1287] "Integration means" refers to methods or systems that combine data from multiple sources into a single dataset that can be further analyzed and processed.

[1288] "Real-time multilingual translation means" refers to software or algorithms that translate speech or text into different languages ​​in real time.

[1289] "Emotion analysis means" refers to technology or systems that automatically identify a user's emotional state (e.g., joy, sadness, anger) from speech or text.

[1290] "Means of feeding back the results of emotion analysis and reflecting them in the translation content" refers to a method or system for incorporating the emotional information obtained through emotion analysis into the translation process and adjusting the translation results to an appropriate tone and expression according to the emotion.

[1291] "Means for transmitting translated speech data to a receiving terminal" refers to a method or system for quickly and accurately delivering real-time translated speech data to a receiving terminal.

[1292] MODE FOR CARRYING OUT THE INVENTION

[1293] This invention is a system that identifies the user's language based on information such as the IP address and caller ID, provides real-time multilingual translation, and improves the naturalness and accuracy of the translation content by analyzing and recognizing the user's emotions. As a concrete example for implementing this invention, the configuration and operation of the system will be described.

[1294] System configuration

[1295] This system mainly consists of three elements: a server, a terminal, and a user.

[1296] Server: The core part of the system, responsible for analyzing and processing various data. Specifically, it uses a cloud-based server (e.g., AWS EC2 instance).

[1297] Device: A device used by a user to communicate with a server and send and receive voice data. For example, a smartphone or VoIP device.

[1298] Emotion engine: Uses software (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice.

[1299] Translation engine: Uses software (e.g. Google Cloud Translation API) to translate speech in real time.

[1300] How it works

[1301] server

[1302] The server receives the IP address and caller ID of the connecting user and analyzes the data. Using the IP address, it uses an IP geolocation database (e.g., MaxMind GeoIP) to identify the country and primary language of the connecting user. Based on the caller ID, it examines past communication history and extracts a language profile used by each individual user.

[1303] Furthermore, the server receives voice data in real time and sends it to the emotion engine. The emotion engine recognizes the user's emotion based on the analysis results and feeds the results back to the translation engine. The translation engine then adjusts the tone and expression of the translation based on the emotional information.

[1304] Terminal

[1305] When a user initiates a call, the device sends the caller ID and IP address to the server. During the call, the device captures the user's voice data and sends it to the server in real time. It also plays back the translated voice data sent from the server for the user to listen to.

[1306] Specific scenario example

[1307] A specific scenario is shown below.

[1308] User A (living in Japan) calls User B (living in the US).

[1309] Terminal A sends User A's caller number and IP address information to the server.

[1310] The server recognizes the connection from Japan and identifies Japanese as the primary language.

[1311] Terminal B is in the United States, and the server identifies User B's primary language as English.

[1312] When user A speaks in Japanese, terminal A sends the speech to the server.

[1313] The server translates the Japanese speech into English and analyzes User A's emotions using an emotion engine.

[1314] The translation engine translates based on emotional information, using a stronger tone if the person is angry and a softer tone if the person is happy.

[1315] The server sends the translated voice data to terminal B.

[1316] Device B plays the English audio and lets User B listen to it. User B's voice is also subjected to real-time emotion analysis and translation.

[1317] Examples of prompt statements

[1318] Below is an example of a prompt sentence to input to the AI ​​model.

[1319] "User A, who speaks Japanese, calls User B, who speaks English and lives in the United States. Please translate the conversation in real time and adjust the translation result to a natural tone based on emotional information."

[1320] By inputting this prompt into a generative AI model, appropriate and natural translation results can be obtained. This system enables real-time, highly accurate translation and emotional conveyance in calls between users who speak different languages.

[1321] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1322] Processing Steps

[1323] Step 1:

[1324] A user initiates a call

[1325] The user launches the phone app on their smartphone or VoIP device, enters the phone number of the person they want to call, and presses the call button.

[1326] Input: Phone number of the person you want to call

[1327] Output: Trigger signal to start a call

[1328] Step 2:

[1329] The device detects the call

[1330] The device detects the user's call start operation and recognizes the call using internal sensors and software.

[1331] The device temporarily stores the caller's phone number in memory and obtains the current IP address through the internet connection.

[1332] Input: User's call operation

[1333] Output: Get caller ID and IP address

[1334] Step 3:

[1335] The device sends the caller ID and IP address to the server.

[1336] The terminal collects the caller ID and IP address and assembles them into a data packet, which is then sent to the server using a communication protocol (e.g., TCP / IP).

[1337] Input: Caller ID and IP address

[1338] Output: Sending data packets to the server

[1339] Step 4:

[1340] The server analyzes the IP address

[1341] The server compares the received IP address with a database (e.g., MaxMind GeoIP) to identify the country or region from which the connection originates.

[1342] The server determines the primary language based on the identified country or region.

[1343] Input: IP address

[1344] Output: Identified country / region and primary language

[1345] Step 5:

[1346] The server parses the caller ID

[1347] The server uses the received caller ID to query a communication history database to reference past communication history.

[1348] The server extracts the languages ​​the user has used in the past from historical data and creates an individual language profile.

[1349] Input: Caller ID

[1350] Output: Language profile

[1351] Step 6:

[1352] The server combines the IP address information with the caller ID information.

[1353] The server combines the IP address information and caller ID information to determine the optimal language pair.

[1354] If necessary, the results of statistical analysis of communication history data will be used to optimize real-time translation algorithms.

[1355] Input: IP address information and caller ID information

[1356] Output: Best language pair

[1357] Step 7:

[1358] Emotion analysis using an emotion engine

[1359] The server captures the user's voice data in real time and sends it to an emotion engine (e.g., IBM Watson Tone Analyzer).

[1360] The emotion engine analyzes voice tone, speed, pitch, etc. to recognize the user's emotional state.

[1361] Input: User's voice data

[1362] Output: Emotion analysis results

[1363] Step 8:

[1364] Real-time translation by translation engine

[1365] The server's translation engine (e.g., Google Cloud Translation API) receives the sentiment analysis results as feedback and translates the speech in real time.

[1366] The translation engine adjusts the tone and expression of the translation based on emotional information.

[1367] Input: User's voice data, emotion analysis results

[1368] Output: Translated audio data

[1369] Step 9:

[1370] Delivery and playback of translation results

[1371] The server sends the translated voice data to the receiving terminal.

[1372] The receiving device receives the translated voice data and plays it back on a speaker.

[1373] Input: Translated audio data

[1374] Output: Played audio

[1375] In this way, through each step, the system translates real-time conversations between users with low latency and high accuracy, enabling natural communication including emotional information.

[1376] (Application example 2)

[1377] 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."

[1378] In the food delivery industry, where smooth communication between users who speak different languages ​​is required, natural conversation that reflects the user's emotions is important in addition to real-time multilingual translation. However, current food delivery systems lack the technology to achieve this, which can lead to misunderstandings and frustration between customers and delivery personnel. This issue needs to be resolved.

[1379] 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.

[1380] In this invention, the server includes means for acquiring the IP address of the connecting party and determining the country and language used from the IP address, means for acquiring the caller's number and identifying the language used by each user based on the caller's past call history, means for integrating the acquired IP address information and caller number information to perform real-time multilingual translation, means for analyzing the user's voice data in real time and recognizing the user's emotion using an emotion engine, means for adjusting the tone and expression of the translation result based on the recognized emotion information, and means for transmitting the translated voice data to the receiving terminal, thereby enabling real-time, natural multilingual communication between the orderer and the delivery person.

[1381] The "source IP address" is a unique number assigned when connecting to the Internet, and is used to identify the location or region from which the connection is made.

[1382] "Caller ID" refers to the caller's telephone number or communication identifier when initiating a call or communication, and is used to identify the caller and to refer to past call history.

[1383] The "means for real-time multilingual translation" refers to a process for instantly translating a user's speech into another language based on the acquired language information.

[1384] An "emotion engine" is software or a system that analyzes a user's voice data and recognizes emotions such as joy or anger.

[1385] "Emotion information" refers to data on the user's emotional state obtained as a result of analysis by the emotion engine, and is reflected in the translation results.

[1386] "Tone and expression adjustment" refers to the process of appropriately changing the nuances and phrasing of the translated language based on the recognized emotional information.

[1387] "Translated audio data" refers to audio files or audio data that have been translated from an original language into another specified language.

[1388] The "receiving terminal" is a device that receives and plays back translated audio data, and includes, for example, a smartphone or tablet.

[1389] System configuration

[1390] This invention is mainly composed of three elements: a server, a terminal, and a user. The server is the core of the system and is responsible for analyzing and processing various data. The terminal is used by the user and communicates with the server and sends and receives voice data. It also has an emotion engine that recognizes emotions from the user's voice.

[1391] Program processing flow

[1392] Hardware and Software

[1393] Hardware:

[1394] Smartphone (iOS or Android)

[1395] Server (cloud server with high-performance processing capabilities)

[1396] software:

[1397] Real-time translation: Google Cloud Translation API, Microsoft Translator

[1398] Emotion analysis: IBM Watson Tone Analyzer, Azure Emotion API

[1399] Communication: Firebase, RESTful API

[1400] Processing Description

[1401] 1. User authentication and initialization:

[1402] When a user launches the app, their IP address is automatically acquired. The acquired IP address and caller ID are sent to the server, which then uses this information to identify the country or region from which the connection originates and determine the language being used.

[1403] 2. Sending IP address and caller ID:

[1404] Based on IP addresses and caller IDs, past call history is used to identify the language used by each individual user.

[1405] 3. Real-time translation:

[1406] When an orderer sends a message to a delivery person, the voice data is sent in real time to the server, which instantly translates it into the specified language.

[1407] 4. Sentiment analysis and tone adjustment:

[1408] The server analyzes the user's voice data using an emotion engine to recognize the user's emotions. Based on the recognized emotion information, the tone and expression of the translation results are adjusted. For example, if the user is angry, the translation will be stronger.

[1409] 5. Send and play translation results:

[1410] The translated voice data is sent to the receiving device, where the voice is played back. The delivery person understands the message in their own language. The voice from the delivery person is also translated in real time.

[1411] Specific examples

[1412] For example, if a Japanese customer says, "Please deliver the pizza quickly," the app will not only translate it as "Please deliver the pizza quickly," but if it detects a strong emotion (anger), it will convert it into a stronger message such as "Could you please hurry up with the pizza delivery?"

[1413] Prompt Sentence Examples

[1414] Example prompt for a generative AI model:

[1415] User types message: "Please deliver the pizza quickly"

[1416] The system identifies Japanese from the user's IP address and caller ID.

[1417] The voice data is analyzed using an emotion engine, and the emotion is recognized as anger.

[1418] Translation result: "Please deliver the pizza quickly"

[1419] Adjust based on emotional information: "Could you please hurry up with the pizza delivery?"

[1420] The tailored message is delivered to the delivery person, who plays the audio in English through the app.

[1421] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1422] Step 1:

[1423] When a user launches the app, the IP address and caller ID are automatically acquired. This information is sent to the server as the initial setting. The input is the user's operation, IP address, and caller ID, and data is sent based on this. The output is the IP address and caller ID sent to the server.

[1424] Step 2:

[1425] The server analyzes the received IP address to determine the country and language used by the connection. It also uses the caller ID to look up past call history and identify the language used by the user. The input is the IP address and caller ID sent to the server, and a database search is performed based on this. The output is the identified language information.

[1426] Step 3:

[1427] The user inputs a message and sends the voice data from the terminal to the server. The input is the user's voice data, which is received by the server. The output is the received voice data.

[1428] Step 4:

[1429] The server analyzes the voice data in real time and translates it into the specified language. The input is the voice data and the specified language information, and the translation engine operates based on this. The output is the translated voice data.

[1430] Step 5:

[1431] The server then runs the translated voice data through an emotion engine to recognize the user's emotions. The input is the translated voice data, which the emotion engine analyzes based on. The output is the recognized emotion information.

[1432] Step 6:

[1433] The server adjusts the tone and expression of the translation result based on the recognized emotional information. The input is the emotional information and translated speech data, and the tone and expression are adjusted based on this. The output is the adjusted translated speech data.

[1434] Step 7:

[1435] The server sends the adjusted translated audio data to the receiving terminal, which then plays it back. The input is the adjusted translated audio data that is sent to the terminal. The output is the played audio.

[1436] 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.

[1437] 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.

[1438] 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.

[1439] [Fourth embodiment]

[1440] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1441] 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.

[1442] 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).

[1443] 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.

[1444] 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.

[1445] 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).

[1446] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1447] 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.

[1448] 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.

[1449] 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.

[1450] 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.

[1451] 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.

[1452] 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."

[1453] The present invention is a system that identifies the user's language based on information such as the IP address and caller ID, and provides real-time multilingual translation. As a specific example of how to implement this invention, the following configuration and program processing will be described.

[1454] System configuration

[1455] This system is mainly composed of three elements: the server, the terminal, and the user. The server is the core of the system and is responsible for analyzing and processing various data. The terminal is used by the user and communicates with the server and sends and receives voice data. The user is the individual who uses the system, initiates calls, and receives translation services.

[1456] Program processing flow

[1457] 1. The user initiates a call

[1458] When a user makes a call, the terminal detects the call and acquires the caller ID.

[1459] 2. The device obtains the IP address and caller ID

[1460] The terminal sends the caller ID to the server, and at the same time connects to the Internet and obtains an IP address, which is also sent to the server.

[1461] 3. The server determines the country and primary language from which you are connecting

[1462] The server uses the IP address it receives to determine the geographic location of the connection, which allows it to determine the language that is primarily spoken in that region.

[1463] 4. The server identifies personal language information based on the caller ID.

[1464] The server references past call history linked to the caller ID and identifies the user's language patterns and preferred languages.

[1465] 5. The server selects the optimal language pair based on the integrated data

[1466] The acquired IP address information and caller ID information are integrated to determine the most appropriate language pair for real-time translation, where statistical analysis technology is used to enable high-speed, highly accurate translation.

[1467] 6. Real-time translation

[1468] When the user starts speaking, the device transmits the voice data in real time to the server, which instantly translates the received voice into the specified language.

[1469] 7. Delivery and playback of translation results

[1470] The translated voice data is sent to the receiving device, which plays the voice back, allowing the receiving user to understand the conversation in their own language.

[1471] Specific scenario example

[1472] A specific scenario is shown below.

[1473] User A (living in Japan) calls User B (living in the US).

[1474] Terminal A sends User A's caller number and IP address information to the server.

[1475] The server recognizes the connection from Japan and identifies Japanese as the primary language.

[1476] Terminal B is in the United States, and the server identifies User B's primary language as English.

[1477] When user A speaks in Japanese, terminal A sends the speech to the server.

[1478] The server translates the Japanese speech into English and sends the translated speech data to terminal B.

[1479] Terminal B plays the English audio and lets User B listen to it.

[1480] In this way, the system can provide low-latency, highly accurate translation in calls between users who speak different languages.

[1481] The processing flow will be explained below.

[1482] Step 1:

[1483] The user initiates a call.

[1484] The user performs an operation to make a call and gives an instruction to start a call.

[1485] Step 2:

[1486] The device detects the call.

[1487] The terminal detects the user's call initiation operation and captures the caller number.

[1488] At the same time, an IP address is obtained through the Internet connection.

[1489] Step 3:

[1490] The terminal sends the caller number and IP address to the server.

[1491] The terminal sends the acquired caller ID and IP address information to the server, completing preparations for connecting the call.

[1492] Step 4:

[1493] The server analyzes the IP address.

[1494] The server compares the received IP address with a database to identify the country or region from which the connection originates.

[1495] Determine the primary language spoken based on the identified country or region.

[1496] Step 5:

[1497] The server parses the caller ID.

[1498] The server uses the received caller ID to look up past call history.

[1499] Extracts caller's past language usage from call history to create an individual language profile.

[1500] Step 6:

[1501] The server combines the IP address information with the caller ID information.

[1502] The server combines the IP address information and caller ID information it has acquired to determine the optimal language pair.

[1503] If necessary, the results of statistical analysis of communication history data will be used to optimize real-time translation algorithms.

[1504] Step 7:

[1505] When the user starts speaking, the terminal transmits the voice data to the server.

[1506] The device captures the user's voice and transmits the voice data to the server in real time.

[1507] Step 8:

[1508] The server translates the received audio data.

[1509] The server uses a translation engine to translate the received voice data into the specified language in real time.

[1510] The translated text is converted into audio data using a speech synthesis engine.

[1511] Step 9:

[1512] The server sends the translated voice data to the receiving terminal.

[1513] The server sends the translated voice data to the receiving terminal.

[1514] Step 10:

[1515] The receiving terminal plays the audio data.

[1516] The receiving terminal plays the received translated voice data through a speaker and conveys it to the user.

[1517] Step 11:

[1518] The user ends the call.

[1519] End the call, and the system will save the call record and end the session.

[1520] Example 1

[1521] 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."

[1522] There has long been a demand for a system that provides high-precision, low-latency real-time translation for calls between users who speak different languages, but current technology has not been able to fully achieve this. Furthermore, conventional systems are unable to accurately and quickly identify the user's language or region information, resulting in insufficient translation accuracy and speed.

[1523] 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.

[1524] In this invention, the server includes means for acquiring the Internet Protocol address of the connecting party and determining the region and primary language of the connecting party from the Internet Protocol address, means for acquiring the caller's number and identifying the language used by an individual user based on the caller's past communication records, and means for integrating the acquired Internet Protocol address information and caller number information to perform real-time multilingual translation, thereby enabling real-time and highly accurate translation in calls between users who speak different languages.

[1525] The "Internet Protocol address of the connecting device" is a number that uniquely identifies the connecting device on the Internet.

[1526] The "region of origin" refers to geographical location information identified based on the Internet Protocol address of the origin.

[1527] A "primary language" is a language that is primarily used in a particular region or by a particular user.

[1528] A "caller number" is a telephone number that identifies the user making a call.

[1529] "Past communication records" refers to historical data relating to communications such as phone calls that the user has made in the past.

[1530] The "language used by an individual user" refers to the language that a particular user primarily uses.

[1531] "Means for real-time multilingual translation" refers to technology that instantly translates spoken content and converts it into the next language.

[1532] "Translated speech data" refers to speech data that has been translated from a source language into a target language.

[1533] "Receiving terminal" means the device that receives the call.

[1534] "Statistical analysis" means analyzing large amounts of data using statistical methods.

[1535] "Optimization methods" refer to techniques and processes for optimizing system performance.

[1536] "Real-time translated voice data" refers to voice data after it has been instantly translated.

[1537] "Receiving terminal" means the device that receives the call.

[1538] "Means for reproducing audio" refers to the technology or device for outputting audio signals as sound.

[1539] The present invention is a system that identifies the user's language based on the connection source's Internet Protocol address and caller ID, and provides real-time multilingual translation. This system is primarily composed of three elements: a server, a terminal, and a user. The following describes specific embodiments of the present invention.

[1540] System Hardware and Software

[1541] Hardware

[1542] Server: Responsible for data analysis and processing. For example, a cloud-based server (e.g., a virtual server on a general cloud platform) is used.

[1543] Terminal: A device used by a user to communicate with a server and send and receive voice data. Examples include smartphones and personal computers.

[1544] software

[1545] Speech recognition engine (e.g., a speech recognition API for a general cloud service): Converts the user's speech into text data.

[1546] Translation engine (e.g., a translation API for a general cloud service): Translates recognized text data into different languages.

[1547] Speech synthesis engine (e.g., speech synthesis API of a general cloud service): Converts translated text data into speech data.

[1548] Specific operation of the system

[1549] First, a user starts a call using a terminal. At the start of the call, the terminal acquires the caller ID and sends it to the server. At the same time, the terminal connects to the Internet, acquires the Internet Protocol address, and sends this to the server.

[1550] The server uses the received Internet Protocol address to identify the region from which the connection originates through a GeoIP service (e.g., a common geolocation service) and determines the primary language spoken in that region. It also references past communication records based on the caller ID to identify the language spoken by the user.

[1551] The server then integrates this information and selects the optimal language pair in real time, using statistical analysis techniques and machine learning models (e.g., common machine learning libraries) to achieve highly accurate results.

[1552] When a user speaks during a call, the device sends the voice data to the server in real time. The server converts the voice data into text using a speech recognition engine, and then translates it into the target language using a translation engine. The translated text is then converted back into voice data using a speech synthesis engine and sent to the receiving device. The receiving device then plays back this voice data for the user to listen to.

[1553] Specific examples

[1554] For example, when user A in Japan calls user B in the United States, the following steps are taken:

[1555] Terminal A sends User A's caller number and Internet Protocol address to the server.

[1556] The server identifies the Internet Protocol address as being in Japan and has Japanese as the primary language.

[1557] The server determines from past communication records that User A uses Japanese.

[1558] When user A speaks in Japanese, terminal A sends the speech to the server.

[1559] The server converts the speech to text, which is then translated into English.

[1560] The translated English audio data is sent to terminal B, where user B listens to it.

[1561] Prompt Sentence Examples

[1562] Person A, who lives in Japan, calls Person B, who lives in the U.S. During the call, what Person A says in Japanese is translated into English in real time and sent to Person B's device. Please tell me the process.

[1563] In this way, the system can provide real-time, highly accurate translation for calls between users who speak different languages.

[1564] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1565] Step 1:

[1566] The user initiates a call.

[1567] When a user uses a terminal to initiate a call, the terminal obtains the caller ID when the user presses the "Start Call" button in a specific application. The input is the user's operation, and the output is the caller ID obtained by the terminal.

[1568] Step 2:

[1569] The device obtains the IP address and caller ID.

[1570] The terminal sends the caller ID to the server. The terminal also connects to the Internet and obtains an Internet Protocol address. The obtained IP address is also sent to the server. The input is the caller ID and connection process, and the output is the IP address and caller ID sent to the server.

[1571] Step 3:

[1572] The server determines the country and primary language from which you are connecting.

[1573] The server analyzes the received Internet Protocol address using the GeoIP service to identify the region of the connecting user. It then determines the primary language used in that region. The input is the Internet Protocol address, and the output is the region of the connecting user and the primary language. Specifically, the server calls the GeoIP API to obtain location information from the IP address.

[1574] Step 4:

[1575] The server identifies the personal language information based on the caller number.

[1576] The server references a database of past communication records based on the caller ID to identify the user's preferred language. The input is the caller ID, and the output is the preferred language of the user. Specifically, the server executes an SQL query to retrieve the language information from the database.

[1577] Step 5:

[1578] The server selects the optimal language pair based on the integrated data.

[1579] The server integrates the regional information, primary language, and personal language information acquired in the previous step to select a highly accurate language pair. The input is regional information and personal language information, and the optimal language pair is determined as the output. Specifically, the server analyzes this information using statistical analysis methods and machine learning models to select the optimal language pair.

[1580] Step 6:

[1581] Perform real-time translation.

[1582] When a user speaks during a call, the device immediately sends the voice data to the server. The server then runs the voice data through a voice recognition engine in real time to convert it into text. The text is then translated into the target language using a translation engine. The input is the voice data, and the output is the translated text. Specifically, the server calls the voice recognition API to convert the voice data into text data.

[1583] Step 7:

[1584] Delivery and playback of translation results.

[1585] The translated text is converted into audio data using a speech synthesis engine and sent to the receiving device. The receiving device then plays this audio data and lets the user listen to it. The input is the translated text and the output is audio data. Specifically, the server uses a speech synthesis API to convert the text into audio and sends it to the receiving device.

[1586] Through the above steps, the system can provide real-time, highly accurate translation in calls between users who speak different languages.

[1587] (Application example 1)

[1588] 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."

[1589] To achieve smooth communication between multinational passengers and between passengers and the autonomous driving system in autonomous vehicles, real-time translation that overcomes language barriers is essential. However, conventional translation systems are not designed for use in vehicles, and it is difficult to achieve low-latency, high-precision translation. Furthermore, they lack the ability to automatically determine the language used by passengers or their location, making them impractical. Therefore, it is necessary to solve this problem.

[1590] 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.

[1591] In this invention, the server includes means for acquiring the IP address of the connecting source and determining the region and primary language of the connecting source from the IP address, means for acquiring the caller ID and identifying the language used by each user based on the caller's past call history, means for integrating the acquired IP address information and caller ID information and performing real-time multilingual translation on a device installed in the autonomous vehicle, and means for transmitting the translated audio data to an output device such as an in-vehicle speaker or an in-vehicle display for playback, thereby enabling smooth communication between passengers who speak different languages ​​in the autonomous vehicle and between passengers and the system.

[1592] The "source IP address" is a unique number that identifies the device connecting to the Internet.

[1593] "Region" refers to a specific geographical location or area.

[1594] A "dominant language" is the language that is primarily used in a region or country.

[1595] The "caller number" is identification information such as a telephone number for identifying the caller in a communication.

[1596] "Past call history" refers to recorded information about calls made by the user in the past.

[1597] "Real-time multilingual translation" refers to translation between multiple languages ​​in real time.

[1598] An "autonomous vehicle" is a vehicle that drives itself based on its own judgment without any driver intervention.

[1599] A "device" refers to an electronic device with a specific function, and in the present invention refers to a smartphone or an in-vehicle display.

[1600] "Translated speech data" refers to speech data that has been translated from an original language into another language.

[1601] An "output device" is a device for conveying information such as audio and video to a user, and in the present invention refers to a speaker or a display.

[1602] The present invention provides a system that performs real-time multilingual translation within an autonomous vehicle, enabling smooth communication between passengers who speak different languages ​​and between passengers and the system. Specific embodiments and program processing for implementing the present invention are described below.

[1603] System configuration

[1604] This system mainly consists of three elements: a server, an in-vehicle terminal, and a user. The server is the core of the system and is responsible for analyzing and translating voice data. The in-vehicle terminal is used by the user and communicates with the server and sends and receives voice data. The user is an individual who uses the system.

[1605] Program processing

[1606] 1. Acquiring voice input

[1607] When a user speaks in the car, the microphone built into the smartphone or in-car display picks up the voice data.

[1608] 2. Obtaining IP addresses and vehicle IDs

[1609] The in-vehicle terminal connects to the Internet, obtains the IP address and vehicle ID of the connection source, and sends them to the server.

[1610] 3. Language-specific processing

[1611] The server identifies geographic information based on the IP address and determines the predominant language used in that area.

[1612] Additionally, the language used by the speaker is identified by referring to past call history data.

[1613] 4. Selecting the best language pair

[1614] The acquired IP address information and caller ID information are integrated to determine the optimal translation language pair.

[1615] 5. Real-time speech translation

[1616] The server translates the acquired voice data in real time using multilingual translation APIs such as Google Cloud Speech-to-Text, DeepL, and Google Translate.

[1617] 6. Playback of translation results

[1618] The translated voice data is sent to an in-car terminal and played back through the car's speakers and display.

[1619] Hardware and software used

[1620] Hardware

[1621] Smartphones, in-vehicle displays, microphones, speakers

[1622] software

[1623] Speech recognition system (Google Cloud Speech-to-Text, etc.)

[1624] Multilingual translation API (DeepL, Google Translate)

[1625] Data processing server (AWS Lambda, etc.)

[1626] Geographical information analysis system (MaxMind GeoIP2, etc.)

[1627] Specific examples

[1628] When User A says in Japanese, "Where is the next stop?" in an autonomous vehicle, the system inside the autonomous vehicle immediately detects this speech, translates it into English, and tells the driver, "Where is the next stop?"

[1629] Prompt Sentence Examples

[1630] Prompt: "A passenger speaks in Japanese in a self-driving vehicle. Please translate what they said into English and convey it to the driver."

[1631] The system configured as described above enables smooth communication between passengers of various nationalities and between passengers and the automated driving system.

[1632] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1633] Step 1:

[1634] Processing description: When a user starts speaking in the car, the terminal uses the microphone to capture voice data.

[1635] Specific operation: When passenger A says, "Where is the next stop?", the microphone on the device picks up the voice.

[1636] Input: Passenger voice data

[1637] Output: Digitized signal of audio data

[1638] Step 2:

[1639] Processing description: The terminal connects to the Internet, obtains the IP address and vehicle ID of the connection source, and sends them to the server.

[1640] Specific operation: The terminal automatically obtains the vehicle's IP address and ID and sends that information to the server.

[1641] Input: Vehicle network connection information

[1642] Output: IP address and vehicle ID sent to the server

[1643] Step 3:

[1644] Process Description: The server determines geographic information based on the IP address and determines the predominant language used in that region.

[1645] How it works: Using a geographic information analysis system such as MaxMind GeoIP2, the server identifies the geographic location from the IP address, then determines the primary language of the specified region.

[1646] Input: IP address

[1647] Output: Region of origin and primary language

[1648] Step 4:

[1649] Process description: The server refers to past call history data to identify the language used by the speaker.

[1650] What it does: The server accesses a database and looks up past call history associated with the caller's number to identify the most commonly used language.

[1651] Input: Caller ID, past call history data

[1652] Output: Caller's preferred language information

[1653] Step 5:

[1654] Process description: The server integrates the acquired IP address information and caller ID information to determine the optimal translation language pair.

[1655] Specific operation: Using statistical analysis techniques, the acquired regional information is combined with the sender's language data to determine the language pair to be translated.

[1656] Input: IP address information, caller ID information

[1657] Output: Best translation language pair

[1658] Step 6:

[1659] Process description: The server translates the acquired voice data in real time using multilingual translation APIs such as Google Cloud Speech-to-Text, DeepL, and Google Translate.

[1660] Specific operation: The speech is converted into text using a speech recognition system, and the text is translated into the specified language using a multilingual translation API.

[1661] Input: Audio data, translation language pair

[1662] Output: Translated audio data

[1663] Step 7:

[1664] Process description: The server sends the translated voice data to the in-vehicle terminal, which then plays it through the car's speakers and display.

[1665] Specific operation: The device receives the translation results from the server and plays the audio data on the speaker.

[1666] Input: Translation audio data

[1667] Output: Translated speech played through the vehicle's speakers

[1668] 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.

[1669] The present invention is a system that identifies the user's language based on information such as the IP address and caller ID, provides real-time multilingual translation, and analyzes and recognizes the user's emotions to improve the naturalness and accuracy of the translation. The following configuration and program processing will be described as a specific example of how to implement the present invention.

[1670] System configuration

[1671] This system is mainly composed of three elements: the server, the terminal, and the user. The server is the core of the system and is responsible for analyzing and processing various data. The terminal is used by the user and communicates with the server and sends and receives voice data. It also has an emotion engine that recognizes emotions from the user's voice.

[1672] Program processing flow

[1673] 1. The user initiates a call

[1674] The user performs an operation to make a call and instructs the start of a call.

[1675] 2. The device detects the call

[1676] The device detects when the user initiates a call and captures the caller ID, while also obtaining the IP address via the internet connection.

[1677] 3. The device sends the caller ID and IP address to the server.

[1678] The terminal sends the acquired caller ID and IP address information to the server, completing preparations for connecting the call.

[1679] 4. The server analyzes the IP address

[1680] The server checks the IP address against a database to determine the country or region from which the connection originates, and then determines the primary language used.

[1681] 5. The server parses the caller ID

[1682] The server uses the received caller ID to look up past call history, extracting the caller's past language usage from the call history and creating an individual language profile.

[1683] 6. The server combines the IP address information with the caller ID information

[1684] The server combines the IP address and caller ID information it has acquired to determine the optimal language pair. If necessary, it also utilizes the results of statistical analysis of communication history data to optimize the real-time translation algorithm.

[1685] 7. Emotion Analysis Using an Emotion Engine

[1686] The server analyzes the user's voice data in real time and recognizes the user's emotions using an emotion engine, which then feeds the recognized emotion information back to the translation engine.

[1687] 8. Real-time translation by translation engine

[1688] The server translates the user's speech into the specified language in real time using a translation engine. At the same time, the tone and expression of the translation results are adjusted based on the emotional information obtained from the emotion engine. For example, if the user is angry, the translation will be stronger.

[1689] 9. Delivery and playback of translation results

[1690] The translated voice data is sent to the receiving device, which plays the voice back, allowing the receiving user to understand the conversation in their own language.

[1691] Specific scenario example

[1692] A specific scenario is shown below.

[1693] User A (living in Japan) calls User B (living in the US).

[1694] Terminal A sends User A's caller number and IP address information to the server.

[1695] The server recognizes the connection from Japan and identifies Japanese as the primary language.

[1696] Terminal B is in the United States, and the server identifies User B's primary language as English.

[1697] When user A speaks in Japanese, terminal A sends the speech to the server.

[1698] The server translates the Japanese speech into English and analyzes User A's emotions using an emotion engine.

[1699] The translation engine translates based on emotional information, using a stronger tone if the person is angry and a softer tone if the person is happy.

[1700] The server sends the translated voice data to terminal B.

[1701] Device B plays the English audio and lets User B listen to it. User B's voice is also subjected to real-time emotion analysis and translation.

[1702] In this way, the system provides low-latency, highly accurate translation in calls between users who speak different languages, while also realizing natural communication that reflects the user's emotions.

[1703] The processing flow will be explained below.

[1704] Step 1:

[1705] The user initiates a call.

[1706] The user performs an operation to make a call and gives an instruction to start a call.

[1707] Step 2:

[1708] The device detects the call.

[1709] The terminal detects the user's call initiation operation and captures the caller number.

[1710] At the same time, an IP address is obtained through the Internet connection.

[1711] Step 3:

[1712] The terminal sends the caller number and IP address to the server.

[1713] The terminal sends the acquired caller ID and IP address information to the server, completing preparations for connecting the call.

[1714] Step 4:

[1715] The server analyzes the IP address.

[1716] The server compares the received IP address with a database to identify the country or region from which the connection originates.

[1717] Determine the primary language spoken based on the identified country or region.

[1718] Step 5:

[1719] The server parses the caller ID.

[1720] The server uses the received caller ID to look up past call history.

[1721] Extracts caller's past language usage from call history to create an individual language profile.

[1722] Step 6:

[1723] The server combines the IP address information with the caller ID information.

[1724] The server combines the IP address information and caller ID information it has acquired to determine the optimal language pair.

[1725] The results of statistical analysis of communication history data are used to optimize real-time translation algorithms.

[1726] Step 7:

[1727] The server starts the emotion engine.

[1728] The server activates the emotion engine to analyze the user's voice data in real time.

[1729] Step 8:

[1730] The emotion engine analyzes the user's emotions.

[1731] The emotion engine uses an algorithm to recognize the user's emotions from the voice data and extracts emotion information.

[1732] The extracted emotion information is sent to the server.

[1733] Step 9:

[1734] The user begins speaking.

[1735] The user initiates a call with voice, which the terminal captures.

[1736] Step 10:

[1737] The terminal transmits the voice data to the server.

[1738] The terminal transmits the user's voice data to the server in real time.

[1739] Step 11:

[1740] The server translates the audio data.

[1741] The server uses a translation engine to translate the received voice data into the specified language in real time.

[1742] When translating, the tone and expression of the translation results are adjusted based on the emotional information recognized by the emotion engine.

[1743] Step 12:

[1744] The server sends the translated voice data to the receiving terminal.

[1745] The server sends the translated voice data to the receiving terminal.

[1746] Step 13:

[1747] The receiving terminal plays the audio data.

[1748] The receiving terminal plays the received translated voice data through a speaker and conveys it to the user.

[1749] Step 14:

[1750] The user ends the call.

[1751] The user then performs an operation to end the call, and the system saves the call record and ends the session.

[1752] Example 2

[1753] 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."

[1754] In today's global communication environment, it is difficult to provide low-latency, highly accurate translation for real-time conversations between users who speak different languages. Furthermore, there is a demand for systems that can accurately convey emotions, rather than simply translating words. While conventional translation systems can resolve language differences, they are unable to reflect emotional nuances, resulting in a decline in the quality of communication.

[1755] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: means for acquiring the IP address of the connection source and determining the country and language used by the connection source from the IP address; means for acquiring the caller number and identifying the language used by each user based on the caller's past communication record; means for integrating the acquired IP address information and caller number information and performing multilingual translation in real time; emotion analysis means for analyzing the user's voice data in real time and performing emotion analysis; means for feeding back the emotion analysis results and reflecting them in the translation content; and means for transmitting the translated voice data to the receiving terminal. This makes it possible to accurately translate in real time and accurately convey emotions even in calls between users speaking different languages.

[1756] The "IP address of the connecting device" is an identifier for a device connected to the Internet, and is a numerical address used to identify the location of a device on a network.

[1757] The "caller number" is an identification number for identifying the terminal of the caller in telephone communication, and usually means the telephone number of the caller.

[1758] "Country and language determination means" refers to methods or systems that analyze IP addresses or other geographic information to identify the primary language associated with a particular country or region.

[1759] "Past communication records" are historical data of the user's past communications, and are a collection of information including the contents of calls and messages, the language used, and so on.

[1760] "Integration means" refers to methods or systems that combine data from multiple sources into a single dataset that can be further analyzed and processed.

[1761] "Real-time multilingual translation means" refers to software or algorithms that translate speech or text into different languages ​​in real time.

[1762] "Emotion analysis means" refers to technology or systems that automatically identify a user's emotional state (e.g., joy, sadness, anger) from speech or text.

[1763] "Means of feeding back the results of emotion analysis and reflecting them in the translation content" refers to a method or system for incorporating the emotional information obtained through emotion analysis into the translation process and adjusting the translation results to an appropriate tone and expression according to the emotion.

[1764] "Means for transmitting translated speech data to a receiving terminal" refers to a method or system for quickly and accurately delivering real-time translated speech data to a receiving terminal.

[1765] MODE FOR CARRYING OUT THE INVENTION

[1766] This invention is a system that identifies the user's language based on information such as the IP address and caller ID, provides real-time multilingual translation, and improves the naturalness and accuracy of the translation content by analyzing and recognizing the user's emotions. As a concrete example for implementing this invention, the configuration and operation of the system will be described.

[1767] System configuration

[1768] This system mainly consists of three elements: a server, a terminal, and a user.

[1769] Server: The core part of the system, responsible for analyzing and processing various data. Specifically, it uses a cloud-based server (e.g., AWS EC2 instance).

[1770] Device: A device used by a user to communicate with a server and send and receive voice data. For example, a smartphone or VoIP device.

[1771] Emotion engine: Uses software (e.g., IBM Watson Tone Analyzer) to recognize emotions from the user's voice.

[1772] Translation engine: Uses software (e.g. Google Cloud Translation API) to translate speech in real time.

[1773] How it works

[1774] server

[1775] The server receives the IP address and caller ID of the connecting user and analyzes the data. Using the IP address, it uses an IP geolocation database (e.g., MaxMind GeoIP) to identify the country and primary language of the connecting user. Based on the caller ID, it examines past communication history and extracts a language profile used by each individual user.

[1776] Furthermore, the server receives voice data in real time and sends it to the emotion engine. The emotion engine recognizes the user's emotion based on the analysis results and feeds the results back to the translation engine. The translation engine then adjusts the tone and expression of the translation based on the emotional information.

[1777] Terminal

[1778] When a user initiates a call, the device sends the caller ID and IP address to the server. During the call, the device captures the user's voice data and sends it to the server in real time. It also plays back the translated voice data sent from the server for the user to listen to.

[1779] Specific scenario example

[1780] A specific scenario is shown below.

[1781] User A (living in Japan) calls User B (living in the US).

[1782] Terminal A sends User A's caller number and IP address information to the server.

[1783] The server recognizes the connection from Japan and identifies Japanese as the primary language.

[1784] Terminal B is in the United States, and the server identifies User B's primary language as English.

[1785] When user A speaks in Japanese, terminal A sends the speech to the server.

[1786] The server translates the Japanese speech into English and analyzes User A's emotions using an emotion engine.

[1787] The translation engine translates based on emotional information, using a stronger tone if the person is angry and a softer tone if the person is happy.

[1788] The server sends the translated voice data to terminal B.

[1789] Device B plays the English audio and lets User B listen to it. User B's voice is also subjected to real-time emotion analysis and translation.

[1790] Examples of prompt statements

[1791] Below is an example of a prompt sentence to input to the AI ​​model.

[1792] "User A, who speaks Japanese, calls User B, who speaks English and lives in the United States. Please translate the conversation in real time and adjust the translation result to a natural tone based on emotional information."

[1793] By inputting this prompt into a generative AI model, appropriate and natural translation results can be obtained. This system enables real-time, highly accurate translation and emotional conveyance in calls between users who speak different languages.

[1794] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1795] Processing Steps

[1796] Step 1:

[1797] A user initiates a call

[1798] The user launches the phone app on their smartphone or VoIP device, enters the phone number of the person they want to call, and presses the call button.

[1799] Input: Phone number of the person you want to call

[1800] Output: Trigger signal to start a call

[1801] Step 2:

[1802] The device detects the call

[1803] The device detects the user's call start operation and recognizes the call using internal sensors and software.

[1804] The device temporarily stores the caller's phone number in memory and obtains the current IP address through the internet connection.

[1805] Input: User's call operation

[1806] Output: Get caller ID and IP address

[1807] Step 3:

[1808] The device sends the caller ID and IP address to the server.

[1809] The terminal collects the caller ID and IP address and assembles them into a data packet, which is then sent to the server using a communication protocol (e.g., TCP / IP).

[1810] Input: Caller ID and IP address

[1811] Output: Sending data packets to the server

[1812] Step 4:

[1813] The server analyzes the IP address

[1814] The server compares the received IP address with a database (e.g., MaxMind GeoIP) to identify the country or region from which the connection originates.

[1815] The server determines the primary language based on the identified country or region.

[1816] Input: IP address

[1817] Output: Identified country / region and primary language

[1818] Step 5:

[1819] The server parses the caller ID

[1820] The server uses the received caller ID to query a communication history database to reference past communication history.

[1821] The server extracts the languages ​​the user has used in the past from historical data and creates an individual language profile.

[1822] Input: Caller ID

[1823] Output: Language profile

[1824] Step 6:

[1825] The server combines the IP address information with the caller ID information.

[1826] The server combines the IP address information and caller ID information to determine the optimal language pair.

[1827] If necessary, the results of statistical analysis of communication history data will be used to optimize real-time translation algorithms.

[1828] Input: IP address information and caller ID information

[1829] Output: Best language pair

[1830] Step 7:

[1831] Emotion analysis using an emotion engine

[1832] The server captures the user's voice data in real time and sends it to an emotion engine (e.g., IBM Watson Tone Analyzer).

[1833] The emotion engine analyzes voice tone, speed, pitch, etc. to recognize the user's emotional state.

[1834] Input: User's voice data

[1835] Output: Emotion analysis results

[1836] Step 8:

[1837] Real-time translation by translation engine

[1838] The server's translation engine (e.g., Google Cloud Translation API) receives the sentiment analysis results as feedback and translates the speech in real time.

[1839] The translation engine adjusts the tone and expression of the translation based on emotional information.

[1840] Input: User's voice data, emotion analysis results

[1841] Output: Translated audio data

[1842] Step 9:

[1843] Delivery and playback of translation results

[1844] The server sends the translated voice data to the receiving terminal.

[1845] The receiving device receives the translated voice data and plays it back on a speaker.

[1846] Input: Translated audio data

[1847] Output: Played audio

[1848] In this way, through each step, the system translates real-time conversations between users with low latency and high accuracy, enabling natural communication including emotional information.

[1849] (Application example 2)

[1850] 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."

[1851] In the food delivery industry, where smooth communication between users who speak different languages ​​is required, natural conversation that reflects the user's emotions is important in addition to real-time multilingual translation. However, current food delivery systems lack the technology to achieve this, which can lead to misunderstandings and frustration between customers and delivery personnel. This issue needs to be resolved.

[1852] 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.

[1853] In this invention, the server includes means for acquiring the IP address of the connecting party and determining the country and language used from the IP address, means for acquiring the caller's number and identifying the language used by each user based on the caller's past call history, means for integrating the acquired IP address information and caller number information to perform real-time multilingual translation, means for analyzing the user's voice data in real time and recognizing the user's emotion using an emotion engine, means for adjusting the tone and expression of the translation result based on the recognized emotion information, and means for transmitting the translated voice data to the receiving terminal, thereby enabling real-time, natural multilingual communication between the orderer and the delivery person.

[1854] The "source IP address" is a unique number assigned when connecting to the Internet, and is used to identify the location or region from which the connection is made.

[1855] "Caller ID" refers to the caller's telephone number or communication identifier when initiating a call or communication, and is used to identify the caller and to refer to past call history.

[1856] The "means for real-time multilingual translation" refers to a process for instantly translating a user's speech into another language based on the acquired language information.

[1857] An "emotion engine" is software or a system that analyzes a user's voice data and recognizes emotions such as joy or anger.

[1858] "Emotion information" refers to data on the user's emotional state obtained as a result of analysis by the emotion engine, and is reflected in the translation results.

[1859] "Tone and expression adjustment" refers to the process of appropriately changing the nuances and phrasing of the translated language based on the recognized emotional information.

[1860] "Translated audio data" refers to audio files or audio data that have been translated from an original language into another specified language.

[1861] The "receiving terminal" is a device that receives and plays back translated audio data, and includes, for example, a smartphone or tablet.

[1862] System configuration

[1863] This invention is mainly composed of three elements: a server, a terminal, and a user. The server is the core of the system and is responsible for analyzing and processing various data. The terminal is used by the user and communicates with the server and sends and receives voice data. It also has an emotion engine that recognizes emotions from the user's voice.

[1864] Program processing flow

[1865] Hardware and Software

[1866] Hardware:

[1867] Smartphone (iOS or Android)

[1868] Server (cloud server with high-performance processing capabilities)

[1869] software:

[1870] Real-time translation: Google Cloud Translation API, Microsoft Translator

[1871] Emotion analysis: IBM Watson Tone Analyzer, Azure Emotion API

[1872] Communication: Firebase, RESTful API

[1873] Processing Description

[1874] 1. User authentication and initialization:

[1875] When a user launches the app, their IP address is automatically acquired. The acquired IP address and caller ID are sent to the server, which then uses this information to identify the country or region from which the connection originates and determine the language being used.

[1876] 2. Sending IP address and caller ID:

[1877] Based on IP addresses and caller IDs, past call history is used to identify the language used by each individual user.

[1878] 3. Real-time translation:

[1879] When an orderer sends a message to a delivery person, the voice data is sent in real time to the server, which instantly translates it into the specified language.

[1880] 4. Sentiment analysis and tone adjustment:

[1881] The server analyzes the user's voice data using an emotion engine to recognize the user's emotions. Based on the recognized emotion information, the tone and expression of the translation results are adjusted. For example, if the user is angry, the translation will be stronger.

[1882] 5. Send and play translation results:

[1883] The translated voice data is sent to the receiving device, where the voice is played back. The delivery person understands the message in their own language. The voice from the delivery person is also translated in real time.

[1884] Specific examples

[1885] For example, if a Japanese customer says, "Please deliver the pizza quickly," the app will not only translate it as "Please deliver the pizza quickly," but if it detects a strong emotion (anger), it will convert it into a stronger message such as "Could you please hurry up with the pizza delivery?"

[1886] Prompt Sentence Examples

[1887] Example prompt for a generative AI model:

[1888] User types message: "Please deliver the pizza quickly"

[1889] The system identifies Japanese from the user's IP address and caller ID.

[1890] The voice data is analyzed using an emotion engine, and the emotion is recognized as anger.

[1891] Translation result: "Please deliver the pizza quickly"

[1892] Adjust based on emotional information: "Could you please hurry up with the pizza delivery?"

[1893] The tailored message is delivered to the delivery person, who plays the audio in English through the app.

[1894] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1895] Step 1:

[1896] When a user launches the app, the IP address and caller ID are automatically acquired. This information is sent to the server as the initial setting. The input is the user's operation, IP address, and caller ID, and data is sent based on this. The output is the IP address and caller ID sent to the server.

[1897] Step 2:

[1898] The server analyzes the received IP address to determine the country and language used by the connection. It also uses the caller ID to look up past call history and identify the language used by the user. The input is the IP address and caller ID sent to the server, and a database search is performed based on this. The output is the identified language information.

[1899] Step 3:

[1900] The user inputs a message and sends the voice data from the terminal to the server. The input is the user's voice data, which is received by the server. The output is the received voice data.

[1901] Step 4:

[1902] The server analyzes the voice data in real time and translates it into the specified language. The input is the voice data and the specified language information, and the translation engine operates based on this. The output is the translated voice data.

[1903] Step 5:

[1904] The server then runs the translated voice data through an emotion engine to recognize the user's emotions. The input is the translated voice data, which the emotion engine analyzes based on. The output is the recognized emotion information.

[1905] Step 6:

[1906] The server adjusts the tone and expression of the translation result based on the recognized emotional information. The input is the emotional information and translated speech data, and the tone and expression are adjusted based on this. The output is the adjusted translated speech data.

[1907] Step 7:

[1908] The server sends the adjusted translated audio data to the receiving terminal, which then plays it back. The input is the adjusted translated audio data that is sent to the terminal. The output is the played audio.

[1909] 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.

[1910] 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.

[1911] 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.

[1912] 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.

[1913] 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.

[1914] 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.

[1915] 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).

[1916] 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.

[1917] 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."

[1918] 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.

[1919] 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).

[1920] 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.

[1921] 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.

[1922] 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.

[1923] 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.

[1924] 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.

[1925] 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.

[1926] 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.

[1927] 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.

[1928] 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.

[1929] 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.

[1930] The following is further disclosed regarding the above embodiment.

[1931] (Claim 1)

[1932] A means for acquiring an IP address of a connecting source and determining the country and language used by the connecting source from the IP address;

[1933] a means for obtaining a caller ID and identifying the language used by an individual user based on the caller's past call history;

[1934] A means of integrating the acquired IP address information and caller ID information to perform real-time multilingual translation;

[1935] The system includes means for transmitting the translated speech data to a receiving terminal.

[1936] (Claim 2)

[1937] 10. The system according to claim 1, further comprising means for statistically analyzing communication history data and optimizing it to improve the speed and accuracy of real-time translation.

[1938] (Claim 3)

[1939] 10. The system of claim 1, further comprising means for transmitting the real-time translated speech data to a receiving terminal and playing the speech at the receiving terminal.

[1940] "Example 1"

[1941] (Claim 1)

[1942] means for acquiring an internet protocol address of a connecting source and determining the region and primary language of the connecting source from the internet protocol address;

[1943] means for obtaining a caller ID and determining the language used by the individual user based on the caller's past communications records;

[1944] A means for integrating the acquired internet protocol address information and caller ID information to perform real-time multilingual translation;

[1945] The system includes means for transmitting the translated speech data to a receiving terminal.

[1946] (Claim 2)

[1947] 10. The system according to claim 1, further comprising means for statistically analyzing communication record data and optimizing it to improve the speed and accuracy of real-time translation.

[1948] (Claim 3)

[1949] 10. The system of claim 1, further comprising means for transmitting the real-time translated speech data to a receiving terminal and playing the speech at the receiving terminal.

[1950] "Application Example 1"

[1951] (Claim 1)

[1952] A means for acquiring an IP address of a connecting source and determining the region and primary language used by the connecting source from the IP address;

[1953] a means for obtaining a caller ID and identifying the language used by an individual user based on the caller's past call history;

[1954] A means for integrating the acquired IP address information and caller ID information and performing real-time multilingual translation on a device installed in an autonomous vehicle;

[1955] The system includes a means for transmitting the translated speech data to an output device such as a speaker or an in-vehicle display for playback.

[1956] (Claim 2)

[1957] 10. The system according to claim 1, further comprising means for statistically analyzing communication history data and optimizing it to improve the speed and accuracy of real-time translation.

[1958] (Claim 3)

[1959] 10. The system of claim 1, further comprising means for transmitting the real-time translated speech data to a receiving terminal in the vehicle and playing back the speech at the receiving terminal.

[1960] "Example 2: Combining Emotion Engines"

[1961] (Claim 1)

[1962] A means for acquiring an IP address of a connecting source and determining the country and language used by the connecting source from the IP address;

[1963] a means for obtaining a caller ID and identifying the language used by an individual user based on the caller's past communication records;

[1964] A means of integrating the acquired IP address information and caller ID information to perform real-time multilingual translation;

[1965] emotion analysis means for analyzing user voice data in real time and performing emotion analysis;

[1966] A means to feed back the results of sentiment analysis and reflect them in the translation content,

[1967] The system includes means for transmitting the translated speech data to a receiving terminal.

[1968] (Claim 2)

[1969] 10. The system according to claim 1, further comprising means for statistically analyzing communication record data and optimizing it to improve the speed and accuracy of real-time translation.

[1970] (Claim 3)

[1971] 10. The system of claim 1, further comprising means for transmitting the real-time translated speech data to a receiving terminal and playing the speech at the receiving terminal.

[1972] "Application example 2 when combining emotion engines"

[1973] (Claim 1)

[1974] A means for acquiring an IP address of a connecting source and determining the country and language used by the connecting source from the IP address;

[1975] a means for obtaining a caller ID and identifying the language used by an individual user based on the caller's past call history;

[1976] A means of integrating the acquired IP address information and caller ID information to perform real-time multilingual translation;

[1977] means for analyzing the user's voice data in real time and recognizing the user's emotions using an emotion engine;

[1978] a means for adjusting the tone and expression of the translation result based on the recognized emotional information;

[1979] The system includes means for transmitting the translated speech data to a receiving terminal.

[1980] (Claim 2)

[1981] 10. The system according to claim 1, further comprising means for statistically analyzing communication history data and optimizing it to improve the speed and accuracy of real-time translation.

[1982] (Claim 3)

[1983] 10. The system of claim 1, further comprising means for transmitting the real-time translated speech data to a receiving terminal and playing the speech at the receiving terminal. [Explanation of symbols]

[1984] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring an IP address of a connecting source and determining the country and language used by the connecting source from the IP address; a means for obtaining a caller ID and identifying the language used by an individual user based on the caller's past call history; A means of integrating the acquired IP address information and caller ID information to perform real-time multilingual translation; The system includes means for transmitting the translated speech data to a receiving terminal.

2. 2. The system according to claim 1, further comprising means for statistically analyzing communication history data and optimizing it to improve the speed and accuracy of real-time translation.

3. 2. The system of claim 1, further comprising means for transmitting the real-time translated speech data to a receiving terminal and for playing the speech at the receiving terminal.

Images