System

Abstract

A system is provided.SOLUTION: A system, characterized in that the means for receiving and converting a user's speech input into text, the means for sending the text data to a server, the means for receiving the text data and generating a translation result using a translation model at the server, the means for returning the translation result to a terminal, the means for displaying the translation result at the terminal, and the means for converting speech into text at the terminal use a speech recognition module, and the server uses a deep learning model as the translation model.SELECTED DRAWING: Figure 1

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] While many systems offer real-time translation functions to facilitate smooth communication in local areas, many of them are difficult to use, and lack the support necessary for users to communicate effectively with local people, especially when traveling abroad. Furthermore, the translation results can be stiff and lack humor, making them unfamiliar with the local culture. Given this background, there is a need for a system that can adapt to the user's situation and provide effective, humorous translations in real time. [Means for solving the problem]

[0005] To solve the above problems, the present invention proposes a system having the following configuration: means for receiving a user's voice input and converting it into text; means for transmitting the text data to a server; means for receiving the text data at the server and generating a translation result using a translation model; means for returning the translation result to a terminal; and means for displaying the translation result at the terminal. Furthermore, the means for converting speech to text at the terminal uses a speech recognition module, and the server uses a deep learning model as the translation model, thereby enabling the system to provide user-friendly translation and support appropriate to the situation. This allows users to communicate smoothly with local people and engage in humorous conversations that are attuned to the local culture.

[0006] "User" refers to a person who uses the system.

[0007] "Voice input" refers to inputting spoken information from a user into a system.

[0008] "Text" is speech input converted into written information.

[0009] "Terminal" refers to a device operated by a user, such as a smartphone or tablet.

[0010] "Server" refers to a centralized computer system that processes data over a network and provides the results to other devices.

[0011] "Speech Recognition Module" means a software or hardware component for converting voice input into text.

[0012] "Translation model" refers to an AI algorithm that translates input text into another language.

[0013] A "deep learning model" is a form of machine learning that uses multi-layered neural networks and enables complex data analysis.

[0014] An "HTTP POST request" is one of the communication protocols used by a client to send data to a server.

[0015] An "HTTP response" is one of the communication protocols in which a server returns data to a client. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0024] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0037] The following describes in detail an embodiment of the present invention. This system provides a real-time translation function, enabling users to communicate smoothly with local people. Specifically, the system converts the user's voice input into text, processes it using a translation model on a server, and returns and displays the translation results to the user.

[0038] Overall structure

[0039] The system mainly consists of the following components:

[0040] 1. User device: The device that receives voice input.

[0041] 2. Server: A central computer that analyzes the audio data and performs the translation.

[0042] 3. Speech Recognition Module: Software that converts speech into text.

[0043] 4. Translation model: An AI algorithm that translates text data into another language.

[0044] 5. Communication method: A method for sending and receiving data between the terminal and the server (such as HTTP protocol).

[0045] Program processing flow

[0046] 1. User voice input

[0047] The user provides voice input by speaking into the device (e.g., "Hello, where is the station?").

[0048] 2. Speech-to-text

[0049] The device receives voice input and converts it into text using a built-in speech recognition module.

[0050] The speech recognition module analyzes the user's voice and converts the results into text data, with high accuracy taking into account the user's pronunciation and accent.

[0051] 3. Sending text data to the server

[0052] The terminal sends the converted text data to the server using an HTTP POST request.

[0053] Example: The device sends the text "Hello, where is the station?" to the endpoint https: / / example.com / translate.

[0054] 4. Translation processing on the server

[0055] The server receives the text data sent from the terminal.

[0056] The server inputs the received data into a translation model, which is based on deep learning and uses a multi-layered neural network.

[0057] The translation model analyzes text and generates appropriate translation results, taking into account context and appropriate expressions based on a vast amount of training data.

[0058] Example: Translating the Japanese phrase "Hello, where is the station?" into English "Hello, where is the station?"

[0059] 5. Returning and displaying translation results

[0060] The server returns the generated translation results to the terminal using an HTTP response.

[0061] The device receives the translation results and displays them to the user in text format, with a notification for the user to review.

[0062] Example: The device displays the translation result "Hello, where is the station?" on the screen for the user to confirm.

[0063] Specific examples

[0064] As an example, we will explain in detail how the system operates when a user says, "Hello, where is the station?"

[0065] User: Says to the device, "Hello, where is the station?"

[0066] Terminal: The speech recognition module converts the speech into text "Hello, where is the station?"

[0067] Terminal: Sends text data to the server via an HTTP POST request.

[0068] Server: Input the received text into the translation model and generate the English translation result "Hello, where is the station?"

[0069] Server: Sends the translation result to the device as an HTTP response.

[0070] Terminal: Display the translation result and notify the user.

[0071] With the above configuration, the system of the present invention provides real-time translation that allows users to communicate effectively with local people. Furthermore, by utilizing deep learning models, it is possible to achieve highly accurate and context-appropriate translation. This is expected to improve user convenience in many situations, including overseas travel.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] The user speaks to the terminal and performs voice input. For example, the user might say, "Hello, where is the station?"

[0075] Step 2:

[0076] The terminal receives the user's voice input and activates a voice recognition module. The voice recognition module analyzes the user's speech and converts it into text data. In this case, the text generated is "Hello, where is the station?"

[0077] Step 3:

[0078] The device temporarily stores the converted text data in local memory and then sends it to the server using an HTTP POST request. Specifically, the text data is sent to the endpoint https: / / example.com / translate.

[0079] Step 4:

[0080] The server receives the HTTP POST request and obtains the text data. Specifically, the text data "Hello, where is the station?" arrives at the server.

[0081] Step 5:

[0082] The server inputs the received text data into a deep learning-based translation model, which translates the input Japanese text into English and generates the appropriate English translation result, in this case, "Hello, where is the station?"

[0083] Step 6:

[0084] The server returns the generated translation result to the device using an HTTP response, specifically the translated text "Hello, where is the station?"

[0085] Step 7:

[0086] The device stores the translation results received from the server in its local memory and notifies the user. The device's display shows the text "Hello, where is the station?" in English.

[0087] Step 8:

[0088] The user can check the displayed translation results and communicate with the local person. For example, they can ask the local person a question using the displayed English.

[0089] Example 1

[0090] 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."

[0091] Real-time translation is necessary for users who do not understand the local language to communicate smoothly with local people. However, conventional translation systems have problems such as low speech input accuracy and inaccurate translation results. Furthermore, there is also the issue of operation becoming cumbersome due to the need to use multiple applications.

[0092] 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.

[0093] In this invention, the server includes a means for converting speech input into text with high accuracy, a means for transmitting text data to the server using a communication protocol, and a means for generating translation results using deep learning, thereby enabling users to seamlessly obtain highly accurate translation results from speech input.

[0094] A "user" is an individual or group that uses the system and is the subject that performs voice input.

[0095] "Voice input" refers to the operation of inputting the user's voice into the terminal as digital information.

[0096] A "terminal" is a device used by a user that receives voice input, converts text, communicates, displays translation results, and provides voice notification.

[0097] "Means for converting to text" refers to the process of converting voice data into text data using a voice recognition module.

[0098] A "communication protocol" is a standardized communication method for sending and receiving data between a terminal and a server, and examples include HTTP and HTTPS.

[0099] A "server" is a central computer system that receives text data, processes it using a translation model, and generates and returns the translation results.

[0100] A "voice recognition module" is a software or hardware technology that analyzes input speech and converts it into text.

[0101] A "translation model" is a machine learning algorithm that uses deep learning to translate text data into another language.

[0102] "Deep learning" is a branch of artificial intelligence that uses multi-layered neural networks to analyze data and perform specific tasks automatically.

[0103] A "generative AI model" is an artificial intelligence algorithm that learns from a large amount of data in advance and then generates text based on new data.

[0104] A "translation result" is text data in another language generated by a translation model.

[0105] "Encrypted communication means" refers to technology that encrypts data to prevent eavesdropping or tampering by third parties when sending and receiving data.

[0106] "Voice notification" is a function that notifies the user of the generated translation result by voice.

[0107] The following describes in detail an embodiment of the present invention. This system provides a real-time translation function that enables users to communicate smoothly with local people. Specifically, the system converts user voice input into text, translates the text on the server, and returns the translation result to the user for display.

[0108] The overall system consists of the following components:

[0109] 1. User device: This is the device that receives the voice input, such as a smartphone or a dedicated translation device.

[0110] 2. Server: A central computer that analyzes the audio data and performs the translation.

[0111] 3. Speech recognition module: Software that converts the user's voice into text. Specifically, Google Cloud Speech-to-Text API is used.

[0112] 4. Translation model: An AI algorithm that translates text data into other languages. Examples include the Google Translate API and BERT-based models that use deep learning.

[0113] 5. Communication method: A method for sending and receiving data between the terminal and the server. For example, the HTTP or HTTPS protocol is used.

[0114] The specific system operation is explained below:

[0115] 1. User voice input: The user speaks to the terminal, "Hello, where is the station?" The voice input is received as digital data through the terminal's microphone.

[0116] 2. Speech-to-text conversion: The device sends the received voice data to a voice recognition module (e.g., Google Cloud Speech-to-Text API) and converts it into text data: "Hello, where is the station?"

[0117] 3. Sending text data to the server: The device sends the converted text data to the server via an HTTP POST request, using https: / / example.com / translate as the destination endpoint.

[0118] 4. Translation processing on the server: The server inputs the received text data into a translation model (e.g., Google Translate API) and generates the translation result "Hello, where is the station?" In this process, the server uses a deep learning-based generative AI model.

[0119] 5. Return and display of translation results: The server returns the generated translation results to the terminal as an HTTP response. The terminal displays the translation results on the screen and can also use a voice notification function to notify the user.

[0120] As a concrete example, here is what the system does again when the user says "Hello, where is the station?":

[0121] User: Says to the device, "Hello, where is the station?"

[0122] Terminal: Uses a speech recognition module to convert the speech into text: "Hello, where is the station?"

[0123] Terminal: Sends text data to the server via an HTTP POST request.

[0124] Server: Inputs the received text into the translation model and generates the English translation result "Hello, where is the station?"

[0125] Server: Sends the translation result to the terminal as an HTTP response.

[0126] Terminal: Displays the translation results and notifies the user.

[0127] Example prompt sentence:

[0128] "Please translate the Japanese text "Hello, where is the station?" into English."

[0129] As described above, this system enables users to communicate smoothly even if they do not understand the local language. By utilizing advanced speech recognition and translation technology, it is possible to provide real-time, highly accurate translation results.

[0130] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0131] Step 1:

[0132] The user speaks to the terminal. When the user speaks, "Hello, where is the station?", the microphone converts the voice into a digital signal. The input is the user's voice data, which is then passed on to the next step of processing.

[0133] Step 2:

[0134] The device receives the voice data and sends it to a built-in voice recognition module. The voice recognition module (for example, Google Cloud Speech-to-Text API) converts the voice data into text. Specifically, the voice signal is analyzed and each phoneme is mapped to a character. The output is the text data "Hello, where is the station?"

[0135] Step 3:

[0136] The terminal sends the converted text data to the server via an HTTP POST request. The input is the text data "Hello, where is the station?", which is sent to the server in the form of an HTTP request. The HTTPS protocol is used as the transmission method, and the data is sent to the endpoint https: / / example.com / translate.

[0137] Step 4:

[0138] The server receives the text data sent from the terminal. When the server receives the text data, it passes it on to the next process. The input is the text data "Hello, where is the station?", which is stored in the server's main memory or storage.

[0139] Step 5:

[0140] The server inputs the received text data into a translation model. The input data, "Hello, where is the station?", is passed to a deep learning-based translation model (for example, Google Translate API). Specifically, the translation model analyzes the text data and generates a translation result. The output is the English translation, "Hello, where is the station?"

[0141] Step 6:

[0142] The server returns the generated translation result to the terminal as an HTTP response. The input is the translation result text data "Hello, where is the station?", which is sent to the terminal in HTTP response format. HTTPS is again used as the communication method.

[0143] Step 7:

[0144] The terminal receives the returned translation result. The input is the text data of the translation result sent from the server, "Hello, where is the station?". It receives this and passes it on to the next process.

[0145] Step 8:

[0146] The device displays the received translation results to the user and provides voice notification if necessary. Specifically, the text data is displayed on the screen for the user to review. Furthermore, it is possible to provide voice notification of the translation results using a speech synthesis module. The output is the displayed text and voice notification.

[0147] Through these steps, the system enables users to communicate smoothly with local people in real time through translation, providing highly accurate and context-appropriate translation results.

[0148] (Application example 1)

[0149] 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."

[0150] There is a problem in that it is difficult to communicate smoothly in real time between users who speak different languages. In particular, in situations such as food delivery services, if the customer and delivery person cannot exchange information smoothly, delivery delays and misunderstandings can occur. To solve this problem, a highly accurate, real-time speech translation system is required.

[0151] 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.

[0152] In this invention, the server includes means for receiving a user's voice input and converting it into text, means for transmitting the text data to the server, means for receiving the text data at the server and generating a translation result using a translation model, means for returning the translation result to the terminal, means for displaying the translation result at the terminal, and means for reading out the translation result aloud, thereby enabling users who speak different languages ​​to communicate smoothly in real time.

[0153] "User voice input" refers to voice data uttered by a user, which is input received by the system.

[0154] "Means for converting to text" refers to software or hardware for converting audio data into corresponding text data.

[0155] "Means for sending to the server" refers to a communication means for sending the converted text data to the server via a network.

[0156] "Means for receiving at the server" refers to means for receiving text data transmitted via a network at the server side.

[0157] "Means for generating translation results using a translation model" refers to means that include a process using an AI algorithm or deep learning model to translate received text data into another language.

[0158] The "means for returning the translation result to the terminal" refers to a means for transmitting the generated translation result to the user's terminal via a network.

[0159] "Means for displaying the translation result on the terminal" refers to means for displaying the received translation result in text format on the user's terminal.

[0160] "Means for reading out the translation result aloud" refers to means for reading out the displayed translation result in audio format using text-to-speech conversion technology.

[0161] "Speech recognition module" refers to software or a device for analyzing a user's voice data and converting it into text data.

[0162] A "deep learning model" refers to an AI algorithm that uses multi-layered neural networks to process information and perform advanced pattern recognition and prediction.

[0163] This system provides a real-time translation function to facilitate communication between users who speak different languages. A specific embodiment is described below.

[0164] Overall system configuration

[0165] The system mainly consists of the following components:

[0166] 1. User device: The device that receives voice input, such as a smartphone or tablet.

[0167] 2. Server: A central computer that analyzes the audio data and performs the translation.

[0168] 3. Speech recognition module: Uses "RecognizerIntent", software that converts speech to text.

[0169] 4. Translation model: An AI algorithm for translating text data into another language, using the Google Cloud Translate API.

[0170] 5. Communication method: The HTTP protocol is used to send and receive data between the terminal and the server.

[0171] System processing flow

[0172] 1. Voice input: When the user speaks to the device, the device converts the speech into text. This is done using "RecognizerIntent".

[0173] For example, a user might say, "Hello, I'd like to know the status of my order." This speech is analyzed by "RecognizerIntent" and converted into the text "Hello, I'd like to know the status of my order."

[0174] 2. Sending text data: The converted text data is sent to the server as an HTTP POST request. For example, the device sends the text data "Hello, I'd like to know the status of my order" to the specified endpoint (e.g., https: / / example.com / translate).

[0175] 3. Translation processing on the server: The server inputs the received data into the Google Cloud Translate API for translation. The AI ​​algorithm used as the translation model is based on deep learning and uses a multi-layer neural network to achieve high-precision translation.

[0176] As a concrete example, the Japanese phrase "Hello, I'd like to know the status of my order" is translated into English as "Hello, I'd like to know the status of my order."

[0177] 4. Return and display of translation results: The server returns the translation results to the device as an HTTP response, which the device receives and displays to the user. Additionally, a function has been added to read the translation results aloud.

[0178] For example, the device will display the translation result "Hello, I'd like to know the status of my order" on the screen and read it aloud, allowing the user to check the translation result both in text and audio.

[0179] Example prompt sentences

[0180] Examples of prompts include:

[0181] "A user says, 'Hello, I'd like to know the status of my order.' Please translate this Japanese sentence into English."

[0182] This system enables smooth real-time communication between users who speak different languages, and is particularly useful for food delivery services, where information can be exchanged quickly and accurately between customers and delivery personnel.

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

[0184] Step 1:

[0185] The user speaks to the device. Specifically, the user says, "Hello, I'd like to know the status of my order." This voice input is captured through the device's microphone.

[0186] Input: User's voice data

[0187] Output: Raw audio data captured by the microphone

[0188] Step 2:

[0189] The device uses a speech recognition module ("RecognizerIntent") to convert the acquired speech data into text data. During the conversion process, the speech is analyzed, and words are recognized and converted into text.

[0190] Input: Raw audio data

[0191] Data processing: Analysis and recognition of voice data

[0192] Output: Text data (e.g. "Hello, I'd like to know the status of my order.")

[0193] Step 3:

[0194] The terminal sends the converted text data to the server using an HTTP POST request.

[0195] Input: Text data

[0196] Data processing: Generating HTTP requests

[0197] Output: Request sent to server

[0198] Step 4:

[0199] The server receives the text data sent from the terminal, analyzes the HTTP request, and obtains the text data.

[0200] Input: HTTP request

[0201] Data processing: HTTP request analysis

[0202] Output: Received text data

[0203] Step 5:

[0204] The server sends the received text data to the Google Cloud Translate API for translation. The translation model is based on deep learning, and the data is analyzed and translated.

[0205] Input: Received text data

[0206] Data processing: Data analysis and translation using translation models

[0207] Output: Translated text data (e.g., "Hello, I'd like to know the status of my order")

[0208] Step 6:

[0209] The server returns the translation results to the terminal as an HTTP response, which is then generated and sent over the network.

[0210] Input: Translated text data

[0211] Data processing: Generating HTTP responses

[0212] Output: Sending HTTP response to the terminal

[0213] Step 7:

[0214] The device receives the HTTP response from the server, analyzes the received data, and obtains the translation result.

[0215] Input: HTTP response

[0216] Data processing: HTTP response analysis

[0217] Output: Translated text data

[0218] Step 8:

[0219] The device displays the translation results on the screen and notifies the user. The translation results are also read aloud, allowing the user to check the translation results both in text and audio.

[0220] Input: Translated text data

[0221] Data processing: Screen display and voice reading

[0222] Output: On-screen text and spoken notifications

[0223] The above processing steps enable a user to smoothly communicate in real time with others who speak different languages.

[0224] 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.

[0225] The following describes in detail the mode for carrying out the present invention. This system combines a real-time translation function with an emotion engine that recognizes the user's emotions. This allows users to not only communicate smoothly with local people, but also convey their emotions.

[0226] Overall structure

[0227] The system mainly consists of the following components:

[0228] 1. User's device: A device that receives voice input and has a speech recognition module and an emotion engine.

[0229] 2. Server: A central computer that analyzes voice and emotion data and performs translation.

[0230] 3. Speech Recognition Module: Software that converts speech into text.

[0231] 4. Emotion engine: Software that analyzes emotions from the user's voice.

[0232] 5. Translation model: An AI algorithm that translates text and sentiment data into another language.

[0233] 6. Communication method: A method for sending and receiving data between the terminal and the server (such as HTTP protocol).

[0234] Program processing flow

[0235] 1. User voice input

[0236] The user speaks to the device to input voice information. For example, the user might say, "Hello, where is the station?" This includes emotional information such as tone and speed of voice.

[0237] 2. Speech-to-text

[0238] The terminal receives the user's voice input and activates a voice recognition module. The voice recognition module analyzes the user's speech and converts it into text data. In this case, the text generated is "Hello, where is the station?"

[0239] 3. Emotional Recognition

[0240] The device uses an emotion engine to analyze emotions from the user's voice input. The emotion engine analyzes the tone, speed, accent, etc. of the voice to generate emotion data for the user. For example, emotions such as "happiness," "surprise," and "doubt" can be recognized.

[0241] 4. Sending text data and emotion data to the server

[0242] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request. Specifically, the text data and emotion data are sent to the endpoint https: / / example.com / translate.

[0243] 5. Translation processing on the server

[0244] The server receives the HTTP POST request and obtains the text data and emotion data. Specifically, the text data "Hello, where is the station?" and the emotion data "joy" arrive at the server.

[0245] The server inputs the received text data and emotion data into a deep learning-based translation model, which generates an English translation result taking into account the input Japanese text and corresponding emotion data.

[0246] The translation model takes into account emotional data and adds appropriate expressions depending on the context. For example, the translation "Hello, where is the station?" is given an emotional value and translated as "Hi, could you tell me where the station is, please?"

[0247] 6. Returning and displaying translation results

[0248] The server returns the generated translation result to the device using an HTTP response, specifically the translated text "Hi, could you tell me where the station is, please?"

[0249] The device stores the translation results received from the server in its local memory and notifies the user. The device's display shows the emotional English translation, "Hi, could you tell me where the station is, please?"

[0250] Specific examples

[0251] As an example, we will explain in detail how the system operates when a user says, "Hello, where is the station?"

[0252] User: Says to the device, "Hello, where is the station?"

[0253] Terminal: The speech recognition module converts the speech into text "Hello, where is the station?"

[0254] Device: The emotion engine recognizes the emotion of "joy" from voice.

[0255] Device: Send text and emotion data to the server via an HTTP POST request.

[0256] Server: The received text and emotion data are input into the translation model, and the emotion-sensitive English translation result "Hi, could you tell me where the station is, please?" is generated.

[0257] Server: Sends the translation result to the device as an HTTP response.

[0258] Terminal: Display the translation result and notify the user.

[0259] With the above configuration, the system of the present invention provides real-time translation that allows users to communicate effectively and emotionally with local people. Furthermore, by utilizing an emotion engine, highly accurate translation that incorporates emotion becomes possible. This is expected to improve the user's communication experience in a variety of situations.

[0260] The processing flow will be explained below.

[0261] Step 1:

[0262] The user speaks to the terminal and performs voice input. For example, the user might say, "Hello, where is the station?"

[0263] Step 2:

[0264] The device receives the user's voice input and activates a voice recognition module. The voice recognition module analyzes the user's speech and converts it into text data. In this case, the text generated is "Hello, where is the station?"

[0265] Step 3:

[0266] The device uses an emotion engine to analyze emotions from the user's voice input. The emotion engine analyzes the tone, rate, and voice pattern of the voice to generate emotion data for the user. In this case, the emotion engine recognizes the emotion of "happiness."

[0267] Step 4:

[0268] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request to the endpoint https: / / example.com / translate.

[0269] Step 5:

[0270] The server receives the HTTP POST request and obtains the text data and emotion data. Specifically, the text data "Hello, where is the station?" and the emotion data "joy" arrive at the server.

[0271] Step 6:

[0272] The server inputs the received text data and emotion data into a deep learning-based translation model. This model takes into account the input Japanese text and corresponding emotion data and generates an English translation result. In this case, the translation "Hello, where is the station?" is annotated with emotion and generated as "Hi, could you tell me where the station is, please?"

[0273] Step 7:

[0274] The server returns the generated translation result to the device using an HTTP response, specifically the translated text "Hi, could you tell me where the station is, please?"

[0275] Step 8:

[0276] The device receives the translation results from the server, stores them in its local memory, and notifies the user. The device displays the emotional English translation, "Hi, could you tell me where the station is, please?"

[0277] Step 9:

[0278] The user can check the displayed translation results and communicate with the local person, for example, by asking a question to the local person using the displayed English.

[0279] Example 2

[0280] 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."

[0281] Conventional real-time translation systems convert a user's speech into text and translate it into different languages, but they do not take the user's emotions into account when translating. As a result, the user's intentions and emotions are not accurately conveyed, resulting in a decline in the quality of communication. In particular, in situations where emotions play an important role, translations that ignore emotions can lead to misunderstandings and inappropriate expressions.

[0282] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0283] In this invention, the server includes a means for converting speech input into text, a means for recognizing and acquiring user emotion data, and a means for generating translation results using a generative model, thereby enabling highly accurate translation that takes user emotion into consideration.

[0284] "Voice input" refers to voice data spoken by a user.

[0285] "Means for converting to text" refers to a process or device that converts audio data into text data.

[0286] "Emotion data" refers to information about emotions extracted from the user's voice.

[0287] "Means for transmitting to a server" refers to the mechanisms and protocols that allow a terminal to transmit data to a server via the Internet or other communication means.

[0288] A "generative model" is an algorithm or computer program that generates a specific output based on given input data, particularly one that uses artificial intelligence techniques such as deep learning.

[0289] "Means for generating a translation result" refers to a process or system that translates received text data and emotion data into another language and generates the translation result.

[0290] "Display means" refers to devices or software that visually notify the user of the translation results.

[0291] The following describes in detail an embodiment of the present invention. This system combines a real-time translation function with an emotion engine that recognizes the user's emotions. This system allows users to not only communicate smoothly with local people, but also convey their emotions.

[0292] Overall structure

[0293] The system mainly consists of the following components:

[0294] 1. User's device: This is the device that receives voice input and runs the voice recognition module and emotion engine. For example, a smartphone or tablet is used here, and a dedicated application is installed.

[0295] 2. Server: This is the central computer that analyzes the voice and emotion data and performs the translation. A cloud-based server is ideal and has the capacity to process large amounts of data.

[0296] 3. Speech Recognition Module: Software that converts speech into text. Specifically, Google Speech-to-Text API is used.

[0297] 4. Emotion engine: Software that analyzes emotions from the user's voice. For example, Azure Cognitive Services' Emotion API falls into this category.

[0298] 5. Generative models: AI algorithms that translate text and sentiment data into another language. Deep learning-based models such as Google Translate API and DeepL API are used.

[0299] 6. Communication method: A method for sending and receiving data between the terminal and the server. HTTP protocol and REST API are commonly used.

[0300] Example of operation

[0301] Here is a concrete example of how this system works:

[0302] 1. User voice input:

[0303] The user speaks to the terminal, "Hello, where is the station?" The speech includes emotional (e.g., joy) tone and rate.

[0304] 2. Speech to text transcription:

[0305] The device activates a speech recognition module (Google Speech-to-Text API) to convert the speech into text data, resulting in the text "Hello, where is the station?"

[0306] 3. Emotion Recognition:

[0307] The device uses an emotion engine (Azure Cognitive Services' Emotion API) to analyze emotion data from the voice and generate emotion data for "joy" in this case.

[0308] 4. Sending data to the server:

[0309] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request, with an endpoint such as https: / / example.com / translate.

[0310] 5. Translation processing on the server:

[0311] The server receives the text data and emotion data and inputs them into a generative model (Google Translate API or DeepL API). Taking into account the text "Hello, where is the station?" and the emotion "joy," the server generates the English translation result "Hi, could you tell me where the station is, please?"

[0312] 6. Returning and displaying translation results:

[0313] The server sends the translation results back to the device using an HTTP response, which the device receives and displays on its screen.

[0314] In this way, real-time translation based on the user's voice and emotions is realized. By using this system, users can obtain highly accurate translation results that include emotions, enabling smooth communication with local people.

[0315] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0316] Step 1:

[0317] The user inputs voice into the terminal. For example, they might say, "Hello, where is the station?" This voice data also contains emotional information such as tone and speed. The input is the user's voice, and the output is sent to the terminal as voice data.

[0318] Step 2:

[0319] The device receives voice input and launches a voice recognition module (e.g., Google Speech-to-Text API). The voice recognition module analyzes the voice data and generates text data such as "Hello, where is the station?". Specifically, it preprocesses the voice signal, extracts features, and then converts the signal to text. The input is voice data, and the output is text data.

[0320] Step 3:

[0321] The device calls an emotion engine (e.g., Azure Cognitive Services' Emotion API) at the same time as receiving the text data. The emotion engine analyzes the user's voice data and generates emotion data. In this case, the emotion data obtained is "joy." Specific operations include processes that analyze the tone, speed, and accent of the voice. The input is voice data, and the output is emotion data.

[0322] Step 4:

[0323] The device sends the generated text data and emotion data to the server using an HTTP POST request. Specific operations include constructing the HTTP request header and body and sending the data to the endpoint https: / / example.com / translate. The input is text data and emotion data, and the output is an HTTP request.

[0324] Step 5:

[0325] The server receives an HTTP POST request and retrieves text data and emotion data. Specifically, it analyzes the HTTP request and extracts the text data "Hello, where is the station?" and the emotion data "Joy." The input is the HTTP request, and the output is the analyzed text data and emotion data.

[0326] Step 6:

[0327] The server inputs text data and emotion data into a generative model (e.g., Google Translate API or DeepL API). The generative model uses this data to generate the translation result, "Hi, could you tell me where the station is, please?" Specifically, the deep learning-based model processes the data through multiple layers to generate the final translation result. The input is text data and emotion data, and the output is the translation result.

[0328] Step 7:

[0329] The server returns the generated translation results to the terminal in the form of an HTTP response. Specific operations include setting the translation results in the header and body of the HTTP response and sending it to the terminal. The input is the translation results, and the output is the HTTP response.

[0330] Step 8:

[0331] The terminal receives the HTTP response returned from the server and obtains the translation result, "Hi, could you tell me where the station is, please?". The translation result is displayed on the screen and notified to the user. Specifically, it analyzes the HTTP response and updates the user interface to display the result. The input is the HTTP response, and the output is the displayed translation result.

[0332] (Application example 2)

[0333] 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."

[0334] When a user makes an inquiry about a food delivery service, conventional systems are unable to respond in a way that takes into account the user's emotions, making it difficult to respond in a way that appropriately reflects the user's emotions.Furthermore, the inability to recognize emotions in real time and provide an appropriate response results in a poor user experience.

[0335] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a user's voice input and converting it into text, means for transmitting the text data and emotion data to the server, and means for receiving the text data and emotion data in the server and generating a translation result using a translation model. This makes it possible to provide a highly accurate translation result that reflects the user's emotion.

[0336] "User's voice input" refers to a voice signal emitted by a user into a terminal.

[0337] "Text data" refers to character data obtained by converting a voice signal into text by a voice recognition module.

[0338] "Emotion data" refers to data that indicates the user's emotional state as analyzed by the emotion engine.

[0339] "Server" refers to a central computer that receives speech input, text data, and emotion data, and uses a translation model to generate a translation result.

[0340] "Translation model" refers to an algorithm that uses AI technologies such as deep learning to generate translation results based on input text data and emotional data.

[0341] "Terminal" refers to a device that receives a user's voice input and has a voice recognition module and an emotion engine.

[0342] "Speech recognition module" refers to software that converts a user's voice input into text data.

[0343] "Emotion engine" refers to software that analyzes emotions from the user's voice.

[0344] "Translation result" refers to the output text in another language that a translation model generates, taking into account the input text and sentiment.

[0345] "HTTP POST request" refers to one of the communication protocols used to transfer text data and emotion data from a terminal to a server.

[0346] "HTTP response" refers to one of the communication protocols used to return translation results from the server to the terminal.

[0347] The following describes in detail an embodiment of the present invention. The present invention is a system for recognizing a user's emotions and providing appropriate responses in a food delivery service. This system converts a user's voice input into text data and emotion data in real time, transmits the data to a server, and generates a response using a translation model.

[0348] Overall structure

[0349] The system of the present invention mainly consists of the following components:

[0350] 1. Terminal: A device that receives voice input and has a speech recognition module and an emotion engine.

[0351] 2. Server: A central computer that analyzes voice and emotion data and performs translation.

[0352] 3. Speech Recognition Module: Software that converts speech into text.

[0353] 4. Emotion engine: Software that analyzes emotions from the user's voice.

[0354] 5. Translation model: An AI algorithm that translates text and sentiment data into another language.

[0355] 6. Communication method: A method for sending and receiving data between the terminal and the server (such as HTTP protocol).

[0356] Program processing flow

[0357] 1. User voice input:

[0358] The user speaks to the device and performs voice input. For example, they might say, "My delivery is delayed. What's going on?" This includes emotional information such as tone and speed of voice.

[0359] 2. Speech to text transcription:

[0360] The device receives the user's voice input and converts the speech into text using a speech recognition module, in this case "My delivery is late, what's going on?"

[0361] 3. Emotion Recognition:

[0362] The device uses an emotion engine to analyze emotions from the user's voice input and generate emotion data. For example, emotions such as "dissatisfaction" and "frustration" are recognized.

[0363] 4. Sending data to the server:

[0364] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request. Specifically, the device sends the text data "Delivery is delayed, what's going on?" and the emotion data "Unhappy" to the endpoint https: / / example.com / translate.

[0365] 5. Translation processing on the server:

[0366] The server inputs the received text data and emotion data into a translation model and generates a translation result that takes emotion into account. For example, the translation result "The delivery is late, what is happening?" will be translated into "The delivery is late, what is happening? How can we help to resolve this?", which includes a sense of dissatisfaction.

[0367] 6. Returning and displaying translation results:

[0368] The server then sends the translation back to the device, specifically the text "The delivery is late, what is happening? How can we help to resolve this?"

[0369] The terminal displays the translation results received from the server and notifies the user.

[0370] Software and hardware used

[0371] This system uses the following software and hardware:

[0372] Device: Smartphones and tablets are used.

[0373] Speech Recognition Module: SpeechRecognition library.

[0374] Emotion Engine: A pipeline of transformers libraries.

[0375] Server: A server that communicates using the HTTP protocol.

[0376] Translation model: A deep learning-based translation model.

[0377] Specific examples

[0378] An example of a prompt sentence would be "The delivery is late, what's going on?" The system recognizes this utterance and converts the speech into text data: "The delivery is late, what is happening?" The emotion engine recognizes the emotion "dissatisfied" from this utterance. Finally, the translation result, "The delivery is late, what is happening? How can we help to resolve this?", is generated and displayed on the device.

[0379] This system enables smooth and emotional communication with users.

[0380] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0381] Step 1:

[0382] The user makes a voice input to the terminal. For example, the user says, "The delivery is delayed. What's going on?" At this time, the input is recognized by the terminal as a voice signal.

[0383] Step 2:

[0384] The device uses a speech recognition module to convert the user's voice input into text data. The input voice signal is processed by the speech recognition library, and the text data "My delivery is delayed, what's going on?" is generated.

[0385] Step 3:

[0386] The device uses an emotion engine to analyze and generate emotion data from the user's voice input. Elements such as tone, speed, and accent of the voice are analyzed to calculate emotion data such as dissatisfaction or frustration.

[0387] Step 4:

[0388] The device sends the text data and emotion data to the server using an HTTP POST request. Specifically, it sends the generated text data "Delivery is delayed, what's going on?" and emotion data "Unhappy" to the endpoint https: / / example.com / translate.

[0389] Step 5:

[0390] The server receives the HTTP POST request, retrieves the submitted text data and emotion data, and inputs this data into a deep learning-based translation model to generate a translation result that reflects the appropriate emotion. For example, the resulting English translation would be "The delivery is late, what is happening? How can we help to resolve this?"

[0391] Step 6:

[0392] The server returns the generated translation result to the terminal as an HTTP response. The server then sends data including the translation result to the terminal, which then receives the data.

[0393] Step 7:

[0394] The device displays the translation results from the server, and the following text appears on the device screen to the user: "The delivery is late, what is happening? How can we help to resolve this?"

[0395] This process allows users to receive responses that reflect their own emotions in real time, enabling smooth communication.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] [Second embodiment]

[0400] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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).

[0406] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] 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."

[0412] The following describes in detail an embodiment of the present invention. This system provides a real-time translation function, enabling users to communicate smoothly with local people. Specifically, the system converts the user's voice input into text, processes it using a translation model on a server, and returns and displays the translation results to the user.

[0413] Overall structure

[0414] The system mainly consists of the following components:

[0415] 1. User device: The device that receives voice input.

[0416] 2. Server: A central computer that analyzes the audio data and performs the translation.

[0417] 3. Speech Recognition Module: Software that converts speech into text.

[0418] 4. Translation model: An AI algorithm that translates text data into another language.

[0419] 5. Communication method: A method for sending and receiving data between the terminal and the server (such as HTTP protocol).

[0420] Program processing flow

[0421] 1. User voice input

[0422] The user provides voice input by speaking into the device (e.g., "Hello, where is the station?").

[0423] 2. Speech-to-text

[0424] The device receives voice input and converts it into text using a built-in speech recognition module.

[0425] The speech recognition module analyzes the user's voice and converts the results into text data, with high accuracy taking into account the user's pronunciation and accent.

[0426] 3. Sending text data to the server

[0427] The terminal sends the converted text data to the server using an HTTP POST request.

[0428] Example: The device sends the text "Hello, where is the station?" to the endpoint https: / / example.com / translate.

[0429] 4. Translation processing on the server

[0430] The server receives the text data sent from the terminal.

[0431] The server inputs the received data into a translation model, which is based on deep learning and uses a multi-layered neural network.

[0432] The translation model analyzes text and generates appropriate translation results, taking into account context and appropriate expressions based on a vast amount of training data.

[0433] Example: Translating the Japanese phrase "Hello, where is the station?" into English "Hello, where is the station?"

[0434] 5. Returning and displaying translation results

[0435] The server returns the generated translation results to the terminal using an HTTP response.

[0436] The device receives the translation results and displays them to the user in text format, with a notification for the user to review.

[0437] Example: The device displays the translation result "Hello, where is the station?" on the screen for the user to confirm.

[0438] Specific examples

[0439] As an example, we will explain in detail how the system operates when a user says, "Hello, where is the station?"

[0440] User: Says to the device, "Hello, where is the station?"

[0441] Terminal: The speech recognition module converts the speech into text "Hello, where is the station?"

[0442] Terminal: Sends text data to the server via an HTTP POST request.

[0443] Server: Input the received text into the translation model and generate the English translation result "Hello, where is the station?"

[0444] Server: Sends the translation result to the device as an HTTP response.

[0445] Terminal: Display the translation result and notify the user.

[0446] With the above configuration, the system of the present invention provides real-time translation that allows users to communicate effectively with local people. Furthermore, by utilizing deep learning models, it is possible to achieve highly accurate and context-appropriate translation. This is expected to improve user convenience in many situations, including overseas travel.

[0447] The processing flow will be explained below.

[0448] Step 1:

[0449] The user speaks to the terminal and performs voice input. For example, the user might say, "Hello, where is the station?"

[0450] Step 2:

[0451] The terminal receives the user's voice input and activates a voice recognition module. The voice recognition module analyzes the user's speech and converts it into text data. In this case, the text generated is "Hello, where is the station?"

[0452] Step 3:

[0453] The device temporarily stores the converted text data in local memory and then sends it to the server using an HTTP POST request. Specifically, the text data is sent to the endpoint https: / / example.com / translate.

[0454] Step 4:

[0455] The server receives the HTTP POST request and obtains the text data. Specifically, the text data "Hello, where is the station?" arrives at the server.

[0456] Step 5:

[0457] The server inputs the received text data into a deep learning-based translation model, which translates the input Japanese text into English and generates the appropriate English translation result, in this case, "Hello, where is the station?"

[0458] Step 6:

[0459] The server returns the generated translation result to the device using an HTTP response, specifically the translated text "Hello, where is the station?"

[0460] Step 7:

[0461] The device stores the translation results received from the server in its local memory and notifies the user. The device's display shows the text "Hello, where is the station?" in English.

[0462] Step 8:

[0463] The user can check the displayed translation results and communicate with the local person. For example, they can ask the local person a question using the displayed English.

[0464] Example 1

[0465] 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."

[0466] Real-time translation is necessary for users who do not understand the local language to communicate smoothly with local people. However, conventional translation systems have problems such as low speech input accuracy and inaccurate translation results. Furthermore, there is also the issue of operation becoming cumbersome due to the need to use multiple applications.

[0467] 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.

[0468] In this invention, the server includes a means for converting speech input into text with high accuracy, a means for transmitting text data to the server using a communication protocol, and a means for generating translation results using deep learning, thereby enabling users to seamlessly obtain highly accurate translation results from speech input.

[0469] A "user" is an individual or group that uses the system and is the subject that performs voice input.

[0470] "Voice input" refers to the operation of inputting the user's voice into the terminal as digital information.

[0471] A "terminal" is a device used by a user that receives voice input, converts text, communicates, displays translation results, and provides voice notification.

[0472] "Means for converting to text" refers to the process of converting voice data into text data using a voice recognition module.

[0473] A "communication protocol" is a standardized communication method for sending and receiving data between a terminal and a server, and examples include HTTP and HTTPS.

[0474] A "server" is a central computer system that receives text data, processes it using a translation model, and generates and returns the translation results.

[0475] A "voice recognition module" is a software or hardware technology that analyzes input speech and converts it into text.

[0476] A "translation model" is a machine learning algorithm that uses deep learning to translate text data into another language.

[0477] "Deep learning" is a branch of artificial intelligence that uses multi-layered neural networks to analyze data and perform specific tasks automatically.

[0478] A "generative AI model" is an artificial intelligence algorithm that learns from a large amount of data in advance and then generates text based on new data.

[0479] A "translation result" is text data in another language generated by a translation model.

[0480] "Encrypted communication means" refers to technology that encrypts data to prevent eavesdropping or tampering by third parties when sending and receiving data.

[0481] "Voice notification" is a function that notifies the user of the generated translation result by voice.

[0482] The following describes in detail an embodiment of the present invention. This system provides a real-time translation function that enables users to communicate smoothly with local people. Specifically, the system converts user voice input into text, translates the text on the server, and returns the translation result to the user for display.

[0483] The overall system consists of the following components:

[0484] 1. User device: This is the device that receives the voice input, such as a smartphone or a dedicated translation device.

[0485] 2. Server: A central computer that analyzes the audio data and performs the translation.

[0486] 3. Speech recognition module: Software that converts the user's voice into text. Specifically, Google Cloud Speech-to-Text API is used.

[0487] 4. Translation model: An AI algorithm that translates text data into other languages. Examples include the Google Translate API and BERT-based models that use deep learning.

[0488] 5. Communication method: A method for sending and receiving data between the terminal and the server. For example, the HTTP or HTTPS protocol is used.

[0489] The specific system operation is explained below:

[0490] 1. User voice input: The user speaks to the terminal, "Hello, where is the station?" The voice input is received as digital data through the terminal's microphone.

[0491] 2. Speech-to-text conversion: The device sends the received voice data to a voice recognition module (e.g., Google Cloud Speech-to-Text API) and converts it into text data: "Hello, where is the station?"

[0492] 3. Sending text data to the server: The device sends the converted text data to the server via an HTTP POST request, using https: / / example.com / translate as the destination endpoint.

[0493] 4. Translation processing on the server: The server inputs the received text data into a translation model (e.g., Google Translate API) and generates the translation result "Hello, where is the station?" In this process, the server uses a deep learning-based generative AI model.

[0494] 5. Return and display of translation results: The server returns the generated translation results to the terminal as an HTTP response. The terminal displays the translation results on the screen and can also use a voice notification function to notify the user.

[0495] As a concrete example, here is what the system does again when the user says "Hello, where is the station?":

[0496] User: Says to the device, "Hello, where is the station?"

[0497] Terminal: Uses a speech recognition module to convert the speech into text: "Hello, where is the station?"

[0498] Terminal: Sends text data to the server via an HTTP POST request.

[0499] Server: Inputs the received text into the translation model and generates the English translation result "Hello, where is the station?"

[0500] Server: Sends the translation result to the terminal as an HTTP response.

[0501] Terminal: Displays the translation results and notifies the user.

[0502] Example prompt sentence:

[0503] "Please translate the Japanese text "Hello, where is the station?" into English."

[0504] As described above, this system enables users to communicate smoothly even if they do not understand the local language. By utilizing advanced speech recognition and translation technology, it is possible to provide real-time, highly accurate translation results.

[0505] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0506] Step 1:

[0507] The user speaks to the terminal. When the user speaks, "Hello, where is the station?", the microphone converts the voice into a digital signal. The input is the user's voice data, which is then passed on to the next step of processing.

[0508] Step 2:

[0509] The device receives the voice data and sends it to a built-in voice recognition module. The voice recognition module (for example, Google Cloud Speech-to-Text API) converts the voice data into text. Specifically, the voice signal is analyzed and each phoneme is mapped to a character. The output is the text data "Hello, where is the station?"

[0510] Step 3:

[0511] The terminal sends the converted text data to the server via an HTTP POST request. The input is the text data "Hello, where is the station?", which is sent to the server in the form of an HTTP request. The HTTPS protocol is used as the transmission method, and the data is sent to the endpoint https: / / example.com / translate.

[0512] Step 4:

[0513] The server receives the text data sent from the terminal. When the server receives the text data, it passes it on to the next process. The input is the text data "Hello, where is the station?", which is stored in the server's main memory or storage.

[0514] Step 5:

[0515] The server inputs the received text data into a translation model. The input data, "Hello, where is the station?", is passed to a deep learning-based translation model (for example, Google Translate API). Specifically, the translation model analyzes the text data and generates a translation result. The output is the English translation, "Hello, where is the station?"

[0516] Step 6:

[0517] The server returns the generated translation result to the terminal as an HTTP response. The input is the translation result text data "Hello, where is the station?", which is sent to the terminal in HTTP response format. HTTPS is again used as the communication method.

[0518] Step 7:

[0519] The terminal receives the returned translation result. The input is the text data of the translation result sent from the server, "Hello, where is the station?". It receives this and passes it on to the next process.

[0520] Step 8:

[0521] The device displays the received translation results to the user and provides voice notification if necessary. Specifically, the text data is displayed on the screen for the user to review. Furthermore, it is possible to provide voice notification of the translation results using a speech synthesis module. The output is the displayed text and voice notification.

[0522] Through these steps, the system enables users to communicate smoothly with local people in real time through translation, providing highly accurate and context-appropriate translation results.

[0523] (Application example 1)

[0524] 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."

[0525] There is a problem in that it is difficult to communicate smoothly in real time between users who speak different languages. In particular, in situations such as food delivery services, if the customer and delivery person cannot exchange information smoothly, delivery delays and misunderstandings can occur. To solve this problem, a highly accurate, real-time speech translation system is required.

[0526] 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.

[0527] In this invention, the server includes means for receiving a user's voice input and converting it into text, means for transmitting the text data to the server, means for receiving the text data at the server and generating a translation result using a translation model, means for returning the translation result to the terminal, means for displaying the translation result at the terminal, and means for reading out the translation result aloud, thereby enabling users who speak different languages ​​to communicate smoothly in real time.

[0528] "User voice input" refers to voice data uttered by a user, which is input received by the system.

[0529] "Means for converting to text" refers to software or hardware for converting audio data into corresponding text data.

[0530] "Means for sending to the server" refers to a communication means for sending the converted text data to the server via a network.

[0531] "Means for receiving at the server" refers to means for receiving text data transmitted via a network at the server side.

[0532] "Means for generating translation results using a translation model" refers to means that include a process using an AI algorithm or deep learning model to translate received text data into another language.

[0533] The "means for returning the translation result to the terminal" refers to a means for transmitting the generated translation result to the user's terminal via a network.

[0534] "Means for displaying the translation result on the terminal" refers to means for displaying the received translation result in text format on the user's terminal.

[0535] "Means for reading out the translation result aloud" refers to means for reading out the displayed translation result in audio format using text-to-speech conversion technology.

[0536] "Speech recognition module" refers to software or a device for analyzing a user's voice data and converting it into text data.

[0537] A "deep learning model" refers to an AI algorithm that uses multi-layered neural networks to process information and perform advanced pattern recognition and prediction.

[0538] This system provides a real-time translation function to facilitate communication between users who speak different languages. A specific embodiment is described below.

[0539] Overall system configuration

[0540] The system mainly consists of the following components:

[0541] 1. User device: The device that receives voice input, such as a smartphone or tablet.

[0542] 2. Server: A central computer that analyzes the audio data and performs the translation.

[0543] 3. Speech recognition module: Uses "RecognizerIntent", software that converts speech to text.

[0544] 4. Translation model: An AI algorithm for translating text data into another language, using the Google Cloud Translate API.

[0545] 5. Communication method: The HTTP protocol is used to send and receive data between the terminal and the server.

[0546] System processing flow

[0547] 1. Voice input: When the user speaks to the device, the device converts the speech into text. This is done using "RecognizerIntent".

[0548] For example, a user might say, "Hello, I'd like to know the status of my order." This speech is analyzed by "RecognizerIntent" and converted into the text "Hello, I'd like to know the status of my order."

[0549] 2. Sending text data: The converted text data is sent to the server as an HTTP POST request. For example, the device sends the text data "Hello, I'd like to know the status of my order" to the specified endpoint (e.g., https: / / example.com / translate).

[0550] 3. Translation processing on the server: The server inputs the received data into the Google Cloud Translate API for translation. The AI ​​algorithm used as the translation model is based on deep learning and uses a multi-layer neural network to achieve high-precision translation.

[0551] As a concrete example, the Japanese phrase "Hello, I'd like to know the status of my order" is translated into English as "Hello, I'd like to know the status of my order."

[0552] 4. Return and display of translation results: The server returns the translation results to the device as an HTTP response, which the device receives and displays to the user. Additionally, a function has been added to read the translation results aloud.

[0553] For example, the device will display the translation result "Hello, I'd like to know the status of my order" on the screen and read it aloud, allowing the user to check the translation result both in text and audio.

[0554] Example prompt sentences

[0555] Examples of prompts include:

[0556] "A user says, 'Hello, I'd like to know the status of my order.' Please translate this Japanese sentence into English."

[0557] This system enables smooth real-time communication between users who speak different languages, and is particularly useful for food delivery services, where information can be exchanged quickly and accurately between customers and delivery personnel.

[0558] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0559] Step 1:

[0560] The user speaks to the device. Specifically, the user says, "Hello, I'd like to know the status of my order." This voice input is captured through the device's microphone.

[0561] Input: User's voice data

[0562] Output: Raw audio data captured by the microphone

[0563] Step 2:

[0564] The device uses a speech recognition module ("RecognizerIntent") to convert the acquired speech data into text data. During the conversion process, the speech is analyzed, and words are recognized and converted into text.

[0565] Input: Raw audio data

[0566] Data processing: Analysis and recognition of voice data

[0567] Output: Text data (e.g. "Hello, I'd like to know the status of my order.")

[0568] Step 3:

[0569] The terminal sends the converted text data to the server using an HTTP POST request.

[0570] Input: Text data

[0571] Data processing: Generating HTTP requests

[0572] Output: Request sent to server

[0573] Step 4:

[0574] The server receives the text data sent from the terminal, analyzes the HTTP request, and obtains the text data.

[0575] Input: HTTP request

[0576] Data processing: HTTP request analysis

[0577] Output: Received text data

[0578] Step 5:

[0579] The server sends the received text data to the Google Cloud Translate API for translation. The translation model is based on deep learning, and the data is analyzed and translated.

[0580] Input: Received text data

[0581] Data processing: Data analysis and translation using translation models

[0582] Output: Translated text data (e.g., "Hello, I'd like to know the status of my order")

[0583] Step 6:

[0584] The server returns the translation results to the terminal as an HTTP response, which is then generated and sent over the network.

[0585] Input: Translated text data

[0586] Data processing: Generating HTTP responses

[0587] Output: Sending HTTP response to the terminal

[0588] Step 7:

[0589] The device receives the HTTP response from the server, analyzes the received data, and obtains the translation result.

[0590] Input: HTTP response

[0591] Data processing: HTTP response analysis

[0592] Output: Translated text data

[0593] Step 8:

[0594] The device displays the translation results on the screen and notifies the user. The translation results are also read aloud, allowing the user to check the translation results both in text and audio.

[0595] Input: Translated text data

[0596] Data processing: Screen display and voice reading

[0597] Output: On-screen text and spoken notifications

[0598] The above processing steps enable a user to smoothly communicate in real time with others who speak different languages.

[0599] 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.

[0600] The following describes in detail the mode for carrying out the present invention. This system combines a real-time translation function with an emotion engine that recognizes the user's emotions. This allows users to not only communicate smoothly with local people, but also convey their emotions.

[0601] Overall structure

[0602] The system mainly consists of the following components:

[0603] 1. User's device: A device that receives voice input and has a speech recognition module and an emotion engine.

[0604] 2. Server: A central computer that analyzes voice and emotion data and performs translation.

[0605] 3. Speech Recognition Module: Software that converts speech into text.

[0606] 4. Emotion engine: Software that analyzes emotions from the user's voice.

[0607] 5. Translation model: An AI algorithm that translates text and sentiment data into another language.

[0608] 6. Communication method: A method for sending and receiving data between the terminal and the server (such as HTTP protocol).

[0609] Program processing flow

[0610] 1. User voice input

[0611] The user speaks to the device to input voice information. For example, the user might say, "Hello, where is the station?" This includes emotional information such as tone and speed of voice.

[0612] 2. Speech-to-text

[0613] The terminal receives the user's voice input and activates a voice recognition module. The voice recognition module analyzes the user's speech and converts it into text data. In this case, the text generated is "Hello, where is the station?"

[0614] 3. Emotional Recognition

[0615] The device uses an emotion engine to analyze emotions from the user's voice input. The emotion engine analyzes the tone, speed, accent, etc. of the voice to generate emotion data for the user. For example, emotions such as "happiness," "surprise," and "doubt" can be recognized.

[0616] 4. Sending text data and emotion data to the server

[0617] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request. Specifically, the text data and emotion data are sent to the endpoint https: / / example.com / translate.

[0618] 5. Translation processing on the server

[0619] The server receives the HTTP POST request and obtains the text data and emotion data. Specifically, the text data "Hello, where is the station?" and the emotion data "joy" arrive at the server.

[0620] The server inputs the received text data and emotion data into a deep learning-based translation model, which generates an English translation result taking into account the input Japanese text and corresponding emotion data.

[0621] The translation model takes into account emotional data and adds appropriate expressions depending on the context. For example, the translation "Hello, where is the station?" is given an emotional value and translated as "Hi, could you tell me where the station is, please?"

[0622] 6. Returning and displaying translation results

[0623] The server returns the generated translation result to the device using an HTTP response, specifically the translated text "Hi, could you tell me where the station is, please?"

[0624] The device stores the translation results received from the server in its local memory and notifies the user. The device's display shows the emotional English translation, "Hi, could you tell me where the station is, please?"

[0625] Specific examples

[0626] As an example, we will explain in detail how the system operates when a user says, "Hello, where is the station?"

[0627] User: Says to the device, "Hello, where is the station?"

[0628] Terminal: The speech recognition module converts the speech into text "Hello, where is the station?"

[0629] Device: The emotion engine recognizes the emotion of "joy" from voice.

[0630] Device: Send text and emotion data to the server via an HTTP POST request.

[0631] Server: The received text and emotion data are input into the translation model, and the emotion-sensitive English translation result "Hi, could you tell me where the station is, please?" is generated.

[0632] Server: Sends the translation result to the device as an HTTP response.

[0633] Terminal: Display the translation result and notify the user.

[0634] With the above configuration, the system of the present invention provides real-time translation that allows users to communicate effectively and emotionally with local people. Furthermore, by utilizing an emotion engine, highly accurate translation that incorporates emotion becomes possible. This is expected to improve the user's communication experience in a variety of situations.

[0635] The processing flow will be explained below.

[0636] Step 1:

[0637] The user speaks to the terminal and performs voice input. For example, the user might say, "Hello, where is the station?"

[0638] Step 2:

[0639] The device receives the user's voice input and activates a voice recognition module. The voice recognition module analyzes the user's speech and converts it into text data. In this case, the text generated is "Hello, where is the station?"

[0640] Step 3:

[0641] The device uses an emotion engine to analyze emotions from the user's voice input. The emotion engine analyzes the tone, rate, and voice pattern of the voice to generate emotion data for the user. In this case, the emotion engine recognizes the emotion of "happiness."

[0642] Step 4:

[0643] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request to the endpoint https: / / example.com / translate.

[0644] Step 5:

[0645] The server receives the HTTP POST request and obtains the text data and emotion data. Specifically, the text data "Hello, where is the station?" and the emotion data "joy" arrive at the server.

[0646] Step 6:

[0647] The server inputs the received text data and emotion data into a deep learning-based translation model. This model takes into account the input Japanese text and corresponding emotion data and generates an English translation result. In this case, the translation "Hello, where is the station?" is annotated with emotion and generated as "Hi, could you tell me where the station is, please?"

[0648] Step 7:

[0649] The server returns the generated translation result to the device using an HTTP response, specifically the translated text "Hi, could you tell me where the station is, please?"

[0650] Step 8:

[0651] The device receives the translation results from the server, stores them in its local memory, and notifies the user. The device displays the emotional English translation, "Hi, could you tell me where the station is, please?"

[0652] Step 9:

[0653] The user can check the displayed translation results and communicate with the local person, for example, by asking a question to the local person using the displayed English.

[0654] Example 2

[0655] 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."

[0656] Conventional real-time translation systems convert a user's speech into text and translate it into different languages, but they do not take the user's emotions into account when translating. As a result, the user's intentions and emotions are not accurately conveyed, resulting in a decline in the quality of communication. In particular, in situations where emotions play an important role, translations that ignore emotions can lead to misunderstandings and inappropriate expressions.

[0657] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0658] In this invention, the server includes a means for converting speech input into text, a means for recognizing and acquiring user emotion data, and a means for generating translation results using a generative model, thereby enabling highly accurate translation that takes user emotion into consideration.

[0659] "Voice input" refers to voice data spoken by a user.

[0660] "Means for converting to text" refers to a process or device that converts audio data into text data.

[0661] "Emotion data" refers to information about emotions extracted from the user's voice.

[0662] "Means for transmitting to a server" refers to the mechanisms and protocols that allow a terminal to transmit data to a server via the Internet or other communication means.

[0663] A "generative model" is an algorithm or computer program that generates a specific output based on given input data, particularly one that uses artificial intelligence techniques such as deep learning.

[0664] "Means for generating a translation result" refers to a process or system that translates received text data and emotion data into another language and generates the translation result.

[0665] "Display means" refers to devices or software that visually notify the user of the translation results.

[0666] The following describes in detail an embodiment of the present invention. This system combines a real-time translation function with an emotion engine that recognizes the user's emotions. This system allows users to not only communicate smoothly with local people, but also convey their emotions.

[0667] Overall structure

[0668] The system mainly consists of the following components:

[0669] 1. User's device: This is the device that receives voice input and runs the voice recognition module and emotion engine. For example, a smartphone or tablet is used here, and a dedicated application is installed.

[0670] 2. Server: This is the central computer that analyzes the voice and emotion data and performs the translation. A cloud-based server is ideal and has the capacity to process large amounts of data.

[0671] 3. Speech Recognition Module: Software that converts speech into text. Specifically, Google Speech-to-Text API is used.

[0672] 4. Emotion engine: Software that analyzes emotions from the user's voice. For example, Azure Cognitive Services' Emotion API falls into this category.

[0673] 5. Generative models: AI algorithms that translate text and sentiment data into another language. Deep learning-based models such as Google Translate API and DeepL API are used.

[0674] 6. Communication method: A method for sending and receiving data between the terminal and the server. HTTP protocol and REST API are commonly used.

[0675] Example of operation

[0676] Here is a concrete example of how this system works:

[0677] 1. User voice input:

[0678] The user speaks to the terminal, "Hello, where is the station?" The speech includes emotional (e.g., joy) tone and rate.

[0679] 2. Speech to text transcription:

[0680] The device activates a speech recognition module (Google Speech-to-Text API) to convert the speech into text data, resulting in the text "Hello, where is the station?"

[0681] 3. Emotion Recognition:

[0682] The device uses an emotion engine (Azure Cognitive Services' Emotion API) to analyze emotion data from the voice and generate emotion data for "joy" in this case.

[0683] 4. Sending data to the server:

[0684] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request, with an endpoint such as https: / / example.com / translate.

[0685] 5. Translation processing on the server:

[0686] The server receives the text data and emotion data and inputs them into a generative model (Google Translate API or DeepL API). Taking into account the text "Hello, where is the station?" and the emotion "joy," the server generates the English translation result "Hi, could you tell me where the station is, please?"

[0687] 6. Returning and displaying translation results:

[0688] The server sends the translation results back to the device using an HTTP response, which the device receives and displays on its screen.

[0689] In this way, real-time translation based on the user's voice and emotions is realized. By using this system, users can obtain highly accurate translation results that include emotions, enabling smooth communication with local people.

[0690] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0691] Step 1:

[0692] The user inputs voice into the terminal. For example, they might say, "Hello, where is the station?" This voice data also contains emotional information such as tone and speed. The input is the user's voice, and the output is sent to the terminal as voice data.

[0693] Step 2:

[0694] The device receives voice input and launches a voice recognition module (e.g., Google Speech-to-Text API). The voice recognition module analyzes the voice data and generates text data such as "Hello, where is the station?". Specifically, it preprocesses the voice signal, extracts features, and then converts the signal to text. The input is voice data, and the output is text data.

[0695] Step 3:

[0696] The device calls an emotion engine (e.g., Azure Cognitive Services' Emotion API) at the same time as receiving the text data. The emotion engine analyzes the user's voice data and generates emotion data. In this case, the emotion data obtained is "joy." Specific operations include processes that analyze the tone, speed, and accent of the voice. The input is voice data, and the output is emotion data.

[0697] Step 4:

[0698] The device sends the generated text data and emotion data to the server using an HTTP POST request. Specific operations include constructing the HTTP request header and body and sending the data to the endpoint https: / / example.com / translate. The input is text data and emotion data, and the output is an HTTP request.

[0699] Step 5:

[0700] The server receives an HTTP POST request and retrieves text data and emotion data. Specifically, it analyzes the HTTP request and extracts the text data "Hello, where is the station?" and the emotion data "Joy." The input is the HTTP request, and the output is the analyzed text data and emotion data.

[0701] Step 6:

[0702] The server inputs text data and emotion data into a generative model (e.g., Google Translate API or DeepL API). The generative model uses this data to generate the translation result, "Hi, could you tell me where the station is, please?" Specifically, the deep learning-based model processes the data through multiple layers to generate the final translation result. The input is text data and emotion data, and the output is the translation result.

[0703] Step 7:

[0704] The server returns the generated translation results to the terminal in the form of an HTTP response. Specific operations include setting the translation results in the header and body of the HTTP response and sending it to the terminal. The input is the translation results, and the output is the HTTP response.

[0705] Step 8:

[0706] The terminal receives the HTTP response returned from the server and obtains the translation result, "Hi, could you tell me where the station is, please?". The translation result is displayed on the screen and notified to the user. Specifically, it analyzes the HTTP response and updates the user interface to display the result. The input is the HTTP response, and the output is the displayed translation result.

[0707] (Application example 2)

[0708] 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."

[0709] When a user makes an inquiry about a food delivery service, conventional systems are unable to respond in a way that takes into account the user's emotions, making it difficult to respond in a way that appropriately reflects the user's emotions.Furthermore, the inability to recognize emotions in real time and provide an appropriate response results in a poor user experience.

[0710] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a user's voice input and converting it into text, means for transmitting the text data and emotion data to the server, and means for receiving the text data and emotion data in the server and generating a translation result using a translation model. This makes it possible to provide a highly accurate translation result that reflects the user's emotion.

[0711] "User's voice input" refers to a voice signal emitted by a user into a terminal.

[0712] "Text data" refers to character data obtained by converting a voice signal into text by a voice recognition module.

[0713] "Emotion data" refers to data that indicates the user's emotional state as analyzed by the emotion engine.

[0714] "Server" refers to a central computer that receives speech input, text data, and emotion data, and uses a translation model to generate a translation result.

[0715] "Translation model" refers to an algorithm that uses AI technologies such as deep learning to generate translation results based on input text data and emotional data.

[0716] "Terminal" refers to a device that receives a user's voice input and has a voice recognition module and an emotion engine.

[0717] "Speech recognition module" refers to software that converts a user's voice input into text data.

[0718] "Emotion engine" refers to software that analyzes emotions from the user's voice.

[0719] "Translation result" refers to the output text in another language that a translation model generates, taking into account the input text and sentiment.

[0720] "HTTP POST request" refers to one of the communication protocols used to transfer text data and emotion data from a terminal to a server.

[0721] "HTTP response" refers to one of the communication protocols used to return translation results from the server to the terminal.

[0722] The following describes in detail an embodiment of the present invention. The present invention is a system for recognizing a user's emotions and providing appropriate responses in a food delivery service. This system converts a user's voice input into text data and emotion data in real time, transmits the data to a server, and generates a response using a translation model.

[0723] Overall structure

[0724] The system of the present invention mainly consists of the following components:

[0725] 1. Terminal: A device that receives voice input and has a speech recognition module and an emotion engine.

[0726] 2. Server: A central computer that analyzes voice and emotion data and performs translation.

[0727] 3. Speech Recognition Module: Software that converts speech into text.

[0728] 4. Emotion engine: Software that analyzes emotions from the user's voice.

[0729] 5. Translation model: An AI algorithm that translates text and sentiment data into another language.

[0730] 6. Communication method: A method for sending and receiving data between the terminal and the server (such as HTTP protocol).

[0731] Program processing flow

[0732] 1. User voice input:

[0733] The user speaks to the device and performs voice input. For example, they might say, "My delivery is delayed. What's going on?" This includes emotional information such as tone and speed of voice.

[0734] 2. Speech to text transcription:

[0735] The device receives the user's voice input and converts the speech into text using a speech recognition module, in this case "My delivery is late, what's going on?"

[0736] 3. Emotion Recognition:

[0737] The device uses an emotion engine to analyze emotions from the user's voice input and generate emotion data. For example, emotions such as "dissatisfaction" and "frustration" are recognized.

[0738] 4. Sending data to the server:

[0739] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request. Specifically, the device sends the text data "Delivery is delayed, what's going on?" and the emotion data "Unhappy" to the endpoint https: / / example.com / translate.

[0740] 5. Translation processing on the server:

[0741] The server inputs the received text data and emotion data into a translation model and generates a translation result that takes emotion into account. For example, the translation result "The delivery is late, what is happening?" will be translated into "The delivery is late, what is happening? How can we help to resolve this?", which includes a sense of dissatisfaction.

[0742] 6. Returning and displaying translation results:

[0743] The server then sends the translation back to the device, specifically the text "The delivery is late, what is happening? How can we help to resolve this?"

[0744] The terminal displays the translation results received from the server and notifies the user.

[0745] Software and hardware used

[0746] This system uses the following software and hardware:

[0747] Device: Smartphones and tablets are used.

[0748] Speech Recognition Module: SpeechRecognition library.

[0749] Emotion Engine: A pipeline of transformers libraries.

[0750] Server: A server that communicates using the HTTP protocol.

[0751] Translation model: A deep learning-based translation model.

[0752] Specific examples

[0753] An example of a prompt sentence would be "The delivery is late, what's going on?" The system recognizes this utterance and converts the speech into text data: "The delivery is late, what is happening?" The emotion engine recognizes the emotion "dissatisfied" from this utterance. Finally, the translation result, "The delivery is late, what is happening? How can we help to resolve this?", is generated and displayed on the device.

[0754] This system enables smooth and emotional communication with users.

[0755] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0756] Step 1:

[0757] The user makes a voice input to the terminal. For example, the user says, "The delivery is delayed. What's going on?" At this time, the input is recognized by the terminal as a voice signal.

[0758] Step 2:

[0759] The device uses a speech recognition module to convert the user's voice input into text data. The input voice signal is processed by the speech recognition library, and the text data "My delivery is delayed, what's going on?" is generated.

[0760] Step 3:

[0761] The device uses an emotion engine to analyze and generate emotion data from the user's voice input. Elements such as tone, speed, and accent of the voice are analyzed to calculate emotion data such as dissatisfaction or frustration.

[0762] Step 4:

[0763] The device sends the text data and emotion data to the server using an HTTP POST request. Specifically, it sends the generated text data "Delivery is delayed, what's going on?" and emotion data "Unhappy" to the endpoint https: / / example.com / translate.

[0764] Step 5:

[0765] The server receives the HTTP POST request, retrieves the submitted text data and emotion data, and inputs this data into a deep learning-based translation model to generate a translation result that reflects the appropriate emotion. For example, the resulting English translation would be "The delivery is late, what is happening? How can we help to resolve this?"

[0766] Step 6:

[0767] The server returns the generated translation result to the terminal as an HTTP response. The server then sends data including the translation result to the terminal, which then receives the data.

[0768] Step 7:

[0769] The device displays the translation results from the server, and the following text appears on the device screen to the user: "The delivery is late, what is happening? How can we help to resolve this?"

[0770] This process allows users to receive responses that reflect their own emotions in real time, enabling smooth communication.

[0771] 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.

[0772] 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.

[0773] 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.

[0774] [Third embodiment]

[0775] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0776] 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.

[0777] 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).

[0778] 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.

[0779] 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.

[0780] 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).

[0781] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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."

[0787] The following describes in detail an embodiment of the present invention. This system provides a real-time translation function, enabling users to communicate smoothly with local people. Specifically, the system converts the user's voice input into text, processes it using a translation model on a server, and returns and displays the translation results to the user.

[0788] Overall structure

[0789] The system mainly consists of the following components:

[0790] 1. User device: The device that receives voice input.

[0791] 2. Server: A central computer that analyzes the audio data and performs the translation.

[0792] 3. Speech Recognition Module: Software that converts speech into text.

[0793] 4. Translation model: An AI algorithm that translates text data into another language.

[0794] 5. Communication method: A method for sending and receiving data between the terminal and the server (such as HTTP protocol).

[0795] Program processing flow

[0796] 1. User voice input

[0797] The user provides voice input by speaking into the device (e.g., "Hello, where is the station?").

[0798] 2. Speech-to-text

[0799] The device receives voice input and converts it into text using a built-in speech recognition module.

[0800] The speech recognition module analyzes the user's voice and converts the results into text data, with high accuracy taking into account the user's pronunciation and accent.

[0801] 3. Sending text data to the server

[0802] The terminal sends the converted text data to the server using an HTTP POST request.

[0803] Example: The device sends the text "Hello, where is the station?" to the endpoint https: / / example.com / translate.

[0804] 4. Translation processing on the server

[0805] The server receives the text data sent from the terminal.

[0806] The server inputs the received data into a translation model, which is based on deep learning and uses a multi-layered neural network.

[0807] The translation model analyzes text and generates appropriate translation results, taking into account context and appropriate expressions based on a vast amount of training data.

[0808] Example: Translating the Japanese phrase "Hello, where is the station?" into English "Hello, where is the station?"

[0809] 5. Returning and displaying translation results

[0810] The server returns the generated translation results to the terminal using an HTTP response.

[0811] The device receives the translation results and displays them to the user in text format, with a notification for the user to review.

[0812] Example: The device displays the translation result "Hello, where is the station?" on the screen for the user to confirm.

[0813] Specific examples

[0814] As an example, we will explain in detail how the system operates when a user says, "Hello, where is the station?"

[0815] User: Says to the device, "Hello, where is the station?"

[0816] Terminal: The speech recognition module converts the speech into text "Hello, where is the station?"

[0817] Terminal: Sends text data to the server via an HTTP POST request.

[0818] Server: Input the received text into the translation model and generate the English translation result "Hello, where is the station?"

[0819] Server: Sends the translation result to the device as an HTTP response.

[0820] Terminal: Display the translation result and notify the user.

[0821] With the above configuration, the system of the present invention provides real-time translation that allows users to communicate effectively with local people. Furthermore, by utilizing deep learning models, it is possible to achieve highly accurate and context-appropriate translation. This is expected to improve user convenience in many situations, including overseas travel.

[0822] The processing flow will be explained below.

[0823] Step 1:

[0824] The user speaks to the terminal and performs voice input. For example, the user might say, "Hello, where is the station?"

[0825] Step 2:

[0826] The terminal receives the user's voice input and activates a voice recognition module. The voice recognition module analyzes the user's speech and converts it into text data. In this case, the text generated is "Hello, where is the station?"

[0827] Step 3:

[0828] The device temporarily stores the converted text data in local memory and then sends it to the server using an HTTP POST request. Specifically, the text data is sent to the endpoint https: / / example.com / translate.

[0829] Step 4:

[0830] The server receives the HTTP POST request and obtains the text data. Specifically, the text data "Hello, where is the station?" arrives at the server.

[0831] Step 5:

[0832] The server inputs the received text data into a deep learning-based translation model, which translates the input Japanese text into English and generates the appropriate English translation result, in this case, "Hello, where is the station?"

[0833] Step 6:

[0834] The server returns the generated translation result to the device using an HTTP response, specifically the translated text "Hello, where is the station?"

[0835] Step 7:

[0836] The device stores the translation results received from the server in its local memory and notifies the user. The device's display shows the text "Hello, where is the station?" in English.

[0837] Step 8:

[0838] The user can check the displayed translation results and communicate with the local person. For example, they can ask the local person a question using the displayed English.

[0839] Example 1

[0840] 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."

[0841] Real-time translation is necessary for users who do not understand the local language to communicate smoothly with local people. However, conventional translation systems have problems such as low speech input accuracy and inaccurate translation results. Furthermore, there is also the issue of operation becoming cumbersome due to the need to use multiple applications.

[0842] 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.

[0843] In this invention, the server includes a means for converting speech input into text with high accuracy, a means for transmitting text data to the server using a communication protocol, and a means for generating translation results using deep learning, thereby enabling users to seamlessly obtain highly accurate translation results from speech input.

[0844] A "user" is an individual or group that uses the system and is the subject that performs voice input.

[0845] "Voice input" refers to the operation of inputting the user's voice into the terminal as digital information.

[0846] A "terminal" is a device used by a user that receives voice input, converts text, communicates, displays translation results, and provides voice notification.

[0847] "Means for converting to text" refers to the process of converting voice data into text data using a voice recognition module.

[0848] A "communication protocol" is a standardized communication method for sending and receiving data between a terminal and a server, and examples include HTTP and HTTPS.

[0849] A "server" is a central computer system that receives text data, processes it using a translation model, and generates and returns the translation results.

[0850] A "voice recognition module" is a software or hardware technology that analyzes input speech and converts it into text.

[0851] A "translation model" is a machine learning algorithm that uses deep learning to translate text data into another language.

[0852] "Deep learning" is a branch of artificial intelligence that uses multi-layered neural networks to analyze data and perform specific tasks automatically.

[0853] A "generative AI model" is an artificial intelligence algorithm that learns from a large amount of data in advance and then generates text based on new data.

[0854] A "translation result" is text data in another language generated by a translation model.

[0855] "Encrypted communication means" refers to technology that encrypts data to prevent eavesdropping or tampering by third parties when sending and receiving data.

[0856] "Voice notification" is a function that notifies the user of the generated translation result by voice.

[0857] The following describes in detail an embodiment of the present invention. This system provides a real-time translation function that enables users to communicate smoothly with local people. Specifically, the system converts user voice input into text, translates the text on the server, and returns the translation result to the user for display.

[0858] The overall system consists of the following components:

[0859] 1. User device: This is the device that receives the voice input, such as a smartphone or a dedicated translation device.

[0860] 2. Server: A central computer that analyzes the audio data and performs the translation.

[0861] 3. Speech recognition module: Software that converts the user's voice into text. Specifically, Google Cloud Speech-to-Text API is used.

[0862] 4. Translation model: An AI algorithm that translates text data into other languages. Examples include the Google Translate API and BERT-based models that use deep learning.

[0863] 5. Communication method: A method for sending and receiving data between the terminal and the server. For example, the HTTP or HTTPS protocol is used.

[0864] The specific system operation is explained below:

[0865] 1. User voice input: The user speaks to the terminal, "Hello, where is the station?" The voice input is received as digital data through the terminal's microphone.

[0866] 2. Speech-to-text conversion: The device sends the received voice data to a voice recognition module (e.g., Google Cloud Speech-to-Text API) and converts it into text data: "Hello, where is the station?"

[0867] 3. Sending text data to the server: The device sends the converted text data to the server via an HTTP POST request, using https: / / example.com / translate as the destination endpoint.

[0868] 4. Translation processing on the server: The server inputs the received text data into a translation model (e.g., Google Translate API) and generates the translation result "Hello, where is the station?" In this process, the server uses a deep learning-based generative AI model.

[0869] 5. Return and display of translation results: The server returns the generated translation results to the terminal as an HTTP response. The terminal displays the translation results on the screen and can also use a voice notification function to notify the user.

[0870] As a concrete example, here is what the system does again when the user says "Hello, where is the station?":

[0871] User: Says to the device, "Hello, where is the station?"

[0872] Terminal: Uses a speech recognition module to convert the speech into text: "Hello, where is the station?"

[0873] Terminal: Sends text data to the server via an HTTP POST request.

[0874] Server: Inputs the received text into the translation model and generates the English translation result "Hello, where is the station?"

[0875] Server: Sends the translation result to the terminal as an HTTP response.

[0876] Terminal: Displays the translation results and notifies the user.

[0877] Example prompt sentence:

[0878] "Please translate the Japanese text "Hello, where is the station?" into English."

[0879] As described above, this system enables users to communicate smoothly even if they do not understand the local language. By utilizing advanced speech recognition and translation technology, it is possible to provide real-time, highly accurate translation results.

[0880] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0881] Step 1:

[0882] The user speaks to the terminal. When the user speaks, "Hello, where is the station?", the microphone converts the voice into a digital signal. The input is the user's voice data, which is then passed on to the next step of processing.

[0883] Step 2:

[0884] The device receives the voice data and sends it to a built-in voice recognition module. The voice recognition module (for example, Google Cloud Speech-to-Text API) converts the voice data into text. Specifically, the voice signal is analyzed and each phoneme is mapped to a character. The output is the text data "Hello, where is the station?"

[0885] Step 3:

[0886] The terminal sends the converted text data to the server via an HTTP POST request. The input is the text data "Hello, where is the station?", which is sent to the server in the form of an HTTP request. The HTTPS protocol is used as the transmission method, and the data is sent to the endpoint https: / / example.com / translate.

[0887] Step 4:

[0888] The server receives the text data sent from the terminal. When the server receives the text data, it passes it on to the next process. The input is the text data "Hello, where is the station?", which is stored in the server's main memory or storage.

[0889] Step 5:

[0890] The server inputs the received text data into a translation model. The input data, "Hello, where is the station?", is passed to a deep learning-based translation model (for example, Google Translate API). Specifically, the translation model analyzes the text data and generates a translation result. The output is the English translation, "Hello, where is the station?"

[0891] Step 6:

[0892] The server returns the generated translation result to the terminal as an HTTP response. The input is the translation result text data "Hello, where is the station?", which is sent to the terminal in HTTP response format. HTTPS is again used as the communication method.

[0893] Step 7:

[0894] The terminal receives the returned translation result. The input is the text data of the translation result sent from the server, "Hello, where is the station?". It receives this and passes it on to the next process.

[0895] Step 8:

[0896] The device displays the received translation results to the user and provides voice notification if necessary. Specifically, the text data is displayed on the screen for the user to review. Furthermore, it is possible to provide voice notification of the translation results using a speech synthesis module. The output is the displayed text and voice notification.

[0897] Through these steps, the system enables users to communicate smoothly with local people in real time through translation, providing highly accurate and context-appropriate translation results.

[0898] (Application example 1)

[0899] 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."

[0900] There is a problem in that it is difficult to communicate smoothly in real time between users who speak different languages. In particular, in situations such as food delivery services, if the customer and delivery person cannot exchange information smoothly, delivery delays and misunderstandings can occur. To solve this problem, a highly accurate, real-time speech translation system is required.

[0901] 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.

[0902] In this invention, the server includes means for receiving a user's voice input and converting it into text, means for transmitting the text data to the server, means for receiving the text data at the server and generating a translation result using a translation model, means for returning the translation result to the terminal, means for displaying the translation result at the terminal, and means for reading out the translation result aloud, thereby enabling users who speak different languages ​​to communicate smoothly in real time.

[0903] "User voice input" refers to voice data uttered by a user, which is input received by the system.

[0904] "Means for converting to text" refers to software or hardware for converting audio data into corresponding text data.

[0905] "Means for sending to the server" refers to a communication means for sending the converted text data to the server via a network.

[0906] "Means for receiving at the server" refers to means for receiving text data transmitted via a network at the server side.

[0907] "Means for generating translation results using a translation model" refers to means that include a process using an AI algorithm or deep learning model to translate received text data into another language.

[0908] The "means for returning the translation result to the terminal" refers to a means for transmitting the generated translation result to the user's terminal via a network.

[0909] "Means for displaying the translation result on the terminal" refers to means for displaying the received translation result in text format on the user's terminal.

[0910] "Means for reading out the translation result aloud" refers to means for reading out the displayed translation result in audio format using text-to-speech conversion technology.

[0911] "Speech recognition module" refers to software or a device for analyzing a user's voice data and converting it into text data.

[0912] A "deep learning model" refers to an AI algorithm that uses multi-layered neural networks to process information and perform advanced pattern recognition and prediction.

[0913] This system provides a real-time translation function to facilitate communication between users who speak different languages. A specific embodiment is described below.

[0914] Overall system configuration

[0915] The system mainly consists of the following components:

[0916] 1. User device: The device that receives voice input, such as a smartphone or tablet.

[0917] 2. Server: A central computer that analyzes the audio data and performs the translation.

[0918] 3. Speech recognition module: Uses "RecognizerIntent", software that converts speech to text.

[0919] 4. Translation model: An AI algorithm for translating text data into another language, using the Google Cloud Translate API.

[0920] 5. Communication method: The HTTP protocol is used to send and receive data between the terminal and the server.

[0921] System processing flow

[0922] 1. Voice input: When the user speaks to the device, the device converts the speech into text. This is done using "RecognizerIntent".

[0923] For example, a user might say, "Hello, I'd like to know the status of my order." This speech is analyzed by "RecognizerIntent" and converted into the text "Hello, I'd like to know the status of my order."

[0924] 2. Sending text data: The converted text data is sent to the server as an HTTP POST request. For example, the device sends the text data "Hello, I'd like to know the status of my order" to the specified endpoint (e.g., https: / / example.com / translate).

[0925] 3. Translation processing on the server: The server inputs the received data into the Google Cloud Translate API for translation. The AI ​​algorithm used as the translation model is based on deep learning and uses a multi-layer neural network to achieve high-precision translation.

[0926] As a concrete example, the Japanese phrase "Hello, I'd like to know the status of my order" is translated into English as "Hello, I'd like to know the status of my order."

[0927] 4. Return and display of translation results: The server returns the translation results to the device as an HTTP response, which the device receives and displays to the user. Additionally, a function has been added to read the translation results aloud.

[0928] For example, the device will display the translation result "Hello, I'd like to know the status of my order" on the screen and read it aloud, allowing the user to check the translation result both in text and audio.

[0929] Example prompt sentences

[0930] Examples of prompts include:

[0931] "A user says, 'Hello, I'd like to know the status of my order.' Please translate this Japanese sentence into English."

[0932] This system enables smooth real-time communication between users who speak different languages, and is particularly useful for food delivery services, where information can be exchanged quickly and accurately between customers and delivery personnel.

[0933] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0934] Step 1:

[0935] The user speaks to the device. Specifically, the user says, "Hello, I'd like to know the status of my order." This voice input is captured through the device's microphone.

[0936] Input: User's voice data

[0937] Output: Raw audio data captured by the microphone

[0938] Step 2:

[0939] The device uses a speech recognition module ("RecognizerIntent") to convert the acquired speech data into text data. During the conversion process, the speech is analyzed, and words are recognized and converted into text.

[0940] Input: Raw audio data

[0941] Data processing: Analysis and recognition of voice data

[0942] Output: Text data (e.g. "Hello, I'd like to know the status of my order.")

[0943] Step 3:

[0944] The terminal sends the converted text data to the server using an HTTP POST request.

[0945] Input: Text data

[0946] Data processing: Generating HTTP requests

[0947] Output: Request sent to server

[0948] Step 4:

[0949] The server receives the text data sent from the terminal, analyzes the HTTP request, and obtains the text data.

[0950] Input: HTTP request

[0951] Data processing: HTTP request analysis

[0952] Output: Received text data

[0953] Step 5:

[0954] The server sends the received text data to the Google Cloud Translate API for translation. The translation model is based on deep learning, and the data is analyzed and translated.

[0955] Input: Received text data

[0956] Data processing: Data analysis and translation using translation models

[0957] Output: Translated text data (e.g., "Hello, I'd like to know the status of my order")

[0958] Step 6:

[0959] The server returns the translation results to the terminal as an HTTP response, which is then generated and sent over the network.

[0960] Input: Translated text data

[0961] Data processing: Generating HTTP responses

[0962] Output: Sending HTTP response to the terminal

[0963] Step 7:

[0964] The device receives the HTTP response from the server, analyzes the received data, and obtains the translation result.

[0965] Input: HTTP response

[0966] Data processing: HTTP response analysis

[0967] Output: Translated text data

[0968] Step 8:

[0969] The device displays the translation results on the screen and notifies the user. The translation results are also read aloud, allowing the user to check the translation results both in text and audio.

[0970] Input: Translated text data

[0971] Data processing: Screen display and voice reading

[0972] Output: On-screen text and spoken notifications

[0973] The above processing steps enable a user to smoothly communicate in real time with others who speak different languages.

[0974] 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.

[0975] The following describes in detail the mode for carrying out the present invention. This system combines a real-time translation function with an emotion engine that recognizes the user's emotions. This allows users to not only communicate smoothly with local people, but also convey their emotions.

[0976] Overall structure

[0977] The system mainly consists of the following components:

[0978] 1. User's device: A device that receives voice input and has a speech recognition module and an emotion engine.

[0979] 2. Server: A central computer that analyzes voice and emotion data and performs translation.

[0980] 3. Speech Recognition Module: Software that converts speech into text.

[0981] 4. Emotion engine: Software that analyzes emotions from the user's voice.

[0982] 5. Translation model: An AI algorithm that translates text and sentiment data into another language.

[0983] 6. Communication method: A method for sending and receiving data between the terminal and the server (such as HTTP protocol).

[0984] Program processing flow

[0985] 1. User voice input

[0986] The user speaks to the device to input voice information. For example, the user might say, "Hello, where is the station?" This includes emotional information such as tone and speed of voice.

[0987] 2. Speech-to-text

[0988] The terminal receives the user's voice input and activates a voice recognition module. The voice recognition module analyzes the user's speech and converts it into text data. In this case, the text generated is "Hello, where is the station?"

[0989] 3. Emotional Recognition

[0990] The device uses an emotion engine to analyze emotions from the user's voice input. The emotion engine analyzes the tone, speed, accent, etc. of the voice to generate emotion data for the user. For example, emotions such as "happiness," "surprise," and "doubt" can be recognized.

[0991] 4. Sending text data and emotion data to the server

[0992] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request. Specifically, the text data and emotion data are sent to the endpoint https: / / example.com / translate.

[0993] 5. Translation processing on the server

[0994] The server receives the HTTP POST request and obtains the text data and emotion data. Specifically, the text data "Hello, where is the station?" and the emotion data "joy" arrive at the server.

[0995] The server inputs the received text data and emotion data into a deep learning-based translation model, which generates an English translation result taking into account the input Japanese text and corresponding emotion data.

[0996] The translation model takes into account emotional data and adds appropriate expressions depending on the context. For example, the translation "Hello, where is the station?" is given an emotional value and translated as "Hi, could you tell me where the station is, please?"

[0997] 6. Returning and displaying translation results

[0998] The server returns the generated translation result to the device using an HTTP response, specifically the translated text "Hi, could you tell me where the station is, please?"

[0999] The device stores the translation results received from the server in its local memory and notifies the user. The device's display shows the emotional English translation, "Hi, could you tell me where the station is, please?"

[1000] Specific examples

[1001] As an example, we will explain in detail how the system operates when a user says, "Hello, where is the station?"

[1002] User: Says to the device, "Hello, where is the station?"

[1003] Terminal: The speech recognition module converts the speech into text "Hello, where is the station?"

[1004] Device: The emotion engine recognizes the emotion of "joy" from voice.

[1005] Device: Send text and emotion data to the server via an HTTP POST request.

[1006] Server: The received text and emotion data are input into the translation model, and the emotion-sensitive English translation result "Hi, could you tell me where the station is, please?" is generated.

[1007] Server: Sends the translation result to the device as an HTTP response.

[1008] Terminal: Display the translation result and notify the user.

[1009] With the above configuration, the system of the present invention provides real-time translation that allows users to communicate effectively and emotionally with local people. Furthermore, by utilizing an emotion engine, highly accurate translation that incorporates emotion becomes possible. This is expected to improve the user's communication experience in a variety of situations.

[1010] The processing flow will be explained below.

[1011] Step 1:

[1012] The user speaks to the terminal and performs voice input. For example, the user might say, "Hello, where is the station?"

[1013] Step 2:

[1014] The device receives the user's voice input and activates a voice recognition module. The voice recognition module analyzes the user's speech and converts it into text data. In this case, the text generated is "Hello, where is the station?"

[1015] Step 3:

[1016] The device uses an emotion engine to analyze emotions from the user's voice input. The emotion engine analyzes the tone, rate, and voice pattern of the voice to generate emotion data for the user. In this case, the emotion engine recognizes the emotion of "happiness."

[1017] Step 4:

[1018] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request to the endpoint https: / / example.com / translate.

[1019] Step 5:

[1020] The server receives the HTTP POST request and obtains the text data and emotion data. Specifically, the text data "Hello, where is the station?" and the emotion data "joy" arrive at the server.

[1021] Step 6:

[1022] The server inputs the received text data and emotion data into a deep learning-based translation model. This model takes into account the input Japanese text and corresponding emotion data and generates an English translation result. In this case, the translation "Hello, where is the station?" is annotated with emotion and generated as "Hi, could you tell me where the station is, please?"

[1023] Step 7:

[1024] The server returns the generated translation result to the device using an HTTP response, specifically the translated text "Hi, could you tell me where the station is, please?"

[1025] Step 8:

[1026] The device receives the translation results from the server, stores them in its local memory, and notifies the user. The device displays the emotional English translation, "Hi, could you tell me where the station is, please?"

[1027] Step 9:

[1028] The user can check the displayed translation results and communicate with the local person, for example, by asking a question to the local person using the displayed English.

[1029] Example 2

[1030] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1031] Conventional real-time translation systems convert a user's speech into text and translate it into different languages, but they do not take the user's emotions into account when translating. As a result, the user's intentions and emotions are not accurately conveyed, resulting in a decline in the quality of communication. In particular, in situations where emotions play an important role, translations that ignore emotions can lead to misunderstandings and inappropriate expressions.

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

[1033] In this invention, the server includes a means for converting speech input into text, a means for recognizing and acquiring user emotion data, and a means for generating translation results using a generative model, thereby enabling highly accurate translation that takes user emotion into consideration.

[1034] "Voice input" refers to voice data spoken by a user.

[1035] "Means for converting to text" refers to a process or device that converts audio data into text data.

[1036] "Emotion data" refers to information about emotions extracted from the user's voice.

[1037] "Means for transmitting to a server" refers to the mechanisms and protocols that allow a terminal to transmit data to a server via the Internet or other communication means.

[1038] A "generative model" is an algorithm or computer program that generates a specific output based on given input data, particularly one that uses artificial intelligence techniques such as deep learning.

[1039] "Means for generating a translation result" refers to a process or system that translates received text data and emotion data into another language and generates the translation result.

[1040] "Display means" refers to devices or software that visually notify the user of the translation results.

[1041] The following describes in detail an embodiment of the present invention. This system combines a real-time translation function with an emotion engine that recognizes the user's emotions. This system allows users to not only communicate smoothly with local people, but also convey their emotions.

[1042] Overall structure

[1043] The system mainly consists of the following components:

[1044] 1. User's device: This is the device that receives voice input and runs the voice recognition module and emotion engine. For example, a smartphone or tablet is used here, and a dedicated application is installed.

[1045] 2. Server: This is the central computer that analyzes the voice and emotion data and performs the translation. A cloud-based server is ideal and has the capacity to process large amounts of data.

[1046] 3. Speech Recognition Module: Software that converts speech into text. Specifically, Google Speech-to-Text API is used.

[1047] 4. Emotion engine: Software that analyzes emotions from the user's voice. For example, Azure Cognitive Services' Emotion API falls into this category.

[1048] 5. Generative models: AI algorithms that translate text and sentiment data into another language. Deep learning-based models such as Google Translate API and DeepL API are used.

[1049] 6. Communication method: A method for sending and receiving data between the terminal and the server. HTTP protocol and REST API are commonly used.

[1050] Example of operation

[1051] Here is a concrete example of how this system works:

[1052] 1. User voice input:

[1053] The user speaks to the terminal, "Hello, where is the station?" The speech includes emotional (e.g., joy) tone and rate.

[1054] 2. Speech to text transcription:

[1055] The device activates a speech recognition module (Google Speech-to-Text API) to convert the speech into text data, resulting in the text "Hello, where is the station?"

[1056] 3. Emotion Recognition:

[1057] The device uses an emotion engine (Azure Cognitive Services' Emotion API) to analyze emotion data from the voice and generate emotion data for "joy" in this case.

[1058] 4. Sending data to the server:

[1059] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request, with an endpoint such as https: / / example.com / translate.

[1060] 5. Translation processing on the server:

[1061] The server receives the text data and emotion data and inputs them into a generative model (Google Translate API or DeepL API). Taking into account the text "Hello, where is the station?" and the emotion "joy," the server generates the English translation result "Hi, could you tell me where the station is, please?"

[1062] 6. Returning and displaying translation results:

[1063] The server sends the translation results back to the device using an HTTP response, which the device receives and displays on its screen.

[1064] In this way, real-time translation based on the user's voice and emotions is realized. By using this system, users can obtain highly accurate translation results that include emotions, enabling smooth communication with local people.

[1065] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1066] Step 1:

[1067] The user inputs voice into the terminal. For example, they might say, "Hello, where is the station?" This voice data also contains emotional information such as tone and speed. The input is the user's voice, and the output is sent to the terminal as voice data.

[1068] Step 2:

[1069] The device receives voice input and launches a voice recognition module (e.g., Google Speech-to-Text API). The voice recognition module analyzes the voice data and generates text data such as "Hello, where is the station?". Specifically, it preprocesses the voice signal, extracts features, and then converts the signal to text. The input is voice data, and the output is text data.

[1070] Step 3:

[1071] The device calls an emotion engine (e.g., Azure Cognitive Services' Emotion API) at the same time as receiving the text data. The emotion engine analyzes the user's voice data and generates emotion data. In this case, the emotion data obtained is "joy." Specific operations include processes that analyze the tone, speed, and accent of the voice. The input is voice data, and the output is emotion data.

[1072] Step 4:

[1073] The device sends the generated text data and emotion data to the server using an HTTP POST request. Specific operations include constructing the HTTP request header and body and sending the data to the endpoint https: / / example.com / translate. The input is text data and emotion data, and the output is an HTTP request.

[1074] Step 5:

[1075] The server receives an HTTP POST request and retrieves text data and emotion data. Specifically, it analyzes the HTTP request and extracts the text data "Hello, where is the station?" and the emotion data "Joy." The input is the HTTP request, and the output is the analyzed text data and emotion data.

[1076] Step 6:

[1077] The server inputs text data and emotion data into a generative model (e.g., Google Translate API or DeepL API). The generative model uses this data to generate the translation result, "Hi, could you tell me where the station is, please?" Specifically, the deep learning-based model processes the data through multiple layers to generate the final translation result. The input is text data and emotion data, and the output is the translation result.

[1078] Step 7:

[1079] The server returns the generated translation results to the terminal in the form of an HTTP response. Specific operations include setting the translation results in the header and body of the HTTP response and sending it to the terminal. The input is the translation results, and the output is the HTTP response.

[1080] Step 8:

[1081] The terminal receives the HTTP response returned from the server and obtains the translation result, "Hi, could you tell me where the station is, please?". The translation result is displayed on the screen and notified to the user. Specifically, it analyzes the HTTP response and updates the user interface to display the result. The input is the HTTP response, and the output is the displayed translation result.

[1082] (Application example 2)

[1083] 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."

[1084] When a user makes an inquiry about a food delivery service, conventional systems are unable to respond in a way that takes into account the user's emotions, making it difficult to respond in a way that appropriately reflects the user's emotions.Furthermore, the inability to recognize emotions in real time and provide an appropriate response results in a poor user experience.

[1085] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a user's voice input and converting it into text, means for transmitting the text data and emotion data to the server, and means for receiving the text data and emotion data in the server and generating a translation result using a translation model. This makes it possible to provide a highly accurate translation result that reflects the user's emotion.

[1086] "User's voice input" refers to a voice signal emitted by a user into a terminal.

[1087] "Text data" refers to character data obtained by converting a voice signal into text by a voice recognition module.

[1088] "Emotion data" refers to data that indicates the user's emotional state as analyzed by the emotion engine.

[1089] "Server" refers to a central computer that receives speech input, text data, and emotion data, and uses a translation model to generate a translation result.

[1090] "Translation model" refers to an algorithm that uses AI technologies such as deep learning to generate translation results based on input text data and emotional data.

[1091] "Terminal" refers to a device that receives a user's voice input and has a voice recognition module and an emotion engine.

[1092] "Speech recognition module" refers to software that converts a user's voice input into text data.

[1093] "Emotion engine" refers to software that analyzes emotions from the user's voice.

[1094] "Translation result" refers to the output text in another language that a translation model generates, taking into account the input text and sentiment.

[1095] "HTTP POST request" refers to one of the communication protocols used to transfer text data and emotion data from a terminal to a server.

[1096] "HTTP response" refers to one of the communication protocols used to return translation results from the server to the terminal.

[1097] The following describes in detail an embodiment of the present invention. The present invention is a system for recognizing a user's emotions and providing appropriate responses in a food delivery service. This system converts a user's voice input into text data and emotion data in real time, transmits the data to a server, and generates a response using a translation model.

[1098] Overall structure

[1099] The system of the present invention mainly consists of the following components:

[1100] 1. Terminal: A device that receives voice input and has a speech recognition module and an emotion engine.

[1101] 2. Server: A central computer that analyzes voice and emotion data and performs translation.

[1102] 3. Speech Recognition Module: Software that converts speech into text.

[1103] 4. Emotion engine: Software that analyzes emotions from the user's voice.

[1104] 5. Translation model: An AI algorithm that translates text and sentiment data into another language.

[1105] 6. Communication method: A method for sending and receiving data between the terminal and the server (such as HTTP protocol).

[1106] Program processing flow

[1107] 1. User voice input:

[1108] The user speaks to the device and performs voice input. For example, they might say, "My delivery is delayed. What's going on?" This includes emotional information such as tone and speed of voice.

[1109] 2. Speech to text transcription:

[1110] The device receives the user's voice input and converts the speech into text using a speech recognition module, in this case "My delivery is late, what's going on?"

[1111] 3. Emotion Recognition:

[1112] The device uses an emotion engine to analyze emotions from the user's voice input and generate emotion data. For example, emotions such as "dissatisfaction" and "frustration" are recognized.

[1113] 4. Sending data to the server:

[1114] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request. Specifically, the device sends the text data "Delivery is delayed, what's going on?" and the emotion data "Unhappy" to the endpoint https: / / example.com / translate.

[1115] 5. Translation processing on the server:

[1116] The server inputs the received text data and emotion data into a translation model and generates a translation result that takes emotion into account. For example, the translation result "The delivery is late, what is happening?" will be translated into "The delivery is late, what is happening? How can we help to resolve this?", which includes a sense of dissatisfaction.

[1117] 6. Returning and displaying translation results:

[1118] The server then sends the translation back to the device, specifically the text "The delivery is late, what is happening? How can we help to resolve this?"

[1119] The terminal displays the translation results received from the server and notifies the user.

[1120] Software and hardware used

[1121] This system uses the following software and hardware:

[1122] Device: Smartphones and tablets are used.

[1123] Speech Recognition Module: SpeechRecognition library.

[1124] Emotion Engine: A pipeline of transformers libraries.

[1125] Server: A server that communicates using the HTTP protocol.

[1126] Translation model: A deep learning-based translation model.

[1127] Specific examples

[1128] An example of a prompt sentence would be "The delivery is late, what's going on?" The system recognizes this utterance and converts the speech into text data: "The delivery is late, what is happening?" The emotion engine recognizes the emotion "dissatisfied" from this utterance. Finally, the translation result, "The delivery is late, what is happening? How can we help to resolve this?", is generated and displayed on the device.

[1129] This system enables smooth and emotional communication with users.

[1130] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1131] Step 1:

[1132] The user makes a voice input to the terminal. For example, the user says, "The delivery is delayed. What's going on?" At this time, the input is recognized by the terminal as a voice signal.

[1133] Step 2:

[1134] The device uses a speech recognition module to convert the user's voice input into text data. The input voice signal is processed by the speech recognition library, and the text data "My delivery is delayed, what's going on?" is generated.

[1135] Step 3:

[1136] The device uses an emotion engine to analyze and generate emotion data from the user's voice input. Elements such as tone, speed, and accent of the voice are analyzed to calculate emotion data such as dissatisfaction or frustration.

[1137] Step 4:

[1138] The device sends the text data and emotion data to the server using an HTTP POST request. Specifically, it sends the generated text data "Delivery is delayed, what's going on?" and emotion data "Unhappy" to the endpoint https: / / example.com / translate.

[1139] Step 5:

[1140] The server receives the HTTP POST request, retrieves the submitted text data and emotion data, and inputs this data into a deep learning-based translation model to generate a translation result that reflects the appropriate emotion. For example, the resulting English translation would be "The delivery is late, what is happening? How can we help to resolve this?"

[1141] Step 6:

[1142] The server returns the generated translation result to the terminal as an HTTP response. The server then sends data including the translation result to the terminal, which then receives the data.

[1143] Step 7:

[1144] The device displays the translation results from the server, and the following text appears on the device screen to the user: "The delivery is late, what is happening? How can we help to resolve this?"

[1145] This process allows users to receive responses that reflect their own emotions in real time, enabling smooth communication.

[1146] 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.

[1147] 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.

[1148] 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.

[1149] [Fourth embodiment]

[1150] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1151] 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.

[1152] 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).

[1153] 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.

[1154] 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.

[1155] 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).

[1156] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1157] 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.

[1158] 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.

[1159] 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.

[1160] 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.

[1161] 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.

[1162] 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."

[1163] The following describes in detail an embodiment of the present invention. This system provides a real-time translation function, enabling users to communicate smoothly with local people. Specifically, the system converts the user's voice input into text, processes it using a translation model on a server, and returns and displays the translation results to the user.

[1164] Overall structure

[1165] The system mainly consists of the following components:

[1166] 1. User device: The device that receives voice input.

[1167] 2. Server: A central computer that analyzes the audio data and performs the translation.

[1168] 3. Speech Recognition Module: Software that converts speech into text.

[1169] 4. Translation model: An AI algorithm that translates text data into another language.

[1170] 5. Communication method: A method for sending and receiving data between the terminal and the server (such as HTTP protocol).

[1171] Program processing flow

[1172] 1. User voice input

[1173] The user provides voice input by speaking into the device (e.g., "Hello, where is the station?").

[1174] 2. Speech-to-text

[1175] The device receives voice input and converts it into text using a built-in speech recognition module.

[1176] The speech recognition module analyzes the user's voice and converts the results into text data, with high accuracy taking into account the user's pronunciation and accent.

[1177] 3. Sending text data to the server

[1178] The terminal sends the converted text data to the server using an HTTP POST request.

[1179] Example: The device sends the text "Hello, where is the station?" to the endpoint https: / / example.com / translate.

[1180] 4. Translation processing on the server

[1181] The server receives the text data sent from the terminal.

[1182] The server inputs the received data into a translation model, which is based on deep learning and uses a multi-layered neural network.

[1183] The translation model analyzes text and generates appropriate translation results, taking into account context and appropriate expressions based on a vast amount of training data.

[1184] Example: Translating the Japanese phrase "Hello, where is the station?" into English "Hello, where is the station?"

[1185] 5. Returning and displaying translation results

[1186] The server returns the generated translation results to the terminal using an HTTP response.

[1187] The device receives the translation results and displays them to the user in text format, with a notification for the user to review.

[1188] Example: The device displays the translation result "Hello, where is the station?" on the screen for the user to confirm.

[1189] Specific examples

[1190] As an example, we will explain in detail how the system operates when a user says, "Hello, where is the station?"

[1191] User: Says to the device, "Hello, where is the station?"

[1192] Terminal: The speech recognition module converts the speech into text "Hello, where is the station?"

[1193] Terminal: Sends text data to the server via an HTTP POST request.

[1194] Server: Input the received text into the translation model and generate the English translation result "Hello, where is the station?"

[1195] Server: Sends the translation result to the device as an HTTP response.

[1196] Terminal: Display the translation result and notify the user.

[1197] With the above configuration, the system of the present invention provides real-time translation that allows users to communicate effectively with local people. Furthermore, by utilizing deep learning models, it is possible to achieve highly accurate and context-appropriate translation. This is expected to improve user convenience in many situations, including overseas travel.

[1198] The processing flow will be explained below.

[1199] Step 1:

[1200] The user speaks to the terminal and performs voice input. For example, the user might say, "Hello, where is the station?"

[1201] Step 2:

[1202] The terminal receives the user's voice input and activates a voice recognition module. The voice recognition module analyzes the user's speech and converts it into text data. In this case, the text generated is "Hello, where is the station?"

[1203] Step 3:

[1204] The device temporarily stores the converted text data in local memory and then sends it to the server using an HTTP POST request. Specifically, the text data is sent to the endpoint https: / / example.com / translate.

[1205] Step 4:

[1206] The server receives the HTTP POST request and obtains the text data. Specifically, the text data "Hello, where is the station?" arrives at the server.

[1207] Step 5:

[1208] The server inputs the received text data into a deep learning-based translation model, which translates the input Japanese text into English and generates the appropriate English translation result, in this case, "Hello, where is the station?"

[1209] Step 6:

[1210] The server returns the generated translation result to the device using an HTTP response, specifically the translated text "Hello, where is the station?"

[1211] Step 7:

[1212] The device stores the translation results received from the server in its local memory and notifies the user. The device's display shows the text "Hello, where is the station?" in English.

[1213] Step 8:

[1214] The user can check the displayed translation results and communicate with the local person. For example, they can ask the local person a question using the displayed English.

[1215] Example 1

[1216] 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."

[1217] Real-time translation is necessary for users who do not understand the local language to communicate smoothly with local people. However, conventional translation systems have problems such as low speech input accuracy and inaccurate translation results. Furthermore, there is also the issue of operation becoming cumbersome due to the need to use multiple applications.

[1218] 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.

[1219] In this invention, the server includes a means for converting speech input into text with high accuracy, a means for transmitting text data to the server using a communication protocol, and a means for generating translation results using deep learning, thereby enabling users to seamlessly obtain highly accurate translation results from speech input.

[1220] A "user" is an individual or group that uses the system and is the subject that performs voice input.

[1221] "Voice input" refers to the operation of inputting the user's voice into the terminal as digital information.

[1222] A "terminal" is a device used by a user that receives voice input, converts text, communicates, displays translation results, and provides voice notification.

[1223] "Means for converting to text" refers to the process of converting voice data into text data using a voice recognition module.

[1224] A "communication protocol" is a standardized communication method for sending and receiving data between a terminal and a server, and examples include HTTP and HTTPS.

[1225] A "server" is a central computer system that receives text data, processes it using a translation model, and generates and returns the translation results.

[1226] A "voice recognition module" is a software or hardware technology that analyzes input speech and converts it into text.

[1227] A "translation model" is a machine learning algorithm that uses deep learning to translate text data into another language.

[1228] "Deep learning" is a branch of artificial intelligence that uses multi-layered neural networks to analyze data and perform specific tasks automatically.

[1229] A "generative AI model" is an artificial intelligence algorithm that learns from a large amount of data in advance and then generates text based on new data.

[1230] A "translation result" is text data in another language generated by a translation model.

[1231] "Encrypted communication means" refers to technology that encrypts data to prevent eavesdropping or tampering by third parties when sending and receiving data.

[1232] "Voice notification" is a function that notifies the user of the generated translation result by voice.

[1233] The following describes in detail an embodiment of the present invention. This system provides a real-time translation function that enables users to communicate smoothly with local people. Specifically, the system converts user voice input into text, translates the text on the server, and returns the translation result to the user for display.

[1234] The overall system consists of the following components:

[1235] 1. User device: This is the device that receives the voice input, such as a smartphone or a dedicated translation device.

[1236] 2. Server: A central computer that analyzes the audio data and performs the translation.

[1237] 3. Speech recognition module: Software that converts the user's voice into text. Specifically, Google Cloud Speech-to-Text API is used.

[1238] 4. Translation model: An AI algorithm that translates text data into other languages. Examples include the Google Translate API and BERT-based models that use deep learning.

[1239] 5. Communication method: A method for sending and receiving data between the terminal and the server. For example, the HTTP or HTTPS protocol is used.

[1240] The specific system operation is explained below:

[1241] 1. User voice input: The user speaks to the terminal, "Hello, where is the station?" The voice input is received as digital data through the terminal's microphone.

[1242] 2. Speech-to-text conversion: The device sends the received voice data to a voice recognition module (e.g., Google Cloud Speech-to-Text API) and converts it into text data: "Hello, where is the station?"

[1243] 3. Sending text data to the server: The device sends the converted text data to the server via an HTTP POST request, using https: / / example.com / translate as the destination endpoint.

[1244] 4. Translation processing on the server: The server inputs the received text data into a translation model (e.g., Google Translate API) and generates the translation result "Hello, where is the station?" In this process, the server uses a deep learning-based generative AI model.

[1245] 5. Return and display of translation results: The server returns the generated translation results to the terminal as an HTTP response. The terminal displays the translation results on the screen and can also use a voice notification function to notify the user.

[1246] As a concrete example, here is what the system does again when the user says "Hello, where is the station?":

[1247] User: Says to the device, "Hello, where is the station?"

[1248] Terminal: Uses a speech recognition module to convert the speech into text: "Hello, where is the station?"

[1249] Terminal: Sends text data to the server via an HTTP POST request.

[1250] Server: Inputs the received text into the translation model and generates the English translation result "Hello, where is the station?"

[1251] Server: Sends the translation result to the terminal as an HTTP response.

[1252] Terminal: Displays the translation results and notifies the user.

[1253] Example prompt sentence:

[1254] "Please translate the Japanese text "Hello, where is the station?" into English."

[1255] As described above, this system enables users to communicate smoothly even if they do not understand the local language. By utilizing advanced speech recognition and translation technology, it is possible to provide real-time, highly accurate translation results.

[1256] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1257] Step 1:

[1258] The user speaks to the terminal. When the user speaks, "Hello, where is the station?", the microphone converts the voice into a digital signal. The input is the user's voice data, which is then passed on to the next step of processing.

[1259] Step 2:

[1260] The device receives the voice data and sends it to a built-in voice recognition module. The voice recognition module (for example, Google Cloud Speech-to-Text API) converts the voice data into text. Specifically, the voice signal is analyzed and each phoneme is mapped to a character. The output is the text data "Hello, where is the station?"

[1261] Step 3:

[1262] The terminal sends the converted text data to the server via an HTTP POST request. The input is the text data "Hello, where is the station?", which is sent to the server in the form of an HTTP request. The HTTPS protocol is used as the transmission method, and the data is sent to the endpoint https: / / example.com / translate.

[1263] Step 4:

[1264] The server receives the text data sent from the terminal. When the server receives the text data, it passes it on to the next process. The input is the text data "Hello, where is the station?", which is stored in the server's main memory or storage.

[1265] Step 5:

[1266] The server inputs the received text data into a translation model. The input data, "Hello, where is the station?", is passed to a deep learning-based translation model (for example, Google Translate API). Specifically, the translation model analyzes the text data and generates a translation result. The output is the English translation, "Hello, where is the station?"

[1267] Step 6:

[1268] The server returns the generated translation result to the terminal as an HTTP response. The input is the translation result text data "Hello, where is the station?", which is sent to the terminal in HTTP response format. HTTPS is again used as the communication method.

[1269] Step 7:

[1270] The terminal receives the returned translation result. The input is the text data of the translation result sent from the server, "Hello, where is the station?". It receives this and passes it on to the next process.

[1271] Step 8:

[1272] The device displays the received translation results to the user and provides voice notification if necessary. Specifically, the text data is displayed on the screen for the user to review. Furthermore, it is possible to provide voice notification of the translation results using a speech synthesis module. The output is the displayed text and voice notification.

[1273] Through these steps, the system enables users to communicate smoothly with local people in real time through translation, providing highly accurate and context-appropriate translation results.

[1274] (Application example 1)

[1275] 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."

[1276] There is a problem in that it is difficult to communicate smoothly in real time between users who speak different languages. In particular, in situations such as food delivery services, if the customer and delivery person cannot exchange information smoothly, delivery delays and misunderstandings can occur. To solve this problem, a highly accurate, real-time speech translation system is required.

[1277] 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.

[1278] In this invention, the server includes means for receiving a user's voice input and converting it into text, means for transmitting the text data to the server, means for receiving the text data at the server and generating a translation result using a translation model, means for returning the translation result to the terminal, means for displaying the translation result at the terminal, and means for reading out the translation result aloud, thereby enabling users who speak different languages ​​to communicate smoothly in real time.

[1279] "User voice input" refers to voice data uttered by a user, which is input received by the system.

[1280] "Means for converting to text" refers to software or hardware for converting audio data into corresponding text data.

[1281] "Means for sending to the server" refers to a communication means for sending the converted text data to the server via a network.

[1282] "Means for receiving at the server" refers to means for receiving text data transmitted via a network at the server side.

[1283] "Means for generating translation results using a translation model" refers to means that include a process using an AI algorithm or deep learning model to translate received text data into another language.

[1284] The "means for returning the translation result to the terminal" refers to a means for transmitting the generated translation result to the user's terminal via a network.

[1285] "Means for displaying the translation result on the terminal" refers to means for displaying the received translation result in text format on the user's terminal.

[1286] "Means for reading out the translation result aloud" refers to means for reading out the displayed translation result in audio format using text-to-speech conversion technology.

[1287] "Speech recognition module" refers to software or a device for analyzing a user's voice data and converting it into text data.

[1288] A "deep learning model" refers to an AI algorithm that uses multi-layered neural networks to process information and perform advanced pattern recognition and prediction.

[1289] This system provides a real-time translation function to facilitate communication between users who speak different languages. A specific embodiment is described below.

[1290] Overall system configuration

[1291] The system mainly consists of the following components:

[1292] 1. User device: The device that receives voice input, such as a smartphone or tablet.

[1293] 2. Server: A central computer that analyzes the audio data and performs the translation.

[1294] 3. Speech recognition module: Uses "RecognizerIntent", software that converts speech to text.

[1295] 4. Translation model: An AI algorithm for translating text data into another language, using the Google Cloud Translate API.

[1296] 5. Communication method: The HTTP protocol is used to send and receive data between the terminal and the server.

[1297] System processing flow

[1298] 1. Voice input: When the user speaks to the device, the device converts the speech into text. This is done using "RecognizerIntent".

[1299] For example, a user might say, "Hello, I'd like to know the status of my order." This speech is analyzed by "RecognizerIntent" and converted into the text "Hello, I'd like to know the status of my order."

[1300] 2. Sending text data: The converted text data is sent to the server as an HTTP POST request. For example, the device sends the text data "Hello, I'd like to know the status of my order" to the specified endpoint (e.g., https: / / example.com / translate).

[1301] 3. Translation processing on the server: The server inputs the received data into the Google Cloud Translate API for translation. The AI ​​algorithm used as the translation model is based on deep learning and uses a multi-layer neural network to achieve high-precision translation.

[1302] As a concrete example, the Japanese phrase "Hello, I'd like to know the status of my order" is translated into English as "Hello, I'd like to know the status of my order."

[1303] 4. Return and display of translation results: The server returns the translation results to the device as an HTTP response, which the device receives and displays to the user. Additionally, a function has been added to read the translation results aloud.

[1304] For example, the device will display the translation result "Hello, I'd like to know the status of my order" on the screen and read it aloud, allowing the user to check the translation result both in text and audio.

[1305] Example prompt sentences

[1306] Examples of prompts include:

[1307] "A user says, 'Hello, I'd like to know the status of my order.' Please translate this Japanese sentence into English."

[1308] This system enables smooth real-time communication between users who speak different languages, and is particularly useful for food delivery services, where information can be exchanged quickly and accurately between customers and delivery personnel.

[1309] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1310] Step 1:

[1311] The user speaks to the device. Specifically, the user says, "Hello, I'd like to know the status of my order." This voice input is captured through the device's microphone.

[1312] Input: User's voice data

[1313] Output: Raw audio data captured by the microphone

[1314] Step 2:

[1315] The device uses a speech recognition module ("RecognizerIntent") to convert the acquired speech data into text data. During the conversion process, the speech is analyzed, and words are recognized and converted into text.

[1316] Input: Raw audio data

[1317] Data processing: Analysis and recognition of voice data

[1318] Output: Text data (e.g. "Hello, I'd like to know the status of my order.")

[1319] Step 3:

[1320] The terminal sends the converted text data to the server using an HTTP POST request.

[1321] Input: Text data

[1322] Data processing: Generating HTTP requests

[1323] Output: Request sent to server

[1324] Step 4:

[1325] The server receives the text data sent from the terminal, analyzes the HTTP request, and obtains the text data.

[1326] Input: HTTP request

[1327] Data processing: HTTP request analysis

[1328] Output: Received text data

[1329] Step 5:

[1330] The server sends the received text data to the Google Cloud Translate API for translation. The translation model is based on deep learning, and the data is analyzed and translated.

[1331] Input: Received text data

[1332] Data processing: Data analysis and translation using translation models

[1333] Output: Translated text data (e.g., "Hello, I'd like to know the status of my order")

[1334] Step 6:

[1335] The server returns the translation results to the terminal as an HTTP response, which is then generated and sent over the network.

[1336] Input: Translated text data

[1337] Data processing: Generating HTTP responses

[1338] Output: Sending HTTP response to the terminal

[1339] Step 7:

[1340] The device receives the HTTP response from the server, analyzes the received data, and obtains the translation result.

[1341] Input: HTTP response

[1342] Data processing: HTTP response analysis

[1343] Output: Translated text data

[1344] Step 8:

[1345] The device displays the translation results on the screen and notifies the user. The translation results are also read aloud, allowing the user to check the translation results both in text and audio.

[1346] Input: Translated text data

[1347] Data processing: Screen display and voice reading

[1348] Output: On-screen text and spoken notifications

[1349] The above processing steps enable a user to smoothly communicate in real time with others who speak different languages.

[1350] 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.

[1351] The following describes in detail the mode for carrying out the present invention. This system combines a real-time translation function with an emotion engine that recognizes the user's emotions. This allows users to not only communicate smoothly with local people, but also convey their emotions.

[1352] Overall structure

[1353] The system mainly consists of the following components:

[1354] 1. User's device: A device that receives voice input and has a speech recognition module and an emotion engine.

[1355] 2. Server: A central computer that analyzes voice and emotion data and performs translation.

[1356] 3. Speech Recognition Module: Software that converts speech into text.

[1357] 4. Emotion engine: Software that analyzes emotions from the user's voice.

[1358] 5. Translation model: An AI algorithm that translates text and sentiment data into another language.

[1359] 6. Communication method: A method for sending and receiving data between the terminal and the server (such as HTTP protocol).

[1360] Program processing flow

[1361] 1. User voice input

[1362] The user speaks to the device to input voice information. For example, the user might say, "Hello, where is the station?" This includes emotional information such as tone and speed of voice.

[1363] 2. Speech-to-text

[1364] The terminal receives the user's voice input and activates a voice recognition module. The voice recognition module analyzes the user's speech and converts it into text data. In this case, the text generated is "Hello, where is the station?"

[1365] 3. Emotional Recognition

[1366] The device uses an emotion engine to analyze emotions from the user's voice input. The emotion engine analyzes the tone, speed, accent, etc. of the voice to generate emotion data for the user. For example, emotions such as "happiness," "surprise," and "doubt" can be recognized.

[1367] 4. Sending text data and emotion data to the server

[1368] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request. Specifically, the text data and emotion data are sent to the endpoint https: / / example.com / translate.

[1369] 5. Translation processing on the server

[1370] The server receives the HTTP POST request and obtains the text data and emotion data. Specifically, the text data "Hello, where is the station?" and the emotion data "joy" arrive at the server.

[1371] The server inputs the received text data and emotion data into a deep learning-based translation model, which generates an English translation result taking into account the input Japanese text and corresponding emotion data.

[1372] The translation model takes into account emotional data and adds appropriate expressions depending on the context. For example, the translation "Hello, where is the station?" is given an emotional value and translated as "Hi, could you tell me where the station is, please?"

[1373] 6. Returning and displaying translation results

[1374] The server returns the generated translation result to the device using an HTTP response, specifically the translated text "Hi, could you tell me where the station is, please?"

[1375] The device stores the translation results received from the server in its local memory and notifies the user. The device's display shows the emotional English translation, "Hi, could you tell me where the station is, please?"

[1376] Specific examples

[1377] As an example, we will explain in detail how the system operates when a user says, "Hello, where is the station?"

[1378] User: Says to the device, "Hello, where is the station?"

[1379] Terminal: The speech recognition module converts the speech into text "Hello, where is the station?"

[1380] Device: The emotion engine recognizes the emotion of "joy" from voice.

[1381] Device: Send text and emotion data to the server via an HTTP POST request.

[1382] Server: The received text and emotion data are input into the translation model, and the emotion-sensitive English translation result "Hi, could you tell me where the station is, please?" is generated.

[1383] Server: Sends the translation result to the device as an HTTP response.

[1384] Terminal: Display the translation result and notify the user.

[1385] With the above configuration, the system of the present invention provides real-time translation that allows users to communicate effectively and emotionally with local people. Furthermore, by utilizing an emotion engine, highly accurate translation that incorporates emotion becomes possible. This is expected to improve the user's communication experience in a variety of situations.

[1386] The processing flow will be explained below.

[1387] Step 1:

[1388] The user speaks to the terminal and performs voice input. For example, the user might say, "Hello, where is the station?"

[1389] Step 2:

[1390] The device receives the user's voice input and activates a voice recognition module. The voice recognition module analyzes the user's speech and converts it into text data. In this case, the text generated is "Hello, where is the station?"

[1391] Step 3:

[1392] The device uses an emotion engine to analyze emotions from the user's voice input. The emotion engine analyzes the tone, rate, and voice pattern of the voice to generate emotion data for the user. In this case, the emotion engine recognizes the emotion of "happiness."

[1393] Step 4:

[1394] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request to the endpoint https: / / example.com / translate.

[1395] Step 5:

[1396] The server receives the HTTP POST request and obtains the text data and emotion data. Specifically, the text data "Hello, where is the station?" and the emotion data "joy" arrive at the server.

[1397] Step 6:

[1398] The server inputs the received text data and emotion data into a deep learning-based translation model. This model takes into account the input Japanese text and corresponding emotion data and generates an English translation result. In this case, the translation "Hello, where is the station?" is annotated with emotion and generated as "Hi, could you tell me where the station is, please?"

[1399] Step 7:

[1400] The server returns the generated translation result to the device using an HTTP response, specifically the translated text "Hi, could you tell me where the station is, please?"

[1401] Step 8:

[1402] The device receives the translation results from the server, stores them in its local memory, and notifies the user. The device displays the emotional English translation, "Hi, could you tell me where the station is, please?"

[1403] Step 9:

[1404] The user can check the displayed translation results and communicate with the local person, for example, by asking a question to the local person using the displayed English.

[1405] Example 2

[1406] 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."

[1407] Conventional real-time translation systems convert a user's speech into text and translate it into different languages, but they do not take the user's emotions into account when translating. As a result, the user's intentions and emotions are not accurately conveyed, resulting in a decline in the quality of communication. In particular, in situations where emotions play an important role, translations that ignore emotions can lead to misunderstandings and inappropriate expressions.

[1408] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1409] In this invention, the server includes a means for converting speech input into text, a means for recognizing and acquiring user emotion data, and a means for generating translation results using a generative model, thereby enabling highly accurate translation that takes user emotion into consideration.

[1410] "Voice input" refers to voice data spoken by a user.

[1411] "Means for converting to text" refers to a process or device that converts audio data into text data.

[1412] "Emotion data" refers to information about emotions extracted from the user's voice.

[1413] "Means for transmitting to a server" refers to the mechanisms and protocols that allow a terminal to transmit data to a server via the Internet or other communication means.

[1414] A "generative model" is an algorithm or computer program that generates a specific output based on given input data, particularly one that uses artificial intelligence techniques such as deep learning.

[1415] "Means for generating a translation result" refers to a process or system that translates received text data and emotion data into another language and generates the translation result.

[1416] "Display means" refers to devices or software that visually notify the user of the translation results.

[1417] The following describes in detail an embodiment of the present invention. This system combines a real-time translation function with an emotion engine that recognizes the user's emotions. This system allows users to not only communicate smoothly with local people, but also convey their emotions.

[1418] Overall structure

[1419] The system mainly consists of the following components:

[1420] 1. User's device: This is the device that receives voice input and runs the voice recognition module and emotion engine. For example, a smartphone or tablet is used here, and a dedicated application is installed.

[1421] 2. Server: This is the central computer that analyzes the voice and emotion data and performs the translation. A cloud-based server is ideal and has the capacity to process large amounts of data.

[1422] 3. Speech Recognition Module: Software that converts speech into text. Specifically, Google Speech-to-Text API is used.

[1423] 4. Emotion engine: Software that analyzes emotions from the user's voice. For example, Azure Cognitive Services' Emotion API falls into this category.

[1424] 5. Generative models: AI algorithms that translate text and sentiment data into another language. Deep learning-based models such as Google Translate API and DeepL API are used.

[1425] 6. Communication method: A method for sending and receiving data between the terminal and the server. HTTP protocol and REST API are commonly used.

[1426] Example of operation

[1427] Here is a concrete example of how this system works:

[1428] 1. User voice input:

[1429] The user speaks to the terminal, "Hello, where is the station?" The speech includes emotional (e.g., joy) tone and rate.

[1430] 2. Speech to text transcription:

[1431] The device activates a speech recognition module (Google Speech-to-Text API) to convert the speech into text data, resulting in the text "Hello, where is the station?"

[1432] 3. Emotion Recognition:

[1433] The device uses an emotion engine (Azure Cognitive Services' Emotion API) to analyze emotion data from the voice and generate emotion data for "joy" in this case.

[1434] 4. Sending data to the server:

[1435] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request, with an endpoint such as https: / / example.com / translate.

[1436] 5. Translation processing on the server:

[1437] The server receives the text data and emotion data and inputs them into a generative model (Google Translate API or DeepL API). Taking into account the text "Hello, where is the station?" and the emotion "joy," the server generates the English translation result "Hi, could you tell me where the station is, please?"

[1438] 6. Returning and displaying translation results:

[1439] The server sends the translation results back to the device using an HTTP response, which the device receives and displays on its screen.

[1440] In this way, real-time translation based on the user's voice and emotions is realized. By using this system, users can obtain highly accurate translation results that include emotions, enabling smooth communication with local people.

[1441] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1442] Step 1:

[1443] The user inputs voice into the terminal. For example, they might say, "Hello, where is the station?" This voice data also contains emotional information such as tone and speed. The input is the user's voice, and the output is sent to the terminal as voice data.

[1444] Step 2:

[1445] The device receives voice input and launches a voice recognition module (e.g., Google Speech-to-Text API). The voice recognition module analyzes the voice data and generates text data such as "Hello, where is the station?". Specifically, it preprocesses the voice signal, extracts features, and then converts the signal to text. The input is voice data, and the output is text data.

[1446] Step 3:

[1447] The device calls an emotion engine (e.g., Azure Cognitive Services' Emotion API) at the same time as receiving the text data. The emotion engine analyzes the user's voice data and generates emotion data. In this case, the emotion data obtained is "joy." Specific operations include processes that analyze the tone, speed, and accent of the voice. The input is voice data, and the output is emotion data.

[1448] Step 4:

[1449] The device sends the generated text data and emotion data to the server using an HTTP POST request. Specific operations include constructing the HTTP request header and body and sending the data to the endpoint https: / / example.com / translate. The input is text data and emotion data, and the output is an HTTP request.

[1450] Step 5:

[1451] The server receives an HTTP POST request and retrieves text data and emotion data. Specifically, it analyzes the HTTP request and extracts the text data "Hello, where is the station?" and the emotion data "Joy." The input is the HTTP request, and the output is the analyzed text data and emotion data.

[1452] Step 6:

[1453] The server inputs text data and emotion data into a generative model (e.g., Google Translate API or DeepL API). The generative model uses this data to generate the translation result, "Hi, could you tell me where the station is, please?" Specifically, the deep learning-based model processes the data through multiple layers to generate the final translation result. The input is text data and emotion data, and the output is the translation result.

[1454] Step 7:

[1455] The server returns the generated translation results to the terminal in the form of an HTTP response. Specific operations include setting the translation results in the header and body of the HTTP response and sending it to the terminal. The input is the translation results, and the output is the HTTP response.

[1456] Step 8:

[1457] The terminal receives the HTTP response returned from the server and obtains the translation result, "Hi, could you tell me where the station is, please?". The translation result is displayed on the screen and notified to the user. Specifically, it analyzes the HTTP response and updates the user interface to display the result. The input is the HTTP response, and the output is the displayed translation result.

[1458] (Application example 2)

[1459] 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."

[1460] When a user makes an inquiry about a food delivery service, conventional systems are unable to respond in a way that takes into account the user's emotions, making it difficult to respond in a way that appropriately reflects the user's emotions.Furthermore, the inability to recognize emotions in real time and provide an appropriate response results in a poor user experience.

[1461] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving a user's voice input and converting it into text, means for transmitting the text data and emotion data to the server, and means for receiving the text data and emotion data in the server and generating a translation result using a translation model. This makes it possible to provide a highly accurate translation result that reflects the user's emotion.

[1462] "User's voice input" refers to a voice signal emitted by a user into a terminal.

[1463] "Text data" refers to character data obtained by converting a voice signal into text by a voice recognition module.

[1464] "Emotion data" refers to data that indicates the user's emotional state as analyzed by the emotion engine.

[1465] "Server" refers to a central computer that receives speech input, text data, and emotion data, and uses a translation model to generate a translation result.

[1466] "Translation model" refers to an algorithm that uses AI technologies such as deep learning to generate translation results based on input text data and emotional data.

[1467] "Terminal" refers to a device that receives a user's voice input and has a voice recognition module and an emotion engine.

[1468] "Speech recognition module" refers to software that converts a user's voice input into text data.

[1469] "Emotion engine" refers to software that analyzes emotions from the user's voice.

[1470] "Translation result" refers to the output text in another language that a translation model generates, taking into account the input text and sentiment.

[1471] "HTTP POST request" refers to one of the communication protocols used to transfer text data and emotion data from a terminal to a server.

[1472] "HTTP response" refers to one of the communication protocols used to return translation results from the server to the terminal.

[1473] The following describes in detail an embodiment of the present invention. The present invention is a system for recognizing a user's emotions and providing appropriate responses in a food delivery service. This system converts a user's voice input into text data and emotion data in real time, transmits the data to a server, and generates a response using a translation model.

[1474] Overall structure

[1475] The system of the present invention mainly consists of the following components:

[1476] 1. Terminal: A device that receives voice input and has a speech recognition module and an emotion engine.

[1477] 2. Server: A central computer that analyzes voice and emotion data and performs translation.

[1478] 3. Speech Recognition Module: Software that converts speech into text.

[1479] 4. Emotion engine: Software that analyzes emotions from the user's voice.

[1480] 5. Translation model: An AI algorithm that translates text and sentiment data into another language.

[1481] 6. Communication method: A method for sending and receiving data between the terminal and the server (such as HTTP protocol).

[1482] Program processing flow

[1483] 1. User voice input:

[1484] The user speaks to the device and performs voice input. For example, they might say, "My delivery is delayed. What's going on?" This includes emotional information such as tone and speed of voice.

[1485] 2. Speech to text transcription:

[1486] The device receives the user's voice input and converts the speech into text using a speech recognition module, in this case "My delivery is late, what's going on?"

[1487] 3. Emotion Recognition:

[1488] The device uses an emotion engine to analyze emotions from the user's voice input and generate emotion data. For example, emotions such as "dissatisfaction" and "frustration" are recognized.

[1489] 4. Sending data to the server:

[1490] The device sends the converted text data and the recognized emotion data to the server using an HTTP POST request. Specifically, the device sends the text data "Delivery is delayed, what's going on?" and the emotion data "Unhappy" to the endpoint https: / / example.com / translate.

[1491] 5. Translation processing on the server:

[1492] The server inputs the received text data and emotion data into a translation model and generates a translation result that takes emotion into account. For example, the translation result "The delivery is late, what is happening?" will be translated into "The delivery is late, what is happening? How can we help to resolve this?", which includes a sense of dissatisfaction.

[1493] 6. Returning and displaying translation results:

[1494] The server then sends the translation back to the device, specifically the text "The delivery is late, what is happening? How can we help to resolve this?"

[1495] The terminal displays the translation results received from the server and notifies the user.

[1496] Software and hardware used

[1497] This system uses the following software and hardware:

[1498] Device: Smartphones and tablets are used.

[1499] Speech Recognition Module: SpeechRecognition library.

[1500] Emotion Engine: A pipeline of transformers libraries.

[1501] Server: A server that communicates using the HTTP protocol.

[1502] Translation model: A deep learning-based translation model.

[1503] Specific examples

[1504] An example of a prompt sentence would be "The delivery is late, what's going on?" The system recognizes this utterance and converts the speech into text data: "The delivery is late, what is happening?" The emotion engine recognizes the emotion "dissatisfied" from this utterance. Finally, the translation result, "The delivery is late, what is happening? How can we help to resolve this?", is generated and displayed on the device.

[1505] This system enables smooth and emotional communication with users.

[1506] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1507] Step 1:

[1508] The user makes a voice input to the terminal. For example, the user says, "The delivery is delayed. What's going on?" At this time, the input is recognized by the terminal as a voice signal.

[1509] Step 2:

[1510] The device uses a speech recognition module to convert the user's voice input into text data. The input voice signal is processed by the speech recognition library, and the text data "My delivery is delayed, what's going on?" is generated.

[1511] Step 3:

[1512] The device uses an emotion engine to analyze and generate emotion data from the user's voice input. Elements such as tone, speed, and accent of the voice are analyzed to calculate emotion data such as dissatisfaction or frustration.

[1513] Step 4:

[1514] The device sends the text data and emotion data to the server using an HTTP POST request. Specifically, it sends the generated text data "Delivery is delayed, what's going on?" and emotion data "Unhappy" to the endpoint https: / / example.com / translate.

[1515] Step 5:

[1516] The server receives the HTTP POST request, retrieves the submitted text data and emotion data, and inputs this data into a deep learning-based translation model to generate a translation result that reflects the appropriate emotion. For example, the resulting English translation would be "The delivery is late, what is happening? How can we help to resolve this?"

[1517] Step 6:

[1518] The server returns the generated translation result to the terminal as an HTTP response. The server then sends data including the translation result to the terminal, which then receives the data.

[1519] Step 7:

[1520] The device displays the translation results from the server, and the following text appears on the device screen to the user: "The delivery is late, what is happening? How can we help to resolve this?"

[1521] This process allows users to receive responses that reflect their own emotions in real time, enabling smooth communication.

[1522] 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.

[1523] 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.

[1524] 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.

[1525] 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.

[1526] 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.

[1527] 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.

[1528] 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).

[1529] 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.

[1530] 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."

[1531] 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.

[1532] 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).

[1533] 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.

[1534] 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.

[1535] 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.

[1536] 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.

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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.

[1541] 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.

[1542] 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.

[1543] The following is further disclosed regarding the above embodiment.

[1544] (Claim 1)

[1545] means for receiving and converting user voice input into text;

[1546] means for transmitting the text data to a server;

[1547] a server that receives the text data and generates a translation result using a translation model;

[1548] means for returning the translation result to the terminal;

[1549] means for displaying the translation result on the terminal;

[1550] A system including:

[1551] (Claim 2)

[1552] 2. The system of claim 1, wherein the means for converting speech to text at the terminal uses a speech recognition module.

[1553] (Claim 3)

[1554] The system of claim 1, wherein the server uses a deep learning model as the translation model.

[1555] "Example 1"

[1556] (Claim 1)

[1557] means for receiving and converting user voice input into text;

[1558] means for utilizing a communication protocol to transmit the text data to a server;

[1559] a server that receives the text data and converts the speech into text using a highly accurate speech recognition module;

[1560] A means for inputting the text data into a translation model and generating a translation result using deep learning;

[1561] a means for using encrypted communication means to return the translation result to the terminal;

[1562] means for displaying and audibly notifying the translation result on the terminal;

[1563] A system including:

[1564] (Claim 2)

[1565] 10. The system of claim 1, wherein the terminal uses a cloud-based speech recognition module to convert speech to text.

[1566] (Claim 3)

[1567] The system according to claim 1, characterized in that the server uses a deep learning model as the translation model and generates translation results based on a generative AI model.

[1568] "Application Example 1"

[1569] (Claim 1)

[1570] means for receiving and converting user voice input into text;

[1571] means for transmitting the text data to a server;

[1572] a server that receives the text data and generates a translation result using a translation model;

[1573] means for returning the translation result to the terminal;

[1574] means for displaying the translation result on the terminal;

[1575] means for reading out the translation result aloud;

[1576] A system including:

[1577] (Claim 2)

[1578] 2. The system of claim 1, wherein the means for converting speech to text at the terminal uses a speech recognition module.

[1579] (Claim 3)

[1580] The system of claim 1, wherein the server uses a deep learning model as the translation model.

[1581] "Example 2: Combining Emotion Engines"

[1582] (Claim 1)

[1583] means for receiving and converting user voice input into text;

[1584] means for transmitting the text data and user emotion data to a server;

[1585] a means for receiving the text data and emotion data in a server and generating a translation result using a generative model;

[1586] means for returning the translation result to the terminal;

[1587] means for displaying the translation result on the terminal;

[1588] A system including:

[1589] (Claim 2)

[1590] 2. The system of claim 1, wherein the means for converting speech to text at the terminal uses a speech recognition module.

[1591] (Claim 3)

[1592] The system of claim 1, wherein the generative model in the server uses a deep learning model.

[1593] "Application example 2 when combining emotion engines"

[1594] New Claims

[1595] (Claim 1)

[1596] means for receiving and converting user voice input into text;

[1597] means for transmitting the text data and emotion data to a server;

[1598] a server that receives the text data and emotion data and generates a translation result using a translation model;

[1599] means for returning a translation result including the translation result to the terminal;

[1600] means for displaying the translation result on the terminal;

[1601] A system including:

[1602] (Claim 2)

[1603] 2. The system of claim 1, wherein the means for converting speech to text at the terminal uses a speech recognition module.

[1604] (Claim 3)

[1605] The system of claim 1, wherein the server uses a deep learning model as the translation model. [Explanation of symbols]

[1606] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving and converting user voice input into text; means for transmitting the text data to a server; a server that receives the text data and generates a translation result using a translation model; means for returning the translation result to the terminal; means for displaying the translation result on the terminal; A system including:

2. 2. The system of claim 1, wherein the means for converting speech to text at the terminal uses a speech recognition module.

3. The system of claim 1, wherein the server uses a deep learning model as the translation model.

Images