System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving user input data; means for pre-processing the input data; means for translating the pre-processed data; means for adjusting the translation based on usage; and means for providing the adjusted translation to a user.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] Conventional real-time translation systems require extensive instruction and prior knowledge for users to use the system properly. Furthermore, translation results often do not fully match the user's current situation or context, hindering smooth communication. Furthermore, user feedback is not fully reflected in system training, limiting improvements in translation accuracy. To address these issues, a system is needed that can preprocess user input data in real time and adjust translation results based on the current situation. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides a translation system for receiving input data from a user, preprocessing the input data, and translating the input data. Specifically, the system includes the following means:

[0006] A means of receiving user input data

[0007] means for preprocessing the input data;

[0008] a translation means for translating the preprocessed data;

[0009] means for adjusting the translation results based on usage conditions;

[0010] Means for providing the adjusted translation result to the user

[0011] This system can provide optimal translation results based on the user's situation and context, enabling smooth communication in real time, effectively resolving existing problems. Furthermore, by adding a means to receive user feedback data and update the translation model based on that analysis, the system can continuously learn and improve translation accuracy, providing users with a better translation experience.

[0012] "Means for receiving user input data" refers to a function that allows users to input data such as voice or text via smartphones or other devices and send that data to the system.

[0013] The "means for preprocessing the input data" is a function that removes noise and misrecognition from the received data (voice or text) and prepares it to improve the accuracy of the translation.

[0014] The "translation means for translating the pre-processed data" is an AI-based translation engine for converting the pre-processed data into another language.

[0015] The "means for adjusting the translation result based on the usage situation" is a function for appropriately correcting the translated text to suit the user's current situation and context.

[0016] The "means for providing the adjusted translation result to the user" is a function for displaying the adjusted translation result on the user's device and playing it back aloud as needed.

[0017] "Means for receiving user feedback data" refers to a function that allows users to input their evaluation of the translation results and suggestions for improvement, and then transmit that information to the system.

[0018] The "means for analyzing the feedback data" is a function for analyzing the feedback data received from users and using it to improve the system and translation accuracy.

[0019] The "means for updating the translation model based on the analyzed data" is a function that uses the analysis results to retrain the AI ​​translation model and improve the translation accuracy of the system. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] This invention relates to a system that can preprocess user input data in real time and adjust the translation results based on the current situation. Below, as a specific embodiment of the invention, the program processing and flow of the system will be explained in natural language with concrete examples.

[0042] System Program Processing

[0043] A means of receiving user input data

[0044] (User) Installs the smartphone app and prepares to input voice or text for translation.

[0045] (Terminal) Provides an interface that receives data provided by the user via voice input buttons or text input fields. If a user speaks, "Please tell me how to get to the airport," the terminal sends this voice data to the server.

[0046] means for preprocessing the input data;

[0047] (Server) Receives voice data sent from the terminal and converts the voice to text using a speech recognition algorithm. It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data. At this stage, clean text such as "Please tell me how to get to the airport" is obtained.

[0048] a translation means for translating the preprocessed data;

[0049] (Server) The preprocessed text data is input into the translation engine and translated into the specified language. The translation result is "How do I get to the airport?"

[0050] means for adjusting the translation results based on usage conditions;

[0051] (Server) Checks the translation result and adjusts it based on the user's current situation and context (GPS data, time zone, user profile, etc.). For example, if the user is already close to the airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation result more relevant to the local situation.

[0052] Means for providing the adjusted translation result to the user

[0053] (Server) Sends the adjusted translation results to the device.

[0054] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[0055] Specific examples

[0056] Example 1: Japanese to English translation

[0057] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[0058] 2. (Device) Sends voice data to the server.

[0059] 3. (Server) Convert the voice data into text data and perform preprocessing.

[0060] 4. (Server) Translate this as "How do I get to the airport?"

[0061] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[0062] 6. (Server) Sends the adjusted translation results to the device.

[0063] 7. (Device) The translation results are displayed to the user and audio is also played.

[0064] 8. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[0065] Example 2: Updating a model based on user feedback

[0066] 1. (User) After using the translation result "The airport is quite close. How do I get to the airport from here?", enter feedback within the app. Rate the translation as "helpful."

[0067] 2. (Server) Receive user feedback data.

[0068] 3. (Server) Analyze the feedback data and save it as training data.

[0069] 4. (Server) Retrain the translation model using the new feedback data to improve accuracy.

[0070] In this way, the present invention can provide more accurate and useful translation results by translating and adjusting the translation based on real-time input data from the user and by incorporating feedback from the user.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] (User) Opens the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[0074] Step 2:

[0075] (Device) The user's voice data is temporarily stored and immediately sent to the server.

[0076] Step 3:

[0077] (Server) Receives voice data from the terminal and converts the voice into text using a voice recognition algorithm.

[0078] Step 4:

[0079] (Server) Remove noise and misrecognitions from the text data and preprocess it into an appropriate format. This results in clean text: "Please tell me how to get to the airport."

[0080] Step 5:

[0081] (Server) The preprocessed text data is input into the "translation means" and translated into the specified language. The translation result is "How do I get to the airport?"

[0082] Step 6:

[0083] (Server) Check the user's current location and situation (e.g. GPS data and time zone) and adjust the translation result based on that context. For example, if the user is already near an airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?"

[0084] Step 7:

[0085] (Server) Sends the adjusted translation results to the device.

[0086] Step 8:

[0087] (Device) The received translation result is displayed to the user and played aloud if necessary. The message "The airport is quite close. How do I get to the airport from here?" is displayed and played aloud.

[0088] Step 9:

[0089] (User) Using the displayed translation results as a reference, ask a local person, "The airport is quite close. How do I get to the airport from here?"

[0090] Step 10:

[0091] (User) Enter feedback on the translation result within the app. For example, rate it as "The translation was helpful."

[0092] Step 11:

[0093] (Server) Receives feedback data from users.

[0094] Step 12:

[0095] (Server) Analyze the received feedback data and save it as learning data.

[0096] Step 13:

[0097] (Server) Retrain the translation model using new feedback data to improve translation accuracy.

[0098] In this way, processing progresses step by step, and a system can be realized that provides optimal real-time translation and support to users.

[0099] Example 1

[0100] 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."

[0101] Conventional translation systems have difficulty preprocessing user input data in real time and adjusting translation results based on the current situation. Furthermore, they are unable to effectively incorporate user feedback, resulting in problems such as reduced translation accuracy and usability. This invention aims to solve these problems and provide users with more accurate and context-appropriate translation results.

[0102] 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.

[0103] In this invention, the server includes means for receiving input data in the form of voice or text from a user, means for preprocessing the input data and converting it into text data using a speech recognition algorithm, means for removing unnecessary noise and misrecognition from the preprocessed text data, means for translating the cleaned text data, means for adjusting the translation result based on the user's location information, time zone, and variables, and means for providing the adjusted translation result to the user. This makes it possible to provide more accurate and current translation results based on the user's real-time input data.

[0104] "User" means an individual or organization that uses this system to input voice or text data and obtain translation results.

[0105] "Voice data" refers to digital data containing linguistic information spoken by a user.

[0106] "Text data" refers to data that includes language information in the form of a string of characters.

[0107] "Preprocessing" refers to the process of converting voice data into text data and then removing noise and misrecognized parts from the text data.

[0108] A "speech recognition algorithm" is a computational method and model for analyzing speech data and converting it into corresponding text data.

[0109] "Noise" refers to unnecessary information or misrecognized parts contained in the voice data or text data, which may reduce translation accuracy.

[0110] A "translator" is an engine or algorithm for converting pre-processed clean text data into a different language.

[0111] "User Location Information" means information about a User's current geographic location obtained using GPS or other means.

[0112] "User's time zone" is information based on the local time when the user uses the system.

[0113] "Feedback data" refers to data that includes users' evaluations and opinions on the translation results.

[0114] A "generative artificial intelligence model" is a computational model that has been trained using machine learning or deep learning to perform a specific task.

[0115] A "database" is a structured collection of data that stores feedback data and other relevant information and is used for analysis and learning.

[0116] "Adjustment" refers to the process of appropriately modifying translation results based on the user's location, time of day, and other variables.

[0117] "Providing means" refers to functions and modules for displaying the adjusted translation results to the user or playing them aloud.

[0118] This invention relates to a system that preprocesses user input data in real time and adjusts translation results based on the current situation. This invention allows users to obtain more accurate and context-appropriate translation results. Specific embodiments for implementing the invention are described below.

[0119] This system combines a speech recognition algorithm, a natural language processing algorithm, a translation engine, and a feedback analysis system. The hardware used includes a server, a terminal (e.g., a smartphone), and an internet connection. The software used includes a speech recognition API, a natural language processing library, a translation API, and a database system.

[0120] Hardware and Software Usage

[0121] (User) Installs the smartphone app, launches the app, and inputs the voice or text to be translated. When the user inputs "Please tell me how to get to the airport," the smartphone's microphone is used to capture the voice data.

[0122] (Device) Provides an interface for transmitting captured voice data to a server. The data is encrypted using a security protocol such as TLS. The device collects data provided by the user via voice input buttons or text input fields, formats it appropriately, and transmits it to the server via the Internet.

[0123] (Server) The received voice data is converted into text data using a speech recognition algorithm. At this stage, the voice is converted into text using, for example, the Google Cloud Speech-to-Text API. The converted text is then cleaned of unnecessary noise and misrecognitions to generate accurate text data. A natural language processing (NLP) system is used for preprocessing to obtain clean text such as "Please tell me how to get to the airport."

[0124] Next, the preprocessed text data is input into a translation engine and translated into the specified language, for example, using the DeepL API or another high-precision translation engine. The resulting translation is "How do I get to the airport?"

[0125] Additionally, the translation will be adjusted based on the user's current situation and context (GPS data, time of day, user profile, etc.). For example, if the user is already close to an airport, the translation will be adjusted to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation more relevant to the local situation.

[0126] The adjusted translation result is sent to the device, where it is displayed to the user and, if necessary, played aloud. The user receives the result, "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[0127] Specific examples

[0128] (Example 1) Translation from Japanese to English

[0129] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[0130] 2. (Device) Sends voice data to the server.

[0131] 3. (Server) Convert the voice data into text data and perform preprocessing.

[0132] 4. (Server) Translate this as "How do I get to the airport?"

[0133] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[0134] 6. (Server) Sends the adjusted translation results to the device.

[0135] 7. (Device) The translation results are displayed to the user and audio is also played.

[0136] 8. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[0137] (Example 2) Model update based on user feedback

[0138] 1. (User) After using the translation result "The airport is quite close. How do I get to the airport from here?", enter feedback within the app. Rate the translation as "helpful."

[0139] 2. (Server) Receive user feedback data.

[0140] 3. (Server) Analyze the feedback data and save it as training data.

[0141] 4. (Server) Retrain the generative AI model with new feedback data to improve accuracy.

[0142] In this way, the present invention translates and adjusts the translation based on real-time user input data, and can also incorporate user feedback to provide more accurate and useful translation results.

[0143] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0144] Step 1:

[0145] (User) opens the smartphone app, presses the voice input button, and says, "Please tell me how to get to the airport." At this time, the input data is the user's voice data, and this voice data is acquired by the device. Input data: User's voice data. Output data: Voice data stored on the device.

[0146] Step 2:

[0147] (Device) The acquired voice data is sent to the server via the internet. At this time, encryption protocols such as TLS are used to ensure data security. Input data: Voice data stored in the device. Output data: Encrypted voice data sent to the server.

[0148] Step 3:

[0149] (Server) Converts the received voice data into text data using a voice recognition algorithm. In this process, for example, a general voice recognition API is used to convert voice to text. Input data: Encrypted voice data. Output data: Converted text data.

[0150] Step 4:

[0151] (Server) A natural language processing algorithm is used to remove unnecessary noise and misrecognition from text data and generate accurate text data. For example, if "Please tell me how to get to the airport" is misrecognized, it is corrected to "Please tell me how to get to the airport." Input data: Converted text data. Output data: Preprocessed, clean text data.

[0152] Step 5:

[0153] (Server) The preprocessed text data is input into the translation engine and translated into the specified language. For example, a highly accurate translation API is used to obtain the translation result "How do I get to the airport?". Input data: Preprocessed, clean text data. Output data: Translated text data.

[0154] Step 6:

[0155] (Server) Adjust the translation result based on the user's location, time zone, and variables. For example, if the user is already close to the airport, adjust it to "The airport is quite close. How do I get to the airport from here?" This operation allows for translation results that are more in line with the context. Input data: Translated text data and the user's location and time zone data. Output data: Translated text data adjusted based on the context.

[0156] Step 7:

[0157] (Server) The adjusted translation results are sent to the terminal. Security is ensured during this process using encryption protocols such as TLS. Input data: Adjusted translation text data. Output data: Adjusted translation data sent to the terminal.

[0158] Step 8:

[0159] (Device) The received adjusted translation result is displayed to the user and played aloud if necessary. This gives the user the result "The airport is quite close. How do I get to the airport from here?" Input data: The sent adjusted translation data. Output data: The translation result displayed on the user's screen or played aloud.

[0160] Step 9:

[0161] (User) Enter feedback on the translation results within the app. Enter an evaluation such as "The translation was helpful" or "The translation was inappropriate." Input data: User feedback data. Output data: Feedback data stored on the device.

[0162] Step 10:

[0163] (Terminal) Feedback data from the user is sent to the server. Here too, data security is ensured using encryption protocols such as TLS. Input data: Feedback data stored in the terminal. Output data: Feedback data sent to the server.

[0164] Step 11:

[0165] (Server) Receives the feedback data, analyzes it, and stores it in a database. Then, it retrains the generative AI model based on the stored feedback data to improve the model's accuracy. Input data: Feedback data sent to the server. Output data: Updated generative AI model.

[0166] In this way, specific operations are performed at each step, and the system provides more appropriate translation results to the user.

[0167] (Application example 1)

[0168] 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."

[0169] Conventional translation systems have difficulty providing flexible translation that takes into account the user's current situation and profile information. In addition, in certain scenarios, such as food delivery, it is necessary to provide a better user experience by providing appropriate translation in real time. Therefore, there is a demand for a translation system that reflects local conditions and user history information.

[0170] 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.

[0171] In this invention, the server includes means for adjusting the translation result taking into account the user's profile data, means for improving the translation result based on the user's history data and current situation data, and means for converting the voice data into text data, thereby enabling more accurate real-time translation based on the local situation and the user's profile information.

[0172] "User input data" refers to voice and text data that a user provides to the system.

[0173] "Preprocessing" refers to the process of removing noise and misrecognition from input data and converting it into a format suitable for analysis.

[0174] The "translation means" is a means for translating the preprocessed text data into a specified language.

[0175] "Means for adjusting based on usage situation" refers to means for correcting and adjusting translation results based on the user's current situation and context.

[0176] "Means for providing to the user" refers to means for providing the adjusted translation results to the user by display or audio.

[0177] "User profile data" is data that includes historical information and current status information about a user.

[0178] "Feedback data" refers to data such as evaluations and comments about system usage provided by users.

[0179] The "means for updating the translation model" refers to a means for retraining the model to improve translation accuracy and applicability based on received feedback data.

[0180] The "means for converting voice data into text data" refers to a means for converting voice input into a string of characters using voice recognition technology.

[0181] This invention relates to a system that preprocesses voice or text data input by a user in real time and provides translation results. The actual system program and its processing content will be described in detail below.

[0182] System Overview

[0183] The system of the present invention includes the following major components:

[0184] 1. Terminal that receives user input data

[0185] 2. Server that preprocesses input data

[0186] 3. Server that translates preprocessed data

[0187] 4. Server that adjusts translation results based on usage

[0188] 5. Device that provides users with adjusted translation results

[0189] Hardware and Software

[0190] Device: A mobile communication device such as a smartphone or tablet. This device is equipped with a microphone for audio input and a speaker for display and audio output.

[0191] Server: A cloud server for speech recognition, pre-processing, translation, and tuning. This server is a computer with a powerful processor and sufficient memory.

[0192] Speech Recognition Library: A software library for speech recognition, such as speech_recognition.

[0193] Translation engine: A software library for translation, such as googletrans.

[0194] Generative AI model: An AI model that updates and trains the translation model based on user feedback and profile data.

[0195] System processing flow

[0196] 1. The user launches the "Food Delivery ChatBot" app and inputs a question via voice or text. The device then sends this input data to the server.

[0197] 2. The server converts the voice data into text data. It uses a speech recognition library (e.g., speech_recognition) to convert the voice data into text data.

[0198] 3. The server preprocesses the text data, removing unnecessary noise and misrecognitions to generate clean data.

[0199] 4. The server translates the preprocessed text data into the specified language using a translation engine (e.g., googletrans).

[0200] 5. Context-sensitive translation: Using user profile data (e.g., location, allergies, order history), the translation is tailored to the local context.

[0201] 6. The adjusted translation result is sent to the device and provided to the user as a display and audio.

[0202] Specific examples

[0203] Example 1: Proposing appropriate alternative menu items for food allergies

[0204] 1. User: "I'm allergic to a certain dish. Can you recommend an alternative menu item?"

[0205] 2. Terminal: Sends voice data to the server.

[0206] 3. Server: Converts voice data into text data and performs preprocessing.

[0207] 4. Server: Translate this to "Please tell me if there are any alternative dishes because I am allergic to a particular dish."

[0208] 5. Server: Adjust the translation to say, "Based on your allergy information, here are some recommended alternative menu items."

[0209] 6. Server: Sends the adjusted translation results to the device.

[0210] 7. Terminal: The translation results are displayed to the user and played aloud.

[0211] 8. User: Tell the restaurant staff, "Please tell me if there are any alternative dishes because I am allergic to a particular dish. Additionally, there are some allergy-free options nearby."

[0212] Prompt Sentence Examples

[0213] Please translate "I'm allergic to a certain dish. Can you recommend an alternative menu item?" into English. And this user is in Tokyo and has a nut allergy. Please add advice based on that information.

[0214] The above is a specific embodiment for carrying out the present invention. The present invention makes it possible to provide a more accurate translation that is in line with the current situation and profile information of the user.

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

[0216] Step 1:

[0217] A user launches the "Food Delivery ChatBot" app and enters a question by voice or text. Voice or text data is provided as input. This data is sent from the device to the server as output.

[0218] Step 2:

[0219] The terminal transmits the voice data input by the user to the server. It receives the voice data as input and transmits it as output to the server. Specific operations include capturing the voice with a microphone and transmitting the data to the server via a network.

[0220] Step 3:

[0221] The server uses a speech recognition library (e.g., speech_recognition) to convert the audio data into text data. It takes audio data as input and produces text data as output. The specific operations include applying a speech recognition algorithm to extract text from the audio waveform.

[0222] Step 4:

[0223] The server performs preprocessing to remove unnecessary noise and misrecognition from the text data. It receives text data as input and generates clean text data as output. Specific operations include text cleansing using regular expressions and filtering algorithms.

[0224] Step 5:

[0225] The server uses a translation engine (e.g., googletrans) to translate the preprocessed text data into the specified language. It takes clean text data as input and produces translated text data as output. Specific operations include calling a translation API to convert the text into another language.

[0226] Step 6:

[0227] The server adjusts the translation results based on usage. It references the user's profile data and local information to modify the translation results to fit the context. It takes translated text data and profile data as input and generates an adjusted translation result as output. Specific operations include supplementing and modifying the translated text based on location information, allergy data, etc.

[0228] Step 7:

[0229] The server sends the adjusted translation result to the terminal. It takes the adjusted translation data as input and sends it to the terminal as output. The specific operation includes transmitting the adjusted text via the network.

[0230] Step 8:

[0231] The device displays the translation results to the user and plays them aloud if necessary. It receives the adjusted translation data as input and displays and plays them aloud to the user as output. Specific operations include text display and speech synthesis using a speech synthesis library.

[0232] 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.

[0233] This invention relates to a system that can preprocess user input data in real time and adjust translation results based on the current situation. Furthermore, by combining an emotion engine that recognizes the user's emotions, translation results can be adapted to the user's emotions, providing more appropriate and effective real-time translation. Below, as a specific embodiment of the present invention, the program processing and flow of a system that combines an emotion engine will be explained in natural language, with specific examples.

[0234] System Program Processing

[0235] A means of receiving user input data

[0236] (User) Launches the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[0237] (Terminal) Receives data provided by the user via voice input buttons or text input fields and sends the voice data to the server.

[0238] means for preprocessing the input data;

[0239] (Server) Receives voice data sent from the device and converts the voice to text using a speech recognition algorithm. It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data. At this stage, clean text such as "Please tell me how to get to the airport" is obtained.

[0240] a translation means for translating the preprocessed data;

[0241] (Server) The preprocessed text data is input into the translation engine and translated into the specified language. The translation result is "How do I get to the airport?"

[0242] means for adjusting the translation results based on usage conditions;

[0243] (Server) Checks the translation result and adjusts it based on the user's current situation and context (GPS data, time zone, user profile, etc.). For example, if the user is already close to the airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation result more relevant to the local situation.

[0244] Means for providing the adjusted translation result to the user

[0245] (Server) Sends the adjusted translation results to the device.

[0246] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[0247] Emotion engine that recognizes user emotions

[0248] (Server) Operates an emotion engine that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the voice input by the user and the emotional expressions contained in the text to recognize the user's emotional state.

[0249] A means for further adjusting the translation result based on the emotion data recognized by the emotion engine.

[0250] (Server) The emotion engine further adjusts the translation results based on the emotional data it recognizes. For example, if the user is in a hurry, the translation results will be adjusted to be concise and easy to understand.

[0251] Specific examples

[0252] Example 1: Japanese to English translation and emotion recognition

[0253] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[0254] 2. (Device) Sends voice data to the server.

[0255] 3. (Server) Convert the voice data into text data and perform preprocessing.

[0256] 4. (Server) Translate this as "How do I get to the airport?"

[0257] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[0258] 6. (Server) The emotion engine analyzes the user's emotions, and if impatience or tension is detected, the translation result is further adjusted to be more concise.

[0259] 7. (Server) The final translation result is sent to the device.

[0260] 8. (Device) The translation results are displayed to the user and audio is also played.

[0261] 9. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[0262] Example 2: Updating emotion models based on user feedback

[0263] 1. (User) Enter feedback on the translation result within the app. For example, feedback including emotions such as "The translation was accurate and helpful" or "I wish it was a little gentler."

[0264] 2. (Server) Receives feedback data and analyzes it, including emotional data.

[0265] 3. (Server) Retrain the emotion recognition model using the new feedback data to improve accuracy.

[0266] In this way, this system, which combines an emotion engine, takes emotion into account in translation and adjusts it based on real-time input data from users, and by incorporating feedback from users, it is possible to provide more accurate and effective translation results.

[0267] The processing flow will be explained below.

[0268] Step 1:

[0269] (User) Opens the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[0270] Step 2:

[0271] (Device) The user's voice data is temporarily stored and immediately sent to the server.

[0272] Step 3:

[0273] (Server) Sends the voice data received from the terminal to a voice recognition algorithm and converts the voice into text.

[0274] Step 4:

[0275] (Server) Remove noise and misrecognitions from the text data and preprocess it into an appropriate format. This results in clean text: "Please tell me how to get to the airport."

[0276] Step 5:

[0277] (Server) The preprocessed text data is input into the translation engine and translated into the specified language (in this case, English). The translation result is "How do I get to the airport?"

[0278] Step 6:

[0279] (Server) Check the user's current location and situation (e.g. GPS data and time zone) and adjust the translation result based on that context. For example, if the user is already near an airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?"

[0280] Step 7:

[0281] (Server) Operates an emotion engine that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the voice input by the user and the emotional expressions contained in the text to recognize the user's emotional state.

[0282] Step 8:

[0283] (Server) Based on the emotional data recognized by the emotion engine, the translation result is further adjusted appropriately. If the user is in a hurry, the translation result is adjusted to be concise and quickly understandable. For example, "Please hurry. The airport is close. How do I get there?"

[0284] Step 9:

[0285] (Server) Sends the adjusted translation results to the device.

[0286] Step 10:

[0287] (Device) The received translation result is displayed to the user and played aloud if necessary. The message "Please hurry. The airport is closed. How do I get there?" is displayed and also played aloud.

[0288] Step 11:

[0289] (User) Using the displayed translation results as a reference, ask a local person, "Please hurry. The airport is close. How do I get there?"

[0290] Step 12:

[0291] (User) Enter feedback on the translation result within the app. For example, provide feedback that reflects specific emotions, such as "The translation was accurate and helpful" or "It would have been better if the wording was a little gentler."

[0292] Step 13:

[0293] (Server) Stores and analyzes feedback data received from users. Based on the feedback, it identifies areas that need improvement.

[0294] Step 14:

[0295] (Server) Retrain the emotion recognition model using new feedback data to improve the accuracy of the system.

[0296] In this way, through step-by-step processing, the system, which combines an emotion engine, determines emotions based on real-time user input data and provides accurate translation results according to the situation. Furthermore, by incorporating feedback from users, continuous improvement is possible.

[0297] Example 2

[0298] 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."

[0299] Conventional translation systems are required to translate user input data in a timely and accurate manner. However, because they do not take into account the user's emotions or usage context, the translation results are often inappropriate for actual usage scenarios. In addition, there is a lack of a mechanism for updating the translation model based on feedback. This makes it difficult to provide users with more appropriate and effective translation results.

[0300] 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.

[0301] In this invention, the server includes means for receiving user input data, means for preprocessing the input data, means for translating the preprocessed data, means for adjusting the translation result based on usage conditions, means for providing the adjusted translation result to the user, means for recognizing the user's emotions, and means for further adjusting the translation result based on the emotion data. This makes it possible to provide translation results that reflect the user's emotions and usage conditions.

[0302] "Means for receiving user input data" refers to a device or interface that has the function of incorporating information input by the user via voice or text into the system.

[0303] The "means for preprocessing the input data" refers to a device or algorithm that has the function of removing unnecessary noise and misrecognition from the input data and converting it into accurate text data.

[0304] The "translation means for translating the preprocessed data" refers to an engine or software for translating the preprocessed text data into another language.

[0305] The "means for adjusting the translation result based on usage" refers to a device or algorithm that has the ability to adjust the translated text based on the user's current situation or context.

[0306] The "means for providing the adjusted translation result to the user" refers to a device or interface that has the function of displaying or audibly providing the adjusted translation result to the user.

[0307] The "means for recognizing user emotions" refers to a device or algorithm that has the function of analyzing the user's voice tone and speed, and emotional expressions contained in the text, to identify the user's emotional state.

[0308] The "means for further adjusting the translation result based on the emotion data" refers to a device or algorithm that has the function of further appropriately adjusting the translation result based on the recognized emotion data.

[0309] The "means for receiving user feedback data" refers to a device or interface that has the function of incorporating user opinions and thoughts about the translation results into the system.

[0310] The "means for analyzing the feedback data" refers to a device or algorithm that has the function of analyzing the captured feedback data and extracting useful information.

[0311] The "means for updating the translation model based on the analyzed data" refers to a device or algorithm that has the function of improving and updating the translation model based on the analyzed feedback data.

[0312] "Voice data" refers to information input by voice by the user.

[0313] "Text data" refers to character information generated by converting voice data.

[0314] The present invention relates to a system that can preprocess user input data in real time and adjust translation results based on the current situation. Furthermore, by combining an emotion engine that recognizes the user's emotions, the translation results can be adapted to the user's emotions, providing more appropriate and effective real-time translation. Below, as a specific embodiment of the present invention, the program processing and flow of a system that combines an emotion engine will be explained in natural language, with specific examples.

[0315] A means of receiving user input data

[0316] (User) Launches the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[0317] (Device) Receives data provided by the user via voice input buttons or text input fields, and sends the voice data to a server. This process uses hardware called a smartphone and application software that provides voice input functionality.

[0318] means for preprocessing the input data;

[0319] (Server) Receives voice data sent from the device and converts the voice to text using a speech recognition algorithm (e.g., Google Cloud Speech-to-Text API). It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data. This process uses a high-performance server and a cloud service that provides speech recognition technology.

[0320] a translation means for translating the preprocessed data;

[0321] (Server) The preprocessed text data is input into a translation engine (e.g., Google Translate API) and translated into the specified language. The translation result, "How do I get to the airport?", is generated. This process also uses a high-performance server and a cloud platform that provides translation services.

[0322] means for adjusting the translation results based on usage conditions;

[0323] (Server) Checks the translation result and adjusts it based on the user's current situation and context (e.g., GPS data, time zone, user profile). For example, if the user is already close to the airport, adjusts the translation result to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation result more relevant to the local situation. At this stage, satellite communication technology is used to obtain GPS data, and technology is used to reference the user profile by linking with a database.

[0324] Means for providing the adjusted translation result to the user

[0325] (Server) Sends the adjusted translation results to the device.

[0326] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person. This process uses the smartphone's display and speaker.

[0327] Emotion engine that recognizes user emotions

[0328] (Server) Operates an emotion engine (e.g., emotion recognition algorithm) that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the user's voice input and the emotional expressions contained in the text to recognize the user's emotional state. This allows the system to respond more appropriately based on the user's current emotions.

[0329] means for further adjusting the translation result based on the emotion data;

[0330] (Server) Based on the emotional data recognized by the emotion engine, the translation results are further adjusted appropriately. For example, if the user is in a hurry, the translation results are adjusted to be concise and quickly understandable. This process uses advanced emotion analysis technology and algorithms to dynamically change the translation results.

[0331] Specific examples

[0332] Example 1: Japanese to English translation and emotion recognition

[0333] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[0334] 2. (Device) Sends voice data to the server.

[0335] 3. (Server) Convert the voice data into text data and perform preprocessing.

[0336] 4. (Server) Translate this as "How do I get to the airport?"

[0337] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[0338] 6. (Server) The emotion engine analyzes the user's emotions, and if impatience or tension is detected, the translation result is further adjusted to be more concise.

[0339] 7. (Server) The final translation result is sent to the device.

[0340] 8. (Device) The translation results are displayed to the user and audio is also played.

[0341] 9. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[0342] Prompt Sentence Examples

[0343] 1. What is the process for speech recognition using natural language processing (NLP) models?

[0344] 2. Describe the specific algorithm that converts audio data into text.

[0345] 3. How does the emotion recognition engine work and how does its data affect the translation results?

[0346] In this way, this system, which combines an emotion engine, takes emotion into account in translation and adjusts it based on real-time input data from users, and by incorporating feedback from users, it is possible to provide more accurate and effective translation results.

[0347] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0348] Step 1:

[0349] (User) Launches the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[0350] Input: User's voice data

[0351] Output: Audio data

[0352] Specific operation: The user operates the smartphone and taps the voice input button. At this point, voice input begins and the smartphone's built-in microphone collects the user's voice.

[0353] Step 2:

[0354] (Device) Receives user voice input and temporarily stores the voice data internally. Once the voice input is complete, the voice data is sent to the server.

[0355] Input: Audio data

[0356] Output: Audio data sent to the server

[0357] Specific operation: The terminal detects the completion of voice input and sends the voice data to the server via the network module.

[0358] Step 3:

[0359] (Server) Receives voice data sent from the device and converts the voice into text using a voice recognition algorithm (e.g., voice recognition API). It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data.

[0360] Input: Audio data sent to the server

[0361] Output: Clean text data

[0362] What happens: The server invokes a speech recognition algorithm to convert the speech data into text. It then applies a filtering algorithm to remove noise and misrecognitions, resulting in the clean text "Please tell me how to get to the airport."

[0363] Step 4:

[0364] (Server) The preprocessed text data is input into a translation engine (e.g., translation API) and translated into the specified language.

[0365] Input: clean text data

[0366] Output: Translated text data ("How do I get to the airport?")

[0367] Specific operation: The server calls the translation engine's API and converts the text data into the specified language. The translation engine returns the translation result to the server.

[0368] Step 5:

[0369] (Server) Checks the translation results and adjusts them based on the user's current situation and context (e.g., GPS data, time zone, user profile).

[0370] Input: translated text data, GPS data, time zone, user profile

[0371] Output: Adjusted translation result ("The airport is quite close. How do I get to the airport from here?")

[0372] How it works: The server obtains the user's current location (GPS data) and inputs it into the translation result adjustment logic, which then adjusts the resulting text appropriately and generates a new translation.

[0373] Step 6:

[0374] (Server) Sends the adjusted translation results to the device.

[0375] Input: Adjusted translation result

[0376] Output: Adjusted translation results sent to your device

[0377] Specific operation: The server generates the adjusted translation result and sends the data to the terminal via the network module.

[0378] Step 7:

[0379] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[0380] Input: Adjusted translation results sent from the server

[0381] Output: The translation results that are displayed and played back to the user

[0382] Specific operation: The translation result is displayed on the device display and the result is played back using the voice module.

[0383] Step 8:

[0384] (Server) Operates an emotion engine (e.g., emotion recognition algorithm) that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the voice input by the user and the emotional expressions contained in the text to recognize the user's emotional state.

[0385] Input: Audio data, text data

[0386] Output: User emotion data

[0387] How it works: The server invokes an emotion recognition algorithm and analyzes the voice and text data to identify the user's emotional state.

[0388] Step 9:

[0389] (Server) The emotion engine further adjusts the translation results based on the emotional data it recognizes. For example, if the user is in a hurry, the translation results will be adjusted to be concise and easy to understand.

[0390] Input: Adjusted translation results, user emotion data

[0391] Output: Translation results further adjusted based on user sentiment

[0392] Specific operation: Emotional data is used to make final adjustments to the translation results, resulting in a translation that is appropriate for the user's emotional state.

[0393] (Application example 2)

[0394] 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."

[0395] Conventional translation systems simply translate user input data, but are unable to provide translation results that reflect the user's current emotions or usage situation. Furthermore, the mechanisms for incorporating user feedback into the system were inadequate, making it difficult to continuously improve the quality of translation results. This can result in users not receiving optimal translations in real time, leading to a decline in user satisfaction. Furthermore, advertising and information provision systems also face the challenge of being unable to provide individualized responses that take emotions and context into account.

[0396] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0397] In this invention, the server includes means for receiving user input data, means for preprocessing the input data, means for translating the preprocessed data, means for adjusting the translation result based on usage status, means for providing the adjusted translation result to the user, means for recognizing the user's emotions using an emotion engine, and means for further adjusting the translation result based on the recognized emotion data. This enables the provision of more appropriate and effective real-time translation according to the user's emotions and current usage status. Furthermore, by further comprising means for receiving user feedback data, means for analyzing the feedback data, means for updating the translation model based on the analyzed data, and means for adjusting the translation result based on user context data, continuous quality improvement and individual response are possible.

[0398] "User Input Data" means any audio or text information provided by a User to the System.

[0399] "Preprocessing" is the process of removing noise and misrecognition from input data to generate accurate text data.

[0400] A "translation means" is an algorithm or program that converts preprocessed data into a specified language.

[0401] "Usage status" refers to contextual information such as the user's current location, time of day, and user profile.

[0402] "Adjustment" refers to the process of optimizing translation results based on usage and emotional data.

[0403] An "emotion engine" is a program or algorithm for analyzing a user's emotional state from their voice or text.

[0404] "Feedback data" refers to information on evaluations and opinions of users regarding translation results.

[0405] "Analysis" is the process of understanding data and deriving patterns and trends based on feedback and sentiment data.

[0406] A "translation model" is a training algorithm or dataset for converting input data into a different language.

[0407] "Context data" is information about the user's current situation and environment, and is used to optimize translation results.

[0408] System configuration

[0409] This system mainly consists of a server and terminals (smartphones, smart glasses, head-mounted displays, etc.). The server is equipped with a speech recognition algorithm, a translation engine, an emotion recognition engine, and a context adjustment engine, and uses these to process input data in real time. The terminals are devices equipped with a microphone, a display, and internet connectivity.

[0410] Program processing flow

[0411] The server processes the data using the following means:

[0412] 1. Means of receiving user input data

[0413] When a user inputs voice into the terminal, the voice data is collected by the microphone and sent to a server via the Internet.

[0414] 2. Means for preprocessing the input data

[0415] The server uses a speech recognition algorithm to convert the speech to text, filtering out unwanted noise and misrecognitions, resulting in clean text data.

[0416] 3. A translation means for translating the preprocessed data.

[0417] The server inputs the preprocessed text data into a translation engine and translates it into the specified language, for example, using the Google Translate API.

[0418] 4. Means for adjusting the translation results based on usage conditions

[0419] The server collects contextual data such as the user's location and time of day, and then adjusts the translation results based on this information. This step is handled by the context adjustment engine.

[0420] 5. Means for providing the adjusted translation results to users

[0421] The server then sends the adjusted translation results to the terminal, which notifies the user by displaying the results in text and playing them aloud.

[0422] 6. Means of recognizing user emotions using an emotion engine

[0423] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions from voice and text data.

[0424] 7. Means for further adjusting the translation result based on the recognized emotion data

[0425] The server uses emotional data to further optimize the translation results, such as providing more concise information if the user is nervous, or more detailed information if the user is relaxed.

[0426] Hardware and software used

[0427] Hardware: Devices with microphones, displays, and internet connectivity (smartphones, smart glasses, head-mounted displays, etc.)

[0428] Software: Google Speech-to-Text API, Google Translate API, IBM Watson Tone Analyzer

[0429] Specific examples

[0430] Prompt Sentence Examples

[0431] User: "What are the latest sales?"

[0432] Voice data received by the server: "Tell me about the latest sales."

[0433] 1. Text after speech recognition:

[0434] "Tell me the latest sales information"

[0435] 2. Translated English text:

[0436] "Tell me the latest sale information"

[0437] 3. Contextual adjustment:

[0438] Customize based on nearby stores:

[0439] "You are near our store, check out our latest sale on electronics!"

[0440] 4. Emotion recognition:

[0441] User Emotions: Stressed

[0442] Adjusted ad text:

[0443] "Relax and enjoy our exclusive discounts on spa packages!"

[0444] 5. Final Ad Delivery:

[0445] The text "Relax and enjoy our exclusive discounts on spa packages!" is displayed on the smart glasses' display and played aloud.

[0446] In this way, the present invention realizes a system that adjusts translation results based on the user's emotions and context, and provides optimal information in real time.

[0447] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0448] Step 1:

[0449] The user inputs voice into the device. Specifically, when the user says, "Tell me about the latest sales," the device's microphone collects this voice and converts it into digital voice data. The input is the user's voice data, and this voice data is sent to the server via the Internet.

[0450] Step 2:

[0451] The server converts the received voice data into text data using a speech recognition algorithm (such as the Google Speech-to-Text API). It removes noise and misrecognition to generate accurate text data. The input is voice data, and the output is preprocessed text data.

[0452] Step 3:

[0453] The server inputs the preprocessed text data into a translation engine (such as Google Translate API) and translates it into the specified language. The input is the preprocessed text data, and the output is the translated text data. For example, "Tell me the latest sale information" is translated into "Tell me the latest sale information."

[0454] Step 4:

[0455] The server collects context data such as the user's location and time of day, and adjusts the translation results based on this. The input is the translated text data and context data, and the output is text data adjusted based on the context. For example, the translation result might be adjusted to "You are near our store, check out our latest sale on electronics!"

[0456] Step 5:

[0457] The server uses an emotion recognition engine (such as IBM Watson Tone Analyzer) to analyze the user's emotions from the input voice or text data. The input is voice data or text data, and the output is data that indicates the user's emotional state.

[0458] Step 6:

[0459] The server further adjusts the translation results based on the emotional data. For example, if the user is stressed, the information is made more concise, and if the user is relaxed, the information is made more detailed. The input is text data that has been adjusted based on the emotional data and context, and the output is the final adjusted text data.

[0460] Step 7:

[0461] The server sends the final adjusted translation result to the device. The device uses the received data to display text and play audio. The input is the final adjusted text data, and the output is information provided to the user visually and audibly. Specifically, the text "Relax and enjoy our exclusive discounts on spa packages!" is displayed on the smart glasses' display and played aloud.

[0462] This series of processing steps allows users to receive optimal translation results that are in line with emotion and context in real time.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] [Second embodiment]

[0467] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0468] 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.

[0469] 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).

[0470] 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.

[0471] 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.

[0472] 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).

[0473] 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.

[0474] 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.

[0475] 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.

[0476] 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.

[0477] 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.

[0478] 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."

[0479] This invention relates to a system that can preprocess user input data in real time and adjust the translation results based on the current situation. Below, as a specific embodiment of the invention, the program processing and flow of the system will be explained in natural language with concrete examples.

[0480] System Program Processing

[0481] A means of receiving user input data

[0482] (User) Installs the smartphone app and prepares to input voice or text for translation.

[0483] (Terminal) Provides an interface that receives data provided by the user via voice input buttons or text input fields. If a user speaks, "Please tell me how to get to the airport," the terminal sends this voice data to the server.

[0484] means for preprocessing the input data;

[0485] (Server) Receives voice data sent from the terminal and converts the voice to text using a speech recognition algorithm. It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data. At this stage, clean text such as "Please tell me how to get to the airport" is obtained.

[0486] a translation means for translating the preprocessed data;

[0487] (Server) The preprocessed text data is input into the translation engine and translated into the specified language. The translation result is "How do I get to the airport?"

[0488] means for adjusting the translation results based on usage conditions;

[0489] (Server) Checks the translation result and adjusts it based on the user's current situation and context (GPS data, time zone, user profile, etc.). For example, if the user is already close to the airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation result more relevant to the local situation.

[0490] Means for providing the adjusted translation result to the user

[0491] (Server) Sends the adjusted translation results to the device.

[0492] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[0493] Specific examples

[0494] Example 1: Japanese to English translation

[0495] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[0496] 2. (Device) Sends voice data to the server.

[0497] 3. (Server) Convert the voice data into text data and perform preprocessing.

[0498] 4. (Server) Translate this as "How do I get to the airport?"

[0499] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[0500] 6. (Server) Sends the adjusted translation results to the device.

[0501] 7. (Device) The translation results are displayed to the user and audio is also played.

[0502] 8. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[0503] Example 2: Updating a model based on user feedback

[0504] 1. (User) After using the translation result "The airport is quite close. How do I get to the airport from here?", enter feedback within the app. Rate the translation as "helpful."

[0505] 2. (Server) Receive user feedback data.

[0506] 3. (Server) Analyze the feedback data and save it as training data.

[0507] 4. (Server) Retrain the translation model using the new feedback data to improve accuracy.

[0508] In this way, the present invention can provide more accurate and useful translation results by translating and adjusting the translation based on real-time input data from the user and by incorporating feedback from the user.

[0509] The processing flow will be explained below.

[0510] Step 1:

[0511] (User) Opens the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[0512] Step 2:

[0513] (Device) The user's voice data is temporarily stored and immediately sent to the server.

[0514] Step 3:

[0515] (Server) Receives voice data from the terminal and converts the voice into text using a voice recognition algorithm.

[0516] Step 4:

[0517] (Server) Remove noise and misrecognitions from the text data and preprocess it into an appropriate format. This results in clean text: "Please tell me how to get to the airport."

[0518] Step 5:

[0519] (Server) The preprocessed text data is input into the "translation means" and translated into the specified language. The translation result is "How do I get to the airport?"

[0520] Step 6:

[0521] (Server) Check the user's current location and situation (e.g. GPS data and time zone) and adjust the translation result based on that context. For example, if the user is already near an airport, adjust the translation to "The airport is quite close. How do I get to the airport from here?"

[0522] Step 7:

[0523] (Server) Sends the adjusted translation results to the device.

[0524] Step 8:

[0525] (Device) The received translation result is displayed to the user and played aloud if necessary. The message "The airport is quite close. How do I get to the airport from here?" is displayed and played aloud.

[0526] Step 9:

[0527] (User) Using the displayed translation results as a reference, ask a local person, "The airport is quite close. How do I get to the airport from here?"

[0528] Step 10:

[0529] (User) Enter feedback on the translation result within the app. For example, rate it as "The translation was helpful."

[0530] Step 11:

[0531] (Server) Receives feedback data from users.

[0532] Step 12:

[0533] (Server) Analyze the received feedback data and save it as learning data.

[0534] Step 13:

[0535] (Server) Retrain the translation model using new feedback data to improve translation accuracy.

[0536] In this way, processing progresses step by step, and a system can be realized that provides optimal real-time translation and support to users.

[0537] Example 1

[0538] 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."

[0539] Conventional translation systems have difficulty preprocessing user input data in real time and adjusting translation results based on the current situation. Furthermore, they are unable to effectively incorporate user feedback, resulting in problems such as reduced translation accuracy and usability. This invention aims to solve these problems and provide users with more accurate and context-appropriate translation results.

[0540] 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.

[0541] In this invention, the server includes means for receiving input data in the form of voice or text from a user, means for preprocessing the input data and converting it into text data using a speech recognition algorithm, means for removing unnecessary noise and misrecognition from the preprocessed text data, means for translating the cleaned text data, means for adjusting the translation result based on the user's location information, time zone, and variables, and means for providing the adjusted translation result to the user. This makes it possible to provide more accurate and current translation results based on the user's real-time input data.

[0542] "User" means an individual or organization that uses this system to input voice or text data and obtain translation results.

[0543] "Voice data" refers to digital data containing linguistic information spoken by a user.

[0544] "Text data" refers to data that includes language information in the form of a string of characters.

[0545] "Preprocessing" refers to the process of converting voice data into text data and then removing noise and misrecognized parts from the text data.

[0546] A "speech recognition algorithm" is a computational method and model for analyzing speech data and converting it into corresponding text data.

[0547] "Noise" refers to unnecessary information or misrecognized parts contained in the voice data or text data, which may reduce translation accuracy.

[0548] A "translator" is an engine or algorithm for converting pre-processed clean text data into a different language.

[0549] "User Location Information" means information about a User's current geographic location obtained using GPS or other means.

[0550] "User's time zone" is information based on the local time when the user uses the system.

[0551] "Feedback data" refers to data that includes users' evaluations and opinions on the translation results.

[0552] A "generative artificial intelligence model" is a computational model that has been trained using machine learning or deep learning to perform a specific task.

[0553] A "database" is a structured collection of data that stores feedback data and other relevant information and is used for analysis and learning.

[0554] "Adjustment" refers to the process of appropriately modifying translation results based on the user's location, time of day, and other variables.

[0555] "Providing means" refers to functions and modules for displaying the adjusted translation results to the user or playing them aloud.

[0556] This invention relates to a system that preprocesses user input data in real time and adjusts translation results based on the current situation. This invention allows users to obtain more accurate and context-appropriate translation results. Specific embodiments for implementing the invention are described below.

[0557] This system combines a speech recognition algorithm, a natural language processing algorithm, a translation engine, and a feedback analysis system. The hardware used includes a server, a terminal (e.g., a smartphone), and an internet connection. The software used includes a speech recognition API, a natural language processing library, a translation API, and a database system.

[0558] Hardware and Software Usage

[0559] (User) Installs the smartphone app, launches the app, and inputs the voice or text to be translated. When the user inputs "Please tell me how to get to the airport," the smartphone's microphone is used to capture the voice data.

[0560] (Device) Provides an interface for transmitting captured voice data to a server. The data is encrypted using a security protocol such as TLS. The device collects data provided by the user via voice input buttons or text input fields, formats it appropriately, and transmits it to the server via the Internet.

[0561] (Server) The received voice data is converted into text data using a speech recognition algorithm. At this stage, the voice is converted into text using, for example, the Google Cloud Speech-to-Text API. The converted text is then cleaned of unnecessary noise and misrecognitions to generate accurate text data. A natural language processing (NLP) system is used for preprocessing to obtain clean text such as "Please tell me how to get to the airport."

[0562] Next, the preprocessed text data is input into a translation engine and translated into the specified language, for example, using the DeepL API or another high-precision translation engine. The resulting translation is "How do I get to the airport?"

[0563] Additionally, the translation will be adjusted based on the user's current situation and context (GPS data, time of day, user profile, etc.). For example, if the user is already close to an airport, the translation will be adjusted to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation more relevant to the local situation.

[0564] The adjusted translation result is sent to the device, where it is displayed to the user and, if necessary, played aloud. The user receives the result, "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[0565] Specific examples

[0566] (Example 1) Translation from Japanese to English

[0567] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[0568] 2. (Device) Sends voice data to the server.

[0569] 3. (Server) Convert the voice data into text data and perform preprocessing.

[0570] 4. (Server) Translate this as "How do I get to the airport?"

[0571] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[0572] 6. (Server) Sends the adjusted translation results to the device.

[0573] 7. (Device) The translation results are displayed to the user and audio is also played.

[0574] 8. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[0575] (Example 2) Model update based on user feedback

[0576] 1. (User) After using the translation result "The airport is quite close. How do I get to the airport from here?", enter feedback within the app. Rate the translation as "helpful."

[0577] 2. (Server) Receive user feedback data.

[0578] 3. (Server) Analyze the feedback data and save it as training data.

[0579] 4. (Server) Retrain the generative AI model with new feedback data to improve accuracy.

[0580] In this way, the present invention translates and adjusts the translation based on real-time user input data, and can also incorporate user feedback to provide more accurate and useful translation results.

[0581] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0582] Step 1:

[0583] (User) opens the smartphone app, presses the voice input button, and says, "Please tell me how to get to the airport." At this time, the input data is the user's voice data, and this voice data is acquired by the device. Input data: User's voice data. Output data: Voice data stored on the device.

[0584] Step 2:

[0585] (Device) The acquired voice data is sent to the server via the internet. At this time, encryption protocols such as TLS are used to ensure data security. Input data: Voice data stored in the device. Output data: Encrypted voice data sent to the server.

[0586] Step 3:

[0587] (Server) Converts the received voice data into text data using a voice recognition algorithm. In this process, for example, a general voice recognition API is used to convert voice to text. Input data: Encrypted voice data. Output data: Converted text data.

[0588] Step 4:

[0589] (Server) A natural language processing algorithm is used to remove unnecessary noise and misrecognition from text data and generate accurate text data. For example, if "Please tell me how to get to the airport" is misrecognized, it is corrected to "Please tell me how to get to the airport." Input data: Converted text data. Output data: Preprocessed, clean text data.

[0590] Step 5:

[0591] (Server) The preprocessed text data is input into the translation engine and translated into the specified language. For example, a highly accurate translation API is used to obtain the translation result "How do I get to the airport?". Input data: Preprocessed, clean text data. Output data: Translated text data.

[0592] Step 6:

[0593] (Server) Adjust the translation result based on the user's location, time zone, and variables. For example, if the user is already close to the airport, adjust it to "The airport is quite close. How do I get to the airport from here?" This operation allows for translation results that are more in line with the context. Input data: Translated text data and the user's location and time zone data. Output data: Translated text data adjusted based on the context.

[0594] Step 7:

[0595] (Server) The adjusted translation results are sent to the terminal. Security is ensured during this process using encryption protocols such as TLS. Input data: Adjusted translation text data. Output data: Adjusted translation data sent to the terminal.

[0596] Step 8:

[0597] (Device) The received adjusted translation result is displayed to the user and played aloud if necessary. This gives the user the result "The airport is quite close. How do I get to the airport from here?" Input data: The sent adjusted translation data. Output data: The translation result displayed on the user's screen or played aloud.

[0598] Step 9:

[0599] (User) Enter feedback on the translation results within the app. Enter an evaluation such as "The translation was helpful" or "The translation was inappropriate." Input data: User feedback data. Output data: Feedback data stored on the device.

[0600] Step 10:

[0601] (Terminal) Feedback data from the user is sent to the server. Here too, data security is ensured using encryption protocols such as TLS. Input data: Feedback data stored in the terminal. Output data: Feedback data sent to the server.

[0602] Step 11:

[0603] (Server) Receives the feedback data, analyzes it, and stores it in a database. Then, it retrains the generative AI model based on the stored feedback data to improve the model's accuracy. Input data: Feedback data sent to the server. Output data: Updated generative AI model.

[0604] In this way, specific operations are performed at each step, and the system provides more appropriate translation results to the user.

[0605] (Application example 1)

[0606] 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."

[0607] Conventional translation systems have difficulty providing flexible translation that takes into account the user's current situation and profile information. In addition, in certain scenarios, such as food delivery, it is necessary to provide a better user experience by providing appropriate translation in real time. Therefore, there is a demand for a translation system that reflects local conditions and user history information.

[0608] 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.

[0609] In this invention, the server includes means for adjusting the translation result taking into account the user's profile data, means for improving the translation result based on the user's history data and current situation data, and means for converting the voice data into text data, thereby enabling more accurate real-time translation based on the local situation and the user's profile information.

[0610] "User input data" refers to voice and text data that a user provides to the system.

[0611] "Preprocessing" refers to the process of removing noise and misrecognition from input data and converting it into a format suitable for analysis.

[0612] The "translation means" is a means for translating the preprocessed text data into a specified language.

[0613] "Means for adjusting based on usage situation" refers to means for correcting and adjusting translation results based on the user's current situation and context.

[0614] "Means for providing to the user" refers to means for providing the adjusted translation results to the user by display or audio.

[0615] "User profile data" is data that includes historical information and current status information about a user.

[0616] "Feedback data" refers to data such as evaluations and comments about system usage provided by users.

[0617] The "means for updating the translation model" refers to a means for retraining the model to improve translation accuracy and applicability based on received feedback data.

[0618] The "means for converting voice data into text data" refers to a means for converting voice input into a string of characters using voice recognition technology.

[0619] This invention relates to a system that preprocesses voice or text data input by a user in real time and provides translation results. The actual system program and its processing content will be described in detail below.

[0620] System Overview

[0621] The system of the present invention includes the following major components:

[0622] 1. Terminal that receives user input data

[0623] 2. Server that preprocesses input data

[0624] 3. Server that translates preprocessed data

[0625] 4. Server that adjusts translation results based on usage

[0626] 5. Device that provides users with adjusted translation results

[0627] Hardware and Software

[0628] Device: A mobile communication device such as a smartphone or tablet. This device is equipped with a microphone for audio input and a speaker for display and audio output.

[0629] Server: A cloud server for speech recognition, pre-processing, translation, and tuning. This server is a computer with a powerful processor and sufficient memory.

[0630] Speech Recognition Library: A software library for speech recognition, such as speech_recognition.

[0631] Translation engine: A software library for translation, such as googletrans.

[0632] Generative AI model: An AI model that updates and trains the translation model based on user feedback and profile data.

[0633] System processing flow

[0634] 1. The user launches the "Food Delivery ChatBot" app and inputs a question via voice or text. The device then sends this input data to the server.

[0635] 2. The server converts the voice data into text data. It uses a speech recognition library (e.g., speech_recognition) to convert the voice data into text data.

[0636] 3. The server preprocesses the text data, removing unnecessary noise and misrecognitions to generate clean data.

[0637] 4. The server translates the preprocessed text data into the specified language using a translation engine (e.g., googletrans).

[0638] 5. Context-sensitive translation: Using user profile data (e.g., location, allergies, order history), the translation is tailored to the local context.

[0639] 6. The adjusted translation result is sent to the device and provided to the user as a display and audio.

[0640] Specific examples

[0641] Example 1: Proposing appropriate alternative menu items for food allergies

[0642] 1. User: "I'm allergic to a certain dish. Can you recommend an alternative menu item?"

[0643] 2. Terminal: Sends voice data to the server.

[0644] 3. Server: Converts voice data into text data and performs preprocessing.

[0645] 4. Server: Translate this to "Please tell me if there are any alternative dishes because I am allergic to a particular dish."

[0646] 5. Server: Adjust the translation to say, "Based on your allergy information, here are some recommended alternative menu items."

[0647] 6. Server: Sends the adjusted translation results to the device.

[0648] 7. Terminal: The translation results are displayed to the user and played aloud.

[0649] 8. User: Tell the restaurant staff, "Please tell me if there are any alternative dishes because I am allergic to a particular dish. Additionally, there are some allergy-free options nearby."

[0650] Prompt Sentence Examples

[0651] Please translate "I'm allergic to a certain dish. Can you recommend an alternative menu item?" into English. And this user is in Tokyo and has a nut allergy. Please add advice based on that information.

[0652] The above is a specific embodiment for carrying out the present invention. The present invention makes it possible to provide a more accurate translation that is in line with the current situation and profile information of the user.

[0653] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0654] Step 1:

[0655] A user launches the "Food Delivery ChatBot" app and enters a question by voice or text. Voice or text data is provided as input. This data is sent from the device to the server as output.

[0656] Step 2:

[0657] The terminal transmits the voice data input by the user to the server. It receives the voice data as input and transmits it as output to the server. Specific operations include capturing the voice with a microphone and transmitting the data to the server via a network.

[0658] Step 3:

[0659] The server uses a speech recognition library (e.g., speech_recognition) to convert the audio data into text data. It takes audio data as input and produces text data as output. The specific operations include applying a speech recognition algorithm to extract text from the audio waveform.

[0660] Step 4:

[0661] The server performs preprocessing to remove unnecessary noise and misrecognition from the text data. It receives text data as input and generates clean text data as output. Specific operations include text cleansing using regular expressions and filtering algorithms.

[0662] Step 5:

[0663] The server uses a translation engine (e.g., googletrans) to translate the preprocessed text data into the specified language. It takes clean text data as input and produces translated text data as output. Specific operations include calling a translation API to convert the text into another language.

[0664] Step 6:

[0665] The server adjusts the translation results based on usage. It references the user's profile data and local information to modify the translation results to fit the context. It takes translated text data and profile data as input and generates an adjusted translation result as output. Specific operations include supplementing and modifying the translated text based on location information, allergy data, etc.

[0666] Step 7:

[0667] The server sends the adjusted translation result to the terminal. It takes the adjusted translation data as input and sends it to the terminal as output. The specific operation includes transmitting the adjusted text via the network.

[0668] Step 8:

[0669] The device displays the translation results to the user and plays them aloud if necessary. It receives the adjusted translation data as input and displays and plays them aloud to the user as output. Specific operations include text display and speech synthesis using a speech synthesis library.

[0670] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0671] This invention relates to a system that can preprocess user input data in real time and adjust translation results based on the current situation. Furthermore, by combining an emotion engine that recognizes the user's emotions, translation results can be adapted to the user's emotions, providing more appropriate and effective real-time translation. Below, as a specific embodiment of the present invention, the program processing and flow of a system that combines an emotion engine will be explained in natural language, with specific examples.

[0672] System Program Processing

[0673] A means of receiving user input data

[0674] (User) Launches the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[0675] (Terminal) Receives data provided by the user via voice input buttons or text input fields and sends the voice data to the server.

[0676] means for preprocessing the input data;

[0677] (Server) Receives voice data sent from the device and converts the voice to text using a speech recognition algorithm. It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data. At this stage, clean text such as "Please tell me how to get to the airport" is obtained.

[0678] a translation means for translating the preprocessed data;

[0679] (Server) The preprocessed text data is input into the translation engine and translated into the specified language. The translation result is "How do I get to the airport?"

[0680] means for adjusting the translation results based on usage conditions;

[0681] (Server) Checks the translation result and adjusts it based on the user's current situation and context (GPS data, time zone, user profile, etc.). For example, if the user is already close to the airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation result more relevant to the local situation.

[0682] Means for providing the adjusted translation result to the user

[0683] (Server) Sends the adjusted translation results to the device.

[0684] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[0685] Emotion engine that recognizes user emotions

[0686] (Server) Operates an emotion engine that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the voice input by the user and the emotional expressions contained in the text to recognize the user's emotional state.

[0687] A means for further adjusting the translation result based on the emotion data recognized by the emotion engine.

[0688] (Server) The emotion engine further adjusts the translation results based on the emotional data it recognizes. For example, if the user is in a hurry, the translation results will be adjusted to be concise and easy to understand.

[0689] Specific examples

[0690] Example 1: Japanese to English translation and emotion recognition

[0691] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[0692] 2. (Device) Sends voice data to the server.

[0693] 3. (Server) Convert the voice data into text data and perform preprocessing.

[0694] 4. (Server) Translate this as "How do I get to the airport?"

[0695] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[0696] 6. (Server) The emotion engine analyzes the user's emotions, and if impatience or tension is detected, the translation result is further adjusted to be more concise.

[0697] 7. (Server) The final translation result is sent to the device.

[0698] 8. (Device) The translation results are displayed to the user and audio is also played.

[0699] 9. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[0700] Example 2: Updating emotion models based on user feedback

[0701] 1. (User) Enter feedback on the translation result within the app. For example, feedback including emotions such as "The translation was accurate and helpful" or "I wish it was a little gentler."

[0702] 2. (Server) Receives feedback data and analyzes it, including emotional data.

[0703] 3. (Server) Retrain the emotion recognition model using the new feedback data to improve accuracy.

[0704] In this way, this system, which combines an emotion engine, takes emotion into account in translation and adjusts it based on real-time input data from users, and by incorporating feedback from users, it is possible to provide more accurate and effective translation results.

[0705] The processing flow will be explained below.

[0706] Step 1:

[0707] (User) Opens the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[0708] Step 2:

[0709] (Device) The user's voice data is temporarily stored and immediately sent to the server.

[0710] Step 3:

[0711] (Server) Sends the voice data received from the terminal to a voice recognition algorithm and converts the voice into text.

[0712] Step 4:

[0713] (Server) Remove noise and misrecognitions from the text data and preprocess it into an appropriate format. This results in clean text: "Please tell me how to get to the airport."

[0714] Step 5:

[0715] (Server) The preprocessed text data is input into the translation engine and translated into the specified language (in this case, English). The translation result is "How do I get to the airport?"

[0716] Step 6:

[0717] (Server) Check the user's current location and situation (e.g. GPS data and time zone) and adjust the translation result based on that context. For example, if the user is already near an airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?"

[0718] Step 7:

[0719] (Server) Operates an emotion engine that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the voice input by the user and the emotional expressions contained in the text to recognize the user's emotional state.

[0720] Step 8:

[0721] (Server) Based on the emotional data recognized by the emotion engine, the translation result is further adjusted appropriately. If the user is in a hurry, the translation result is adjusted to be concise and quickly understandable. For example, "Please hurry. The airport is close. How do I get there?"

[0722] Step 9:

[0723] (Server) Sends the adjusted translation results to the device.

[0724] Step 10:

[0725] (Device) The received translation result is displayed to the user and played aloud if necessary. The message "Please hurry. The airport is closed. How do I get there?" is displayed and also played aloud.

[0726] Step 11:

[0727] (User) Using the displayed translation results as a reference, ask a local person, "Please hurry. The airport is close. How do I get there?"

[0728] Step 12:

[0729] (User) Enter feedback on the translation result within the app. For example, provide feedback that reflects specific emotions, such as "The translation was accurate and helpful" or "It would have been better if the wording was a little gentler."

[0730] Step 13:

[0731] (Server) Stores and analyzes feedback data received from users. Based on the feedback, it identifies areas that need improvement.

[0732] Step 14:

[0733] (Server) Retrain the emotion recognition model using new feedback data to improve the accuracy of the system.

[0734] In this way, through step-by-step processing, the system, which combines an emotion engine, determines emotions based on real-time user input data and provides accurate translation results according to the situation. Furthermore, by incorporating feedback from users, continuous improvement is possible.

[0735] Example 2

[0736] 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."

[0737] Conventional translation systems are required to translate user input data in a timely and accurate manner. However, because they do not take into account the user's emotions or usage context, the translation results are often inappropriate for actual usage scenarios. In addition, there is a lack of a mechanism for updating the translation model based on feedback. This makes it difficult to provide users with more appropriate and effective translation results.

[0738] 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.

[0739] In this invention, the server includes means for receiving user input data, means for preprocessing the input data, means for translating the preprocessed data, means for adjusting the translation result based on usage conditions, means for providing the adjusted translation result to the user, means for recognizing the user's emotions, and means for further adjusting the translation result based on the emotion data. This makes it possible to provide translation results that reflect the user's emotions and usage conditions.

[0740] "Means for receiving user input data" refers to a device or interface that has the function of incorporating information input by the user via voice or text into the system.

[0741] The "means for preprocessing the input data" refers to a device or algorithm that has the function of removing unnecessary noise and misrecognition from the input data and converting it into accurate text data.

[0742] The "translation means for translating the preprocessed data" refers to an engine or software for translating the preprocessed text data into another language.

[0743] The "means for adjusting the translation result based on usage" refers to a device or algorithm that has the ability to adjust the translated text based on the user's current situation or context.

[0744] The "means for providing the adjusted translation result to the user" refers to a device or interface that has the function of displaying or audibly providing the adjusted translation result to the user.

[0745] The "means for recognizing user emotions" refers to a device or algorithm that has the function of analyzing the user's voice tone and speed, and emotional expressions contained in the text, to identify the user's emotional state.

[0746] The "means for further adjusting the translation result based on the emotion data" refers to a device or algorithm that has the function of further appropriately adjusting the translation result based on the recognized emotion data.

[0747] The "means for receiving user feedback data" refers to a device or interface that has the function of incorporating user opinions and thoughts about the translation results into the system.

[0748] The "means for analyzing the feedback data" refers to a device or algorithm that has the function of analyzing the captured feedback data and extracting useful information.

[0749] The "means for updating the translation model based on the analyzed data" refers to a device or algorithm that has the function of improving and updating the translation model based on the analyzed feedback data.

[0750] "Voice data" refers to information input by voice by the user.

[0751] "Text data" refers to character information generated by converting voice data.

[0752] The present invention relates to a system that can preprocess user input data in real time and adjust translation results based on the current situation. Furthermore, by combining an emotion engine that recognizes the user's emotions, the translation results can be adapted to the user's emotions, providing more appropriate and effective real-time translation. Below, as a specific embodiment of the present invention, the program processing and flow of a system that combines an emotion engine will be explained in natural language, with specific examples.

[0753] A means of receiving user input data

[0754] (User) Launches the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[0755] (Device) Receives data provided by the user via voice input buttons or text input fields, and sends the voice data to a server. This process uses hardware called a smartphone and application software that provides voice input functionality.

[0756] means for preprocessing the input data;

[0757] (Server) Receives voice data sent from the device and converts the voice to text using a speech recognition algorithm (e.g., Google Cloud Speech-to-Text API). It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data. This process uses a high-performance server and a cloud service that provides speech recognition technology.

[0758] a translation means for translating the preprocessed data;

[0759] (Server) The preprocessed text data is input into a translation engine (e.g., Google Translate API) and translated into the specified language. The translation result, "How do I get to the airport?", is generated. This process also uses a high-performance server and a cloud platform that provides translation services.

[0760] means for adjusting the translation results based on usage conditions;

[0761] (Server) Checks the translation result and adjusts it based on the user's current situation and context (e.g., GPS data, time zone, user profile). For example, if the user is already close to the airport, adjusts the translation result to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation result more relevant to the local situation. At this stage, satellite communication technology is used to obtain GPS data, and technology is used to reference the user profile by linking with a database.

[0762] Means for providing the adjusted translation result to the user

[0763] (Server) Sends the adjusted translation results to the device.

[0764] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person. This process uses the smartphone's display and speaker.

[0765] Emotion engine that recognizes user emotions

[0766] (Server) Operates an emotion engine (e.g., emotion recognition algorithm) that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the user's voice input and the emotional expressions contained in the text to recognize the user's emotional state. This allows the system to respond more appropriately based on the user's current emotions.

[0767] means for further adjusting the translation result based on the emotion data;

[0768] (Server) Based on the emotional data recognized by the emotion engine, the translation results are further adjusted appropriately. For example, if the user is in a hurry, the translation results are adjusted to be concise and quickly understandable. This process uses advanced emotion analysis technology and algorithms to dynamically change the translation results.

[0769] Specific examples

[0770] Example 1: Japanese to English translation and emotion recognition

[0771] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[0772] 2. (Device) Sends voice data to the server.

[0773] 3. (Server) Convert the voice data into text data and perform preprocessing.

[0774] 4. (Server) Translate this as "How do I get to the airport?"

[0775] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[0776] 6. (Server) The emotion engine analyzes the user's emotions, and if impatience or tension is detected, the translation result is further adjusted to be more concise.

[0777] 7. (Server) The final translation result is sent to the device.

[0778] 8. (Device) The translation results are displayed to the user and audio is also played.

[0779] 9. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[0780] Prompt Sentence Examples

[0781] 1. What is the process for speech recognition using natural language processing (NLP) models?

[0782] 2. Describe the specific algorithm that converts audio data into text.

[0783] 3. How does the emotion recognition engine work and how does its data affect the translation results?

[0784] In this way, this system, which combines an emotion engine, takes emotion into account in translation and adjusts it based on real-time input data from users, and by incorporating feedback from users, it is possible to provide more accurate and effective translation results.

[0785] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0786] Step 1:

[0787] (User) Launches the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[0788] Input: User's voice data

[0789] Output: Audio data

[0790] Specific operation: The user operates the smartphone and taps the voice input button. At this point, voice input begins and the smartphone's built-in microphone collects the user's voice.

[0791] Step 2:

[0792] (Device) Receives user voice input and temporarily stores the voice data internally. Once the voice input is complete, the voice data is sent to the server.

[0793] Input: Audio data

[0794] Output: Audio data sent to the server

[0795] Specific operation: The terminal detects the completion of voice input and sends the voice data to the server via the network module.

[0796] Step 3:

[0797] (Server) Receives voice data sent from the device and converts the voice into text using a voice recognition algorithm (e.g., voice recognition API). It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data.

[0798] Input: Audio data sent to the server

[0799] Output: Clean text data

[0800] What happens: The server invokes a speech recognition algorithm to convert the speech data into text. It then applies a filtering algorithm to remove noise and misrecognitions, resulting in the clean text "Please tell me how to get to the airport."

[0801] Step 4:

[0802] (Server) The preprocessed text data is input into a translation engine (e.g., translation API) and translated into the specified language.

[0803] Input: clean text data

[0804] Output: Translated text data ("How do I get to the airport?")

[0805] Specific operation: The server calls the translation engine's API and converts the text data into the specified language. The translation engine returns the translation result to the server.

[0806] Step 5:

[0807] (Server) Checks the translation results and adjusts them based on the user's current situation and context (e.g., GPS data, time zone, user profile).

[0808] Input: translated text data, GPS data, time zone, user profile

[0809] Output: Adjusted translation result ("The airport is quite close. How do I get to the airport from here?")

[0810] How it works: The server obtains the user's current location (GPS data) and inputs it into the translation result adjustment logic, which then adjusts the resulting text appropriately and generates a new translation.

[0811] Step 6:

[0812] (Server) Sends the adjusted translation results to the device.

[0813] Input: Adjusted translation result

[0814] Output: Adjusted translation results sent to your device

[0815] Specific operation: The server generates the adjusted translation result and sends the data to the terminal via the network module.

[0816] Step 7:

[0817] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[0818] Input: Adjusted translation results sent from the server

[0819] Output: The translation results that are displayed and played back to the user

[0820] Specific operation: The translation result is displayed on the device display and the result is played back using the voice module.

[0821] Step 8:

[0822] (Server) Operates an emotion engine (e.g., emotion recognition algorithm) that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the voice input by the user and the emotional expressions contained in the text to recognize the user's emotional state.

[0823] Input: Audio data, text data

[0824] Output: User emotion data

[0825] How it works: The server invokes an emotion recognition algorithm and analyzes the voice and text data to identify the user's emotional state.

[0826] Step 9:

[0827] (Server) The emotion engine further adjusts the translation results based on the emotional data it recognizes. For example, if the user is in a hurry, the translation results will be adjusted to be concise and easy to understand.

[0828] Input: Adjusted translation results, user emotion data

[0829] Output: Translation results further adjusted based on user sentiment

[0830] Specific operation: Emotional data is used to make final adjustments to the translation results, resulting in a translation that is appropriate for the user's emotional state.

[0831] (Application example 2)

[0832] 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."

[0833] Conventional translation systems simply translate user input data, but are unable to provide translation results that reflect the user's current emotions or usage situation. Furthermore, the mechanisms for incorporating user feedback into the system were inadequate, making it difficult to continuously improve the quality of translation results. This can result in users not receiving optimal translations in real time, leading to a decline in user satisfaction. Furthermore, advertising and information provision systems also face the challenge of being unable to provide individualized responses that take emotions and context into account.

[0834] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0835] In this invention, the server includes means for receiving user input data, means for preprocessing the input data, means for translating the preprocessed data, means for adjusting the translation result based on usage status, means for providing the adjusted translation result to the user, means for recognizing the user's emotions using an emotion engine, and means for further adjusting the translation result based on the recognized emotion data. This enables the provision of more appropriate and effective real-time translation according to the user's emotions and current usage status. Furthermore, by further comprising means for receiving user feedback data, means for analyzing the feedback data, means for updating the translation model based on the analyzed data, and means for adjusting the translation result based on user context data, continuous quality improvement and individual response are possible.

[0836] "User Input Data" means any audio or text information provided by a User to the System.

[0837] "Preprocessing" is the process of removing noise and misrecognition from input data to generate accurate text data.

[0838] A "translation means" is an algorithm or program that converts preprocessed data into a specified language.

[0839] "Usage status" refers to contextual information such as the user's current location, time of day, and user profile.

[0840] "Adjustment" refers to the process of optimizing translation results based on usage and emotional data.

[0841] An "emotion engine" is a program or algorithm for analyzing a user's emotional state from their voice or text.

[0842] "Feedback data" refers to information on evaluations and opinions of users regarding translation results.

[0843] "Analysis" is the process of understanding data and deriving patterns and trends based on feedback and sentiment data.

[0844] A "translation model" is a training algorithm or dataset for converting input data into a different language.

[0845] "Context data" is information about the user's current situation and environment, and is used to optimize translation results.

[0846] System configuration

[0847] This system mainly consists of a server and terminals (smartphones, smart glasses, head-mounted displays, etc.). The server is equipped with a speech recognition algorithm, a translation engine, an emotion recognition engine, and a context adjustment engine, and uses these to process input data in real time. The terminals are devices equipped with a microphone, a display, and internet connectivity.

[0848] Program processing flow

[0849] The server processes the data using the following means:

[0850] 1. Means of receiving user input data

[0851] When a user inputs voice into the terminal, the voice data is collected by the microphone and sent to a server via the Internet.

[0852] 2. Means for preprocessing the input data

[0853] The server uses a speech recognition algorithm to convert the speech to text, filtering out unwanted noise and misrecognitions, resulting in clean text data.

[0854] 3. A translation means for translating the preprocessed data.

[0855] The server inputs the preprocessed text data into a translation engine and translates it into the specified language, for example, using the Google Translate API.

[0856] 4. Means for adjusting the translation results based on usage conditions

[0857] The server collects contextual data such as the user's location and time of day, and then adjusts the translation results based on this information. This step is handled by the context adjustment engine.

[0858] 5. Means for providing the adjusted translation results to users

[0859] The server then sends the adjusted translation results to the terminal, which notifies the user by displaying the results in text and playing them aloud.

[0860] 6. Means of recognizing user emotions using an emotion engine

[0861] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions from voice and text data.

[0862] 7. Means for further adjusting the translation result based on the recognized emotion data

[0863] The server uses emotional data to further optimize the translation results, such as providing more concise information if the user is nervous, or more detailed information if the user is relaxed.

[0864] Hardware and software used

[0865] Hardware: Devices with microphones, displays, and internet connectivity (smartphones, smart glasses, head-mounted displays, etc.)

[0866] Software: Google Speech-to-Text API, Google Translate API, IBM Watson Tone Analyzer

[0867] Specific examples

[0868] Prompt Sentence Examples

[0869] User: "What are the latest sales?"

[0870] Voice data received by the server: "Tell me about the latest sales."

[0871] 1. Text after speech recognition:

[0872] "Tell me the latest sales information"

[0873] 2. Translated English text:

[0874] "Tell me the latest sale information"

[0875] 3. Contextual adjustment:

[0876] Customize based on nearby stores:

[0877] "You are near our store, check out our latest sale on electronics!"

[0878] 4. Emotion recognition:

[0879] User Emotions: Stressed

[0880] Adjusted ad text:

[0881] "Relax and enjoy our exclusive discounts on spa packages!"

[0882] 5. Final Ad Delivery:

[0883] The text "Relax and enjoy our exclusive discounts on spa packages!" is displayed on the smart glasses' display and played aloud.

[0884] In this way, the present invention realizes a system that adjusts translation results based on the user's emotions and context, and provides optimal information in real time.

[0885] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0886] Step 1:

[0887] The user inputs voice into the device. Specifically, when the user says, "Tell me about the latest sales," the device's microphone collects this voice and converts it into digital voice data. The input is the user's voice data, and this voice data is sent to the server via the Internet.

[0888] Step 2:

[0889] The server converts the received voice data into text data using a speech recognition algorithm (such as the Google Speech-to-Text API). It removes noise and misrecognition to generate accurate text data. The input is voice data, and the output is preprocessed text data.

[0890] Step 3:

[0891] The server inputs the preprocessed text data into a translation engine (such as Google Translate API) and translates it into the specified language. The input is the preprocessed text data, and the output is the translated text data. For example, "Tell me the latest sale information" is translated into "Tell me the latest sale information."

[0892] Step 4:

[0893] The server collects context data such as the user's location and time of day, and adjusts the translation results based on this. The input is the translated text data and context data, and the output is text data adjusted based on the context. For example, the translation result might be adjusted to "You are near our store, check out our latest sale on electronics!"

[0894] Step 5:

[0895] The server uses an emotion recognition engine (such as IBM Watson Tone Analyzer) to analyze the user's emotions from the input voice or text data. The input is voice data or text data, and the output is data that indicates the user's emotional state.

[0896] Step 6:

[0897] The server further adjusts the translation results based on the emotional data. For example, if the user is stressed, the information is made more concise, and if the user is relaxed, the information is made more detailed. The input is text data that has been adjusted based on the emotional data and context, and the output is the final adjusted text data.

[0898] Step 7:

[0899] The server sends the final adjusted translation result to the device. The device uses the received data to display text and play audio. The input is the final adjusted text data, and the output is information provided to the user visually and audibly. Specifically, the text "Relax and enjoy our exclusive discounts on spa packages!" is displayed on the smart glasses' display and played aloud.

[0900] This series of processing steps allows users to receive optimal translation results that are in line with emotion and context in real time.

[0901] 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.

[0902] 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.

[0903] 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.

[0904] [Third embodiment]

[0905] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0906] 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.

[0907] 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).

[0908] 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.

[0909] 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.

[0910] 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).

[0911] 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.

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] 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."

[0917] This invention relates to a system that can preprocess user input data in real time and adjust the translation results based on the current situation. Below, as a specific embodiment of the invention, the program processing and flow of the system will be explained in natural language with concrete examples.

[0918] System Program Processing

[0919] A means of receiving user input data

[0920] (User) Installs the smartphone app and prepares to input voice or text for translation.

[0921] (Terminal) Provides an interface that receives data provided by the user via voice input buttons or text input fields. If a user speaks, "Please tell me how to get to the airport," the terminal sends this voice data to the server.

[0922] means for preprocessing the input data;

[0923] (Server) Receives voice data sent from the terminal and converts the voice to text using a speech recognition algorithm. It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data. At this stage, clean text such as "Please tell me how to get to the airport" is obtained.

[0924] a translation means for translating the preprocessed data;

[0925] (Server) The preprocessed text data is input into the translation engine and translated into the specified language. The translation result is "How do I get to the airport?"

[0926] means for adjusting the translation results based on usage conditions;

[0927] (Server) Checks the translation result and adjusts it based on the user's current situation and context (GPS data, time zone, user profile, etc.). For example, if the user is already close to the airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation result more relevant to the local situation.

[0928] Means for providing the adjusted translation result to the user

[0929] (Server) Sends the adjusted translation results to the device.

[0930] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[0931] Specific examples

[0932] Example 1: Japanese to English translation

[0933] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[0934] 2. (Device) Sends voice data to the server.

[0935] 3. (Server) Convert the voice data into text data and perform preprocessing.

[0936] 4. (Server) Translate this as "How do I get to the airport?"

[0937] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[0938] 6. (Server) Sends the adjusted translation results to the device.

[0939] 7. (Device) The translation results are displayed to the user and audio is also played.

[0940] 8. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[0941] Example 2: Updating a model based on user feedback

[0942] 1. (User) After using the translation result "The airport is quite close. How do I get to the airport from here?", enter feedback within the app. Rate the translation as "helpful."

[0943] 2. (Server) Receive user feedback data.

[0944] 3. (Server) Analyze the feedback data and save it as training data.

[0945] 4. (Server) Retrain the translation model using the new feedback data to improve accuracy.

[0946] In this way, the present invention can provide more accurate and useful translation results by translating and adjusting the translation based on real-time input data from the user and by incorporating feedback from the user.

[0947] The processing flow will be explained below.

[0948] Step 1:

[0949] (User) Opens the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[0950] Step 2:

[0951] (Device) The user's voice data is temporarily stored and immediately sent to the server.

[0952] Step 3:

[0953] (Server) Receives voice data from the terminal and converts the voice into text using a voice recognition algorithm.

[0954] Step 4:

[0955] (Server) Remove noise and misrecognitions from the text data and preprocess it into an appropriate format. This results in clean text: "Please tell me how to get to the airport."

[0956] Step 5:

[0957] (Server) The preprocessed text data is input into the "translation means" and translated into the specified language. The translation result is "How do I get to the airport?"

[0958] Step 6:

[0959] (Server) Check the user's current location and situation (e.g. GPS data and time zone) and adjust the translation result based on that context. For example, if the user is already near an airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?"

[0960] Step 7:

[0961] (Server) Sends the adjusted translation results to the device.

[0962] Step 8:

[0963] (Device) The received translation result is displayed to the user and played aloud if necessary. The message "The airport is quite close. How do I get to the airport from here?" is displayed and played aloud.

[0964] Step 9:

[0965] (User) Using the displayed translation results as a reference, ask a local person, "The airport is quite close. How do I get to the airport from here?"

[0966] Step 10:

[0967] (User) Enter feedback on the translation result within the app. For example, rate it as "The translation was helpful."

[0968] Step 11:

[0969] (Server) Receives feedback data from users.

[0970] Step 12:

[0971] (Server) Analyze the received feedback data and save it as learning data.

[0972] Step 13:

[0973] (Server) Retrain the translation model using new feedback data to improve translation accuracy.

[0974] In this way, processing progresses step by step, and a system can be realized that provides optimal real-time translation and support to users.

[0975] Example 1

[0976] 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."

[0977] Conventional translation systems have difficulty preprocessing user input data in real time and adjusting translation results based on the current situation. Furthermore, they are unable to effectively incorporate user feedback, resulting in problems such as reduced translation accuracy and usability. This invention aims to solve these problems and provide users with more accurate and context-appropriate translation results.

[0978] 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.

[0979] In this invention, the server includes means for receiving input data in the form of voice or text from a user, means for preprocessing the input data and converting it into text data using a speech recognition algorithm, means for removing unnecessary noise and misrecognition from the preprocessed text data, means for translating the cleaned text data, means for adjusting the translation result based on the user's location information, time zone, and variables, and means for providing the adjusted translation result to the user. This makes it possible to provide more accurate and current translation results based on the user's real-time input data.

[0980] "User" means an individual or organization that uses this system to input voice or text data and obtain translation results.

[0981] "Voice data" refers to digital data containing linguistic information spoken by a user.

[0982] "Text data" refers to data that includes language information in the form of a string of characters.

[0983] "Preprocessing" refers to the process of converting voice data into text data and then removing noise and misrecognized parts from the text data.

[0984] A "speech recognition algorithm" is a computational method and model for analyzing speech data and converting it into corresponding text data.

[0985] "Noise" refers to unnecessary information or misrecognized parts contained in the voice data or text data, which may reduce translation accuracy.

[0986] A "translator" is an engine or algorithm for converting pre-processed clean text data into a different language.

[0987] "User Location Information" means information about a User's current geographic location obtained using GPS or other means.

[0988] "User's time zone" is information based on the local time when the user uses the system.

[0989] "Feedback data" refers to data that includes users' evaluations and opinions on the translation results.

[0990] A "generative artificial intelligence model" is a computational model that has been trained using machine learning or deep learning to perform a specific task.

[0991] A "database" is a structured collection of data that stores feedback data and other relevant information and is used for analysis and learning.

[0992] "Adjustment" refers to the process of appropriately modifying translation results based on the user's location, time of day, and other variables.

[0993] "Providing means" refers to functions and modules for displaying the adjusted translation results to the user or playing them aloud.

[0994] This invention relates to a system that preprocesses user input data in real time and adjusts translation results based on the current situation. This invention allows users to obtain more accurate and context-appropriate translation results. Specific embodiments for implementing the invention are described below.

[0995] This system combines a speech recognition algorithm, a natural language processing algorithm, a translation engine, and a feedback analysis system. The hardware used includes a server, a terminal (e.g., a smartphone), and an internet connection. The software used includes a speech recognition API, a natural language processing library, a translation API, and a database system.

[0996] Hardware and Software Usage

[0997] (User) Installs the smartphone app, launches the app, and inputs the voice or text to be translated. When the user inputs "Please tell me how to get to the airport," the smartphone's microphone is used to capture the voice data.

[0998] (Device) Provides an interface for transmitting captured voice data to a server. The data is encrypted using a security protocol such as TLS. The device collects data provided by the user via voice input buttons or text input fields, formats it appropriately, and transmits it to the server via the Internet.

[0999] (Server) The received voice data is converted into text data using a speech recognition algorithm. At this stage, the voice is converted into text using, for example, the Google Cloud Speech-to-Text API. The converted text is then cleaned of unnecessary noise and misrecognitions to generate accurate text data. A natural language processing (NLP) system is used for preprocessing to obtain clean text such as "Please tell me how to get to the airport."

[1000] Next, the preprocessed text data is input into a translation engine and translated into the specified language, for example, using the DeepL API or another high-precision translation engine. The resulting translation is "How do I get to the airport?"

[1001] Additionally, the translation will be adjusted based on the user's current situation and context (GPS data, time of day, user profile, etc.). For example, if the user is already close to an airport, the translation will be adjusted to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation more relevant to the local situation.

[1002] The adjusted translation result is sent to the device, where it is displayed to the user and, if necessary, played aloud. The user receives the result, "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[1003] Specific examples

[1004] (Example 1) Translation from Japanese to English

[1005] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[1006] 2. (Device) Sends voice data to the server.

[1007] 3. (Server) Convert the voice data into text data and perform preprocessing.

[1008] 4. (Server) Translate this as "How do I get to the airport?"

[1009] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[1010] 6. (Server) Sends the adjusted translation results to the device.

[1011] 7. (Device) The translation results are displayed to the user and audio is also played.

[1012] 8. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[1013] (Example 2) Model update based on user feedback

[1014] 1. (User) After using the translation result "The airport is quite close. How do I get to the airport from here?", enter feedback within the app. Rate the translation as "helpful."

[1015] 2. (Server) Receive user feedback data.

[1016] 3. (Server) Analyze the feedback data and save it as training data.

[1017] 4. (Server) Retrain the generative AI model with new feedback data to improve accuracy.

[1018] In this way, the present invention translates and adjusts the translation based on real-time user input data, and can also incorporate user feedback to provide more accurate and useful translation results.

[1019] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1020] Step 1:

[1021] (User) opens the smartphone app, presses the voice input button, and says, "Please tell me how to get to the airport." At this time, the input data is the user's voice data, and this voice data is acquired by the device. Input data: User's voice data. Output data: Voice data stored on the device.

[1022] Step 2:

[1023] (Device) The acquired voice data is sent to the server via the internet. At this time, encryption protocols such as TLS are used to ensure data security. Input data: Voice data stored in the device. Output data: Encrypted voice data sent to the server.

[1024] Step 3:

[1025] (Server) Converts the received voice data into text data using a voice recognition algorithm. In this process, for example, a general voice recognition API is used to convert voice to text. Input data: Encrypted voice data. Output data: Converted text data.

[1026] Step 4:

[1027] (Server) A natural language processing algorithm is used to remove unnecessary noise and misrecognition from text data and generate accurate text data. For example, if "Please tell me how to get to the airport" is misrecognized, it is corrected to "Please tell me how to get to the airport." Input data: Converted text data. Output data: Preprocessed, clean text data.

[1028] Step 5:

[1029] (Server) The preprocessed text data is input into the translation engine and translated into the specified language. For example, a highly accurate translation API is used to obtain the translation result "How do I get to the airport?". Input data: Preprocessed, clean text data. Output data: Translated text data.

[1030] Step 6:

[1031] (Server) Adjust the translation result based on the user's location, time zone, and variables. For example, if the user is already close to the airport, adjust it to "The airport is quite close. How do I get to the airport from here?" This operation allows for translation results that are more in line with the context. Input data: Translated text data and the user's location and time zone data. Output data: Translated text data adjusted based on the context.

[1032] Step 7:

[1033] (Server) The adjusted translation results are sent to the terminal. Security is ensured during this process using encryption protocols such as TLS. Input data: Adjusted translation text data. Output data: Adjusted translation data sent to the terminal.

[1034] Step 8:

[1035] (Device) The received adjusted translation result is displayed to the user and played aloud if necessary. This gives the user the result "The airport is quite close. How do I get to the airport from here?" Input data: The sent adjusted translation data. Output data: The translation result displayed on the user's screen or played aloud.

[1036] Step 9:

[1037] (User) Enter feedback on the translation results within the app. Enter an evaluation such as "The translation was helpful" or "The translation was inappropriate." Input data: User feedback data. Output data: Feedback data stored on the device.

[1038] Step 10:

[1039] (Terminal) Feedback data from the user is sent to the server. Here too, data security is ensured using encryption protocols such as TLS. Input data: Feedback data stored in the terminal. Output data: Feedback data sent to the server.

[1040] Step 11:

[1041] (Server) Receives the feedback data, analyzes it, and stores it in a database. Then, it retrains the generative AI model based on the stored feedback data to improve the model's accuracy. Input data: Feedback data sent to the server. Output data: Updated generative AI model.

[1042] In this way, specific operations are performed at each step, and the system provides more appropriate translation results to the user.

[1043] (Application example 1)

[1044] 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."

[1045] Conventional translation systems have difficulty providing flexible translation that takes into account the user's current situation and profile information. In addition, in certain scenarios, such as food delivery, it is necessary to provide a better user experience by providing appropriate translation in real time. Therefore, there is a demand for a translation system that reflects local conditions and user history information.

[1046] 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.

[1047] In this invention, the server includes means for adjusting the translation result taking into account the user's profile data, means for improving the translation result based on the user's history data and current situation data, and means for converting the voice data into text data, thereby enabling more accurate real-time translation based on the local situation and the user's profile information.

[1048] "User input data" refers to voice and text data that a user provides to the system.

[1049] "Preprocessing" refers to the process of removing noise and misrecognition from input data and converting it into a format suitable for analysis.

[1050] The "translation means" is a means for translating the preprocessed text data into a specified language.

[1051] "Means for adjusting based on usage situation" refers to means for correcting and adjusting translation results based on the user's current situation and context.

[1052] "Means for providing to the user" refers to means for providing the adjusted translation results to the user by display or audio.

[1053] "User profile data" is data that includes historical information and current status information about a user.

[1054] "Feedback data" refers to data such as evaluations and comments about system usage provided by users.

[1055] The "means for updating the translation model" refers to a means for retraining the model to improve translation accuracy and applicability based on received feedback data.

[1056] The "means for converting voice data into text data" refers to a means for converting voice input into a string of characters using voice recognition technology.

[1057] This invention relates to a system that preprocesses voice or text data input by a user in real time and provides translation results. The actual system program and its processing content will be described in detail below.

[1058] System Overview

[1059] The system of the present invention includes the following major components:

[1060] 1. Terminal that receives user input data

[1061] 2. Server that preprocesses input data

[1062] 3. Server that translates preprocessed data

[1063] 4. Server that adjusts translation results based on usage

[1064] 5. Device that provides users with adjusted translation results

[1065] Hardware and Software

[1066] Device: A mobile communication device such as a smartphone or tablet. This device is equipped with a microphone for audio input and a speaker for display and audio output.

[1067] Server: A cloud server for speech recognition, pre-processing, translation, and tuning. This server is a computer with a powerful processor and sufficient memory.

[1068] Speech Recognition Library: A software library for speech recognition, such as speech_recognition.

[1069] Translation engine: A software library for translation, such as googletrans.

[1070] Generative AI model: An AI model that updates and trains the translation model based on user feedback and profile data.

[1071] System processing flow

[1072] 1. The user launches the "Food Delivery ChatBot" app and inputs a question via voice or text. The device then sends this input data to the server.

[1073] 2. The server converts the voice data into text data. It uses a speech recognition library (e.g., speech_recognition) to convert the voice data into text data.

[1074] 3. The server preprocesses the text data, removing unnecessary noise and misrecognitions to generate clean data.

[1075] 4. The server translates the preprocessed text data into the specified language using a translation engine (e.g., googletrans).

[1076] 5. Context-sensitive translation: Using user profile data (e.g., location, allergies, order history), the translation is tailored to the local context.

[1077] 6. The adjusted translation result is sent to the device and provided to the user as a display and audio.

[1078] Specific examples

[1079] Example 1: Proposing appropriate alternative menu items for food allergies

[1080] 1. User: "I'm allergic to a certain dish. Can you recommend an alternative menu item?"

[1081] 2. Terminal: Sends voice data to the server.

[1082] 3. Server: Converts voice data into text data and performs preprocessing.

[1083] 4. Server: Translate this to "Please tell me if there are any alternative dishes because I am allergic to a particular dish."

[1084] 5. Server: Adjust the translation to say, "Based on your allergy information, here are some recommended alternative menu items."

[1085] 6. Server: Sends the adjusted translation results to the device.

[1086] 7. Terminal: The translation results are displayed to the user and played aloud.

[1087] 8. User: Tell the restaurant staff, "Please tell me if there are any alternative dishes because I am allergic to a particular dish. Additionally, there are some allergy-free options nearby."

[1088] Prompt Sentence Examples

[1089] Please translate "I'm allergic to a certain dish. Can you recommend an alternative menu item?" into English. And this user is in Tokyo and has a nut allergy. Please add advice based on that information.

[1090] The above is a specific embodiment for carrying out the present invention. The present invention makes it possible to provide a more accurate translation that is in line with the current situation and profile information of the user.

[1091] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1092] Step 1:

[1093] A user launches the "Food Delivery ChatBot" app and enters a question by voice or text. Voice or text data is provided as input. This data is sent from the device to the server as output.

[1094] Step 2:

[1095] The terminal transmits the voice data input by the user to the server. It receives the voice data as input and transmits it as output to the server. Specific operations include capturing the voice with a microphone and transmitting the data to the server via a network.

[1096] Step 3:

[1097] The server uses a speech recognition library (e.g., speech_recognition) to convert the audio data into text data. It takes audio data as input and produces text data as output. The specific operations include applying a speech recognition algorithm to extract text from the audio waveform.

[1098] Step 4:

[1099] The server performs preprocessing to remove unnecessary noise and misrecognition from the text data. It receives text data as input and generates clean text data as output. Specific operations include text cleansing using regular expressions and filtering algorithms.

[1100] Step 5:

[1101] The server uses a translation engine (e.g., googletrans) to translate the preprocessed text data into the specified language. It takes clean text data as input and produces translated text data as output. Specific operations include calling a translation API to convert the text into another language.

[1102] Step 6:

[1103] The server adjusts the translation results based on usage. It references the user's profile data and local information to modify the translation results to fit the context. It takes translated text data and profile data as input and generates an adjusted translation result as output. Specific operations include supplementing and modifying the translated text based on location information, allergy data, etc.

[1104] Step 7:

[1105] The server sends the adjusted translation result to the terminal. It takes the adjusted translation data as input and sends it to the terminal as output. The specific operation includes transmitting the adjusted text via the network.

[1106] Step 8:

[1107] The device displays the translation results to the user and plays them aloud if necessary. It receives the adjusted translation data as input and displays and plays them aloud to the user as output. Specific operations include text display and speech synthesis using a speech synthesis library.

[1108] 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.

[1109] This invention relates to a system that can preprocess user input data in real time and adjust translation results based on the current situation. Furthermore, by combining an emotion engine that recognizes the user's emotions, translation results can be adapted to the user's emotions, providing more appropriate and effective real-time translation. Below, as a specific embodiment of the present invention, the program processing and flow of a system that combines an emotion engine will be explained in natural language, with specific examples.

[1110] System Program Processing

[1111] A means of receiving user input data

[1112] (User) Launches the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[1113] (Terminal) Receives data provided by the user via voice input buttons or text input fields and sends the voice data to the server.

[1114] means for preprocessing the input data;

[1115] (Server) Receives voice data sent from the device and converts the voice to text using a speech recognition algorithm. It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data. At this stage, clean text such as "Please tell me how to get to the airport" is obtained.

[1116] a translation means for translating the preprocessed data;

[1117] (Server) The preprocessed text data is input into the translation engine and translated into the specified language. The translation result is "How do I get to the airport?"

[1118] means for adjusting the translation results based on usage conditions;

[1119] (Server) Checks the translation result and adjusts it based on the user's current situation and context (GPS data, time zone, user profile, etc.). For example, if the user is already close to the airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation result more relevant to the local situation.

[1120] Means for providing the adjusted translation result to the user

[1121] (Server) Sends the adjusted translation results to the device.

[1122] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[1123] Emotion engine that recognizes user emotions

[1124] (Server) Operates an emotion engine that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the voice input by the user and the emotional expressions contained in the text to recognize the user's emotional state.

[1125] A means for further adjusting the translation result based on the emotion data recognized by the emotion engine.

[1126] (Server) The emotion engine further adjusts the translation results based on the emotional data it recognizes. For example, if the user is in a hurry, the translation results will be adjusted to be concise and easy to understand.

[1127] Specific examples

[1128] Example 1: Japanese to English translation and emotion recognition

[1129] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[1130] 2. (Device) Sends voice data to the server.

[1131] 3. (Server) Convert the voice data into text data and perform preprocessing.

[1132] 4. (Server) Translate this as "How do I get to the airport?"

[1133] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[1134] 6. (Server) The emotion engine analyzes the user's emotions, and if impatience or tension is detected, the translation result is further adjusted to be more concise.

[1135] 7. (Server) The final translation result is sent to the device.

[1136] 8. (Device) The translation results are displayed to the user and audio is also played.

[1137] 9. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[1138] Example 2: Updating emotion models based on user feedback

[1139] 1. (User) Enter feedback on the translation result within the app. For example, feedback including emotions such as "The translation was accurate and helpful" or "I wish it was a little gentler."

[1140] 2. (Server) Receives feedback data and analyzes it, including emotional data.

[1141] 3. (Server) Retrain the emotion recognition model using the new feedback data to improve accuracy.

[1142] In this way, this system, which combines an emotion engine, takes emotion into account in translation and adjusts it based on real-time input data from users, and by incorporating feedback from users, it is possible to provide more accurate and effective translation results.

[1143] The processing flow will be explained below.

[1144] Step 1:

[1145] (User) Opens the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[1146] Step 2:

[1147] (Device) The user's voice data is temporarily stored and immediately sent to the server.

[1148] Step 3:

[1149] (Server) Sends the voice data received from the terminal to a voice recognition algorithm and converts the voice into text.

[1150] Step 4:

[1151] (Server) Remove noise and misrecognitions from the text data and preprocess it into an appropriate format. This results in clean text: "Please tell me how to get to the airport."

[1152] Step 5:

[1153] (Server) The preprocessed text data is input into the translation engine and translated into the specified language (in this case, English). The translation result is "How do I get to the airport?"

[1154] Step 6:

[1155] (Server) Check the user's current location and situation (e.g. GPS data and time zone) and adjust the translation result based on that context. For example, if the user is already near an airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?"

[1156] Step 7:

[1157] (Server) Operates an emotion engine that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the voice input by the user and the emotional expressions contained in the text to recognize the user's emotional state.

[1158] Step 8:

[1159] (Server) Based on the emotional data recognized by the emotion engine, the translation result is further adjusted appropriately. If the user is in a hurry, the translation result is adjusted to be concise and quickly understandable. For example, "Please hurry. The airport is close. How do I get there?"

[1160] Step 9:

[1161] (Server) Sends the adjusted translation results to the device.

[1162] Step 10:

[1163] (Device) The received translation result is displayed to the user and played aloud if necessary. The message "Please hurry. The airport is closed. How do I get there?" is displayed and also played aloud.

[1164] Step 11:

[1165] (User) Using the displayed translation results as a reference, ask a local person, "Please hurry. The airport is close. How do I get there?"

[1166] Step 12:

[1167] (User) Enter feedback on the translation result within the app. For example, provide feedback that reflects specific emotions, such as "The translation was accurate and helpful" or "It would have been better if the wording was a little gentler."

[1168] Step 13:

[1169] (Server) Stores and analyzes feedback data received from users. Based on the feedback, it identifies areas that need improvement.

[1170] Step 14:

[1171] (Server) Retrain the emotion recognition model using new feedback data to improve the accuracy of the system.

[1172] In this way, through step-by-step processing, the system, which combines an emotion engine, determines emotions based on real-time user input data and provides accurate translation results according to the situation. Furthermore, by incorporating feedback from users, continuous improvement is possible.

[1173] Example 2

[1174] 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."

[1175] Conventional translation systems are required to translate user input data in a timely and accurate manner. However, because they do not take into account the user's emotions or usage context, the translation results are often inappropriate for actual usage scenarios. In addition, there is a lack of a mechanism for updating the translation model based on feedback. This makes it difficult to provide users with more appropriate and effective translation results.

[1176] 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.

[1177] In this invention, the server includes means for receiving user input data, means for preprocessing the input data, means for translating the preprocessed data, means for adjusting the translation result based on usage conditions, means for providing the adjusted translation result to the user, means for recognizing the user's emotions, and means for further adjusting the translation result based on the emotion data. This makes it possible to provide translation results that reflect the user's emotions and usage conditions.

[1178] "Means for receiving user input data" refers to a device or interface that has the function of incorporating information input by the user via voice or text into the system.

[1179] The "means for preprocessing the input data" refers to a device or algorithm that has the function of removing unnecessary noise and misrecognition from the input data and converting it into accurate text data.

[1180] The "translation means for translating the preprocessed data" refers to an engine or software for translating the preprocessed text data into another language.

[1181] The "means for adjusting the translation result based on usage" refers to a device or algorithm that has the ability to adjust the translated text based on the user's current situation or context.

[1182] The "means for providing the adjusted translation result to the user" refers to a device or interface that has the function of displaying or audibly providing the adjusted translation result to the user.

[1183] The "means for recognizing user emotions" refers to a device or algorithm that has the function of analyzing the user's voice tone and speed, and emotional expressions contained in the text, to identify the user's emotional state.

[1184] The "means for further adjusting the translation result based on the emotion data" refers to a device or algorithm that has the function of further appropriately adjusting the translation result based on the recognized emotion data.

[1185] The "means for receiving user feedback data" refers to a device or interface that has the function of incorporating user opinions and thoughts about the translation results into the system.

[1186] The "means for analyzing the feedback data" refers to a device or algorithm that has the function of analyzing the captured feedback data and extracting useful information.

[1187] The "means for updating the translation model based on the analyzed data" refers to a device or algorithm that has the function of improving and updating the translation model based on the analyzed feedback data.

[1188] "Voice data" refers to information input by voice by the user.

[1189] "Text data" refers to character information generated by converting voice data.

[1190] The present invention relates to a system that can preprocess user input data in real time and adjust translation results based on the current situation. Furthermore, by combining an emotion engine that recognizes the user's emotions, the translation results can be adapted to the user's emotions, providing more appropriate and effective real-time translation. Below, as a specific embodiment of the present invention, the program processing and flow of a system that combines an emotion engine will be explained in natural language, with specific examples.

[1191] A means of receiving user input data

[1192] (User) Launches the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[1193] (Device) Receives data provided by the user via voice input buttons or text input fields, and sends the voice data to a server. This process uses hardware called a smartphone and application software that provides voice input functionality.

[1194] means for preprocessing the input data;

[1195] (Server) Receives voice data sent from the device and converts the voice to text using a speech recognition algorithm (e.g., Google Cloud Speech-to-Text API). It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data. This process uses a high-performance server and a cloud service that provides speech recognition technology.

[1196] a translation means for translating the preprocessed data;

[1197] (Server) The preprocessed text data is input into a translation engine (e.g., Google Translate API) and translated into the specified language. The translation result, "How do I get to the airport?", is generated. This process also uses a high-performance server and a cloud platform that provides translation services.

[1198] means for adjusting the translation results based on usage conditions;

[1199] (Server) Checks the translation result and adjusts it based on the user's current situation and context (e.g., GPS data, time zone, user profile). For example, if the user is already close to the airport, adjusts the translation result to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation result more relevant to the local situation. At this stage, satellite communication technology is used to obtain GPS data, and technology is used to reference the user profile by linking with a database.

[1200] Means for providing the adjusted translation result to the user

[1201] (Server) Sends the adjusted translation results to the device.

[1202] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person. This process uses the smartphone's display and speaker.

[1203] Emotion engine that recognizes user emotions

[1204] (Server) Operates an emotion engine (e.g., emotion recognition algorithm) that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the user's voice input and the emotional expressions contained in the text to recognize the user's emotional state. This allows the system to respond more appropriately based on the user's current emotions.

[1205] means for further adjusting the translation result based on the emotion data;

[1206] (Server) Based on the emotional data recognized by the emotion engine, the translation results are further adjusted appropriately. For example, if the user is in a hurry, the translation results are adjusted to be concise and quickly understandable. This process uses advanced emotion analysis technology and algorithms to dynamically change the translation results.

[1207] Specific examples

[1208] Example 1: Japanese to English translation and emotion recognition

[1209] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[1210] 2. (Device) Sends voice data to the server.

[1211] 3. (Server) Convert the voice data into text data and perform preprocessing.

[1212] 4. (Server) Translate this as "How do I get to the airport?"

[1213] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[1214] 6. (Server) The emotion engine analyzes the user's emotions, and if impatience or tension is detected, the translation result is further adjusted to be more concise.

[1215] 7. (Server) The final translation result is sent to the device.

[1216] 8. (Device) The translation results are displayed to the user and audio is also played.

[1217] 9. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[1218] Prompt Sentence Examples

[1219] 1. What is the process for speech recognition using natural language processing (NLP) models?

[1220] 2. Describe the specific algorithm that converts audio data into text.

[1221] 3. How does the emotion recognition engine work and how does its data affect the translation results?

[1222] In this way, this system, which combines an emotion engine, takes emotion into account in translation and adjusts it based on real-time input data from users, and by incorporating feedback from users, it is possible to provide more accurate and effective translation results.

[1223] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1224] Step 1:

[1225] (User) Launches the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[1226] Input: User's voice data

[1227] Output: Audio data

[1228] Specific operation: The user operates the smartphone and taps the voice input button. At this point, voice input begins and the smartphone's built-in microphone collects the user's voice.

[1229] Step 2:

[1230] (Device) Receives user voice input and temporarily stores the voice data internally. Once the voice input is complete, the voice data is sent to the server.

[1231] Input: Audio data

[1232] Output: Audio data sent to the server

[1233] Specific operation: The terminal detects the completion of voice input and sends the voice data to the server via the network module.

[1234] Step 3:

[1235] (Server) Receives voice data sent from the device and converts the voice into text using a voice recognition algorithm (e.g., voice recognition API). It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data.

[1236] Input: Audio data sent to the server

[1237] Output: Clean text data

[1238] What happens: The server invokes a speech recognition algorithm to convert the speech data into text. It then applies a filtering algorithm to remove noise and misrecognitions, resulting in the clean text "Please tell me how to get to the airport."

[1239] Step 4:

[1240] (Server) The preprocessed text data is input into a translation engine (e.g., translation API) and translated into the specified language.

[1241] Input: clean text data

[1242] Output: Translated text data ("How do I get to the airport?")

[1243] Specific operation: The server calls the translation engine's API and converts the text data into the specified language. The translation engine returns the translation result to the server.

[1244] Step 5:

[1245] (Server) Checks the translation results and adjusts them based on the user's current situation and context (e.g., GPS data, time zone, user profile).

[1246] Input: translated text data, GPS data, time zone, user profile

[1247] Output: Adjusted translation result ("The airport is quite close. How do I get to the airport from here?")

[1248] How it works: The server obtains the user's current location (GPS data) and inputs it into the translation result adjustment logic, which then adjusts the resulting text appropriately and generates a new translation.

[1249] Step 6:

[1250] (Server) Sends the adjusted translation results to the device.

[1251] Input: Adjusted translation result

[1252] Output: Adjusted translation results sent to your device

[1253] Specific operation: The server generates the adjusted translation result and sends the data to the terminal via the network module.

[1254] Step 7:

[1255] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[1256] Input: Adjusted translation results sent from the server

[1257] Output: The translation results that are displayed and played back to the user

[1258] Specific operation: The translation result is displayed on the device display and the result is played back using the voice module.

[1259] Step 8:

[1260] (Server) Operates an emotion engine (e.g., emotion recognition algorithm) that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the voice input by the user and the emotional expressions contained in the text to recognize the user's emotional state.

[1261] Input: Audio data, text data

[1262] Output: User emotion data

[1263] How it works: The server invokes an emotion recognition algorithm and analyzes the voice and text data to identify the user's emotional state.

[1264] Step 9:

[1265] (Server) The emotion engine further adjusts the translation results based on the emotional data it recognizes. For example, if the user is in a hurry, the translation results will be adjusted to be concise and easy to understand.

[1266] Input: Adjusted translation results, user emotion data

[1267] Output: Translation results further adjusted based on user sentiment

[1268] Specific operation: Emotional data is used to make final adjustments to the translation results, resulting in a translation that is appropriate for the user's emotional state.

[1269] (Application example 2)

[1270] 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."

[1271] Conventional translation systems simply translate user input data, but are unable to provide translation results that reflect the user's current emotions or usage situation. Furthermore, the mechanisms for incorporating user feedback into the system were inadequate, making it difficult to continuously improve the quality of translation results. This can result in users not receiving optimal translations in real time, leading to a decline in user satisfaction. Furthermore, advertising and information provision systems also face the challenge of being unable to provide individualized responses that take emotions and context into account.

[1272] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1273] In this invention, the server includes means for receiving user input data, means for preprocessing the input data, means for translating the preprocessed data, means for adjusting the translation result based on usage status, means for providing the adjusted translation result to the user, means for recognizing the user's emotions using an emotion engine, and means for further adjusting the translation result based on the recognized emotion data. This enables the provision of more appropriate and effective real-time translation according to the user's emotions and current usage status. Furthermore, by further comprising means for receiving user feedback data, means for analyzing the feedback data, means for updating the translation model based on the analyzed data, and means for adjusting the translation result based on user context data, continuous quality improvement and individual response are possible.

[1274] "User Input Data" means any audio or text information provided by a User to the System.

[1275] "Preprocessing" is the process of removing noise and misrecognition from input data to generate accurate text data.

[1276] A "translation means" is an algorithm or program that converts preprocessed data into a specified language.

[1277] "Usage status" refers to contextual information such as the user's current location, time of day, and user profile.

[1278] "Adjustment" refers to the process of optimizing translation results based on usage and emotional data.

[1279] An "emotion engine" is a program or algorithm for analyzing a user's emotional state from their voice or text.

[1280] "Feedback data" refers to information on evaluations and opinions of users regarding translation results.

[1281] "Analysis" is the process of understanding data and deriving patterns and trends based on feedback and sentiment data.

[1282] A "translation model" is a training algorithm or dataset for converting input data into a different language.

[1283] "Context data" is information about the user's current situation and environment, and is used to optimize translation results.

[1284] System configuration

[1285] This system mainly consists of a server and terminals (smartphones, smart glasses, head-mounted displays, etc.). The server is equipped with a speech recognition algorithm, a translation engine, an emotion recognition engine, and a context adjustment engine, and uses these to process input data in real time. The terminals are devices equipped with a microphone, a display, and internet connectivity.

[1286] Program processing flow

[1287] The server processes the data using the following means:

[1288] 1. Means of receiving user input data

[1289] When a user inputs voice into the terminal, the voice data is collected by the microphone and sent to a server via the Internet.

[1290] 2. Means for preprocessing the input data

[1291] The server uses a speech recognition algorithm to convert the speech to text, filtering out unwanted noise and misrecognitions, resulting in clean text data.

[1292] 3. A translation means for translating the preprocessed data.

[1293] The server inputs the preprocessed text data into a translation engine and translates it into the specified language, for example, using the Google Translate API.

[1294] 4. Means for adjusting the translation results based on usage conditions

[1295] The server collects contextual data such as the user's location and time of day, and then adjusts the translation results based on this information. This step is handled by the context adjustment engine.

[1296] 5. Means for providing the adjusted translation results to users

[1297] The server then sends the adjusted translation results to the terminal, which notifies the user by displaying the results in text and playing them aloud.

[1298] 6. Means of recognizing user emotions using an emotion engine

[1299] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions from voice and text data.

[1300] 7. Means for further adjusting the translation result based on the recognized emotion data

[1301] The server uses emotional data to further optimize the translation results, such as providing more concise information if the user is nervous, or more detailed information if the user is relaxed.

[1302] Hardware and software used

[1303] Hardware: Devices with microphones, displays, and internet connectivity (smartphones, smart glasses, head-mounted displays, etc.)

[1304] Software: Google Speech-to-Text API, Google Translate API, IBM Watson Tone Analyzer

[1305] Specific examples

[1306] Prompt Sentence Examples

[1307] User: "What are the latest sales?"

[1308] Voice data received by the server: "Tell me about the latest sales."

[1309] 1. Text after speech recognition:

[1310] "Tell me the latest sales information"

[1311] 2. Translated English text:

[1312] "Tell me the latest sale information"

[1313] 3. Contextual adjustment:

[1314] Customize based on nearby stores:

[1315] "You are near our store, check out our latest sale on electronics!"

[1316] 4. Emotion recognition:

[1317] User Emotions: Stressed

[1318] Adjusted ad text:

[1319] "Relax and enjoy our exclusive discounts on spa packages!"

[1320] 5. Final Ad Delivery:

[1321] The text "Relax and enjoy our exclusive discounts on spa packages!" is displayed on the smart glasses' display and played aloud.

[1322] In this way, the present invention realizes a system that adjusts translation results based on the user's emotions and context, and provides optimal information in real time.

[1323] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1324] Step 1:

[1325] The user inputs voice into the device. Specifically, when the user says, "Tell me about the latest sales," the device's microphone collects this voice and converts it into digital voice data. The input is the user's voice data, and this voice data is sent to the server via the Internet.

[1326] Step 2:

[1327] The server converts the received voice data into text data using a speech recognition algorithm (such as the Google Speech-to-Text API). It removes noise and misrecognition to generate accurate text data. The input is voice data, and the output is preprocessed text data.

[1328] Step 3:

[1329] The server inputs the preprocessed text data into a translation engine (such as Google Translate API) and translates it into the specified language. The input is the preprocessed text data, and the output is the translated text data. For example, "Tell me the latest sale information" is translated into "Tell me the latest sale information."

[1330] Step 4:

[1331] The server collects context data such as the user's location and time of day, and adjusts the translation results based on this. The input is the translated text data and context data, and the output is text data adjusted based on the context. For example, the translation result might be adjusted to "You are near our store, check out our latest sale on electronics!"

[1332] Step 5:

[1333] The server uses an emotion recognition engine (such as IBM Watson Tone Analyzer) to analyze the user's emotions from the input voice or text data. The input is voice data or text data, and the output is data that indicates the user's emotional state.

[1334] Step 6:

[1335] The server further adjusts the translation results based on the emotional data. For example, if the user is stressed, the information is made more concise, and if the user is relaxed, the information is made more detailed. The input is text data that has been adjusted based on the emotional data and context, and the output is the final adjusted text data.

[1336] Step 7:

[1337] The server sends the final adjusted translation result to the device. The device uses the received data to display text and play audio. The input is the final adjusted text data, and the output is information provided to the user visually and audibly. Specifically, the text "Relax and enjoy our exclusive discounts on spa packages!" is displayed on the smart glasses' display and played aloud.

[1338] This series of processing steps allows users to receive optimal translation results that are in line with emotion and context in real time.

[1339] 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.

[1340] 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.

[1341] 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.

[1342] [Fourth embodiment]

[1343] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1344] 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.

[1345] 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).

[1346] 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.

[1347] 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.

[1348] 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).

[1349] 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.

[1350] 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.

[1351] 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.

[1352] 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.

[1353] 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.

[1354] 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.

[1355] 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."

[1356] This invention relates to a system that can preprocess user input data in real time and adjust the translation results based on the current situation. Below, as a specific embodiment of the invention, the program processing and flow of the system will be explained in natural language with concrete examples.

[1357] System Program Processing

[1358] A means of receiving user input data

[1359] (User) Installs the smartphone app and prepares to input voice or text for translation.

[1360] (Terminal) Provides an interface that receives data provided by the user via voice input buttons or text input fields. If a user speaks, "Please tell me how to get to the airport," the terminal sends this voice data to the server.

[1361] means for preprocessing the input data;

[1362] (Server) Receives voice data sent from the terminal and converts the voice to text using a speech recognition algorithm. It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data. At this stage, clean text such as "Please tell me how to get to the airport" is obtained.

[1363] a translation means for translating the preprocessed data;

[1364] (Server) The preprocessed text data is input into the translation engine and translated into the specified language. The translation result is "How do I get to the airport?"

[1365] means for adjusting the translation results based on usage conditions;

[1366] (Server) Checks the translation result and adjusts it based on the user's current situation and context (GPS data, time zone, user profile, etc.). For example, if the user is already close to the airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation result more relevant to the local situation.

[1367] Means for providing the adjusted translation result to the user

[1368] (Server) Sends the adjusted translation results to the device.

[1369] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[1370] Specific examples

[1371] Example 1: Japanese to English translation

[1372] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[1373] 2. (Device) Sends voice data to the server.

[1374] 3. (Server) Convert the voice data into text data and perform preprocessing.

[1375] 4. (Server) Translate this as "How do I get to the airport?"

[1376] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[1377] 6. (Server) Sends the adjusted translation results to the device.

[1378] 7. (Device) The translation results are displayed to the user and audio is also played.

[1379] 8. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[1380] Example 2: Updating a model based on user feedback

[1381] 1. (User) After using the translation result "The airport is quite close. How do I get to the airport from here?", enter feedback within the app. Rate the translation as "helpful."

[1382] 2. (Server) Receive user feedback data.

[1383] 3. (Server) Analyze the feedback data and save it as training data.

[1384] 4. (Server) Retrain the translation model using the new feedback data to improve accuracy.

[1385] In this way, the present invention can provide more accurate and useful translation results by translating and adjusting the translation based on real-time input data from the user and by incorporating feedback from the user.

[1386] The processing flow will be explained below.

[1387] Step 1:

[1388] (User) Opens the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[1389] Step 2:

[1390] (Device) The user's voice data is temporarily stored and immediately sent to the server.

[1391] Step 3:

[1392] (Server) Receives voice data from the terminal and converts the voice into text using a voice recognition algorithm.

[1393] Step 4:

[1394] (Server) Remove noise and misrecognitions from the text data and preprocess it into an appropriate format. This results in clean text: "Please tell me how to get to the airport."

[1395] Step 5:

[1396] (Server) The preprocessed text data is input into the "translation means" and translated into the specified language. The translation result is "How do I get to the airport?"

[1397] Step 6:

[1398] (Server) Check the user's current location and situation (e.g. GPS data and time zone) and adjust the translation result based on that context. For example, if the user is already near an airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?"

[1399] Step 7:

[1400] (Server) Sends the adjusted translation results to the device.

[1401] Step 8:

[1402] (Device) The received translation result is displayed to the user and played aloud if necessary. The message "The airport is quite close. How do I get to the airport from here?" is displayed and played aloud.

[1403] Step 9:

[1404] (User) Using the displayed translation results as a reference, ask a local person, "The airport is quite close. How do I get to the airport from here?"

[1405] Step 10:

[1406] (User) Enter feedback on the translation result within the app. For example, rate it as "The translation was helpful."

[1407] Step 11:

[1408] (Server) Receives feedback data from users.

[1409] Step 12:

[1410] (Server) Analyze the received feedback data and save it as learning data.

[1411] Step 13:

[1412] (Server) Retrain the translation model using new feedback data to improve translation accuracy.

[1413] In this way, processing progresses step by step, and a system can be realized that provides optimal real-time translation and support to users.

[1414] Example 1

[1415] 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."

[1416] Conventional translation systems have difficulty preprocessing user input data in real time and adjusting translation results based on the current situation. Furthermore, they are unable to effectively incorporate user feedback, resulting in problems such as reduced translation accuracy and usability. This invention aims to solve these problems and provide users with more accurate and context-appropriate translation results.

[1417] 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.

[1418] In this invention, the server includes means for receiving input data in the form of voice or text from a user, means for preprocessing the input data and converting it into text data using a speech recognition algorithm, means for removing unnecessary noise and misrecognition from the preprocessed text data, means for translating the cleaned text data, means for adjusting the translation result based on the user's location information, time zone, and variables, and means for providing the adjusted translation result to the user. This makes it possible to provide more accurate and current translation results based on the user's real-time input data.

[1419] "User" means an individual or organization that uses this system to input voice or text data and obtain translation results.

[1420] "Voice data" refers to digital data containing linguistic information spoken by a user.

[1421] "Text data" refers to data that includes language information in the form of a string of characters.

[1422] "Preprocessing" refers to the process of converting voice data into text data and then removing noise and misrecognized parts from the text data.

[1423] A "speech recognition algorithm" is a computational method and model for analyzing speech data and converting it into corresponding text data.

[1424] "Noise" refers to unnecessary information or misrecognized parts contained in the voice data or text data, which may reduce translation accuracy.

[1425] A "translator" is an engine or algorithm for converting pre-processed clean text data into a different language.

[1426] "User Location Information" means information about a User's current geographic location obtained using GPS or other means.

[1427] "User's time zone" is information based on the local time when the user uses the system.

[1428] "Feedback data" refers to data that includes users' evaluations and opinions on the translation results.

[1429] A "generative artificial intelligence model" is a computational model that has been trained using machine learning or deep learning to perform a specific task.

[1430] A "database" is a structured collection of data that stores feedback data and other relevant information and is used for analysis and learning.

[1431] "Adjustment" refers to the process of appropriately modifying translation results based on the user's location, time of day, and other variables.

[1432] "Providing means" refers to functions and modules for displaying the adjusted translation results to the user or playing them aloud.

[1433] This invention relates to a system that preprocesses user input data in real time and adjusts translation results based on the current situation. This invention allows users to obtain more accurate and context-appropriate translation results. Specific embodiments for implementing the invention are described below.

[1434] This system combines a speech recognition algorithm, a natural language processing algorithm, a translation engine, and a feedback analysis system. The hardware used includes a server, a terminal (e.g., a smartphone), and an internet connection. The software used includes a speech recognition API, a natural language processing library, a translation API, and a database system.

[1435] Hardware and Software Usage

[1436] (User) Installs the smartphone app, launches the app, and inputs the voice or text to be translated. When the user inputs "Please tell me how to get to the airport," the smartphone's microphone is used to capture the voice data.

[1437] (Device) Provides an interface for transmitting captured voice data to a server. The data is encrypted using a security protocol such as TLS. The device collects data provided by the user via voice input buttons or text input fields, formats it appropriately, and transmits it to the server via the Internet.

[1438] (Server) The received voice data is converted into text data using a speech recognition algorithm. At this stage, the voice is converted into text using, for example, the Google Cloud Speech-to-Text API. The converted text is then cleaned of unnecessary noise and misrecognitions to generate accurate text data. A natural language processing (NLP) system is used for preprocessing to obtain clean text such as "Please tell me how to get to the airport."

[1439] Next, the preprocessed text data is input into a translation engine and translated into the specified language, for example, using the DeepL API or another high-precision translation engine. The resulting translation is "How do I get to the airport?"

[1440] Additionally, the translation will be adjusted based on the user's current situation and context (GPS data, time of day, user profile, etc.). For example, if the user is already close to an airport, the translation will be adjusted to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation more relevant to the local situation.

[1441] The adjusted translation result is sent to the device, where it is displayed to the user and, if necessary, played aloud. The user receives the result, "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[1442] Specific examples

[1443] (Example 1) Translation from Japanese to English

[1444] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[1445] 2. (Device) Sends voice data to the server.

[1446] 3. (Server) Convert the voice data into text data and perform preprocessing.

[1447] 4. (Server) Translate this as "How do I get to the airport?"

[1448] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[1449] 6. (Server) Sends the adjusted translation results to the device.

[1450] 7. (Device) The translation results are displayed to the user and audio is also played.

[1451] 8. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[1452] (Example 2) Model update based on user feedback

[1453] 1. (User) After using the translation result "The airport is quite close. How do I get to the airport from here?", enter feedback within the app. Rate the translation as "helpful."

[1454] 2. (Server) Receive user feedback data.

[1455] 3. (Server) Analyze the feedback data and save it as training data.

[1456] 4. (Server) Retrain the generative AI model with new feedback data to improve accuracy.

[1457] In this way, the present invention translates and adjusts the translation based on real-time user input data, and can also incorporate user feedback to provide more accurate and useful translation results.

[1458] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1459] Step 1:

[1460] (User) opens the smartphone app, presses the voice input button, and says, "Please tell me how to get to the airport." At this time, the input data is the user's voice data, and this voice data is acquired by the device. Input data: User's voice data. Output data: Voice data stored on the device.

[1461] Step 2:

[1462] (Device) The acquired voice data is sent to the server via the internet. At this time, encryption protocols such as TLS are used to ensure data security. Input data: Voice data stored in the device. Output data: Encrypted voice data sent to the server.

[1463] Step 3:

[1464] (Server) Converts the received voice data into text data using a voice recognition algorithm. In this process, for example, a general voice recognition API is used to convert voice to text. Input data: Encrypted voice data. Output data: Converted text data.

[1465] Step 4:

[1466] (Server) A natural language processing algorithm is used to remove unnecessary noise and misrecognition from text data and generate accurate text data. For example, if "Please tell me how to get to the airport" is misrecognized, it is corrected to "Please tell me how to get to the airport." Input data: Converted text data. Output data: Preprocessed, clean text data.

[1467] Step 5:

[1468] (Server) The preprocessed text data is input into the translation engine and translated into the specified language. For example, a highly accurate translation API is used to obtain the translation result "How do I get to the airport?". Input data: Preprocessed, clean text data. Output data: Translated text data.

[1469] Step 6:

[1470] (Server) Adjust the translation result based on the user's location, time zone, and variables. For example, if the user is already close to the airport, adjust it to "The airport is quite close. How do I get to the airport from here?" This operation allows for translation results that are more in line with the context. Input data: Translated text data and the user's location and time zone data. Output data: Translated text data adjusted based on the context.

[1471] Step 7:

[1472] (Server) The adjusted translation results are sent to the terminal. Security is ensured during this process using encryption protocols such as TLS. Input data: Adjusted translation text data. Output data: Adjusted translation data sent to the terminal.

[1473] Step 8:

[1474] (Device) The received adjusted translation result is displayed to the user and played aloud if necessary. This gives the user the result "The airport is quite close. How do I get to the airport from here?" Input data: The sent adjusted translation data. Output data: The translation result displayed on the user's screen or played aloud.

[1475] Step 9:

[1476] (User) Enter feedback on the translation results within the app. Enter an evaluation such as "The translation was helpful" or "The translation was inappropriate." Input data: User feedback data. Output data: Feedback data stored on the device.

[1477] Step 10:

[1478] (Terminal) Feedback data from the user is sent to the server. Here too, data security is ensured using encryption protocols such as TLS. Input data: Feedback data stored in the terminal. Output data: Feedback data sent to the server.

[1479] Step 11:

[1480] (Server) Receives the feedback data, analyzes it, and stores it in a database. Then, it retrains the generative AI model based on the stored feedback data to improve the model's accuracy. Input data: Feedback data sent to the server. Output data: Updated generative AI model.

[1481] In this way, specific operations are performed at each step, and the system provides more appropriate translation results to the user.

[1482] (Application example 1)

[1483] 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."

[1484] Conventional translation systems have difficulty providing flexible translation that takes into account the user's current situation and profile information. In addition, in certain scenarios, such as food delivery, it is necessary to provide a better user experience by providing appropriate translation in real time. Therefore, there is a demand for a translation system that reflects local conditions and user history information.

[1485] 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.

[1486] In this invention, the server includes means for adjusting the translation result taking into account the user's profile data, means for improving the translation result based on the user's history data and current situation data, and means for converting the voice data into text data, thereby enabling more accurate real-time translation based on the local situation and the user's profile information.

[1487] "User input data" refers to voice and text data that a user provides to the system.

[1488] "Preprocessing" refers to the process of removing noise and misrecognition from input data and converting it into a format suitable for analysis.

[1489] The "translation means" is a means for translating the preprocessed text data into a specified language.

[1490] "Means for adjusting based on usage situation" refers to means for correcting and adjusting translation results based on the user's current situation and context.

[1491] "Means for providing to the user" refers to means for providing the adjusted translation results to the user by display or audio.

[1492] "User profile data" is data that includes historical information and current status information about a user.

[1493] "Feedback data" refers to data such as evaluations and comments about system usage provided by users.

[1494] The "means for updating the translation model" refers to a means for retraining the model to improve translation accuracy and applicability based on received feedback data.

[1495] The "means for converting voice data into text data" refers to a means for converting voice input into a string of characters using voice recognition technology.

[1496] This invention relates to a system that preprocesses voice or text data input by a user in real time and provides translation results. The actual system program and its processing content will be described in detail below.

[1497] System Overview

[1498] The system of the present invention includes the following major components:

[1499] 1. Terminal that receives user input data

[1500] 2. Server that preprocesses input data

[1501] 3. Server that translates preprocessed data

[1502] 4. Server that adjusts translation results based on usage

[1503] 5. Device that provides users with adjusted translation results

[1504] Hardware and Software

[1505] Device: A mobile communication device such as a smartphone or tablet. This device is equipped with a microphone for audio input and a speaker for display and audio output.

[1506] Server: A cloud server for speech recognition, pre-processing, translation, and tuning. This server is a computer with a powerful processor and sufficient memory.

[1507] Speech Recognition Library: A software library for speech recognition, such as speech_recognition.

[1508] Translation engine: A software library for translation, such as googletrans.

[1509] Generative AI model: An AI model that updates and trains the translation model based on user feedback and profile data.

[1510] System processing flow

[1511] 1. The user launches the "Food Delivery ChatBot" app and inputs a question via voice or text. The device then sends this input data to the server.

[1512] 2. The server converts the voice data into text data. It uses a speech recognition library (e.g., speech_recognition) to convert the voice data into text data.

[1513] 3. The server preprocesses the text data, removing unnecessary noise and misrecognitions to generate clean data.

[1514] 4. The server translates the preprocessed text data into the specified language using a translation engine (e.g., googletrans).

[1515] 5. Context-sensitive translation: Using user profile data (e.g., location, allergies, order history), the translation is tailored to the local context.

[1516] 6. The adjusted translation result is sent to the device and provided to the user as a display and audio.

[1517] Specific examples

[1518] Example 1: Proposing appropriate alternative menu items for food allergies

[1519] 1. User: "I'm allergic to a certain dish. Can you recommend an alternative menu item?"

[1520] 2. Terminal: Sends voice data to the server.

[1521] 3. Server: Converts voice data into text data and performs preprocessing.

[1522] 4. Server: Translate this to "Please tell me if there are any alternative dishes because I am allergic to a particular dish."

[1523] 5. Server: Adjust the translation to say, "Based on your allergy information, here are some recommended alternative menu items."

[1524] 6. Server: Sends the adjusted translation results to the device.

[1525] 7. Terminal: The translation results are displayed to the user and played aloud.

[1526] 8. User: Tell the restaurant staff, "Please tell me if there are any alternative dishes because I am allergic to a particular dish. Additionally, there are some allergy-free options nearby."

[1527] Prompt Sentence Examples

[1528] Please translate "I'm allergic to a certain dish. Can you recommend an alternative menu item?" into English. And this user is in Tokyo and has a nut allergy. Please add advice based on that information.

[1529] The above is a specific embodiment for carrying out the present invention. The present invention makes it possible to provide a more accurate translation that is in line with the current situation and profile information of the user.

[1530] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1531] Step 1:

[1532] A user launches the "Food Delivery ChatBot" app and enters a question by voice or text. Voice or text data is provided as input. This data is sent from the device to the server as output.

[1533] Step 2:

[1534] The terminal transmits the voice data input by the user to the server. It receives the voice data as input and transmits it as output to the server. Specific operations include capturing the voice with a microphone and transmitting the data to the server via a network.

[1535] Step 3:

[1536] The server uses a speech recognition library (e.g., speech_recognition) to convert the audio data into text data. It takes audio data as input and produces text data as output. The specific operations include applying a speech recognition algorithm to extract text from the audio waveform.

[1537] Step 4:

[1538] The server performs preprocessing to remove unnecessary noise and misrecognition from the text data. It receives text data as input and generates clean text data as output. Specific operations include text cleansing using regular expressions and filtering algorithms.

[1539] Step 5:

[1540] The server uses a translation engine (e.g., googletrans) to translate the preprocessed text data into the specified language. It takes clean text data as input and produces translated text data as output. Specific operations include calling a translation API to convert the text into another language.

[1541] Step 6:

[1542] The server adjusts the translation results based on usage. It references the user's profile data and local information to modify the translation results to fit the context. It takes translated text data and profile data as input and generates an adjusted translation result as output. Specific operations include supplementing and modifying the translated text based on location information, allergy data, etc.

[1543] Step 7:

[1544] The server sends the adjusted translation result to the terminal. It takes the adjusted translation data as input and sends it to the terminal as output. The specific operation includes transmitting the adjusted text via the network.

[1545] Step 8:

[1546] The device displays the translation results to the user and plays them aloud if necessary. It receives the adjusted translation data as input and displays and plays them aloud to the user as output. Specific operations include text display and speech synthesis using a speech synthesis library.

[1547] 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.

[1548] This invention relates to a system that can preprocess user input data in real time and adjust translation results based on the current situation. Furthermore, by combining an emotion engine that recognizes the user's emotions, translation results can be adapted to the user's emotions, providing more appropriate and effective real-time translation. Below, as a specific embodiment of the present invention, the program processing and flow of a system that combines an emotion engine will be explained in natural language, with specific examples.

[1549] System Program Processing

[1550] A means of receiving user input data

[1551] (User) Launches the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[1552] (Terminal) Receives data provided by the user via voice input buttons or text input fields and sends the voice data to the server.

[1553] means for preprocessing the input data;

[1554] (Server) Receives voice data sent from the device and converts the voice to text using a speech recognition algorithm. It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data. At this stage, clean text such as "Please tell me how to get to the airport" is obtained.

[1555] a translation means for translating the preprocessed data;

[1556] (Server) The preprocessed text data is input into the translation engine and translated into the specified language. The translation result is "How do I get to the airport?"

[1557] means for adjusting the translation results based on usage conditions;

[1558] (Server) Checks the translation result and adjusts it based on the user's current situation and context (GPS data, time zone, user profile, etc.). For example, if the user is already close to the airport, adjust the translation result to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation result more relevant to the local situation.

[1559] Means for providing the adjusted translation result to the user

[1560] (Server) Sends the adjusted translation results to the device.

[1561] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[1562] Emotion engine that recognizes user emotions

[1563] (Server) Operates an emotion engine that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the voice input by the user and the emotional expressions contained in the text to recognize the user's emotional state.

[1564] A means for further adjusting the translation result based on the emotion data recognized by the emotion engine.

[1565] (Server) The emotion engine further adjusts the translation results based on the emotional data it recognizes. For example, if the user is in a hurry, the translation results will be adjusted to be concise and easy to understand.

[1566] Specific examples

[1567] Example 1: Japanese to English translation and emotion recognition

[1568] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[1569] 2. (Device) Sends voice data to the server.

[1570] 3. (Server) Convert the voice data into text data and perform preprocessing.

[1571] 4. (Server) Translate this as "How do I get to the airport?"

[1572] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[1573] 6. (Server) The emotion engine analyzes the user's emotions, and if impatience or tension is detected, the translation result is further adjusted to be more concise.

[1574] 7. (Server) The final translation result is sent to the device.

[1575] 8. (Device) The translation results are displayed to the user and audio is also played.

[1576] 9. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[1577] Example 2: Updating emotion models based on user feedback

[1578] 1. (User) Enter feedback on the translation result within the app. For example, feedback including emotions such as "The translation was accurate and helpful" or "I wish it was a little gentler."

[1579] 2. (Server) Receives feedback data and analyzes it, including emotional data.

[1580] 3. (Server) Retrain the emotion recognition model using the new feedback data to improve accuracy.

[1581] In this way, this system, which combines an emotion engine, takes emotion into account in translation and adjusts it based on real-time input data from users, and by incorporating feedback from users, it is possible to provide more accurate and effective translation results.

[1582] The processing flow will be explained below.

[1583] Step 1:

[1584] (User) Opens the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[1585] Step 2:

[1586] (Device) The user's voice data is temporarily stored and immediately sent to the server.

[1587] Step 3:

[1588] (Server) Sends the voice data received from the terminal to a voice recognition algorithm and converts the voice into text.

[1589] Step 4:

[1590] (Server) Remove noise and misrecognitions from the text data and preprocess it into an appropriate format. This results in clean text: "Please tell me how to get to the airport."

[1591] Step 5:

[1592] (Server) The preprocessed text data is input into the translation engine and translated into the specified language (English in this case). The translation result is "How do I get to the airport?"

[1593] Step 6:

[1594] (Server) Check the user's current location and situation (e.g. GPS data and time zone) and adjust the translation result based on that context. For example, if the user is already near an airport, adjust the translation to "The airport is quite close. How do I get to the airport from here?"

[1595] Step 7:

[1596] (Server) Operates an emotion engine that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the voice input by the user and the emotional expressions contained in the text to recognize the user's emotional state.

[1597] Step 8:

[1598] (Server) Based on the emotional data recognized by the emotion engine, the translation result is further adjusted appropriately. If the user is in a hurry, the translation result is adjusted to be concise and quickly understandable. For example, "Please hurry. The airport is close. How do I get there?"

[1599] Step 9:

[1600] (Server) Sends the adjusted translation results to the device.

[1601] Step 10:

[1602] (Device) The received translation result is displayed to the user and played aloud if necessary. The message "Please hurry. The airport is closed. How do I get there?" is displayed and also played aloud.

[1603] Step 11:

[1604] (User) Using the displayed translation results as a reference, ask a local person, "Please hurry. The airport is close. How do I get there?"

[1605] Step 12:

[1606] (User) Enter feedback on the translation result within the app. For example, provide feedback that reflects specific emotions, such as "The translation was accurate and helpful" or "It would have been better if the wording was a little gentler."

[1607] Step 13:

[1608] (Server) Stores and analyzes feedback data received from users. Based on the feedback, it identifies areas that need improvement.

[1609] Step 14:

[1610] (Server) Retrain the emotion recognition model using new feedback data to improve the accuracy of the system.

[1611] In this way, through step-by-step processing, the system, which combines an emotion engine, determines emotions based on real-time user input data and provides accurate translation results according to the situation. Furthermore, by incorporating feedback from users, continuous improvement is possible.

[1612] Example 2

[1613] 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."

[1614] Conventional translation systems are required to translate user input data in a timely and accurate manner. However, because they do not take into account the user's emotions or usage context, the translation results are often inappropriate for actual usage scenarios. In addition, there is a lack of a mechanism for updating the translation model based on feedback. This makes it difficult to provide users with more appropriate and effective translation results.

[1615] 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.

[1616] In this invention, the server includes means for receiving user input data, means for preprocessing the input data, means for translating the preprocessed data, means for adjusting the translation result based on usage conditions, means for providing the adjusted translation result to the user, means for recognizing the user's emotions, and means for further adjusting the translation result based on the emotion data. This makes it possible to provide translation results that reflect the user's emotions and usage conditions.

[1617] "Means for receiving user input data" refers to a device or interface that has the function of incorporating information input by the user via voice or text into the system.

[1618] The "means for preprocessing the input data" refers to a device or algorithm that has the function of removing unnecessary noise and misrecognition from the input data and converting it into accurate text data.

[1619] The "translation means for translating the preprocessed data" refers to an engine or software for translating the preprocessed text data into another language.

[1620] The "means for adjusting the translation result based on usage" refers to a device or algorithm that has the ability to adjust the translated text based on the user's current situation or context.

[1621] The "means for providing the adjusted translation result to the user" refers to a device or interface that has the function of displaying or audibly providing the adjusted translation result to the user.

[1622] The "means for recognizing user emotions" refers to a device or algorithm that has the function of analyzing the user's voice tone and speed, and emotional expressions contained in the text, to identify the user's emotional state.

[1623] The "means for further adjusting the translation result based on the emotion data" refers to a device or algorithm that has the function of further appropriately adjusting the translation result based on the recognized emotion data.

[1624] The "means for receiving user feedback data" refers to a device or interface that has the function of incorporating user opinions and thoughts about the translation results into the system.

[1625] The "means for analyzing the feedback data" refers to a device or algorithm that has the function of analyzing the captured feedback data and extracting useful information.

[1626] The "means for updating the translation model based on the analyzed data" refers to a device or algorithm that has the function of improving and updating the translation model based on the analyzed feedback data.

[1627] "Voice data" refers to information input by voice by the user.

[1628] "Text data" refers to character information generated by converting voice data.

[1629] The present invention relates to a system that can preprocess user input data in real time and adjust translation results based on the current situation. Furthermore, by combining an emotion engine that recognizes the user's emotions, the translation results can be adapted to the user's emotions, providing more appropriate and effective real-time translation. Below, as a specific embodiment of the present invention, the program processing and flow of a system that combines an emotion engine will be explained in natural language, with specific examples.

[1630] A means of receiving user input data

[1631] (User) Launches the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[1632] (Device) Receives data provided by the user via voice input buttons or text input fields, and sends the voice data to a server. This process uses hardware called a smartphone and application software that provides voice input functionality.

[1633] means for preprocessing the input data;

[1634] (Server) Receives voice data sent from the device and converts the voice to text using a speech recognition algorithm (e.g., Google Cloud Speech-to-Text API). It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data. This process uses a high-performance server and a cloud service that provides speech recognition technology.

[1635] a translation means for translating the preprocessed data;

[1636] (Server) The preprocessed text data is input into a translation engine (e.g., Google Translate API) and translated into the specified language. The translation result, "How do I get to the airport?", is generated. This process also uses a high-performance server and a cloud platform that provides translation services.

[1637] means for adjusting the translation results based on usage conditions;

[1638] (Server) Checks the translation result and adjusts it based on the user's current situation and context (e.g., GPS data, time zone, user profile). For example, if the user is already close to the airport, adjusts the translation result to "The airport is quite close. How do I get to the airport from here?" This adjustment makes the translation result more relevant to the local situation. At this stage, satellite communication technology is used to obtain GPS data, and technology is used to reference the user profile by linking with a database.

[1639] Means for providing the adjusted translation result to the user

[1640] (Server) Sends the adjusted translation results to the device.

[1641] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person. This process uses the smartphone's display and speaker.

[1642] Emotion engine that recognizes user emotions

[1643] (Server) Operates an emotion engine (e.g., emotion recognition algorithm) that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the user's voice input and the emotional expressions contained in the text to recognize the user's emotional state. This allows the system to respond more appropriately based on the user's current emotions.

[1644] means for further adjusting the translation result based on the emotion data;

[1645] (Server) Based on the emotional data recognized by the emotion engine, the translation results are further adjusted appropriately. For example, if the user is in a hurry, the translation results are adjusted to be concise and quickly understandable. This process uses advanced emotion analysis technology and algorithms to dynamically change the translation results.

[1646] Specific examples

[1647] Example 1: Japanese to English translation and emotion recognition

[1648] 1. (User) Speaks into his smartphone, "Please tell me how to get to the airport."

[1649] 2. (Device) Sends voice data to the server.

[1650] 3. (Server) Convert the voice data into text data and perform preprocessing.

[1651] 4. (Server) Translate this as "How do I get to the airport?"

[1652] 5. (Server) Determines that the user is near the airport and responds with, "The airport is quite close. How do I get to the airport from here?"

[1653] 6. (Server) The emotion engine analyzes the user's emotions, and if impatience or tension is detected, the translation result is further adjusted to be more concise.

[1654] 7. (Server) The final translation result is sent to the device.

[1655] 8. (Device) The translation results are displayed to the user and audio is also played.

[1656] 9. (User) Asks a local person, "The airport is quite close. How do I get to the airport from here?"

[1657] Prompt Sentence Examples

[1658] 1. What is the process for speech recognition using natural language processing (NLP) models?

[1659] 2. Describe the specific algorithm that converts audio data into text.

[1660] 3. How does the emotion recognition engine work and how does its data affect the translation results?

[1661] In this way, this system, which combines an emotion engine, takes emotion into account in translation and adjusts it based on real-time input data from users, and by incorporating feedback from users, it is possible to provide more accurate and effective translation results.

[1662] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1663] Step 1:

[1664] (User) Launches the smartphone app, presses the voice input button and says, "Please tell me how to get to the airport."

[1665] Input: User's voice data

[1666] Output: Audio data

[1667] Specific operation: The user operates the smartphone and taps the voice input button. At this point, voice input begins and the smartphone's built-in microphone collects the user's voice.

[1668] Step 2:

[1669] (Device) Receives user voice input and temporarily stores the voice data internally. Once the voice input is complete, the voice data is sent to the server.

[1670] Input: Audio data

[1671] Output: Audio data sent to the server

[1672] Specific operation: The terminal detects the completion of voice input and sends the voice data to the server via the network module.

[1673] Step 3:

[1674] (Server) Receives voice data sent from the device and converts the voice into text using a voice recognition algorithm (e.g., voice recognition API). It also removes unnecessary noise and misrecognition from the converted text to generate accurate text data.

[1675] Input: Audio data sent to the server

[1676] Output: Clean text data

[1677] What happens: The server invokes a speech recognition algorithm to convert the speech data into text. It then applies a filtering algorithm to remove noise and misrecognitions, resulting in the clean text "Please tell me how to get to the airport."

[1678] Step 4:

[1679] (Server) The preprocessed text data is input into a translation engine (e.g., translation API) and translated into the specified language.

[1680] Input: clean text data

[1681] Output: Translated text data ("How do I get to the airport?")

[1682] Specific operation: The server calls the translation engine's API and converts the text data into the specified language. The translation engine returns the translation result to the server.

[1683] Step 5:

[1684] (Server) Checks the translation results and adjusts them based on the user's current situation and context (e.g., GPS data, time zone, user profile).

[1685] Input: translated text data, GPS data, time zone, user profile

[1686] Output: Adjusted translation result ("The airport is quite close. How do I get to the airport from here?")

[1687] How it works: The server obtains the user's current location (GPS data) and inputs it into the translation result adjustment logic, which then adjusts the resulting text appropriately and generates a new translation.

[1688] Step 6:

[1689] (Server) Sends the adjusted translation results to the device.

[1690] Input: Adjusted translation result

[1691] Output: Adjusted translation results sent to your device

[1692] Specific operation: The server generates the adjusted translation result and sends the data to the terminal via the network module.

[1693] Step 7:

[1694] (Device) The received translation result is displayed to the user and played aloud if necessary. The user receives the result "The airport is quite close. How do I get to the airport from here?" and can ask a local person.

[1695] Input: Adjusted translation results sent from the server

[1696] Output: The translation results that are displayed and played back to the user

[1697] Specific operation: The translation result is displayed on the device display and the result is played back using the voice module.

[1698] Step 8:

[1699] (Server) Operates an emotion engine (e.g., emotion recognition algorithm) that analyzes the user's emotions from voice and text data. The emotion engine evaluates the tone and speed of the voice input by the user and the emotional expressions contained in the text to recognize the user's emotional state.

[1700] Input: Audio data, text data

[1701] Output: User emotion data

[1702] How it works: The server invokes an emotion recognition algorithm and analyzes the voice and text data to identify the user's emotional state.

[1703] Step 9:

[1704] (Server) The emotion engine further adjusts the translation results based on the emotional data it recognizes. For example, if the user is in a hurry, the translation results will be adjusted to be concise and easy to understand.

[1705] Input: Adjusted translation results, user emotion data

[1706] Output: Translation results further adjusted based on user sentiment

[1707] Specific operation: Emotional data is used to make final adjustments to the translation results, resulting in a translation that is appropriate for the user's emotional state.

[1708] (Application example 2)

[1709] 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."

[1710] Conventional translation systems simply translate user input data, but are unable to provide translation results that reflect the user's current emotions or usage situation. Furthermore, the mechanisms for incorporating user feedback into the system were inadequate, making it difficult to continuously improve the quality of translation results. This can result in users not receiving optimal translations in real time, leading to a decline in user satisfaction. Furthermore, advertising and information provision systems also face the challenge of being unable to provide individualized responses that take emotions and context into account.

[1711] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1712] In this invention, the server includes means for receiving user input data, means for preprocessing the input data, means for translating the preprocessed data, means for adjusting the translation result based on usage status, means for providing the adjusted translation result to the user, means for recognizing the user's emotions using an emotion engine, and means for further adjusting the translation result based on the recognized emotion data. This enables the provision of more appropriate and effective real-time translation according to the user's emotions and current usage status. Furthermore, by further comprising means for receiving user feedback data, means for analyzing the feedback data, means for updating the translation model based on the analyzed data, and means for adjusting the translation result based on user context data, continuous quality improvement and individual response are possible.

[1713] "User Input Data" means any audio or text information provided by a User to the System.

[1714] "Preprocessing" is the process of removing noise and misrecognition from input data to generate accurate text data.

[1715] A "translation means" is an algorithm or program that converts preprocessed data into a specified language.

[1716] "Usage status" refers to contextual information such as the user's current location, time of day, and user profile.

[1717] "Adjustment" refers to the process of optimizing translation results based on usage and emotional data.

[1718] An "emotion engine" is a program or algorithm for analyzing a user's emotional state from their voice or text.

[1719] "Feedback data" refers to information on evaluations and opinions of users regarding translation results.

[1720] "Analysis" is the process of understanding data and deriving patterns and trends based on feedback and sentiment data.

[1721] A "translation model" is a training algorithm or dataset for converting input data into a different language.

[1722] "Context data" is information about the user's current situation and environment, and is used to optimize translation results.

[1723] System configuration

[1724] This system mainly consists of a server and terminals (smartphones, smart glasses, head-mounted displays, etc.). The server is equipped with a speech recognition algorithm, a translation engine, an emotion recognition engine, and a context adjustment engine, and uses these to process input data in real time. The terminals are devices equipped with a microphone, a display, and internet connectivity.

[1725] Program processing flow

[1726] The server processes the data using the following means:

[1727] 1. Means of receiving user input data

[1728] When a user inputs voice into the terminal, the voice data is collected by the microphone and sent to a server via the Internet.

[1729] 2. Means for preprocessing the input data

[1730] The server uses a speech recognition algorithm to convert the speech to text, filtering out unwanted noise and misrecognitions, resulting in clean text data.

[1731] 3. A translation means for translating the preprocessed data.

[1732] The server inputs the preprocessed text data into a translation engine and translates it into the specified language, for example, using the Google Translate API.

[1733] 4. Means for adjusting the translation results based on usage conditions

[1734] The server collects contextual data such as the user's location and time of day, and then adjusts the translation results based on this information. This step is handled by the context adjustment engine.

[1735] 5. Means for providing the adjusted translation results to users

[1736] The server then sends the adjusted translation results to the terminal, which notifies the user by displaying the results in text and playing them aloud.

[1737] 6. Means of recognizing user emotions using an emotion engine

[1738] The server uses an emotion recognition engine (e.g., IBM Watson Tone Analyzer) to analyze the user's emotions from voice and text data.

[1739] 7. Means for further adjusting the translation result based on the recognized emotion data

[1740] The server uses emotional data to further optimize the translation results, such as providing more concise information if the user is nervous, or more detailed information if the user is relaxed.

[1741] Hardware and software used

[1742] Hardware: Devices with microphones, displays, and internet connectivity (smartphones, smart glasses, head-mounted displays, etc.)

[1743] Software: Google Speech-to-Text API, Google Translate API, IBM Watson Tone Analyzer

[1744] Specific examples

[1745] Prompt Sentence Examples

[1746] User: "What are the latest sales?"

[1747] Voice data received by the server: "Tell me about the latest sales."

[1748] 1. Text after speech recognition:

[1749] "Tell me the latest sales information"

[1750] 2. Translated English text:

[1751] "Tell me the latest sale information"

[1752] 3. Contextual adjustment:

[1753] Customize based on nearby stores:

[1754] "You are near our store, check out our latest sale on electronics!"

[1755] 4. Emotion recognition:

[1756] User Emotions: Stressed

[1757] Adjusted ad text:

[1758] "Relax and enjoy our exclusive discounts on spa packages!"

[1759] 5. Final Ad Delivery:

[1760] The text "Relax and enjoy our exclusive discounts on spa packages!" is displayed on the smart glasses' display and played aloud.

[1761] In this way, the present invention realizes a system that adjusts translation results based on the user's emotions and context, and provides optimal information in real time.

[1762] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1763] Step 1:

[1764] The user inputs voice into the device. Specifically, when the user says, "Tell me about the latest sales," the device's microphone collects this voice and converts it into digital voice data. The input is the user's voice data, and this voice data is sent to the server via the Internet.

[1765] Step 2:

[1766] The server converts the received voice data into text data using a speech recognition algorithm (such as the Google Speech-to-Text API). It removes noise and misrecognition to generate accurate text data. The input is voice data, and the output is preprocessed text data.

[1767] Step 3:

[1768] The server inputs the preprocessed text data into a translation engine (such as Google Translate API) and translates it into the specified language. The input is the preprocessed text data, and the output is the translated text data. For example, "Tell me the latest sale information" is translated into "Tell me the latest sale information."

[1769] Step 4:

[1770] The server collects context data such as the user's location and time of day, and adjusts the translation results based on this. The input is the translated text data and context data, and the output is text data adjusted based on the context. For example, the translation result might be adjusted to "You are near our store, check out our latest sale on electronics!"

[1771] Step 5:

[1772] The server uses an emotion recognition engine (such as IBM Watson Tone Analyzer) to analyze the user's emotions from the input voice or text data. The input is voice data or text data, and the output is data that indicates the user's emotional state.

[1773] Step 6:

[1774] The server further adjusts the translation results based on the emotional data. For example, if the user is stressed, the information is made more concise, and if the user is relaxed, the information is made more detailed. The input is text data that has been adjusted based on the emotional data and context, and the output is the final adjusted text data.

[1775] Step 7:

[1776] The server sends the final adjusted translation result to the device. The device uses the received data to display text and play audio. The input is the final adjusted text data, and the output is information provided to the user visually and audibly. Specifically, the text "Relax and enjoy our exclusive discounts on spa packages!" is displayed on the smart glasses' display and played aloud.

[1777] This series of processing steps allows users to receive optimal translation results that are in line with emotion and context in real time.

[1778] 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.

[1779] 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.

[1780] 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.

[1781] 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.

[1782] 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.

[1783] 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.

[1784] 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).

[1785] 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, motorcycles, and other devices, 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.

[1786] 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."

[1787] 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.

[1788] 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).

[1789] 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.

[1790] 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.

[1791] 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.

[1792] 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.

[1793] 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.

[1794] 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.

[1795] 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.

[1796] 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.

[1797] 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.

[1798] 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.

[1799] The following is further disclosed regarding the above embodiment.

[1800] (Claim 1)

[1801] means for receiving user input data;

[1802] means for preprocessing the input data;

[1803] a translation means for translating the preprocessed data;

[1804] means for adjusting the translation result based on usage conditions;

[1805] means for providing the adjusted translation result to a user;

[1806] A system including:

[1807] (Claim 2)

[1808] a means for receiving user feedback data;

[1809] means for analyzing the feedback data;

[1810] means for updating a translation model based on the analyzed data;

[1811] The system of claim 1 further comprising:

[1812] (Claim 3)

[1813] the input data is audio data,

[1814] 10. The system of claim 1, further comprising means for converting the audio data into text data.

[1815] "Example 1"

[1816] (Claim 1)

[1817] means for receiving user input data in the form of voice or text;

[1818] means for preprocessing the input data and converting it into text data using a speech recognition algorithm;

[1819] means for removing unnecessary noise and misrecognition from the preprocessed text data;

[1820] a translation means for translating the clean text data;

[1821] means for adjusting the translation result based on the user's location, time zone, and variables;

[1822] means for providing the adjusted translation result to a user;

[1823] A system including:

[1824] (Claim 2)

[1825] means for receiving, analyzing and storing user feedback data in a database;

[1826] A means for updating the generative artificial intelligence model based on the analyzed feedback data to improve accuracy;

[1827] The system of claim 1 further comprising:

[1828] (Claim 3)

[1829] 2. The system of claim 1, wherein the input data is voice data, and further comprising means for converting the voice data into text data using a natural language processing algorithm.

[1830] "Application Example 1"

[1831] (Claim 1)

[1832] means for receiving user input data;

[1833] means for preprocessing the input data;

[1834] a translation means for translating the preprocessed data;

[1835] means for adjusting the translation result based on usage conditions;

[1836] means for providing the adjusted translation result to a user;

[1837] means for adjusting the translation results taking into account user profile data;

[1838] A system including:

[1839] (Claim 2)

[1840] a means for receiving user feedback data;

[1841] means for analyzing the feedback data;

[1842] means for updating a translation model based on the analyzed data;

[1843] means for improving translation results based on user history data and current situation data;

[1844] The system of claim 1 further comprising:

[1845] (Claim 3)

[1846] the input data is audio data,

[1847] 10. The system of claim 1, further comprising means for converting the audio data into text data.

[1848] "Example 2: Combining Emotion Engines"

[1849] (Claim 1)

[1850] means for receiving user input data;

[1851] means for preprocessing the input data;

[1852] a translation means for translating the preprocessed data;

[1853] means for adjusting the translation result based on usage conditions;

[1854] means for providing the adjusted translation result to a user;

[1855] means for recognizing a user's emotion;

[1856] means for further adjusting the translation result based on the emotion data;

[1857] A system including:

[1858] (Claim 2)

[1859] a means for receiving user feedback data;

[1860] means for analyzing the feedback data;

[1861] means for updating a translation model based on the analyzed data;

[1862] The system of claim 1 further comprising:

[1863] (Claim 3)

[1864] the input data is audio data,

[1865] 10. The system of claim 1, further comprising means for converting the audio data into text data.

[1866] "Application example 2 when combining emotion engines"

[1867] (Claim 1)

[1868] means for receiving user input data;

[1869] means for preprocessing the input data;

[1870] a translation means for translating the preprocessed data;

[1871] means for adjusting the translation result based on usage conditions;

[1872] means for providing the adjusted translation result to a user;

[1873] a means for recognizing a user's emotion by an emotion engine;

[1874] means for further adjusting the translation result based on the recognized emotion data;

[1875] A system including:

[1876] (Claim 2)

[1877] a means for receiving user feedback data;

[1878] means for analyzing the feedback data;

[1879] means for updating a translation model based on the analyzed data;

[1880] including means to tailor translation results based on user context data;

[1881] 10. The system of claim 1.

[1882] (Claim 3)

[1883] the input data is audio data,

[1884] means for converting the voice data into text data;

[1885] 10. The system of claim 1. [Explanation of symbols]

[1886] 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 user input data; means for preprocessing the input data; a translation means for translating the preprocessed data; means for adjusting the translation result based on usage conditions; means for providing the adjusted translation result to a user; A system including:

2. a means for receiving user feedback data; means for analyzing the feedback data; means for updating a translation model based on the analyzed data; The system of claim 1 further comprising:

3. the input data is audio data, 2. The system of claim 1, further comprising means for converting said audio data into text data.

Images