system

Abstract

We provide the system. [Solution] An interface means for receiving user input, A means for receiving the user input and determining its language, A conversion means for translating the aforementioned language into a different language, A generation means for generating a response based on a translated input, A means for translating the generated response into the user's preferred language, A means of communication for sending the translated response to the user, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern times when information is globally available, communication between users using different languages remains a major barrier. This barrier causes misunderstandings and delays in information transmission, especially for users seeking information exchange between different cultures on the Internet. Also, for global companies, providing multilingual support is a major burden in terms of personnel and resources.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides an interface that can translate user input between multiple languages ​​in real time. Specifically, it includes means for receiving user input and determining its language, and automatically converts the input to a different language as needed. Furthermore, it generates a response using a generative AI based on the translated input, translates this response into the user's desired language, and sends it. This enables effective communication across language barriers and can immediately respond to the user's diverse language needs.

[0006] "User input" refers to information such as questions and comments that a user sends to the system through the interface.

[0007] "Interface means" refers to a user interface and related software components that enable a user to input information and interact with the system.

[0008] A "language determination means" is an algorithm or module for automatically identifying and specifying the language of the received user input.

[0009] A "conversion tool" refers to a translation algorithm or software used to convert text written in one language into another language.

[0010] "Generation means" refers to an AI engine or model that automatically generates appropriate responses based on input data or translated text.

[0011] "Communication means" refers to the physical and software communication channels and protocols (e.g., WebSocket, HTTP requests) used to send and receive data between terminals in real time. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), and the like.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0026] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is implemented in a form that provides an interface means that a user accesses through a web browser. The user uses this interface to input questions or comments. The terminal receives the user input and sends the data to the server. The server uses a language determination means to identify the language of the input text and translate it if necessary. The translated text is processed by a generation means to generate an appropriate response. If the generated response is in a different language, the server uses a conversion means to translate the response into the user's desired language. Finally, the server uses a communication means to send this translated response to the user's terminal in real time.

[0034] For example, if a user types "What is the company's refund policy?" in Japanese, the device sends this input to the server. The server detects the input language as Japanese, and the generation engine generates a response stating, "A full refund is available if the product is returned within 30 days of receipt." The server then translates this information into the user's chosen language as needed, and sends it to the device so that it is displayed to users using an English UI as "The company offers a full refund for products returned within 30 days of receipt."

[0035] Such systems allow users to obtain accurate information in real time, and enable companies to communicate smoothly with users even in multilingual environments.

[0036] The following describes the processing flow.

[0037] Step 1:

[0038] The user opens the web browser interface and enters questions or comments into the chat window.

[0039] Step 2:

[0040] The terminal receives user input and sends the data to the server via a real-time communication protocol (e.g., WebSocket or HTTP request). The input data also includes language information used by the user.

[0041] Step 3:

[0042] The server analyzes the user input it receives and automatically identifies the language of the input using a language detection mechanism. If the detected language differs from the system's default language, a translation mechanism is used to convert the input into a language that the system can process.

[0043] Step 4:

[0044] The server passes the translated input data to the generation mechanism, and the AI ​​engine generates an appropriate response based on it. The generation engine provides accurate and effective content in response to the user's question, based on the training data.

[0045] Step 5:

[0046] If the server needs to translate the generated response into the user's language, it will use the translation means again to translate the response into the user's language.

[0047] Step 6:

[0048] The server sends the translated response to the terminal using a real-time communication protocol.

[0049] Step 7:

[0050] The system displays the responses received by the terminal in the chat window, allowing the user to see the system's reply. The user can continue interacting with the system by entering further questions.

[0051] (Example 1)

[0052] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0053] In a multilingual environment, users are required to obtain accurate information in real time. To achieve this smoothly, it is necessary to automatically determine the target language and quickly generate a response in the appropriate language. However, existing technologies have challenges in efficiently translating information and generating responses across multiple languages, resulting in a lack of improvement in the user experience.

[0054] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0055] In this invention, the server includes means for providing an interface for receiving user input, means including a terminal device for receiving the user input and transmitting the information to the server, means for determining the language of the information, conversion means for translating the determined language into a different language, generation means for using a generation model to generate a response based on the translated information, means for translating the generated response back into the language of the user, and means for communicating to send the translated response to the user. This enables rapid and accurate information acquisition in a multilingual environment.

[0056] An "interface" is a means by which a user connects to a system and provides input.

[0057] A "terminal device" is a device that receives user input and transmits that input to a server.

[0058] "Information" refers to data entered by the user and related processed data.

[0059] A "language determination means" is a means that has the function of identifying the language of the received information.

[0060] A "conversion means" is a means for translating the determined language into a specified different language.

[0061] "Generative means" refers to means that use a generative model to generate a response based on translated information.

[0062] A "generative model" is an algorithm or system based on artificial intelligence technology that generates appropriate responses from input information.

[0063] "Communication means" refers to a means that has the function of data transmission for sending the generated response to the user.

[0064] A "multilingual environment" refers to a situation or context in which multiple different languages ​​are used.

[0065] This invention is a system that enables users to obtain accurate information in real time in a multilingual environment. The system consists of three main elements: the user, the terminal, and the server.

[0066] Users access the interface using a web browser and enter questions or comments. These inputs are structured as specific questions, such as "What is the company's refund policy?". The terminal receiving the user input encrypts the information and securely transmits it to the server.

[0067] The server uses language detection software to determine the language of the received input data. For example, it may use an API that leverages natural language processing technology to identify the input language. If the identified language differs from the language requested by the user, the server uses a translation tool to convert the language. For this purpose, for example, a translation algorithm based on a neural network may be used.

[0068] The server then uses a generative AI model to generate an appropriate response to the user's question. For example, the OpenAI® GPT series can be used as the generative AI model. An example of a prompt for response generation is, "Please provide detailed information about the company's refund policy in Japanese."

[0069] If the generated response needs to be provided in a different language, the server uses the translation mechanism again to translate the response into the required language. Finally, the server sends the obtained response in real time to the user's terminal via the communication mechanism. This system allows users to quickly and smoothly access the necessary information even in a multilingual environment.

[0070] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0071] Step 1:

[0072] Users access the interface using a web browser and enter their questions or comments. An example question is, "What is the company's refund policy?" The input data is sent to the terminal in string format.

[0073] Step 2:

[0074] The terminal encrypts the input data received from the user and securely sends it to the server. The HTTPS protocol is used for transmission, and the input data arrives at the server in an encrypted state. The input in this step is string data, and the output is encrypted data sent to the server.

[0075] Step 3:

[0076] The server decrypts the received encrypted data and extracts the string data. Next, it uses language detection software to determine the language of the extracted string. If it identifies that the input is in Japanese, it sends this information to the next step. Here, the input is the decrypted string data, and the output is language information.

[0077] Step 4:

[0078] The server uses a generative AI model to generate a response appropriate to the question based on the user's language. The generative AI model is input with the prompt "Please provide detailed information about the company's refund policy in Japanese." The response generation process uses natural language processing technology, and a response sentence is generated as output. This response sentence is output as information such as "A full refund is possible within 30 days of receiving the product."

[0079] Step 5:

[0080] The server determines whether the generated response needs to be provided in a different language. If necessary, it uses a translation mechanism to translate the generated response into the user's preferred language. The input in this step is the generated response, and the output is the translated response in the user's preferred language.

[0081] Step 6:

[0082] Finally, the server sends the translated response to the user's terminal in real time using a communication method. The HTTPS protocol is also used for this data transmission, and the user checks the response to their question on the browser screen. The input is the response text in the user's preferred language, and the output is the information displayed on the user's terminal.

[0083] (Application Example 1)

[0084] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0085] Recent advancements in information and communication technology have made multilingual communication commonplace. However, facilitating smooth communication between different languages ​​in real-time environments such as live streaming remains challenging. In particular, rapid and accurate translation is essential for real-time communication with viewers who speak diverse languages. Therefore, there is a need to provide a system that supports real-time translation in live streaming environments.

[0086] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0087] In this invention, the server includes data receiving means for receiving user input, means for receiving the user input and determining its natural language, and data conversion means for translating the natural language into a different natural language. This enables smooth communication with viewers who speak different languages ​​by translating viewer questions in real time during live streaming and presenting them to the streamer.

[0088] A "data reception device" is an interface device for receiving input information from a user.

[0089] A "natural language" is a language that humans use on a daily basis and is not constrained by specific technologies or protocols.

[0090] "Data conversion means" refers to a process or device for converting input natural language into a different natural language.

[0091] "Data generation means" refers to a process or apparatus for creating a corresponding response message based on translated input information.

[0092] "Data communication means" refers to communication devices that transmit generated response messages to a user via a network and protocol.

[0093] "Information processing means" refers to a device or program that processes questions from viewers in real time in a live streaming environment and translates and provides them in the natural language used by the streamer.

[0094] An "open connectivity protocol" is a network protocol that enables continuous data communication and is a standard technology used for bidirectional communication.

[0095] A "machine learning algorithm" is an automated method that enables evolutionary improvement in performance by learning from large datasets.

[0096] The invention will now be described in terms of embodiments for carrying out the invention. The invention is a system that enables real-time communication with multilingual viewers in a live streaming environment. This system is realized by processing input information transmitted from the user's terminal on a server.

[0097] When a user enters a question or comment into a device, the device sends it to a server via a data reception mechanism. The server uses natural language processing technology to determine the language of the received input and translates that natural language into another language using a data conversion mechanism. Machine learning algorithms are used in this translation, and it can be implemented using existing translation APIs (for example, Google® Translate API).

[0098] Based on the translated input, the server constructs an appropriate response message using data generation tools. The response message may then be translated again, adapting its natural language to the user's language. Finally, the response is sent to the user via data communication tools. This communication utilizes open connection protocols (such as WebSocket or HTTP) to ensure real-time performance.

[0099] For example, if a Japanese viewer sends a question such as "Please tell me your thoughts on the movie," the server will instantly translate it into English and provide this information to the broadcaster. A prompt such as "Translate and display the user's comment" will be used, and a generative AI model will generate a response. In this way, mutual understanding between multiple languages ​​can be smoothly promoted in the live streaming environment.

[0100] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0101] Step 1:

[0102] The user enters questions or comments into the device. The input is natural language text data, such as "Please tell me your thoughts on the movie." The device sends this text data to the server via a data reception device.

[0103] Step 2:

[0104] The server identifies the language of the received text data. This process uses natural language processing techniques and machine learning algorithms to determine if the data is multilingual. The input is the user's question text, and the output is the identified natural language. The server records the identified natural language and uses it for subsequent processing.

[0105] Step 3:

[0106] The server translates the identified natural language into a specified language. This process uses an existing translation API as a data conversion tool and performs machine translation. The input is the identified natural language text, and the output is the text translated into the specified language. The server then uses this translation result to proceed to the next step.

[0107] Step 4:

[0108] The server generates a response message based on the translated input. In this process, it uses a generative AI model to initiate a prompt and construct an appropriate response. The input is the translated text, and the output is the generated response message. The server records this response and prepares to reply to the user.

[0109] Step 5:

[0110] The server re-translates the generated response message into the user's preferred language as needed. It then uses data conversion to perform another translation and outputs the message in natural language according to the user's language settings.

[0111] Step 6:

[0112] The server sends the completed response message to the user's terminal via a data communication method. An open connection protocol is used for communication to ensure real-time performance. The input is the final response message, and the output is the response displayed on the user's terminal screen. The user receives their response at this stage.

[0113] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0114] The present invention is implemented in a form that provides an interface means for a user to interactively input text. This system sends the data entered by the user through a terminal to a server for analysis, including the context and sentiment of the input.

[0115] The terminal receives user input and forwards it to the server. The server first determines the language of the input and translates it if necessary. After translation, the sentiment engine analyzes the sentiment of the text and assigns sentiment tags such as positive, negative, and neutral. This sentiment information is used by the generative AI to customize an appropriate response.

[0116] The generated response reflects the sentiment analysis results and is composed in a tone that best suits the user's emotions. For example, if the user asks a question expressing dissatisfaction, the generated response will be adjusted to be empathetic. The server translates the generated response into the user's chosen language as needed and finally sends it to the terminal.

[0117] As a concrete example, suppose a user enters "I am very dissatisfied with my recent order." The terminal sends this input to the server, which then determines the language and translates it, and finally recognizes a strong negative emotion through its emotion engine. The generated response will be something empathetic, such as "We apologize for the inconvenience. We will do our best to resolve your issue as quickly as possible." This response is then translated into the user's language, sent back to the terminal, and displayed on the user's screen.

[0118] This feature enhances the user experience and enables smooth communication that transcends language and emotional barriers.

[0119] The following describes the processing flow.

[0120] Step 1:

[0121] The user opens the web browser interface and enters questions or comments into the chat window.

[0122] Step 2:

[0123] The terminal receives user input and sends the input data to the server using a real-time communication protocol (e.g., WebSocket or HTTP request).

[0124] Step 3:

[0125] The server determines the language of the user input it receives and, if necessary, translates the input language into the system's standard processing language using a translation mechanism.

[0126] Step 4:

[0127] The server passes the translated input to the emotion engine, which analyzes the emotional state of the input. The emotion engine recognizes emotions such as positive, negative, and neutral from the input and also evaluates the intensity of those emotions.

[0128] Step 5:

[0129] Based on the sentiment analysis results, the server uses a generation mechanism to produce an appropriate response to user input. The generated response is then adjusted to a tone that corresponds to the user's emotions.

[0130] Step 6:

[0131] The server translates the generated response into the user's preferred language. If necessary, it also makes minor adjustments to convey emotion.

[0132] Step 7:

[0133] The server sends the translated response to the terminal via real-time communication.

[0134] Step 8:

[0135] The device displays the response it receives in the chat window of the user interface, allowing the user to review the reply and initiate the next interaction.

[0136] This series of steps enables thoughtful responses that respond to the user's emotions, leading to more intimate and effective communication.

[0137] (Example 2)

[0138] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0139] Traditional text-based communication systems not only struggle with multilingual communication but also lack the ability to generate appropriate responses that take user emotions into account. This results in a degraded user experience, particularly hindering smooth communication between users with diverse language and emotional backgrounds.

[0140] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0141] In this invention, the server includes an interface device for receiving user input, a device for determining the language, a conversion device for translating into a different language, and an analysis device for analyzing emotions and assigning emotion tags. This makes it possible to provide appropriate and empathetic responses to users, overcoming language and emotional barriers.

[0142] An "interface device" is a component that receives data input from a user.

[0143] A "determination device" is a component that has the function of identifying the language of the input data.

[0144] A "conversion device" is a component that has the function of converting data from one language to another.

[0145] An "analysis device" is a component that has the function of analyzing the sentiment of text and assigning sentiment tags to it.

[0146] A "generator" is a component that has the function of generating responses based on emotional tags.

[0147] A "communication device" is a component that has the function of transmitting generated data to a user.

[0148] A "bidirectional communication protocol" is a means of communication for exchanging data in real time.

[0149] A "machine learning algorithm" is a method that uses data to train a model and automatically perform various tasks.

[0150] An "emotion tag" is an identifier assigned to text to represent the emotions it expresses.

[0151] This invention is a system for realizing natural and empathetic communication with users in real time. This system has a complex processing flow for processing text data entered by the user via a terminal.

[0152] First, the user inputs text via an interface device on the terminal. The terminal receives this input and sends it to the server. The server analyzes the input data using a device that determines the language of the input, and identifies the language of the input.

[0153] Next, if the language differs from the system's common operating language, the server uses a translation device to translate the input data. It is recommended to use a translation system based on commonly used machine learning algorithms for this translation process.

[0154] The translated data is sent to an analysis device where the sentiment of the text is analyzed. Based on the analysis, sentiment tags such as positive, negative, and neutral are assigned, and the data is passed to a generation device. The generation device uses a generative AI model to generate appropriate responses based on the sentiment tags. This generative AI model generates natural-sounding dialogue by using a language model that has been pre-trained on a large amount of data.

[0155] If the generated response requires translation into the user's desired language, it is translated again through a translation device. The server then uses a communication device to send the final response to the terminal. The terminal displays this response on its user interface and provides it to the user.

[0156] For example, if a user enters "I am very dissatisfied with my recent order," the system receives the input data and determines that the emotion is negative. As a result, the generating AI model creates an empathetic response such as "We apologize for the inconvenience. We will do our best to resolve your issue as quickly as possible," and delivers it to the device.

[0157] An example of a prompt is: "Generate an empathetic response in a context where the user expresses dissatisfaction. Input: 'I am very unhappy with my recent order.'" This prompt is an example of generating an emotion-based response.

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] The user enters text into the terminal. The terminal receives this input data via an interface device. The entered data is stored as a text string and prepared for transmission to the server.

[0161] Step 2:

[0162] The terminal sends the received user input data to the server in HTTP request format. The server passes the received text data to a language detection device to identify the input language. During this process, data analysis is performed using a language detection algorithm, and language information is obtained as output.

[0163] Step 3:

[0164] If the detected language differs from the system's common operating language, the server uses a translation device to translate the input data into the common language. The translation device uses a translation engine based on machine learning algorithms to process the input text and output the translated text data.

[0165] Step 4:

[0166] The translated text data is passed to a server-side analysis device for sentiment analysis. The analysis device applies a sentiment analysis algorithm to analyze the sentiment of each sentence and assigns a positive, negative, or neutral sentiment tag. The output is text data tagged with the sentiment tag.

[0167] Step 5:

[0168] Text data tagged with emotion is passed to a generator running a generative AI model. The generator uses this data as a prompt to create an appropriate response using the generative AI model. Emotion tags are taken into consideration during response generation, and an empathetic response text is generated as output.

[0169] Step 6:

[0170] The server then re-translates the generated response into the user's desired language, using a translation device as needed. This translation process also utilizes a machine learning-based translation engine, and the final response text data is output.

[0171] Step 7:

[0172] The server sends the final response to the terminal in HTTP response format. The terminal receives this data and displays it in the user interface. This allows the user to receive a properly processed response, completing the interactive communication.

[0173] (Application Example 2)

[0174] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0175] In modern information systems, language barriers and emotional differences often pose obstacles when providing real-time user support in multiple languages. Furthermore, generating appropriate responses that align with user emotions is a challenging task. Therefore, there is a need to achieve appropriate user support that transcends language barriers while taking emotions into consideration.

[0176] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0177] In this invention, the server includes an input device means for receiving user input, a language determination means for receiving the user input and determining its language, a translation device means for translating the language into a different language, and a response generation means for generating a response corresponding to the analyzed sentiment information. This enables real-time response generation that corresponds to the user's language and sentiment.

[0178] "User input" refers to information, including characters and symbols, that a user sends to the system.

[0179] "Input device means" refers to a physical or virtual device for receiving information from the user.

[0180] A "language determination means" is a technical element for identifying and classifying the language of the received input data.

[0181] "Translation device means" refers to technical means and devices for converting information expressed in one language into another language.

[0182] "Emotion analysis means" refers to technology that detects a user's emotions from the content of input text and classifies them into a specific category.

[0183] "Response generation means" refers to technical elements and devices for creating an appropriate response to the user based on the information obtained.

[0184] "Communication means" refers to network technology used by a system to transmit information to a user.

[0185] A "bidirectional communication protocol" is a communication standard that enables real-time data exchange between a client and a server.

[0186] A "machine learning algorithm" is a mathematical method for learning patterns from data and automatically making predictions or decisions.

[0187] To implement this invention, a terminal for interacting with the user and a server for analyzing input and generating an appropriate response are required. The user inputs text information via the terminal, and the input information is transferred to the server. The server first identifies the language of the received text using a language determination means, and then performs the necessary translation using a translation device means based on the result.

[0188] Next, the sentiment of the translated text is analyzed using sentiment analysis tools. The server uses sentiment analysis technology based on machine learning algorithms to classify the sentiment expressed in the text into categories such as positive, negative, and neutral. Then, a generative AI model is used to generate a response in the most appropriate tone for the user, and this is translated back into the desired language.

[0189] The server sends the generated response to the terminal via a bidirectional communication protocol. This allows the user to immediately obtain a solution or appropriate information, enabling smooth communication.

[0190] As a concrete example, consider a case where a user enters "I am very dissatisfied with my recent order." This statement is sent to the server, and sentiment analysis recognizes a negative emotion, causing the AI ​​to create an empathetic response. Specifically, a response such as "We apologize for the inconvenience. We will do our best to resolve your issue as quickly as possible" is generated. This message is translated into the user's language and returned to the device, thus appropriately addressing the user's dissatisfaction.

[0191] For example, prompts can be used to instruct the AI ​​in the following format: "User input: I am very dissatisfied with my recent order. Generate an empathetic response considering the negative sentiment."

[0192] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0193] Step 1:

[0194] The user uses a terminal to input text. The terminal receives text data from the user, such as "I am very dissatisfied with my recent order," and prepares this data as input data to send to the server.

[0195] Step 2:

[0196] The server processes the received user input using a language detection mechanism. The server identifies the language of the input text and uses this information to determine if translation is necessary. The output is the language detection result.

[0197] Step 3:

[0198] If necessary, the server uses a translation device to translate user input into a different language. This translation uses a machine translation algorithm to generate translated text data based on the input data. The output is the translated text.

[0199] Step 4:

[0200] The server analyzes the sentiment of the translated text or the original text data using sentiment analysis tools. Here, machine learning algorithms are used to output sentiment categories such as positive, negative, and neutral.

[0201] Step 5:

[0202] The server uses a generative AI model to generate appropriate responses that correspond to the user's emotions through a response generation mechanism. During generation, emotional information is input to the AI ​​model using prompt sentences, and responses with an empathetic or problem-solving tone are generated. The output is the generated response sentence.

[0203] Step 6:

[0204] If the server-generated response needs to be translated again into the user's desired language, a translation device is used to perform the translation. The output is the translated response text.

[0205] Step 7:

[0206] The server sends the generated response to the terminal via the communication method. The terminal receives this and displays it on the user's screen. The output is a response message in a format that the user can understand.

[0207] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0208] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0209] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0210] [Second Embodiment]

[0211] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0212] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0213] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0214] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0215] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0216] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0217] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0218] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0219] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0220] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0221] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0222] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0223] This invention is implemented in a form that provides an interface means that a user accesses through a web browser. The user uses this interface to input questions or comments. The terminal receives the user input and sends the data to the server. The server uses a language determination means to identify the language of the input text and translate it if necessary. The translated text is processed by a generation means to generate an appropriate response. If the generated response is in a different language, the server uses a conversion means to translate the response into the user's desired language. Finally, the server uses a communication means to send this translated response to the user's terminal in real time.

[0224] For example, if a user types "What is the company's refund policy?" in Japanese, the device sends this input to the server. The server detects the input language as Japanese, and the generation engine generates a response stating, "A full refund is available if the product is returned within 30 days of receipt." The server then translates this information into the user's chosen language as needed, and sends it to the device so that it is displayed to users using an English UI as "The company offers a full refund for products returned within 30 days of receipt."

[0225] Such systems allow users to obtain accurate information in real time, and enable companies to communicate smoothly with users even in multilingual environments.

[0226] The following describes the processing flow.

[0227] Step 1:

[0228] The user opens the web browser interface and enters questions or comments into the chat window.

[0229] Step 2:

[0230] The terminal receives user input and sends the data to the server via a real-time communication protocol (e.g., WebSocket or HTTP request). The input data also includes language information used by the user.

[0231] Step 3:

[0232] The server analyzes the user input it receives and automatically identifies the language of the input using a language detection mechanism. If the detected language differs from the system's default language, a translation mechanism is used to convert the input into a language that the system can process.

[0233] Step 4:

[0234] The server passes the translated input data to the generation mechanism, and the AI ​​engine generates an appropriate response based on it. The generation engine provides accurate and effective content in response to the user's question, based on the training data.

[0235] Step 5:

[0236] If the server needs to translate the generated response into the user's language, it will use the translation means again to translate the response into the user's language.

[0237] Step 6:

[0238] The server sends the translated response to the terminal using a real-time communication protocol.

[0239] Step 7:

[0240] The system displays the responses received by the terminal in the chat window, allowing the user to see the system's reply. The user can continue interacting with the system by entering further questions.

[0241] (Example 1)

[0242] Next, we will describe Example 1. 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."

[0243] In a multilingual environment, users are required to obtain accurate information in real time. To achieve this smoothly, it is necessary to automatically determine the target language and quickly generate a response in the appropriate language. However, existing technologies have challenges in efficiently translating information and generating responses across multiple languages, resulting in a lack of improvement in the user experience.

[0244] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0245] In this invention, the server includes means for providing an interface for receiving user input, means including a terminal device for receiving the user input and transmitting the information to the server, means for determining the language of the information, conversion means for translating the determined language into a different language, generation means for using a generation model to generate a response based on the translated information, means for translating the generated response back into the language of the user, and means for communicating to send the translated response to the user. This enables rapid and accurate information acquisition in a multilingual environment.

[0246] An "interface" is a means by which a user connects to a system and provides input.

[0247] A "terminal device" is a device that receives user input and transmits that input to a server.

[0248] "Information" refers to data entered by the user and related processed data.

[0249] A "language determination means" is a means that has the function of identifying the language of the received information.

[0250] A "conversion means" is a means for translating the determined language into a specified different language.

[0251] "Generative means" refers to means that use a generative model to generate a response based on translated information.

[0252] A "generative model" is an algorithm or system based on artificial intelligence technology that generates appropriate responses from input information.

[0253] "Communication means" refers to a means that has the function of data transmission for sending the generated response to the user.

[0254] A "multilingual environment" refers to a situation or context in which multiple different languages ​​are used.

[0255] This invention is a system that enables users to obtain accurate information in real time in a multilingual environment. The system consists of three main elements: the user, the terminal, and the server.

[0256] Users access the interface using a web browser and enter questions or comments. These inputs are structured as specific questions, such as "What is the company's refund policy?". The terminal receiving the user input encrypts the information and securely transmits it to the server.

[0257] The server uses language detection software to determine the language of the received input data. For example, it may use an API that leverages natural language processing technology to identify the input language. If the identified language differs from the language requested by the user, the server uses a translation tool to convert the language. For this purpose, for example, a translation algorithm based on a neural network may be used.

[0258] The server then uses a generative AI model to generate an appropriate response to the user's question. For example, OpenAI's GPT series can be used as the generative AI model. An example of a prompt for response generation is, "Please provide detailed information about the company's refund policy in Japanese."

[0259] If the generated response needs to be provided in a different language, the server uses the translation mechanism again to translate the response into the required language. Finally, the server sends the obtained response in real time to the user's terminal via the communication mechanism. This system allows users to quickly and smoothly access the necessary information even in a multilingual environment.

[0260] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0261] Step 1:

[0262] Users access the interface using a web browser and enter their questions or comments. An example question is, "What is the company's refund policy?" The input data is sent to the terminal in string format.

[0263] Step 2:

[0264] The terminal encrypts the input data received from the user and securely sends it to the server. The HTTPS protocol is used for transmission, and the input data arrives at the server in an encrypted state. The input in this step is string data, and the output is encrypted data sent to the server.

[0265] Step 3:

[0266] The server decrypts the received encrypted data and extracts the string data. Next, it uses language detection software to determine the language of the extracted string. If it identifies that the input is in Japanese, it sends this information to the next step. Here, the input is the decrypted string data, and the output is language information.

[0267] Step 4:

[0268] The server uses a generative AI model to generate a response appropriate to the question based on the user's language. The generative AI model is input with the prompt "Please provide detailed information about the company's refund policy in Japanese." The response generation process uses natural language processing technology, and a response sentence is generated as output. This response sentence is output as information such as "A full refund is possible within 30 days of receiving the product."

[0269] Step 5:

[0270] The server determines whether the generated response needs to be provided in a different language. If necessary, it uses a translation mechanism to translate the generated response into the user's preferred language. The input in this step is the generated response, and the output is the translated response in the user's preferred language.

[0271] Step 6:

[0272] Finally, the server sends the translated response to the user's terminal in real time using a communication method. The HTTPS protocol is also used for this data transmission, and the user checks the response to their question on the browser screen. The input is the response text in the user's preferred language, and the output is the information displayed on the user's terminal.

[0273] (Application Example 1)

[0274] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0275] Recent advancements in information and communication technology have made multilingual communication commonplace. However, facilitating smooth communication between different languages ​​in real-time environments such as live streaming remains challenging. In particular, rapid and accurate translation is essential for real-time communication with viewers who speak diverse languages. Therefore, there is a need to provide a system that supports real-time translation in live streaming environments.

[0276] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0277] In this invention, the server includes data reception means for receiving user input, means for receiving the user input and determining its natural language, and data conversion means for translating the natural language into a different natural language. Thereby, during live distribution, questions from viewers are translated in real time and presented to the distributor, enabling smooth communication with viewers who speak different languages.

[0278] The "data reception means" is an interface device for receiving input information from a user.

[0279] The "natural language" is the language that humans use daily and is not restricted by specific technologies or protocols.

[0280] The "data conversion means" is a process or device for converting the input natural language into a different natural language.

[0281] The "data generation means" is a process or device for creating a corresponding response message based on the translated input information.

[0282] The "data communication means" is a communication device via a network and protocol for transmitting the generated response message to the user.

[0283] The "information processing means" is a device or program for processing questions from viewers in real time in a live distribution environment, translating them into the natural language used by the distributor, and providing them.

[0284] The "open connection protocol" is a network protocol for enabling continuous data communication and is a standard technology used for two-way communication.

[0285] The "machine learning algorithm" is an automated method that enables performance improvement evolutionarily by learning from a large dataset.

[0286] A mode for implementing the invention will be described. The invention is a system that enables real-time communication with multilingual viewers in a live streaming environment. This system is realized by processing input information transmitted from a terminal used by a user in a server.

[0287] When a user inputs a question or comment into the terminal, the terminal transmits it to the server via data reception means. The server uses natural language processing technology to determine the language of the received input information and translates the natural language into a different language by data conversion means. A machine learning algorithm is utilized for this translation, and it can be implemented using an existing translation API (for example, Google Translate API).

[0288] Based on the translated input, the server constructs an appropriate response message using data generation means. Thereafter, the response message may be translated again, and the translation is performed in a form that matches the natural language to the language used by the user. Finally, the response is transmitted to the user via data communication means. An open connection protocol (for example, technologies such as WebSocket or HTTP) is used for this communication to ensure real-time performance.

[0289] As a specific example, when a Japanese viewer sends a question such as "Please tell me your impressions of the movie," the server immediately translates it into English and provides this information to the streamer. Using a prompt such as "Translate the user's comment before displaying it," a response is generated using a generative AI model. In this way, mutual understanding among multiple languages can be smoothly advanced in the live streaming session.

[0290] The flow of specific processing in Application Example 1 will be described using FIG. 12.

[0291] Step 1:

[0292] The user enters questions or comments into the device. The input is natural language text data, such as "Please tell me your thoughts on the movie." The device sends this text data to the server via a data reception device.

[0293] Step 2:

[0294] The server identifies the language of the received text data. This process uses natural language processing techniques and machine learning algorithms to determine if the data is multilingual. The input is the user's question text, and the output is the identified natural language. The server records the identified natural language and uses it for subsequent processing.

[0295] Step 3:

[0296] The server translates the identified natural language into a specified language. This process uses an existing translation API as a data conversion tool and performs machine translation. The input is the identified natural language text, and the output is the text translated into the specified language. The server then uses this translation result to proceed to the next step.

[0297] Step 4:

[0298] The server generates a response message based on the translated input. In this process, it uses a generative AI model to initiate a prompt and construct an appropriate response. The input is the translated text, and the output is the generated response message. The server records this response and prepares to reply to the user.

[0299] Step 5:

[0300] The server re-translates the generated response message into the user's preferred language as needed. It then uses data conversion to perform another translation and outputs the message in natural language according to the user's language settings.

[0301] Step 6:

[0302] The server sends the completed response message to the user's terminal via a data communication method. An open connection protocol is used for communication to ensure real-time performance. The input is the final response message, and the output is the response displayed on the user's terminal screen. The user receives their response at this stage.

[0303] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0304] The present invention is implemented in a form that provides an interface means for a user to interactively input text. This system sends the data entered by the user through a terminal to a server for analysis, including the context and sentiment of the input.

[0305] The terminal receives user input and forwards it to the server. The server first determines the language of the input and translates it if necessary. After translation, the sentiment engine analyzes the sentiment of the text and assigns sentiment tags such as positive, negative, and neutral. This sentiment information is used by the generative AI to customize an appropriate response.

[0306] The generated response reflects the sentiment analysis results and is composed in a tone that best suits the user's emotions. For example, if the user asks a question expressing dissatisfaction, the generated response will be adjusted to be empathetic. The server translates the generated response into the user's chosen language as needed and finally sends it to the terminal.

[0307] As a specific example, assume that the user inputs "I am very dissatisfied with my recent order." The terminal sends this input to the server. After the server determines the language and performs translation, it recognizes a strong negative emotion through the emotion engine. As the generated response, content expressing empathy such as "We apologize for the inconvenience. We will do our best to quickly resolve your issue." is selected. This response is translated into the user's language and then sent back to the terminal and displayed on the user's screen.

[0308] With this function, the system improves the user experience and realizes smooth communication across language and emotion barriers.

[0309] The following describes the processing flow.

[0310] Step 1:

[0311] The user opens the interface of the web browser and enters questions or comments in the chat window.

[0312] Step 2:

[0313] The terminal receives the user's input and uses a real-time communication protocol (e.g., WebSocket or HTTP request) to send the input data to the server.

[0314] Step 3:

[0315] The server determines the language of the received user input and, if necessary, translates the input language into the system's standard processing language using translation means.

[0316] Step 4:

[0317] The server passes the translated input to the emotion engine to analyze the emotional state of the input. The emotion engine recognizes emotions such as positive, negative, and neutral from the input and also evaluates the intensity of the emotion.

[0318] Step 5:

[0319] Based on the sentiment analysis results, the server uses a generation mechanism to produce an appropriate response to user input. The generated response is then adjusted to a tone that corresponds to the user's emotions.

[0320] Step 6:

[0321] The server translates the generated response into the user's preferred language. If necessary, it also makes minor adjustments to convey emotion.

[0322] Step 7:

[0323] The server sends the translated response to the terminal via real-time communication.

[0324] Step 8:

[0325] The device displays the response it receives in the chat window of the user interface, allowing the user to review the reply and initiate the next interaction.

[0326] This series of steps enables thoughtful responses that respond to the user's emotions, leading to more intimate and effective communication.

[0327] (Example 2)

[0328] Next, we will describe Example 2. 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".

[0329] Traditional text-based communication systems not only struggle with multilingual communication but also lack the ability to generate appropriate responses that take user emotions into account. This results in a degraded user experience, particularly hindering smooth communication between users with diverse language and emotional backgrounds.

[0330] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0331] In this invention, the server includes an interface device for receiving user input, a device for determining the language, a conversion device for translating into a different language, and an analysis device for analyzing emotions and assigning emotion tags. This makes it possible to provide appropriate and empathetic responses to users, overcoming language and emotional barriers.

[0332] An "interface device" is a component that receives data input from a user.

[0333] A "determination device" is a component that has the function of identifying the language of the input data.

[0334] A "conversion device" is a component that has the function of converting data from one language to another.

[0335] An "analysis device" is a component that has the function of analyzing the sentiment of text and assigning sentiment tags to it.

[0336] A "generator" is a component that has the function of generating responses based on emotional tags.

[0337] A "communication device" is a component that has the function of transmitting generated data to a user.

[0338] A "bidirectional communication protocol" is a means of communication for exchanging data in real time.

[0339] A "machine learning algorithm" is a method that uses data to train a model and automatically perform various tasks.

[0340] An "emotion tag" is an identifier assigned to text to represent the emotions it expresses.

[0341] This invention is a system for realizing natural and empathetic communication with users in real time. This system has a complex processing flow for processing text data entered by the user via a terminal.

[0342] First, the user inputs text via an interface device on the terminal. The terminal receives this input and sends it to the server. The server analyzes the input data using a device that determines the language of the input, and identifies the language of the input.

[0343] Next, if the language differs from the system's common operating language, the server uses a translation device to translate the input data. It is recommended to use a translation system based on commonly used machine learning algorithms for this translation process.

[0344] The translated data is sent to an analysis device where the sentiment of the text is analyzed. Based on the analysis, sentiment tags such as positive, negative, and neutral are assigned, and the data is passed to a generation device. The generation device uses a generative AI model to generate appropriate responses based on the sentiment tags. This generative AI model generates natural-sounding dialogue by using a language model that has been pre-trained on a large amount of data.

[0345] If the generated response requires translation into the user's desired language, it is translated again through a translation device. The server then uses a communication device to send the final response to the terminal. The terminal displays this response on its user interface and provides it to the user.

[0346] For example, if a user enters "I am very dissatisfied with my recent order," the system receives the input data and determines that the emotion is negative. As a result, the generating AI model creates an empathetic response such as "We apologize for the inconvenience. We will do our best to resolve your issue as quickly as possible," and delivers it to the device.

[0347] An example of a prompt is: "Generate an empathetic response in a context where the user expresses dissatisfaction. Input: 'I am very unhappy with my recent order.'" This prompt is an example of generating an emotion-based response.

[0348] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0349] Step 1:

[0350] The user enters text into the terminal. The terminal receives this input data via an interface device. The entered data is stored as a text string and prepared for transmission to the server.

[0351] Step 2:

[0352] The terminal sends the received user input data to the server in HTTP request format. The server passes the received text data to a language detection device to identify the input language. During this process, data analysis is performed using a language detection algorithm, and language information is obtained as output.

[0353] Step 3:

[0354] If the detected language differs from the system's common operating language, the server uses a translation device to translate the input data into the common language. The translation device uses a translation engine based on machine learning algorithms to process the input text and output the translated text data.

[0355] Step 4:

[0356] The translated text data is passed to a server-side analysis device for sentiment analysis. The analysis device applies a sentiment analysis algorithm to analyze the sentiment of each sentence and assigns a positive, negative, or neutral sentiment tag. The output is text data tagged with the sentiment tag.

[0357] Step 5:

[0358] Text data tagged with emotion is passed to a generator running a generative AI model. The generator uses this data as a prompt to create an appropriate response using the generative AI model. Emotion tags are taken into consideration during response generation, and an empathetic response text is generated as output.

[0359] Step 6:

[0360] The server then re-translates the generated response into the user's desired language, using a translation device as needed. This translation process also utilizes a machine learning-based translation engine, and the final response text data is output.

[0361] Step 7:

[0362] The server sends the final response to the terminal in HTTP response format. The terminal receives this data and displays it in the user interface. This allows the user to receive a properly processed response, completing the interactive communication.

[0363] (Application Example 2)

[0364] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0365] In modern information systems, language barriers and emotional differences often pose obstacles when providing real-time user support in multiple languages. Furthermore, generating appropriate responses that align with user emotions is a challenging task. Therefore, there is a need to achieve appropriate user support that transcends language barriers while taking emotions into consideration.

[0366] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0367] In this invention, the server includes an input device means for receiving user input, a language determination means for receiving the user input and determining its language, a translation device means for translating the language into a different language, and a response generation means for generating a response corresponding to the analyzed sentiment information. This enables real-time response generation that corresponds to the user's language and sentiment.

[0368] "User input" refers to information, including characters and symbols, that a user sends to the system.

[0369] "Input device means" refers to a physical or virtual device for receiving information from the user.

[0370] A "language determination means" is a technical element for identifying and classifying the language of the received input data.

[0371] "Translation device means" refers to technical means and devices for converting information expressed in one language into another language.

[0372] "Emotion analysis means" refers to technology that detects a user's emotions from the content of input text and classifies them into a specific category.

[0373] "Response generation means" refers to technical elements and devices for creating an appropriate response to the user based on the information obtained.

[0374] "Communication means" refers to network technology used by a system to transmit information to a user.

[0375] A "bidirectional communication protocol" is a communication standard that enables real-time data exchange between a client and a server.

[0376] A "machine learning algorithm" is a mathematical method for learning patterns from data and automatically making predictions or decisions.

[0377] To implement this invention, a terminal for interacting with the user and a server for analyzing input and generating an appropriate response are required. The user inputs text information via the terminal, and the input information is transferred to the server. The server first identifies the language of the received text using a language determination means, and then performs the necessary translation using a translation device means based on the result.

[0378] Next, the sentiment of the translated text is analyzed using sentiment analysis tools. The server uses sentiment analysis technology based on machine learning algorithms to classify the sentiment expressed in the text into categories such as positive, negative, and neutral. Then, a generative AI model is used to generate a response in the most appropriate tone for the user, and this is translated back into the desired language.

[0379] The server sends the generated response to the terminal via a bidirectional communication protocol. This allows the user to immediately obtain a solution or appropriate information, enabling smooth communication.

[0380] As a concrete example, consider a case where a user enters "I am very dissatisfied with my recent order." This statement is sent to the server, and sentiment analysis recognizes a negative emotion, causing the AI ​​to create an empathetic response. Specifically, a response such as "We apologize for the inconvenience. We will do our best to resolve your issue as quickly as possible" is generated. This message is translated into the user's language and returned to the device, thus appropriately addressing the user's dissatisfaction.

[0381] For example, prompts can be used to instruct the AI ​​in the following format: "User input: I am very dissatisfied with my recent order. Generate an empathetic response considering the negative sentiment."

[0382] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0383] Step 1:

[0384] The user uses a terminal to input text. The terminal receives text data from the user, such as "I am very dissatisfied with my recent order," and prepares this data as input data to send to the server.

[0385] Step 2:

[0386] The server processes the received user input using a language detection mechanism. The server identifies the language of the input text and uses this information to determine if translation is necessary. The output is the language detection result.

[0387] Step 3:

[0388] If necessary, the server uses a translation device to translate user input into a different language. This translation uses a machine translation algorithm to generate translated text data based on the input data. The output is the translated text.

[0389] Step 4:

[0390] The server analyzes the sentiment of the translated text or the original text data using sentiment analysis tools. Here, machine learning algorithms are used to output sentiment categories such as positive, negative, and neutral.

[0391] Step 5:

[0392] The server uses a generative AI model to generate appropriate responses that correspond to the user's emotions through a response generation mechanism. During generation, emotional information is input to the AI ​​model using prompt sentences, and responses with an empathetic or problem-solving tone are generated. The output is the generated response sentence.

[0393] Step 6:

[0394] If the server-generated response needs to be translated again into the user's desired language, a translation device is used to perform the translation. The output is the translated response text.

[0395] Step 7:

[0396] The server sends the generated response to the terminal via the communication method. The terminal receives this and displays it on the user's screen. The output is a response message in a format that the user can understand.

[0397] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0398] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0399] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0400] [Third Embodiment]

[0401] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0402] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0403] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0404] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0405] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0406] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0407] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0408] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0409] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0410] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0411] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0412] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0413] This invention is implemented in a form that provides an interface means that a user accesses through a web browser. The user uses this interface to input questions or comments. The terminal receives the user input and sends the data to the server. The server uses a language determination means to identify the language of the input text and translate it if necessary. The translated text is processed by a generation means to generate an appropriate response. If the generated response is in a different language, the server uses a conversion means to translate the response into the user's desired language. Finally, the server uses a communication means to send this translated response to the user's terminal in real time.

[0414] For example, if a user types "What is the company's refund policy?" in Japanese, the device sends this input to the server. The server detects the input language as Japanese, and the generation engine generates a response stating, "A full refund is available if the product is returned within 30 days of receipt." The server then translates this information into the user's chosen language as needed, and sends it to the device so that it is displayed to users using an English UI as "The company offers a full refund for products returned within 30 days of receipt."

[0415] Such systems allow users to obtain accurate information in real time, and enable companies to communicate smoothly with users even in multilingual environments.

[0416] The following describes the processing flow.

[0417] Step 1:

[0418] The user opens the web browser interface and enters questions or comments into the chat window.

[0419] Step 2:

[0420] The terminal receives user input and sends the data to the server via a real-time communication protocol (e.g., WebSocket or HTTP request). The input data also includes language information used by the user.

[0421] Step 3:

[0422] The server analyzes the user input it receives and automatically identifies the language of the input using a language detection mechanism. If the detected language differs from the system's default language, a translation mechanism is used to convert the input into a language that the system can process.

[0423] Step 4:

[0424] The server passes the translated input data to the generation mechanism, and the AI ​​engine generates an appropriate response based on it. The generation engine provides accurate and effective content in response to the user's question, based on the training data.

[0425] Step 5:

[0426] If the server needs to translate the generated response into the user's language, it will use the translation means again to translate the response into the user's language.

[0427] Step 6:

[0428] The server sends the translated response to the terminal using a real-time communication protocol.

[0429] Step 7:

[0430] The system displays the responses received by the terminal in the chat window, allowing the user to see the system's reply. The user can continue interacting with the system by entering further questions.

[0431] (Example 1)

[0432] Next, we will describe Example 1. 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."

[0433] In a multilingual environment, users are required to obtain accurate information in real time. To achieve this smoothly, it is necessary to automatically determine the target language and quickly generate a response in the appropriate language. However, existing technologies have challenges in efficiently translating information and generating responses across multiple languages, resulting in a lack of improvement in the user experience.

[0434] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0435] In this invention, the server includes means for providing an interface for receiving user input, means including a terminal device for receiving the user input and transmitting the information to the server, means for determining the language of the information, conversion means for translating the determined language into a different language, generation means for using a generation model to generate a response based on the translated information, means for translating the generated response back into the language of the user, and means for communicating to send the translated response to the user. This enables rapid and accurate information acquisition in a multilingual environment.

[0436] An "interface" is a means by which a user connects to a system and provides input.

[0437] A "terminal device" is a device that receives user input and transmits that input to a server.

[0438] "Information" refers to data entered by the user and related processed data.

[0439] A "language determination means" is a means that has the function of identifying the language of the received information.

[0440] A "conversion means" is a means for translating the determined language into a specified different language.

[0441] "Generative means" refers to means that use a generative model to generate a response based on translated information.

[0442] A "generative model" is an algorithm or system based on artificial intelligence technology that generates appropriate responses from input information.

[0443] "Communication means" refers to a means that has the function of data transmission for sending the generated response to the user.

[0444] A "multilingual environment" refers to a situation or context in which multiple different languages ​​are used.

[0445] This invention is a system that enables users to obtain accurate information in real time in a multilingual environment. The system consists of three main elements: the user, the terminal, and the server.

[0446] Users access the interface using a web browser and enter questions or comments. These inputs are structured as specific questions, such as "What is the company's refund policy?". The terminal receiving the user input encrypts the information and securely transmits it to the server.

[0447] The server uses language detection software to determine the language of the received input data. For example, it may use an API that leverages natural language processing technology to identify the input language. If the identified language differs from the language requested by the user, the server uses a translation tool to convert the language. For this purpose, for example, a translation algorithm based on a neural network may be used.

[0448] The server then uses a generative AI model to generate an appropriate response to the user's question. For example, OpenAI's GPT series can be used as the generative AI model. An example of a prompt for response generation is, "Please provide detailed information about the company's refund policy in Japanese."

[0449] If the generated response needs to be provided in a different language, the server uses the translation mechanism again to translate the response into the required language. Finally, the server sends the obtained response in real time to the user's terminal via the communication mechanism. This system allows users to quickly and smoothly access the necessary information even in a multilingual environment.

[0450] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0451] Step 1:

[0452] Users access the interface using a web browser and enter their questions or comments. An example question is, "What is the company's refund policy?" The input data is sent to the terminal in string format.

[0453] Step 2:

[0454] The terminal encrypts the input data received from the user and securely sends it to the server. The HTTPS protocol is used for transmission, and the input data arrives at the server in an encrypted state. The input in this step is string data, and the output is encrypted data sent to the server.

[0455] Step 3:

[0456] The server decrypts the received encrypted data and extracts the string data. Next, it uses language detection software to determine the language of the extracted string. If it identifies that the input is in Japanese, it sends this information to the next step. Here, the input is the decrypted string data, and the output is language information.

[0457] Step 4:

[0458] The server uses a generative AI model to generate a response appropriate to the question based on the user's language. The generative AI model is input with the prompt "Please provide detailed information about the company's refund policy in Japanese." The response generation process uses natural language processing technology, and a response sentence is generated as output. This response sentence is output as information such as "A full refund is possible within 30 days of receiving the product."

[0459] Step 5:

[0460] The server determines whether the generated response needs to be provided in a different language. If necessary, it uses a translation mechanism to translate the generated response into the user's preferred language. The input in this step is the generated response, and the output is the translated response in the user's preferred language.

[0461] Step 6:

[0462] Finally, the server sends the translated response to the user's terminal in real time using a communication method. The HTTPS protocol is also used for this data transmission, and the user checks the response to their question on the browser screen. The input is the response text in the user's preferred language, and the output is the information displayed on the user's terminal.

[0463] (Application Example 1)

[0464] Next, we will explain Application Example 1. In the following explanation, 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."

[0465] Recent advancements in information and communication technology have made multilingual communication commonplace. However, facilitating smooth communication between different languages ​​in real-time environments such as live streaming remains challenging. In particular, rapid and accurate translation is essential for real-time communication with viewers who speak diverse languages. Therefore, there is a need to provide a system that supports real-time translation in live streaming environments.

[0466] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0467] In this invention, the server includes data receiving means for receiving user input, means for receiving the user input and determining its natural language, and data conversion means for translating the natural language into a different natural language. This enables smooth communication with viewers who speak different languages ​​by translating viewer questions in real time during live streaming and presenting them to the streamer.

[0468] A "data reception device" is an interface device for receiving input information from a user.

[0469] A "natural language" is a language that humans use on a daily basis and is not constrained by specific technologies or protocols.

[0470] "Data conversion means" refers to a process or device for converting input natural language into a different natural language.

[0471] "Data generation means" refers to a process or apparatus for creating a corresponding response message based on translated input information.

[0472] "Data communication means" refers to communication devices that transmit generated response messages to a user via a network and protocol.

[0473] "Information processing means" refers to a device or program that processes questions from viewers in real time in a live streaming environment and translates and provides them in the natural language used by the streamer.

[0474] An "open connectivity protocol" is a network protocol that enables continuous data communication and is a standard technology used for bidirectional communication.

[0475] A "machine learning algorithm" is an automated method that enables evolutionary improvement in performance by learning from large datasets.

[0476] The invention will now be described in terms of embodiments for carrying out the invention. The invention is a system that enables real-time communication with multilingual viewers in a live streaming environment. This system is realized by processing input information transmitted from the user's terminal on a server.

[0477] When a user enters a question or comment into a device, the device sends it to a server via a data reception mechanism. The server uses natural language processing technology to determine the language of the received input and translates that natural language into another language using a data conversion mechanism. Machine learning algorithms are used in this translation, and it can be implemented using existing translation APIs (e.g., Google Translate API).

[0478] Based on the translated input, the server constructs an appropriate response message using data generation tools. The response message may then be translated again, adapting its natural language to the user's language. Finally, the response is sent to the user via data communication tools. This communication utilizes open connection protocols (such as WebSocket or HTTP) to ensure real-time performance.

[0479] For example, if a Japanese viewer sends a question such as "Please tell me your thoughts on the movie," the server will instantly translate it into English and provide this information to the broadcaster. A prompt such as "Translate and display the user's comment" will be used, and a generative AI model will generate a response. In this way, mutual understanding between multiple languages ​​can be smoothly promoted in the live streaming environment.

[0480] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0481] Step 1:

[0482] The user enters questions or comments into the device. The input is natural language text data, such as "Please tell me your thoughts on the movie." The device sends this text data to the server via a data reception device.

[0483] Step 2:

[0484] The server identifies the language of the received text data. This process uses natural language processing techniques and machine learning algorithms to determine if the data is multilingual. The input is the user's question text, and the output is the identified natural language. The server records the identified natural language and uses it for subsequent processing.

[0485] Step 3:

[0486] The server translates the identified natural language into a specified language. This process uses an existing translation API as a data conversion tool and performs machine translation. The input is the identified natural language text, and the output is the text translated into the specified language. The server then uses this translation result to proceed to the next step.

[0487] Step 4:

[0488] The server generates a response message based on the translated input. In this process, it uses a generative AI model to initiate a prompt and construct an appropriate response. The input is the translated text, and the output is the generated response message. The server records this response and prepares to reply to the user.

[0489] Step 5:

[0490] The server re-translates the generated response message into the user's preferred language as needed. It then uses data conversion to perform another translation and outputs the message in natural language according to the user's language settings.

[0491] Step 6:

[0492] The server sends the completed response message to the user's terminal via a data communication method. An open connection protocol is used for communication to ensure real-time performance. The input is the final response message, and the output is the response displayed on the user's terminal screen. The user receives their response at this stage.

[0493] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0494] The present invention is implemented in a form that provides an interface means for a user to interactively input text. This system sends the data entered by the user through a terminal to a server for analysis, including the context and sentiment of the input.

[0495] The terminal receives user input and forwards it to the server. The server first determines the language of the input and translates it if necessary. After translation, the sentiment engine analyzes the sentiment of the text and assigns sentiment tags such as positive, negative, and neutral. This sentiment information is used by the generative AI to customize an appropriate response.

[0496] The generated response reflects the sentiment analysis results and is composed in a tone that best suits the user's emotions. For example, if the user asks a question expressing dissatisfaction, the generated response will be adjusted to be empathetic. The server translates the generated response into the user's chosen language as needed and finally sends it to the terminal.

[0497] As a concrete example, suppose a user enters "I am very dissatisfied with my recent order." The terminal sends this input to the server, which then determines the language and translates it, and finally recognizes a strong negative emotion through its emotion engine. The generated response will be something empathetic, such as "We apologize for the inconvenience. We will do our best to resolve your issue as quickly as possible." This response is then translated into the user's language, sent back to the terminal, and displayed on the user's screen.

[0498] This feature enhances the user experience and enables smooth communication that transcends language and emotional barriers.

[0499] The following describes the processing flow.

[0500] Step 1:

[0501] The user opens the web browser interface and enters questions or comments into the chat window.

[0502] Step 2:

[0503] The terminal receives user input and sends the input data to the server using a real-time communication protocol (e.g., WebSocket or HTTP request).

[0504] Step 3:

[0505] The server determines the language of the user input it receives and, if necessary, translates the input language into the system's standard processing language using a translation mechanism.

[0506] Step 4:

[0507] The server passes the translated input to the emotion engine, which analyzes the emotional state of the input. The emotion engine recognizes emotions such as positive, negative, and neutral from the input and also evaluates the intensity of those emotions.

[0508] Step 5:

[0509] Based on the sentiment analysis results, the server uses a generation mechanism to produce an appropriate response to user input. The generated response is then adjusted to a tone that corresponds to the user's emotions.

[0510] Step 6:

[0511] The server translates the generated response into the user's preferred language. If necessary, it also makes minor adjustments to convey emotion.

[0512] Step 7:

[0513] The server sends the translated response to the terminal via real-time communication.

[0514] Step 8:

[0515] The device displays the response it receives in the chat window of the user interface, allowing the user to review the reply and initiate the next interaction.

[0516] This series of steps enables thoughtful responses that respond to the user's emotions, leading to more intimate and effective communication.

[0517] (Example 2)

[0518] Next, we will describe Example 2. 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."

[0519] Traditional text-based communication systems not only struggle with multilingual communication but also lack the ability to generate appropriate responses that take user emotions into account. This results in a degraded user experience, particularly hindering smooth communication between users with diverse language and emotional backgrounds.

[0520] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0521] In this invention, the server includes an interface device for receiving user input, a device for determining the language, a conversion device for translating into a different language, and an analysis device for analyzing emotions and assigning emotion tags. This makes it possible to provide appropriate and empathetic responses to users, overcoming language and emotional barriers.

[0522] An "interface device" is a component that receives data input from a user.

[0523] A "determination device" is a component that has the function of identifying the language of the input data.

[0524] A "conversion device" is a component that has the function of converting data from one language to another.

[0525] An "analysis device" is a component that has the function of analyzing the sentiment of text and assigning sentiment tags to it.

[0526] A "generator" is a component that has the function of generating responses based on emotional tags.

[0527] A "communication device" is a component that has the function of transmitting generated data to a user.

[0528] A "bidirectional communication protocol" is a means of communication for exchanging data in real time.

[0529] A "machine learning algorithm" is a method that uses data to train a model and automatically perform various tasks.

[0530] An "emotion tag" is an identifier assigned to text to represent the emotions it expresses.

[0531] This invention is a system for realizing natural and empathetic communication with users in real time. This system has a complex processing flow for processing text data entered by the user via a terminal.

[0532] First, the user inputs text via an interface device on the terminal. The terminal receives this input and sends it to the server. The server analyzes the input data using a device that determines the language of the input, and identifies the language of the input.

[0533] Next, if the language differs from the system's common operating language, the server uses a translation device to translate the input data. It is recommended to use a translation system based on commonly used machine learning algorithms for this translation process.

[0534] The translated data is sent to an analysis device where the sentiment of the text is analyzed. Based on the analysis, sentiment tags such as positive, negative, and neutral are assigned, and the data is passed to a generation device. The generation device uses a generative AI model to generate appropriate responses based on the sentiment tags. This generative AI model generates natural-sounding dialogue by using a language model that has been pre-trained on a large amount of data.

[0535] If the generated response requires translation into the user's desired language, it is translated again through a translation device. The server then uses a communication device to send the final response to the terminal. The terminal displays this response on its user interface and provides it to the user.

[0536] For example, if a user enters "I am very dissatisfied with my recent order," the system receives the input data and determines that the emotion is negative. As a result, the generating AI model creates an empathetic response such as "We apologize for the inconvenience. We will do our best to resolve your issue as quickly as possible," and delivers it to the device.

[0537] An example of a prompt is: "Generate an empathetic response in a context where the user expresses dissatisfaction. Input: 'I am very unhappy with my recent order.'" This prompt is an example of generating an emotion-based response.

[0538] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0539] Step 1:

[0540] The user enters text into the terminal. The terminal receives this input data via an interface device. The entered data is stored as a text string and prepared for transmission to the server.

[0541] Step 2:

[0542] The terminal sends the received user input data to the server in HTTP request format. The server passes the received text data to a language detection device to identify the input language. During this process, data analysis is performed using a language detection algorithm, and language information is obtained as output.

[0543] Step 3:

[0544] If the detected language differs from the system's common operating language, the server uses a translation device to translate the input data into the common language. The translation device uses a translation engine based on machine learning algorithms to process the input text and output the translated text data.

[0545] Step 4:

[0546] The translated text data is passed to a server-side analysis device for sentiment analysis. The analysis device applies a sentiment analysis algorithm to analyze the sentiment of each sentence and assigns a positive, negative, or neutral sentiment tag. The output is text data tagged with the sentiment tag.

[0547] Step 5:

[0548] Text data tagged with emotion is passed to a generator running a generative AI model. The generator uses this data as a prompt to create an appropriate response using the generative AI model. Emotion tags are taken into consideration during response generation, and an empathetic response text is generated as output.

[0549] Step 6:

[0550] The server then re-translates the generated response into the user's desired language, using a translation device as needed. This translation process also utilizes a machine learning-based translation engine, and the final response text data is output.

[0551] Step 7:

[0552] The server sends the final response to the terminal in HTTP response format. The terminal receives this data and displays it in the user interface. This allows the user to receive a properly processed response, completing the interactive communication.

[0553] (Application Example 2)

[0554] Next, we will explain application example 2. In the following explanation, 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."

[0555] In modern information systems, language barriers and emotional differences often pose obstacles when providing real-time user support in multiple languages. Furthermore, generating appropriate responses that align with user emotions is a challenging task. Therefore, there is a need to achieve appropriate user support that transcends language barriers while taking emotions into consideration.

[0556] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0557] In this invention, the server includes an input device means for receiving user input, a language determination means for receiving the user input and determining its language, a translation device means for translating the language into a different language, and a response generation means for generating a response corresponding to the analyzed sentiment information. This enables real-time response generation that corresponds to the user's language and sentiment.

[0558] "User input" refers to information, including characters and symbols, that a user sends to the system.

[0559] "Input device means" refers to a physical or virtual device for receiving information from the user.

[0560] A "language determination means" is a technical element for identifying and classifying the language of the received input data.

[0561] "Translation device means" refers to technical means and devices for converting information expressed in one language into another language.

[0562] "Emotion analysis means" refers to technology that detects a user's emotions from the content of input text and classifies them into a specific category.

[0563] "Response generation means" refers to technical elements and devices for creating an appropriate response to the user based on the information obtained.

[0564] "Communication means" refers to network technology used by a system to transmit information to a user.

[0565] A "bidirectional communication protocol" is a communication standard that enables real-time data exchange between a client and a server.

[0566] A "machine learning algorithm" is a mathematical method for learning patterns from data and automatically making predictions or decisions.

[0567] To implement this invention, a terminal for interacting with the user and a server for analyzing input and generating an appropriate response are required. The user inputs text information via the terminal, and the input information is transferred to the server. The server first identifies the language of the received text using a language determination means, and then performs the necessary translation using a translation device means based on the result.

[0568] Next, the sentiment of the translated text is analyzed using sentiment analysis tools. The server uses sentiment analysis technology based on machine learning algorithms to classify the sentiment expressed in the text into categories such as positive, negative, and neutral. Then, a generative AI model is used to generate a response in the most appropriate tone for the user, and this is translated back into the desired language.

[0569] The server sends the generated response to the terminal via a bidirectional communication protocol. This allows the user to immediately obtain a solution or appropriate information, enabling smooth communication.

[0570] As a concrete example, consider a case where a user enters "I am very dissatisfied with my recent order." This statement is sent to the server, and sentiment analysis recognizes a negative emotion, causing the AI ​​to create an empathetic response. Specifically, a response such as "We apologize for the inconvenience. We will do our best to resolve your issue as quickly as possible" is generated. This message is translated into the user's language and returned to the device, thus appropriately addressing the user's dissatisfaction.

[0571] For example, prompts can be used to instruct the AI ​​in the following format: "User input: I am very dissatisfied with my recent order. Generate an empathetic response considering the negative sentiment."

[0572] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0573] Step 1:

[0574] The user uses a terminal to input text. The terminal receives text data from the user, such as "I am very dissatisfied with my recent order," and prepares this data as input data to send to the server.

[0575] Step 2:

[0576] The server processes the received user input using a language detection mechanism. The server identifies the language of the input text and uses this information to determine if translation is necessary. The output is the language detection result.

[0577] Step 3:

[0578] If necessary, the server uses a translation device to translate user input into a different language. This translation uses a machine translation algorithm to generate translated text data based on the input data. The output is the translated text.

[0579] Step 4:

[0580] The server analyzes the sentiment of the translated text or the original text data using sentiment analysis tools. Here, machine learning algorithms are used to output sentiment categories such as positive, negative, and neutral.

[0581] Step 5:

[0582] The server uses a generative AI model to generate appropriate responses that correspond to the user's emotions through a response generation mechanism. During generation, emotional information is input to the AI ​​model using prompt sentences, and responses with an empathetic or problem-solving tone are generated. The output is the generated response sentence.

[0583] Step 6:

[0584] If the server-generated response needs to be translated again into the user's desired language, a translation device is used to perform the translation. The output is the translated response text.

[0585] Step 7:

[0586] The server sends the generated response to the terminal via the communication method. The terminal receives this and displays it on the user's screen. The output is a response message in a format that the user can understand.

[0587] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0588] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0589] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0590] [Fourth Embodiment]

[0591] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0592] As shown in Figure 7, the 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.

[0593] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0594] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0595] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0596] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0597] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0598] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0599] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0600] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0601] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0602] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0603] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0604] This invention is implemented in a form that provides an interface means that a user accesses through a web browser. The user uses this interface to input questions or comments. The terminal receives the user input and sends the data to the server. The server uses a language determination means to identify the language of the input text and translate it if necessary. The translated text is processed by a generation means to generate an appropriate response. If the generated response is in a different language, the server uses a conversion means to translate the response into the user's desired language. Finally, the server uses a communication means to send this translated response to the user's terminal in real time.

[0605] For example, if a user types "What is the company's refund policy?" in Japanese, the device sends this input to the server. The server detects the input language as Japanese, and the generation engine generates a response stating, "A full refund is available if the product is returned within 30 days of receipt." The server then translates this information into the user's chosen language as needed, and sends it to the device so that it is displayed to users using an English UI as "The company offers a full refund for products returned within 30 days of receipt."

[0606] Such systems allow users to obtain accurate information in real time, and enable companies to communicate smoothly with users even in multilingual environments.

[0607] The following describes the processing flow.

[0608] Step 1:

[0609] The user opens the web browser interface and enters questions or comments into the chat window.

[0610] Step 2:

[0611] The terminal receives user input and sends the data to the server via a real-time communication protocol (e.g., WebSocket or HTTP request). The input data also includes language information used by the user.

[0612] Step 3:

[0613] The server analyzes the user input it receives and automatically identifies the language of the input using a language detection mechanism. If the detected language differs from the system's default language, a translation mechanism is used to convert the input into a language that the system can process.

[0614] Step 4:

[0615] The server passes the translated input data to the generation mechanism, and the AI ​​engine generates an appropriate response based on it. The generation engine provides accurate and effective content in response to the user's question, based on the training data.

[0616] Step 5:

[0617] If the server needs to translate the generated response into the user's language, it will use the translation means again to translate the response into the user's language.

[0618] Step 6:

[0619] The server sends the translated response to the terminal using a real-time communication protocol.

[0620] Step 7:

[0621] The system displays the responses received by the terminal in the chat window, allowing the user to see the system's reply. The user can continue interacting with the system by entering further questions.

[0622] (Example 1)

[0623] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0624] In a multilingual environment, users are required to obtain accurate information in real time. To achieve this smoothly, it is necessary to automatically determine the target language and quickly generate a response in the appropriate language. However, existing technologies have challenges in efficiently translating information and generating responses across multiple languages, resulting in a lack of improvement in the user experience.

[0625] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0626] In this invention, the server includes means for providing an interface for receiving user input, means including a terminal device for receiving the user input and transmitting the information to the server, means for determining the language of the information, conversion means for translating the determined language into a different language, generation means for using a generation model to generate a response based on the translated information, means for translating the generated response back into the language of the user, and means for communicating to send the translated response to the user. This enables rapid and accurate information acquisition in a multilingual environment.

[0627] An "interface" is a means by which a user connects to a system and provides input.

[0628] A "terminal device" is a device that receives user input and transmits that input to a server.

[0629] "Information" refers to data entered by the user and related processed data.

[0630] A "language determination means" is a means that has the function of identifying the language of the received information.

[0631] A "conversion means" is a means for translating the determined language into a specified different language.

[0632] "Generative means" refers to means that use a generative model to generate a response based on translated information.

[0633] A "generative model" is an algorithm or system based on artificial intelligence technology that generates appropriate responses from input information.

[0634] "Communication means" refers to a means that has the function of data transmission for sending the generated response to the user.

[0635] A "multilingual environment" refers to a situation or context in which multiple different languages ​​are used.

[0636] This invention is a system that enables users to obtain accurate information in real time in a multilingual environment. The system consists of three main elements: the user, the terminal, and the server.

[0637] Users access the interface using a web browser and enter questions or comments. These inputs are structured as specific questions, such as "What is the company's refund policy?". The terminal receiving the user input encrypts the information and securely transmits it to the server.

[0638] The server uses language detection software to determine the language of the received input data. For example, it may use an API that leverages natural language processing technology to identify the input language. If the identified language differs from the language requested by the user, the server uses a translation tool to convert the language. For this purpose, for example, a translation algorithm based on a neural network may be used.

[0639] The server then uses a generative AI model to generate an appropriate response to the user's question. For example, OpenAI's GPT series can be used as the generative AI model. An example of a prompt for response generation is, "Please provide detailed information about the company's refund policy in Japanese."

[0640] If the generated response needs to be provided in a different language, the server uses the translation mechanism again to translate the response into the required language. Finally, the server sends the obtained response in real time to the user's terminal via the communication mechanism. This system allows users to quickly and smoothly access the necessary information even in a multilingual environment.

[0641] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0642] Step 1:

[0643] Users access the interface using a web browser and enter their questions or comments. An example question is, "What is the company's refund policy?" The input data is sent to the terminal in string format.

[0644] Step 2:

[0645] The terminal encrypts the input data received from the user and securely sends it to the server. The HTTPS protocol is used for transmission, and the input data arrives at the server in an encrypted state. The input in this step is string data, and the output is encrypted data sent to the server.

[0646] Step 3:

[0647] The server decrypts the received encrypted data and extracts the string data. Next, it uses language detection software to determine the language of the extracted string. If it identifies that the input is in Japanese, it sends this information to the next step. Here, the input is the decrypted string data, and the output is language information.

[0648] Step 4:

[0649] The server uses a generative AI model to generate a response appropriate to the question based on the user's language. The generative AI model is input with the prompt "Please provide detailed information about the company's refund policy in Japanese." The response generation process uses natural language processing technology, and a response sentence is generated as output. This response sentence is output as information such as "A full refund is possible within 30 days of receiving the product."

[0650] Step 5:

[0651] The server determines whether the generated response needs to be provided in a different language. If necessary, it uses a translation mechanism to translate the generated response into the user's preferred language. The input in this step is the generated response, and the output is the translated response in the user's preferred language.

[0652] Step 6:

[0653] Finally, the server sends the translated response to the user's terminal in real time using a communication method. The HTTPS protocol is also used for this data transmission, and the user checks the response to their question on the browser screen. The input is the response text in the user's preferred language, and the output is the information displayed on the user's terminal.

[0654] (Application Example 1)

[0655] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0656] Recent advancements in information and communication technology have made multilingual communication commonplace. However, facilitating smooth communication between different languages ​​in real-time environments such as live streaming remains challenging. In particular, rapid and accurate translation is essential for real-time communication with viewers who speak diverse languages. Therefore, there is a need to provide a system that supports real-time translation in live streaming environments.

[0657] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0658] In this invention, the server includes data receiving means for receiving user input, means for receiving the user input and determining its natural language, and data conversion means for translating the natural language into a different natural language. This enables smooth communication with viewers who speak different languages ​​by translating viewer questions in real time during live streaming and presenting them to the streamer.

[0659] A "data reception device" is an interface device for receiving input information from a user.

[0660] A "natural language" is a language that humans use on a daily basis and is not constrained by specific technologies or protocols.

[0661] "Data conversion means" refers to a process or device for converting input natural language into a different natural language.

[0662] "Data generation means" refers to a process or apparatus for creating a corresponding response message based on translated input information.

[0663] "Data communication means" refers to communication devices that transmit generated response messages to a user via a network and protocol.

[0664] "Information processing means" refers to a device or program that processes questions from viewers in real time in a live streaming environment and translates and provides them in the natural language used by the streamer.

[0665] An "open connectivity protocol" is a network protocol that enables continuous data communication and is a standard technology used for bidirectional communication.

[0666] A "machine learning algorithm" is an automated method that enables evolutionary improvement in performance by learning from large datasets.

[0667] The invention will now be described in terms of embodiments for carrying out the invention. The invention is a system that enables real-time communication with multilingual viewers in a live streaming environment. This system is realized by processing input information transmitted from the user's terminal on a server.

[0668] When a user enters a question or comment into a device, the device sends it to a server via a data reception mechanism. The server uses natural language processing technology to determine the language of the received input and translates that natural language into another language using a data conversion mechanism. Machine learning algorithms are used in this translation, and it can be implemented using existing translation APIs (e.g., Google Translate API).

[0669] Based on the translated input, the server constructs an appropriate response message using data generation tools. The response message may then be translated again, adapting its natural language to the user's language. Finally, the response is sent to the user via data communication tools. This communication utilizes open connection protocols (such as WebSocket or HTTP) to ensure real-time performance.

[0670] For example, if a Japanese viewer sends a question such as "Please tell me your thoughts on the movie," the server will instantly translate it into English and provide this information to the broadcaster. A prompt such as "Translate and display the user's comment" will be used, and a generative AI model will generate a response. In this way, mutual understanding between multiple languages ​​can be smoothly promoted in the live streaming environment.

[0671] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0672] Step 1:

[0673] The user enters questions or comments into the device. The input is natural language text data, such as "Please tell me your thoughts on the movie." The device sends this text data to the server via a data reception device.

[0674] Step 2:

[0675] The server identifies the language of the received text data. This process uses natural language processing techniques and machine learning algorithms to determine if the data is multilingual. The input is the user's question text, and the output is the identified natural language. The server records the identified natural language and uses it for subsequent processing.

[0676] Step 3:

[0677] The server translates the identified natural language into a specified language. This process uses an existing translation API as a data conversion tool and performs machine translation. The input is the identified natural language text, and the output is the text translated into the specified language. The server then uses this translation result to proceed to the next step.

[0678] Step 4:

[0679] The server generates a response message based on the translated input. In this process, it uses a generative AI model to initiate a prompt and construct an appropriate response. The input is the translated text, and the output is the generated response message. The server records this response and prepares to reply to the user.

[0680] Step 5:

[0681] The server re-translates the generated response message into the user's preferred language as needed. It then uses data conversion to perform another translation and outputs the message in natural language according to the user's language settings.

[0682] Step 6:

[0683] The server sends the completed response message to the user's terminal via a data communication method. An open connection protocol is used for communication to ensure real-time performance. The input is the final response message, and the output is the response displayed on the user's terminal screen. The user receives their response at this stage.

[0684] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0685] The present invention is implemented in a form that provides an interface means for a user to interactively input text. This system sends the data entered by the user through a terminal to a server for analysis, including the context and sentiment of the input.

[0686] The terminal receives user input and forwards it to the server. The server first determines the language of the input and translates it if necessary. After translation, the sentiment engine analyzes the sentiment of the text and assigns sentiment tags such as positive, negative, and neutral. This sentiment information is used by the generative AI to customize an appropriate response.

[0687] The generated response reflects the sentiment analysis results and is composed in a tone that best suits the user's emotions. For example, if the user asks a question expressing dissatisfaction, the generated response will be adjusted to be empathetic. The server translates the generated response into the user's chosen language as needed and finally sends it to the terminal.

[0688] As a concrete example, suppose a user enters "I am very dissatisfied with my recent order." The terminal sends this input to the server, which then determines the language and translates it, and finally recognizes a strong negative emotion through its emotion engine. The generated response will be something empathetic, such as "We apologize for the inconvenience. We will do our best to resolve your issue as quickly as possible." This response is then translated into the user's language, sent back to the terminal, and displayed on the user's screen.

[0689] This feature enhances the user experience and enables smooth communication that transcends language and emotional barriers.

[0690] The following describes the processing flow.

[0691] Step 1:

[0692] The user opens the web browser interface and enters questions or comments into the chat window.

[0693] Step 2:

[0694] The terminal receives user input and sends the input data to the server using a real-time communication protocol (e.g., WebSocket or HTTP request).

[0695] Step 3:

[0696] The server determines the language of the user input it receives and, if necessary, translates the input language into the system's standard processing language using a translation mechanism.

[0697] Step 4:

[0698] The server passes the translated input to the emotion engine, which analyzes the emotional state of the input. The emotion engine recognizes emotions such as positive, negative, and neutral from the input and also evaluates the intensity of those emotions.

[0699] Step 5:

[0700] Based on the sentiment analysis results, the server uses a generation mechanism to produce an appropriate response to user input. The generated response is then adjusted to a tone that corresponds to the user's emotions.

[0701] Step 6:

[0702] The server translates the generated response into the user's preferred language. If necessary, it also makes minor adjustments to convey emotion.

[0703] Step 7:

[0704] The server sends the translated response to the terminal via real-time communication.

[0705] Step 8:

[0706] The device displays the response it receives in the chat window of the user interface, allowing the user to review the reply and initiate the next interaction.

[0707] This series of steps enables thoughtful responses that respond to the user's emotions, leading to more intimate and effective communication.

[0708] (Example 2)

[0709] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0710] Traditional text-based communication systems not only struggle with multilingual communication but also lack the ability to generate appropriate responses that take user emotions into account. This results in a degraded user experience, particularly hindering smooth communication between users with diverse language and emotional backgrounds.

[0711] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0712] In this invention, the server includes an interface device for receiving user input, a device for determining the language, a conversion device for translating into a different language, and an analysis device for analyzing emotions and assigning emotion tags. This makes it possible to provide appropriate and empathetic responses to users, overcoming language and emotional barriers.

[0713] An "interface device" is a component that receives data input from a user.

[0714] A "determination device" is a component that has the function of identifying the language of the input data.

[0715] A "conversion device" is a component that has the function of converting data from one language to another.

[0716] An "analysis device" is a component that has the function of analyzing the sentiment of text and assigning sentiment tags to it.

[0717] A "generator" is a component that has the function of generating responses based on emotional tags.

[0718] A "communication device" is a component that has the function of transmitting generated data to a user.

[0719] A "bidirectional communication protocol" is a means of communication for exchanging data in real time.

[0720] A "machine learning algorithm" is a method that uses data to train a model and automatically perform various tasks.

[0721] An "emotion tag" is an identifier assigned to text to represent the emotions it expresses.

[0722] This invention is a system for realizing natural and empathetic communication with users in real time. This system has a complex processing flow for processing text data entered by the user via a terminal.

[0723] First, the user inputs text via an interface device on the terminal. The terminal receives this input and sends it to the server. The server analyzes the input data using a device that determines the language of the input, and identifies the language of the input.

[0724] Next, if the language differs from the system's common operating language, the server uses a translation device to translate the input data. It is recommended to use a translation system based on commonly used machine learning algorithms for this translation process.

[0725] The translated data is sent to an analysis device where the sentiment of the text is analyzed. Based on the analysis, sentiment tags such as positive, negative, and neutral are assigned, and the data is passed to a generation device. The generation device uses a generative AI model to generate appropriate responses based on the sentiment tags. This generative AI model generates natural-sounding dialogue by using a language model that has been pre-trained on a large amount of data.

[0726] If the generated response requires translation into the user's desired language, it is translated again through a translation device. The server then uses a communication device to send the final response to the terminal. The terminal displays this response on its user interface and provides it to the user.

[0727] For example, if a user enters "I am very dissatisfied with my recent order," the system receives the input data and determines that the emotion is negative. As a result, the generating AI model creates an empathetic response such as "We apologize for the inconvenience. We will do our best to resolve your issue as quickly as possible," and delivers it to the device.

[0728] An example of a prompt is: "Generate an empathetic response in a context where the user expresses dissatisfaction. Input: 'I am very unhappy with my recent order.'" This prompt is an example of generating an emotion-based response.

[0729] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0730] Step 1:

[0731] The user enters text into the terminal. The terminal receives this input data via an interface device. The entered data is stored as a text string and prepared for transmission to the server.

[0732] Step 2:

[0733] The terminal sends the received user input data to the server in HTTP request format. The server passes the received text data to a language detection device to identify the input language. During this process, data analysis is performed using a language detection algorithm, and language information is obtained as output.

[0734] Step 3:

[0735] If the detected language differs from the system's common operating language, the server uses a translation device to translate the input data into the common language. The translation device uses a translation engine based on machine learning algorithms to process the input text and output the translated text data.

[0736] Step 4:

[0737] The translated text data is passed to a server-side analysis device for sentiment analysis. The analysis device applies a sentiment analysis algorithm to analyze the sentiment of each sentence and assigns a positive, negative, or neutral sentiment tag. The output is text data tagged with the sentiment tag.

[0738] Step 5:

[0739] Text data tagged with emotion is passed to a generator running a generative AI model. The generator uses this data as a prompt to create an appropriate response using the generative AI model. Emotion tags are taken into consideration during response generation, and an empathetic response text is generated as output.

[0740] Step 6:

[0741] The server then re-translates the generated response into the user's desired language, using a translation device as needed. This translation process also utilizes a machine learning-based translation engine, and the final response text data is output.

[0742] Step 7:

[0743] The server sends the final response to the terminal in HTTP response format. The terminal receives this data and displays it in the user interface. This allows the user to receive a properly processed response, completing the interactive communication.

[0744] (Application Example 2)

[0745] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0746] In modern information systems, language barriers and emotional differences often pose obstacles when providing real-time user support in multiple languages. Furthermore, generating appropriate responses that align with user emotions is a challenging task. Therefore, there is a need to achieve appropriate user support that transcends language barriers while taking emotions into consideration.

[0747] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0748] In this invention, the server includes an input device means for receiving user input, a language determination means for receiving the user input and determining its language, a translation device means for translating the language into a different language, and a response generation means for generating a response corresponding to the analyzed sentiment information. This enables real-time response generation that corresponds to the user's language and sentiment.

[0749] "User input" refers to information, including characters and symbols, that a user sends to the system.

[0750] "Input device means" refers to a physical or virtual device for receiving information from the user.

[0751] A "language determination means" is a technical element for identifying and classifying the language of the received input data.

[0752] "Translation device means" refers to technical means and devices for converting information expressed in one language into another language.

[0753] "Emotion analysis means" refers to technology that detects a user's emotions from the content of input text and classifies them into a specific category.

[0754] "Response generation means" refers to technical elements and devices for creating an appropriate response to the user based on the information obtained.

[0755] "Communication means" refers to network technology used by a system to transmit information to a user.

[0756] A "bidirectional communication protocol" is a communication standard that enables real-time data exchange between a client and a server.

[0757] A "machine learning algorithm" is a mathematical method for learning patterns from data and automatically making predictions or decisions.

[0758] To implement this invention, a terminal for interacting with the user and a server for analyzing input and generating an appropriate response are required. The user inputs text information via the terminal, and the input information is transferred to the server. The server first identifies the language of the received text using a language determination means, and then performs the necessary translation using a translation device means based on the result.

[0759] Next, the sentiment of the translated text is analyzed using sentiment analysis tools. The server uses sentiment analysis technology based on machine learning algorithms to classify the sentiment expressed in the text into categories such as positive, negative, and neutral. Then, a generative AI model is used to generate a response in the most appropriate tone for the user, and this is translated back into the desired language.

[0760] The server sends the generated response to the terminal via a bidirectional communication protocol. This allows the user to immediately obtain a solution or appropriate information, enabling smooth communication.

[0761] As a concrete example, consider a case where a user enters "I am very dissatisfied with my recent order." This statement is sent to the server, and sentiment analysis recognizes a negative emotion, causing the AI ​​to create an empathetic response. Specifically, a response such as "We apologize for the inconvenience. We will do our best to resolve your issue as quickly as possible" is generated. This message is translated into the user's language and returned to the device, thus appropriately addressing the user's dissatisfaction.

[0762] For example, prompts can be used to instruct the AI ​​in the following format: "User input: I am very dissatisfied with my recent order. Generate an empathetic response considering the negative sentiment."

[0763] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0764] Step 1:

[0765] The user uses a terminal to input text. The terminal receives text data from the user, such as "I am very dissatisfied with my recent order," and prepares this data as input data to send to the server.

[0766] Step 2:

[0767] The server processes the received user input using a language detection mechanism. The server identifies the language of the input text and uses this information to determine if translation is necessary. The output is the language detection result.

[0768] Step 3:

[0769] If necessary, the server uses a translation device to translate user input into a different language. This translation uses a machine translation algorithm to generate translated text data based on the input data. The output is the translated text.

[0770] Step 4:

[0771] The server analyzes the sentiment of the translated text or the original text data using sentiment analysis tools. Here, machine learning algorithms are used to output sentiment categories such as positive, negative, and neutral.

[0772] Step 5:

[0773] The server uses a generative AI model to generate appropriate responses that correspond to the user's emotions through a response generation mechanism. During generation, emotional information is input to the AI ​​model using prompt sentences, and responses with an empathetic or problem-solving tone are generated. The output is the generated response sentence.

[0774] Step 6:

[0775] If the server-generated response needs to be translated again into the user's desired language, a translation device is used to perform the translation. The output is the translated response text.

[0776] Step 7:

[0777] The server sends the generated response to the terminal via the communication method. The terminal receives this and displays it on the user's screen. The output is a response message in a format that the user can understand.

[0778] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0779] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0780] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0781] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0782] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0783] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0784] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0785] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0786] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0787] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0788] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0789] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0790] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0791] 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.

[0792] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0793] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0794] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0795] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0796] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0797] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0798] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0799] The following is further disclosed regarding the embodiments described above.

[0800] (Claim 1)

[0801] An interface means for receiving user input,

[0802] A means for receiving the user input and determining its language,

[0803] A conversion means for translating the aforementioned language into a different language,

[0804] A generation means for generating a response based on a translated input,

[0805] A means for translating the generated response into the user's preferred language,

[0806] A means of communication for sending the translated response to the user,

[0807] A system that includes this.

[0808] (Claim 2)

[0809] The system according to claim 1, wherein the communication means uses WebSocket or HTTP requests to enable real-time processing of user input.

[0810] (Claim 3)

[0811] The system according to claim 1, wherein the translation means is based on a neural network.

[0812] "Example 1"

[0813] (Claim 1)

[0814] A means of providing an interface for receiving user input,

[0815] Means including a terminal device that receives the user input and transmits the information to a server,

[0816] Means for determining the language of the aforementioned information,

[0817] A conversion means for translating the determined language into a different language,

[0818] A generation means that uses a generation model to generate a response based on translated information,

[0819] A means for translating the generated response back into the language of the user,

[0820] A means of communication for sending the translated response to the user,

[0821] A system that includes this.

[0822] (Claim 2)

[0823] The system according to claim 1, wherein the communication means utilizes Web technology to enable real-time processing of user input.

[0824] (Claim 3)

[0825] The system according to claim 1, wherein the conversion means and the generation means operate based on artificial intelligence technology.

[0826] "Application Example 1"

[0827] (Claim 1)

[0828] A data reception means for receiving user input,

[0829] A means for receiving the user input and determining its natural language,

[0830] A data conversion means for translating the aforementioned natural language into a different natural language,

[0831] A data generation means for generating a response message based on the translated input,

[0832] A means for translating the generated response message into the user's preferred natural language,

[0833] A data communication means for sending a translated response message to the user,

[0834] An information processing means for processing viewer questions in real time in a live streaming environment and translating them into the streamer's natural language,

[0835] A system that includes this.

[0836] (Claim 2)

[0837] The system according to claim 1, which uses an open connection protocol or information transmission request used by the data communication means to enable real-time processing of user input.

[0838] (Claim 3)

[0839] The system according to claim 1, wherein the translation means is based on a machine learning algorithm.

[0840] "Example 2 of combining an emotion engine"

[0841] (Claim 1)

[0842] An interface device for receiving user input,

[0843] A device that receives the user input and determines its language,

[0844] A conversion device for translating the aforementioned language into a different language,

[0845] An analysis device for analyzing the emotions of translated input and assigning emotion tags,

[0846] A generator for generating responses based on emotion tags,

[0847] A conversion device for translating the generated response into the user's preferred language,

[0848] A communication device for sending the translated response to the user,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, wherein a bidirectional communication protocol is used as the data transfer means utilized by the communication device in order to enable real-time processing of user input.

[0852] (Claim 3)

[0853] The system according to claim 1, wherein the translation device and the generation device are based on a machine learning algorithm.

[0854] "Application example 2 when combining with an emotional engine"

[0855] (Claim 1)

[0856] An input device means for receiving user input,

[0857] A language determination means that receives the user input and determines its language,

[0858] A translation device means for translating the aforementioned language into a different language,

[0859] A sentiment analysis tool that analyzes emotions based on translated input,

[0860] A response generation means for generating a response corresponding to the analyzed emotional information,

[0861] A translation device means for translating the generated response into the language desired by the user,

[0862] A means of communication for sending the translated response to the user,

[0863] A system that includes this.

[0864] (Claim 2)

[0865] The system according to claim 1, which uses a bidirectional communication protocol used by the communication means to enable real-time processing of user input.

[0866] (Claim 3)

[0867] The system according to claim 1, wherein the translation device means is based on a machine learning algorithm. [Explanation of Symbols]

[0868] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. An interface means for receiving user input, A means for receiving the user input and determining its language, A conversion means for translating the aforementioned language into a different language, A generation means for generating a response based on a translated input, A means for translating the generated response into the user's preferred language, A means of communication for sending the translated response to the user, A system that includes this.

2. The system according to claim 1, which uses WebSocket or HTTP requests for the communication means to enable real-time processing of user input.

3. The system according to claim 1, wherein the translation means is based on a neural network.

Images