system

Abstract

We provide the system. [Solution] A receiving method that accepts language selection, A generation means for generating learning content based on a generative AI model, An acoustic conversion means that presents the generated learning content as an audio output, A voice analysis method that converts user voice information into text data, A management system that continues the dialogue based on user responses and provides feedback, A dialogue system that includes this.

Description

Technical Field

[0005]

[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 society, language learning is becoming increasingly important. However, in conventional methods, the time and environment for learning are restricted, and in particular, the opportunities for learning to handle multiple languages are limited. In addition, education by experts is costly, and it has been difficult for users to deepen their learning at their own pace. Furthermore, problems such as the need for reservations, time management, and a shortage of instructors for minority languages exist as issues, and there is a demand to solve these problems and easily realize broad language learning.

Means for Solving the Problems

[0005] The present invention provides a system that includes an input means for accepting language selection, a speech synthesis means for generating learning content based on a generative model, and presenting the generated learning content as speech output. Furthermore, it includes a speech recognition means for converting the user's speech input into text data, and a control means for continuing the dialogue based on the user's response, thereby solving the above problems. With this system, users can learn in various languages ​​at their leisure and obtain a rational, multilingual learning environment without the need for reservations.

[0006] "Language selection" is the operation or process of specifying a particular language that the user wants to learn.

[0007] An "input means" is a device or mechanism for receiving data or instructions from a user.

[0008] A "generative model" is a mathematical or computer program model that uses data and algorithms to generate a specific output.

[0009] "Learning content" refers to a collection of information and knowledge that users should learn, and includes publicly available teaching materials and dialogues.

[0010] "Generation means" refers to a system or method for creating or constructing data in a specified manner.

[0011] "Audio output" refers to media technologies that use sound to present information, and includes advanced speakers and synthesized speech systems.

[0012] "Speech synthesis means" refers to technologies and devices that convert text data into speech data and output it.

[0013] "Voice input" refers to the process or operation of transmitting audio signals to a system through a device such as a microphone.

[0014] "Voice recognition means" refers to a technology or device that analyzes the input voice and converts it into corresponding text data.

[0015] "Text data" refers to string data processed by a computer and is in a digital format that contains information that can be read by humans.

[0016] "Response" refers to the reply or action by the user to the questions or instructions presented by the system or program.

[0017] "Continuing the conversation" refers to the state in which the conversation or communication continues without interruption or the technology for that purpose.

[0018] "Control means" refers to the function or device for monitoring and adjusting the operation of the system.

Brief Description of the Drawings

[0019] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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]Shows an emotion map to which a plurality of emotions are mapped. [Figure 10] Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of 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.

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] 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."

[0027] [First Embodiment]

[0028] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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".

[0040] This invention is a multilingual learning system that allows users to select the language they wish to learn and provides dialogue practice and lessons in that language.

[0041] At the heart of this system is an AI agent that integrates speech synthesis and speech recognition technologies, with the server and terminal working together. First, the user launches an application on the terminal and selects the language and mode to learn. Based on this selection, the terminal sends a request to the server.

[0042] Upon receiving this request, the server uses a generative AI model to generate learning content based on the selected language. Specifically, it creates learning materials such as dialogue-based scenarios and question-and-answer sets, and stores them on the server in text format. The server then converts this text data into speech data using speech synthesis technology.

[0043] The generated audio data is sent to the device, which plays it back to provide the user with interactive questions and information. By responding to the audio through the device, the user can repeatedly use the learning content for the next step.

[0044] This response is collected by the terminal and converted into text data through speech recognition technology. This text data is then sent back to the server, which generates and provides appropriate feedback and subsequent dialogue based on the user's response. In this way, users can engage in real-time, two-way dialogue, facilitating smooth multilingual learning.

[0045] For example, if a user wants to learn Spanish, the server generates scenarios of everyday Spanish conversation and presents them to the user as audio. When the user answers questions in Spanish, the audio is transcribed into text using speech recognition, and the next questions and content are provided according to the user's level of understanding. This allows users to learn Spanish efficiently at their own pace, without being restricted by time or location.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The user launches the application on their device and specifies the language and learning mode they want to learn on the selection screen. The device then retrieves this selection information.

[0049] Step 2:

[0050] The terminal generates request data to send the acquired language and mode information to the server, and then sends that data to the server.

[0051] Step 3:

[0052] The server receives requests from terminals and analyzes their content. Based on the analysis results, it uses a generative AI model to generate learning materials and dialogue scenarios corresponding to the specified language.

[0053] Step 4:

[0054] The server converts the generated text data of teaching materials and scenarios into audio data using speech synthesis technology.

[0055] Step 5:

[0056] The server sends the converted audio data to the terminal.

[0057] Step 6:

[0058] The device plays the received audio data, allowing the user to receive the learning content in audio format. Interactive questions and prompts are presented to the user during this process.

[0059] Step 7:

[0060] The user responds to the presented questions using voice. The user's responses are collected in real time by the device.

[0061] Step 8:

[0062] The device uses speech recognition technology to convert the collected user voice responses into text data.

[0063] Step 9:

[0064] The terminal sends the converted text data to the server, which then parses it.

[0065] Step 10:

[0066] The server initiates a process to generate the next question or feedback based on the user's response. This information is again synthesized into speech and sent to the terminal.

[0067] Step 11:

[0068] The device plays the received audio data again, and the user moves on to the next learning step. This allows the user to continue learning through continuous interaction.

[0069] (Example 1)

[0070] 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."

[0071] In multilingual learning, conventional systems have a problem in that they cannot adequately provide individualized support to users, making it difficult to deliver effective learning. Furthermore, technical limitations in speech recognition and speech synthesis make it difficult to provide a smooth, real-time dialogue environment.

[0072] 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.

[0073] In this invention, the server includes an electronic device for accepting language selection, a configuration for generating learning information based on generative AI technology, a speech synthesis device for presenting the generated learning information as an audio signal, a speech recognition device for converting the user's audio data into text data, and a control mechanism for dynamically generating dialogue based on the user's responses. This enables personalized, responsive multilingual learning for the user.

[0074] An "electronic device that accepts language selection" is a hardware or software mechanism that allows a user to select the language they wish to learn and accepts that information as input.

[0075] "Generative AI technology" is a technology that uses artificial intelligence to generate learning information tailored to the user's purpose and skill level.

[0076] A "speech synthesis device that presents as an audio signal" is a device that uses speech synthesis technology to convert text data into speech and provide it to the user.

[0077] A "speech recognition device" is a device that utilizes technology to convert voice input from a user into text data.

[0078] A "control mechanism" is a system component that dynamically generates dialogue based on user responses and adaptively controls the learning process.

[0079] This invention is a system for supporting multilingual learning, operating through a combination of specific hardware and software. Specifically, it functions effectively through the interaction of a server, terminals, and users.

[0080] The server generates training information using generative AI technology. This generative AI technology takes a prompt as input and generates training information in text format, such as dialogue scenarios and question-and-answer sets, based on that prompt. For example, it might be used as a prompt such as, "Generate a beginner-level scenario about everyday Spanish conversation." Widely used generative models are applied to this generative AI technology.

[0081] The generated training information is converted into speech signals by a speech synthesizer on the server. The speech synthesizer uses cloud-based speech synthesis technology, such as Google® Cloud Text-to-Speech or Amazon Polly. This allows the generated text information to be presented to the user in a more intuitive way.

[0082] On the other hand, the terminal plays the role of collecting voice input from the user. The voice responses that the user makes to the terminal are converted into text data by the speech recognition device inside the terminal. For example, speech recognition technology such as Google Speech-to-Text is used. This converted text data is then sent to a server and used to generate the next learning content.

[0083] Through this system, users can experience language learning in real time. For example, if a user wants to learn Spanish, they can select Spanish on their device and proceed with interactive learning. By listening to audio provided by the server and responding with their own voice, they can efficiently acquire the language.

[0084] This invention enables users to learn multiple languages ​​at their own pace, more effectively and efficiently.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The user launches the application on their device and selects the language and mode they wish to learn. This selected information is received by the device's input device. This input information forms the basis of the request data used for subsequent processing.

[0088] Step 2:

[0089] The terminal structures the language and mode information selected by the user and sends it to the server as a request. The request data is transmitted to the server via the HTTP protocol and used as a prompt for the generative AI model. This prompt is necessary to facilitate the generation of the learning scenario.

[0090] Step 3:

[0091] The server launches a generative AI model based on the received request data. The server inputs a command to the generative AI model as a prompt, such as "Generate a learning scenario in the specified language." From this input, the generative AI model outputs conversational text data.

[0092] Step 4:

[0093] The server passes the generated text data to a speech synthesizer, which converts it into an audio signal. The speech synthesizer processes the text data into audio data in a format that is easy for the user to understand. This audio data is then provided to the user in the next step.

[0094] Step 5:

[0095] The server transmits audio data to the terminal. The terminal plays the received audio data through a playback device and presents it to the user. This playback serves as a trigger for the user to answer questions in an interactive format.

[0096] Step 6:

[0097] The user responds verbally to the audio played from the device. The device receives this voice input from the user and converts it into text data using a speech recognition device. The text data generated by the speech recognition process becomes the input for the next step.

[0098] Step 7:

[0099] The device sends text data obtained through speech recognition to the server. The server then uses this data to generate the next learning scenario and feedback. Through this reactive process, a continuous learning cycle for the user is established.

[0100] (Application Example 1)

[0101] 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."

[0102] In multilingual learning, a key challenge is providing an environment where learners can efficiently practice dialogue in their chosen language, without being restricted by time or location. In particular, there is a need to develop a system that enables real-time feedback and continuous conversation, and that supports a variety of languages.

[0103] 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.

[0104] In this invention, the server includes a receiving means for accepting language selection, a generating means for generating learning content based on a generative AI model, and a management means for continuing the dialogue and providing feedback based on the user's response. This enables language learning in a natural dialogue format in multiple languages.

[0105] A "receiving means" is a component that has the function of receiving language information selected by the user as input.

[0106] A "generative AI model" is an artificial intelligence technology that generates appropriate learning content based on language to support users' language learning.

[0107] A "generation method" is a component that has the function of automatically creating learning content to be provided to learners by utilizing a generative AI model.

[0108] "Audio conversion means" refers to a component that has the function of converting generated text data into audio data and presenting it to the user.

[0109] "Voice analysis means" refers to a component that has the function of converting the user's voice into text data.

[0110] A "management device" is a component that has the function of controlling the flow of dialogue based on the user's voice input, enabling continuous conversation, and providing appropriate feedback.

[0111] A "dialogue system" is a system that integrates these methods to realize real-time, interactive language learning in multiple languages.

[0112] In one embodiment of this invention, a dialogue system for supporting language learning is configured so that the user can select a language using a dedicated terminal and learn in a dialogue format. The system basically operates in cooperation between a server and a terminal.

[0113] First, the user launches the application on their device and selects the language they want to learn. The receiving device acquires this information and sends it to the server. The server uses a generative AI model to generate learning materials for the selected language. Specifically, these include conversation scripts and question sets based on various situations. This allows the generating device to provide the user with customized learning content.

[0114] The generated learning content is converted into audio data using an acoustic conversion device. The server sends this to the terminal, which presents it to the user as audio output. When the user responds with audio, the audio is converted into text data via the terminal's audio analysis device and sent back to the server. The server, using a management device, generates the next dialogue based on this text data and provides feedback.

[0115] As a concrete example, if a user wants to learn English, the server creates a script of everyday conversation and provides it as audio through the device. When the user responds in English, the content is transcribed into text, and appropriate feedback and the next question generated by the server are returned to the user as audio. In this way, users can engage in multilingual learning regardless of their location.

[0116] An example of a prompt message would be entered into the server as follows: "Generate a dialogue scenario including basic greetings and everyday conversation phrases in the language selected by the user, and provide the next steps according to the difficulty level." This allows the system to generate appropriate learning content and present it to the user.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The user launches a language learning application on their device and selects the language they want to learn. The input is the language information specified by the user on their device, which is received and sent from the device to the server. The output is the request data sent to the server.

[0120] Step 2:

[0121] Based on the request data received by the server, a generative AI model is used to generate learning content for the selected language. The input is the request data, and by inputting prompt sentences into the generative AI model, it creates text-based dialogue scenarios and question sets. The output is the generated learning content.

[0122] Step 3:

[0123] The generated text-based learning content is converted into audio data by an acoustic conversion device. The input is the generated learning content, and audio data is generated using speech synthesis technology. The output is audio data.

[0124] Step 4:

[0125] The converted audio data is sent from the server to the terminal, which then presents it to the user. The input is the audio data received from the server, which is then played back to the user through the speaker. The output is the audio the user hears.

[0126] Step 5:

[0127] The user responds to the presented audio, and the terminal converts the user's voice into text data using speech analysis. The input is the voice spoken by the user, which is converted into text data using speech recognition technology. The output is text data.

[0128] Step 6:

[0129] Text data is sent to a server, which analyzes this data to generate appropriate feedback and subsequent dialogue. The input is text data obtained from the user's responses, and a generative AI model is used to create dialogue and feedback. The output is new learned information or feedback data.

[0130] 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.

[0131] This invention relates to a multilingual learning system that can recognize a user's emotions during the learning process and adjust the dialogue content accordingly. This system consists of speech synthesis technology, speech recognition technology, and an emotion engine, and the server and terminal work together.

[0132] The user launches the application on their device and selects the language and mode to learn. Based on this selection, the device sends an initial request to the server. The server processes the request and generates learning content and dialogue scenarios using a generative model. This generated text is converted into audio data by a speech synthesis system and sent to the device. The device plays the audio data to the user and begins the dialogue. The user responds to questions using voice.

[0133] The response is collected by the terminal, transcribed into text using speech recognition technology, and then sent back to the server. Furthermore, this speech data is analyzed by an emotion engine to recognize the user's emotional state. The recognized emotion data is then considered by the server when adjusting the content of the next dialogue using a generation mechanism.

[0134] For example, if the emotion engine detects that a user is feeling frustrated while learning French, the server generates easy-to-understand content and encouraging messages. This allows the user to continue learning the language at their own pace and in a relaxed manner. Furthermore, by recording emotions and learning history, individual learning plans are optimized, providing an efficient learning experience.

[0135] In this way, the system of the present invention can not only support language learning but also create an optimal learning environment in response to the user's emotions, thereby more effectively supporting the acquisition of multiple languages.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The user launches the application on their device and selects the language they want to learn and the learning mode (e.g., conversational mode) on the displayed screen. The device then retrieves this information.

[0139] Step 2:

[0140] The terminal generates a request to send the acquired information to the server. This request includes language and mode information.

[0141] Step 3:

[0142] The server analyzes requests received from terminals and uses a generative model to generate learning content and dialogue scenarios. This content is stored in text format.

[0143] Step 4:

[0144] The server converts the generated text data into speech data using speech synthesis technology. It then sends the converted speech data to the terminal.

[0145] Step 5:

[0146] The device plays the received audio data and provides the user with learning content in audio format. The user responds to the presented questions and prompts.

[0147] Step 6:

[0148] The user's voice responses are collected through the device's microphone and stored in real time.

[0149] Step 7:

[0150] The device uses speech recognition technology to convert collected voice responses into text data. The converted text data is then sent to the server.

[0151] Step 8:

[0152] The server analyzes the user's text data and uses an emotion engine to identify the user's emotional state.

[0153] Step 9:

[0154] The emotion information identified by the emotion engine is taken into consideration when the server adjusts the content of subsequent interactions and learning.

[0155] Step 10:

[0156] The server synthesizes new learned content, generated in response to the user's emotions, into speech and sends the audio data to the device.

[0157] Step 11:

[0158] The device plays newly received audio data to the user, providing an emotionally sensitive learning experience, and then proceeds to the next dialogue stage.

[0159] This allows users to continue learning a language through flexible, emotion-responsive feedback and dialogue.

[0160] (Example 2)

[0161] 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 will be referred to as the "terminal."

[0162] Traditional language learning systems do not optimize learning based on the user's emotional state, which can lead to dissatisfaction and frustration. As a result, users may find it difficult to continue learning, making efficient acquisition challenging.

[0163] 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.

[0164] In this invention, the server includes a generation means for generating learning content and dialogue scenarios based on a generative model, an emotion analysis means for recognizing the user's emotional state and adjusting the next dialogue content, and a control means for continuing the dialogue based on the user's response. This makes it possible to provide optimal learning content according to the user's emotional state.

[0165] "Input means for accepting language selection" refers to means that provides an interface for users to select the language they wish to learn and has the function of transmitting that selection information to a processing device.

[0166] "Generative means for generating learning content and dialogue scenarios based on a generative model" refers to a means for automatically creating learning content and dialogue scenarios suitable for the user using a pre-configured learning model.

[0167] "A speech synthesis means that presents the generated learning content as audio output" refers to a means equipped with a mechanism for converting generated text into audio data and presenting it to the user.

[0168] "A speech recognition means that converts user voice input into text data" refers to a means that analyzes the pitch of the user's voice, recognizes that information as text, and provides it to a processing device.

[0169] "An emotion analysis tool that recognizes the user's emotional state and adjusts the content of the next conversation" is a tool that analyzes the user's emotions based on data from their voice and behavior, and adjusts the next conversation or learning materials accordingly.

[0170] "Control means for continuing a conversation based on user responses" refers to means that respond in a timely manner to user input and perform the necessary controls to maintain the flow of the conversation.

[0171] The system of the present invention is designed to enable users to effectively learn multiple languages. This system utilizes speech synthesis technology, speech recognition technology, and sentiment analysis technology, with the server and terminal working together.

[0172] server

[0173] The server uses a generative AI model to generate learning content and dialogue scenarios. This employs advanced natural language processing techniques to generate user-appropriate learning material using prompt sentences. This generated text is converted into speech data using speech synthesis technology (e.g., Google Cloud Text-to-Speech). The server further extracts sentiment data from the user's voice using sentiment analysis technology and adjusts the next learning content accordingly.

[0174] terminal

[0175] The terminal is a device for users to input the information necessary for learning. The user starts the application on the terminal and selects the language and mode they wish to learn. During this process, the terminal smoothly plays audio data and records the user's responses. The terminal converts the collected audio into text using speech recognition technology (e.g., Microsoft® Azure® Speech Service) and sends it to the server.

[0176] User

[0177] Users actively participate in the learning process through their devices. They progress through the learning process in an interactive manner by listening to presented audio materials and responding with voice. An emotion engine recognizes the user's emotional state, and if stress relief is needed, appropriate content is provided.

[0178] Specific examples and prompt statements

[0179] For example, if a user experiences frustration while learning French, the system will generate learning materials using a prompt message such as, "You are experiencing frustration while learning French. Please generate easy-to-understand example sentences and encouraging messages." This creates a flexible learning environment that caters to the individual needs of the user.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The user launches the application on their device and selects the language and mode they want to learn (e.g., beginner, everyday conversation). The device receives information about the language and mode selected by the user as input. The device processes this information and sends it to the server as an initial request.

[0183] Step 2:

[0184] The server analyzes the received request data and generates learning content and dialogue scenarios using a generative AI model. The prompt message is "Generate the optimal learning materials for the mode selected by the user." Natural language processing techniques are used to create the corresponding learning content. The output is the generated text data.

[0185] Step 3:

[0186] The server converts the generated text into audio data using speech synthesis technology. Specifically, it uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert the text data into speech. The output is audio data, which is then sent to the terminal.

[0187] Step 4:

[0188] The terminal plays audio data received from the server to the user. While playback is in progress, the terminal waits for the user's voice response. The input is audio data, and the output is the acquisition of the user's voice.

[0189] Step 5:

[0190] The user responds to voice prompts and engages in dialogue. The user's voice is recorded by the device and converted into text data using speech recognition technology. Specifically, a speech recognition engine (e.g., Microsoft Azure Speech Service) is used to convert the voice to text. The output is text data.

[0191] Step 6:

[0192] The server analyzes the received text and audio data using sentiment analysis tools to recognize the user's emotional state. Using this data, it generates new prompt sentences via a generative AI model to adjust the content of the next dialogue. The output is the adjusted learned content.

[0193] Step 7:

[0194] The server uses the adjusted learning content to generate new audio data and sends it back to the terminal. This allows the conversation session with the user to continue.

[0195] (Application Example 2)

[0196] 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".

[0197] In multilingual learning systems, a challenge exists in optimizing the learning experience due to the inability to engage in appropriate dialogue that responds to the user's emotional state. Furthermore, in systems used in caregiving settings, there is a lack of technical means to adjust dialogue to consider the user's emotions, even though this is necessary.

[0198] 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.

[0199] In this invention, the server includes an input means for accepting language selection, a generation means for generating learning content based on a generative model, a speech synthesis means for presenting the generated learning content as speech output, a speech recognition means for converting the user's speech input into text data, an emotion recognition means for identifying and analyzing the user's emotional state, and an adjustment means for adjusting the dialogue content based on the analyzed emotion information. This makes it possible to realize appropriate dialogue according to the user's emotional state and improve the quality of the learning experience.

[0200] "An input method that accepts language selection" refers to a device or software that provides an interface for users to select the language they wish to learn.

[0201] "Generative means for generating learning content based on a generative model" refers to a device or software that has the function of creating appropriate learning materials and content for the user based on a pre-prepared model.

[0202] "A speech synthesis means that presents the generated learning content as audio output" refers to a device or software that has the function of converting text data into audio data and playing it back as audio through an output device such as a speaker.

[0203] "A speech recognition means that converts a user's voice input into text data" refers to a device or software that has the function of converting voice data obtained through a microphone or the like into text format.

[0204] "An emotion recognition means for identifying and analyzing a user's emotional state" refers to a device or software that has the function of reading and analyzing a user's emotions from voice or text data to interpret that state.

[0205] "Adjustment means for adjusting dialogue content based on analyzed emotional information" refers to a device or software that has the function of appropriately changing the content and tone of dialogue based on information obtained from emotion recognition means.

[0206] The system for realizing this invention primarily involves a server and a terminal working together. The terminal receives language selection from the user and sends this information to the server. The server generates learning content using a generative AI model and sends it to the terminal as text data. On the terminal, a speech synthesis means presents the text data to the user as speech output. This process utilizes software libraries suitable for processing text data and synthesizing speech data. For example, the Google Speech API may be used for speech synthesis.

[0207] The user responds verbally during the learning process. This voice input is collected by the device and converted into text data using speech recognition technology. For example, Google's speech recognition API may be used. The converted text data is sent to a server, which analyzes it using sentiment recognition technology to identify the user's emotional state. Based on this information, the content of the next dialogue is adjusted.

[0208] The system flexibly adjusts the learning experience according to the user's emotions. For example, if a user feels "tired" while learning a particular language, the system generates relaxing interactions and prepares prompts to offer words of encouragement.

[0209] Example of a prompt: "He seems depressed. Please prepare some words of encouragement."

[0210] This allows learners to learn effectively at a pace that suits their own emotions. The system adapts the content and tone of the dialogue in response to changes in the user's emotions, optimizing the learning experience.

[0211] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0212] Step 1:

[0213] The terminal accepts language selection from the user. The user selects the language they wish to learn through the terminal's interface, and this information is sent from the terminal to the server. The input at this time is the user's language selection, and the output is the language selection information. Based on this, the server begins preparing the learning content.

[0214] Step 2:

[0215] The server generates learning content using a generative model. Based on the language selection information sent to the server, the generative AI model is used to generate learning content. In this case, the input is the language selection information, and the output is the generated learning content. Specifically, new dialogue scenarios are created while referring to past databases and existing learning materials.

[0216] Step 3:

[0217] The server generates the learning content and sends it to the terminal as text data. The terminal receives this text data and converts it into audio data for the user to hear via a speech synthesis system. Here, the input is the text data from the server, and the output is the audio data played back to the user. The audio data is played back by the terminal through the speaker for the user to hear.

[0218] Step 4:

[0219] The user responds with voice. This response is collected by the device's microphone and converted into text data by speech recognition technology. The input is the user's voice data, and the output is text data. Google's speech recognition API is used for accurate conversion from voice to text.

[0220] Step 5:

[0221] The converted text data is sent back to the server. The server analyzes the text data using emotion recognition tools to identify the user's emotional state. The input in this process is text data, and the output is emotion information. The server recognizes the emotional state using an emotion analysis library.

[0222] Step 6:

[0223] The server adjusts the next dialogue based on the emotional information. Using the obtained emotional information, it generates the next dialogue scenario appropriate to the user's learning state and emotions. The input in this process is emotional information, and the output is the adjusted dialogue content. The generation of prompt sentences prepares the appropriate conversation content.

[0224] Step 7:

[0225] The adjusted dialogue content is sent to the terminal, and the conversation with the user continues. The terminal presents the newly adjusted dialogue content to the user audibly using speech synthesis. The input is the new dialogue content, and the output is the audio data played back to the user. This returns to the first step, and learning progresses as the conversation is smoothly repeated.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] [Second Embodiment]

[0230] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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".

[0242] This invention is a multilingual learning system that allows users to select the language they wish to learn and provides dialogue practice and lessons in that language.

[0243] At the heart of this system is an AI agent that integrates speech synthesis and speech recognition technologies, with the server and terminal working together. First, the user launches an application on the terminal and selects the language and mode to learn. Based on this selection, the terminal sends a request to the server.

[0244] Upon receiving this request, the server uses a generative AI model to generate learning content based on the selected language. Specifically, it creates learning materials such as dialogue-based scenarios and question-and-answer sets, and stores them on the server in text format. The server then converts this text data into speech data using speech synthesis technology.

[0245] The generated audio data is sent to the device, which plays it back to provide the user with interactive questions and information. By responding to the audio through the device, the user can repeatedly use the learning content for the next step.

[0246] This response is collected by the terminal and converted into text data through speech recognition technology. This text data is then sent back to the server, which generates and provides appropriate feedback and subsequent dialogue based on the user's response. In this way, users can engage in real-time, two-way dialogue, facilitating smooth multilingual learning.

[0247] For example, if a user wants to learn Spanish, the server generates scenarios of everyday Spanish conversation and presents them to the user as audio. When the user answers questions in Spanish, the audio is transcribed into text using speech recognition, and the next questions and content are provided according to the user's level of understanding. This allows users to learn Spanish efficiently at their own pace, without being restricted by time or location.

[0248] The following describes the processing flow.

[0249] Step 1:

[0250] The user launches the application on their device and specifies the language and learning mode they want to learn on the selection screen. The device then retrieves this selection information.

[0251] Step 2:

[0252] The terminal generates request data to send the acquired language and mode information to the server, and then sends that data to the server.

[0253] Step 3:

[0254] The server receives requests from terminals and analyzes their content. Based on the analysis results, it uses a generative AI model to generate learning materials and dialogue scenarios corresponding to the specified language.

[0255] Step 4:

[0256] The server converts the generated text data of teaching materials and scenarios into audio data using speech synthesis technology.

[0257] Step 5:

[0258] The server sends the converted audio data to the terminal.

[0259] Step 6:

[0260] The device plays the received audio data, allowing the user to receive the learning content in audio format. Interactive questions and prompts are presented to the user during this process.

[0261] Step 7:

[0262] The user responds to the presented questions using voice. The user's responses are collected in real time by the device.

[0263] Step 8:

[0264] The device uses speech recognition technology to convert the collected user voice responses into text data.

[0265] Step 9:

[0266] The terminal sends the converted text data to the server, which then parses it.

[0267] Step 10:

[0268] The server initiates a process to generate the next question or feedback based on the user's response. This information is again synthesized into speech and sent to the terminal.

[0269] Step 11:

[0270] The device plays the received audio data again, and the user moves on to the next learning step. This allows the user to continue learning through continuous interaction.

[0271] (Example 1)

[0272] 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".

[0273] In multilingual learning, conventional systems have a problem in that they cannot adequately provide individualized support to users, making it difficult to deliver effective learning. Furthermore, technical limitations in speech recognition and speech synthesis make it difficult to provide a smooth, real-time dialogue environment.

[0274] 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.

[0275] In this invention, the server includes an electronic device for accepting language selection, a configuration for generating learning information based on generative AI technology, a speech synthesis device for presenting the generated learning information as an audio signal, a speech recognition device for converting the user's audio data into text data, and a control mechanism for dynamically generating dialogue based on the user's responses. This enables personalized, responsive multilingual learning for the user.

[0276] An "electronic device that accepts language selection" is a hardware or software mechanism that allows a user to select the language they wish to learn and accepts that information as input.

[0277] "Generative AI technology" is a technology that uses artificial intelligence to generate learning information tailored to the user's purpose and skill level.

[0278] A "speech synthesis device that presents as an audio signal" is a device that uses speech synthesis technology to convert text data into speech and provide it to the user.

[0279] A "speech recognition device" is a device that utilizes technology to convert voice input from a user into text data.

[0280] A "control mechanism" is a system component that dynamically generates dialogue based on user responses and adaptively controls the learning process.

[0281] This invention is a system for supporting multilingual learning, operating through a combination of specific hardware and software. Specifically, it functions effectively through the interaction of a server, terminals, and users.

[0282] The server generates training information using generative AI technology. This generative AI technology takes a prompt as input and generates training information in text format, such as dialogue scenarios and question-and-answer sets, based on that prompt. For example, it might be used as a prompt such as, "Generate a beginner-level scenario about everyday Spanish conversation." Widely used generative models are applied to this generative AI technology.

[0283] The generated training information is converted into speech signals by a speech synthesizer on the server. The speech synthesizer uses cloud-based speech synthesis technology, such as Google Cloud Text-to-Speech or Amazon Polly. This allows the generated text information to be presented to the user in a more intuitive way.

[0284] On the one hand, the terminal serves to collect voice input from the user. The voice response made by the user to the terminal is converted into text data by the voice recognition device in the terminal. As the voice recognition technology, for example, technologies such as Google Speech-to-Text are used. This converted text data is further transmitted to the server and used for the generation of the following learning content.

[0285] Through this system, the user can experience language learning in real time. For example, if the user wants to learn Spanish, they can select Spanish on the terminal and proceed with interactive learning. By listening to the voice provided by the server and repeating the learning while responding with their own voice accordingly, language acquisition can be promoted efficiently.

[0286] With this invention, the user can more effectively and efficiently carry out multilingual learning at their own pace.

[0287] The flow of the specific process in Example 1 will be described using FIG. 11.

[0288] Step 1:

[0289] The user launches an application on the terminal and selects the language and mode they want to learn. The selected information is received by the input device of the terminal. This input information serves as the basis for the request data to be used in subsequent processing.

[0290] Step 2:

[0291] The terminal structures the information of the language and mode selected by the user and sends it as a request to the server. The request data is transmitted to the server via the HTTP protocol and used as a prompt for the generation AI model. This prompt is necessary to prompt the generation of the learning scenario.

[0292] Step 3:

[0293] The server launches a generative AI model based on the received request data. The server inputs a command to the generative AI model as a prompt, such as "Generate a learning scenario in the specified language." From this input, the generative AI model outputs conversational text data.

[0294] Step 4:

[0295] The server passes the generated text data to a speech synthesizer, which converts it into an audio signal. The speech synthesizer processes the text data into audio data in a format that is easy for the user to understand. This audio data is then provided to the user in the next step.

[0296] Step 5:

[0297] The server transmits audio data to the terminal. The terminal plays the received audio data through a playback device and presents it to the user. This playback serves as a trigger for the user to answer questions in an interactive format.

[0298] Step 6:

[0299] The user responds verbally to the audio played from the device. The device receives this voice input from the user and converts it into text data using a speech recognition device. The text data generated by the speech recognition process becomes the input for the next step.

[0300] Step 7:

[0301] The device sends text data obtained through speech recognition to the server. The server then uses this data to generate the next learning scenario and feedback. Through this reactive process, a continuous learning cycle for the user is established.

[0302] (Application Example 1)

[0303] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0304] In multilingual learning, it is an issue to provide an environment where learners can efficiently practice conversations in the language they have selected, without being restricted by time or place. In particular, there is a need to develop a system that enables real-time feedback and continuation of conversations and supports various languages.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0306] In this invention, the server includes a receiving means for receiving a language selection, a generating means for generating learning content based on a generation AI model, and a management means for continuing a conversation based on the user's response and providing feedback. This enables language learning in a natural conversation format in multiple languages.

[0307] The "receiving means" is a component having a function of receiving, as an input, the language information selected by the user.

[0308] The "generation AI model" is an artificial intelligence technology for generating appropriate learning content based on a language in order to support the user's language learning.

[0309] The "generating means" is a component having a function of automatically creating the learning content to be provided to the learner by utilizing the generation AI model.

[0310] The "acoustic conversion means" is a component having a function of converting the generated text data into voice data and presenting it to the user.

[0311] The "voice analysis means" is a component having a function of converting the user's voice into text data.

[0312] A "management device" is a component that has the function of controlling the flow of dialogue based on the user's voice input, enabling continuous conversation, and providing appropriate feedback.

[0313] A "dialogue system" is a system that integrates these methods to realize real-time, interactive language learning in multiple languages.

[0314] In one embodiment of this invention, a dialogue system for supporting language learning is configured so that the user can select a language using a dedicated terminal and learn in a dialogue format. The system basically operates in cooperation between a server and a terminal.

[0315] First, the user launches the application on their device and selects the language they want to learn. The receiving device acquires this information and sends it to the server. The server uses a generative AI model to generate learning materials for the selected language. Specifically, these include conversation scripts and question sets based on various situations. This allows the generating device to provide the user with customized learning content.

[0316] The generated learning content is converted into audio data using an acoustic conversion device. The server sends this to the terminal, which presents it to the user as audio output. When the user responds with audio, the audio is converted into text data via the terminal's audio analysis device and sent back to the server. The server, using a management device, generates the next dialogue based on this text data and provides feedback.

[0317] As a concrete example, if a user wants to learn English, the server creates a script of everyday conversation and provides it as audio through the device. When the user responds in English, the content is transcribed into text, and appropriate feedback and the next question generated by the server are returned to the user as audio. In this way, users can engage in multilingual learning regardless of their location.

[0318] An example of a prompt message would be entered into the server as follows: "Generate a dialogue scenario including basic greetings and everyday conversation phrases in the language selected by the user, and provide the next steps according to the difficulty level." This allows the system to generate appropriate learning content and present it to the user.

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] The user launches a language learning application on their device and selects the language they want to learn. The input is the language information specified by the user on their device, which is received and sent from the device to the server. The output is the request data sent to the server.

[0322] Step 2:

[0323] Based on the request data received by the server, a generative AI model is used to generate learning content for the selected language. The input is the request data, and by inputting prompt sentences into the generative AI model, it creates text-based dialogue scenarios and question sets. The output is the generated learning content.

[0324] Step 3:

[0325] The generated text-based learning content is converted into audio data by an acoustic conversion device. The input is the generated learning content, and audio data is generated using speech synthesis technology. The output is audio data.

[0326] Step 4:

[0327] The converted audio data is sent from the server to the terminal, which then presents it to the user. The input is the audio data received from the server, which is then played back to the user through the speaker. The output is the audio the user hears.

[0328] Step 5:

[0329] The user responds to the presented audio, and the terminal converts the user's voice into text data using speech analysis. The input is the voice spoken by the user, which is converted into text data using speech recognition technology. The output is text data.

[0330] Step 6:

[0331] Text data is sent to a server, which analyzes this data to generate appropriate feedback and subsequent dialogue. The input is text data obtained from the user's responses, and a generative AI model is used to create dialogue and feedback. The output is new learned information or feedback data.

[0332] 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.

[0333] This invention relates to a multilingual learning system that can recognize a user's emotions during the learning process and adjust the dialogue content accordingly. This system consists of speech synthesis technology, speech recognition technology, and an emotion engine, and the server and terminal work together.

[0334] The user launches the application on their device and selects the language and mode to learn. Based on this selection, the device sends an initial request to the server. The server processes the request and generates learning content and dialogue scenarios using a generative model. This generated text is converted into audio data by a speech synthesis system and sent to the device. The device plays the audio data to the user and begins the dialogue. The user responds to questions using voice.

[0335] The response is collected by the terminal, transcribed into text using speech recognition technology, and then sent back to the server. Furthermore, this speech data is analyzed by an emotion engine to recognize the user's emotional state. The recognized emotion data is then considered by the server when adjusting the content of the next dialogue using a generation mechanism.

[0336] For example, if the emotion engine detects that a user is feeling frustrated while learning French, the server generates easy-to-understand content and encouraging messages. This allows the user to continue learning the language at their own pace and in a relaxed manner. Furthermore, by recording emotions and learning history, individual learning plans are optimized, providing an efficient learning experience.

[0337] In this way, the system of the present invention can not only support language learning but also create an optimal learning environment in response to the user's emotions, thereby more effectively supporting the acquisition of multiple languages.

[0338] The following describes the processing flow.

[0339] Step 1:

[0340] The user launches the application on their device and selects the language they want to learn and the learning mode (e.g., conversational mode) on the displayed screen. The device then retrieves this information.

[0341] Step 2:

[0342] The terminal generates a request to send the acquired information to the server. This request includes language and mode information.

[0343] Step 3:

[0344] The server analyzes requests received from terminals and uses a generative model to generate learning content and dialogue scenarios. This content is stored in text format.

[0345] Step 4:

[0346] The server converts the generated text data into speech data using speech synthesis technology. It then sends the converted speech data to the terminal.

[0347] Step 5:

[0348] The device plays the received audio data and provides the user with learning content in audio format. The user responds to the presented questions and prompts.

[0349] Step 6:

[0350] The user's voice responses are collected through the device's microphone and stored in real time.

[0351] Step 7:

[0352] The device uses speech recognition technology to convert collected voice responses into text data. The converted text data is then sent to the server.

[0353] Step 8:

[0354] The server analyzes the user's text data and uses an emotion engine to identify the user's emotional state.

[0355] Step 9:

[0356] The emotion information identified by the emotion engine is taken into consideration when the server adjusts the content of subsequent interactions and learning.

[0357] Step 10:

[0358] The server synthesizes new learned content, generated in response to the user's emotions, into speech and sends the audio data to the device.

[0359] Step 11:

[0360] The device plays newly received audio data to the user, providing an emotionally sensitive learning experience, and then proceeds to the next dialogue stage.

[0361] This allows users to continue learning a language through flexible, emotion-responsive feedback and dialogue.

[0362] (Example 2)

[0363] 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".

[0364] Traditional language learning systems do not optimize learning based on the user's emotional state, which can lead to dissatisfaction and frustration. As a result, users may find it difficult to continue learning, making efficient acquisition challenging.

[0365] 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.

[0366] In this invention, the server includes a generation means for generating learning content and dialogue scenarios based on a generative model, an emotion analysis means for recognizing the user's emotional state and adjusting the next dialogue content, and a control means for continuing the dialogue based on the user's response. This makes it possible to provide optimal learning content according to the user's emotional state.

[0367] "Input means for accepting language selection" refers to means that provides an interface for users to select the language they wish to learn and has the function of transmitting that selection information to a processing device.

[0368] "Generative means for generating learning content and dialogue scenarios based on a generative model" refers to a means for automatically creating learning content and dialogue scenarios suitable for the user using a pre-configured learning model.

[0369] "A speech synthesis means that presents the generated learning content as audio output" refers to a means equipped with a mechanism for converting generated text into audio data and presenting it to the user.

[0370] "A speech recognition means that converts user voice input into text data" refers to a means that analyzes the pitch of the user's voice, recognizes that information as text, and provides it to a processing device.

[0371] "An emotion analysis tool that recognizes the user's emotional state and adjusts the content of the next conversation" is a tool that analyzes the user's emotions based on data from their voice and behavior, and adjusts the next conversation or learning materials accordingly.

[0372] "Control means for continuing a conversation based on user responses" refers to means that respond in a timely manner to user input and perform the necessary controls to maintain the flow of the conversation.

[0373] The system of the present invention is designed to enable users to effectively learn multiple languages. This system utilizes speech synthesis technology, speech recognition technology, and sentiment analysis technology, with the server and terminal working together.

[0374] server

[0375] The server uses a generative AI model to generate learning content and dialogue scenarios. This employs advanced natural language processing techniques to generate user-appropriate learning material using prompt sentences. This generated text is converted into speech data using speech synthesis technology (e.g., Google Cloud Text-to-Speech). The server further extracts sentiment data from the user's voice using sentiment analysis technology and adjusts the next learning content accordingly.

[0376] terminal

[0377] The terminal is a device for users to input the information necessary for learning. The user starts the application on the terminal and selects the language and mode they wish to learn. During this process, the terminal smoothly plays audio data and records the user's responses. The terminal converts the collected audio into text using speech recognition technology (e.g., Microsoft Azure Speech Service) and sends it to the server.

[0378] User

[0379] Users actively participate in the learning process through their devices. They progress through the learning process in an interactive manner by listening to presented audio materials and responding with voice. An emotion engine recognizes the user's emotional state, and if stress relief is needed, appropriate content is provided.

[0380] Specific examples and prompt statements

[0381] For example, if a user experiences frustration while learning French, the system will generate learning materials using a prompt message such as, "You are experiencing frustration while learning French. Please generate easy-to-understand example sentences and encouraging messages." This creates a flexible learning environment that caters to the individual needs of the user.

[0382] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0383] Step 1:

[0384] The user launches the application on their device and selects the language and mode they want to learn (e.g., beginner, everyday conversation). The device receives information about the language and mode selected by the user as input. The device processes this information and sends it to the server as an initial request.

[0385] Step 2:

[0386] The server analyzes the received request data and generates learning content and dialogue scenarios using a generative AI model. The prompt message is "Generate the optimal learning materials for the mode selected by the user." Natural language processing techniques are used to create the corresponding learning content. The output is the generated text data.

[0387] Step 3:

[0388] The server converts the generated text into audio data using speech synthesis technology. Specifically, it uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert the text data into speech. The output is audio data, which is then sent to the terminal.

[0389] Step 4:

[0390] The terminal plays audio data received from the server to the user. While playback is in progress, the terminal waits for the user's voice response. The input is audio data, and the output is the acquisition of the user's voice.

[0391] Step 5:

[0392] The user responds to voice prompts and engages in dialogue. The user's voice is recorded by the device and converted into text data using speech recognition technology. Specifically, a speech recognition engine (e.g., Microsoft Azure Speech Service) is used to convert the voice to text. The output is text data.

[0393] Step 6:

[0394] The server analyzes the received text and audio data using sentiment analysis tools to recognize the user's emotional state. Using this data, it generates new prompt sentences via a generative AI model to adjust the content of the next dialogue. The output is the adjusted learned content.

[0395] Step 7:

[0396] The server uses the adjusted learning content to generate new audio data and sends it back to the terminal. This allows the conversation session with the user to continue.

[0397] (Application Example 2)

[0398] 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 as the "terminal".

[0399] In multilingual learning systems, a challenge exists in optimizing the learning experience due to the inability to engage in appropriate dialogue that responds to the user's emotional state. Furthermore, in systems used in caregiving settings, there is a lack of technical means to adjust dialogue to consider the user's emotions, even though this is necessary.

[0400] 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.

[0401] In this invention, the server includes an input means for accepting language selection, a generation means for generating learning content based on a generative model, a speech synthesis means for presenting the generated learning content as speech output, a speech recognition means for converting the user's speech input into text data, an emotion recognition means for identifying and analyzing the user's emotional state, and an adjustment means for adjusting the dialogue content based on the analyzed emotion information. This makes it possible to realize appropriate dialogue according to the user's emotional state and improve the quality of the learning experience.

[0402] "An input method that accepts language selection" refers to a device or software that provides an interface for users to select the language they wish to learn.

[0403] "Generative means for generating learning content based on a generative model" refers to a device or software that has the function of creating appropriate learning materials and content for the user based on a pre-prepared model.

[0404] "A speech synthesis means that presents the generated learning content as audio output" refers to a device or software that has the function of converting text data into audio data and playing it back as audio through an output device such as a speaker.

[0405] "A speech recognition means that converts a user's voice input into text data" refers to a device or software that has the function of converting voice data obtained through a microphone or the like into text format.

[0406] "An emotion recognition means for identifying and analyzing a user's emotional state" refers to a device or software that has the function of reading and analyzing a user's emotions from voice or text data to interpret that state.

[0407] "Adjustment means for adjusting dialogue content based on analyzed emotional information" refers to a device or software that has the function of appropriately changing the content and tone of dialogue based on information obtained from emotion recognition means.

[0408] The system for realizing this invention primarily involves a server and a terminal working together. The terminal receives language selection from the user and sends this information to the server. The server generates learning content using a generative AI model and sends it to the terminal as text data. On the terminal, a speech synthesis means presents the text data to the user as speech output. This process utilizes software libraries suitable for processing text data and synthesizing speech data. For example, the Google Speech API may be used for speech synthesis.

[0409] The user responds verbally during the learning process. This voice input is collected by the device and converted into text data using speech recognition technology. For example, Google's speech recognition API may be used. The converted text data is sent to a server, which analyzes it using sentiment recognition technology to identify the user's emotional state. Based on this information, the content of the next dialogue is adjusted.

[0410] The system flexibly adjusts the learning experience according to the user's emotions. For example, if a user feels "tired" while learning a particular language, the system generates relaxing interactions and prepares prompts to offer words of encouragement.

[0411] Example of a prompt: "He seems depressed. Please prepare some words of encouragement."

[0412] This allows learners to learn effectively at a pace that suits their own emotions. The system adapts the content and tone of the dialogue in response to changes in the user's emotions, optimizing the learning experience.

[0413] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0414] Step 1:

[0415] The terminal accepts language selection from the user. The user selects the language they wish to learn through the terminal's interface, and this information is sent from the terminal to the server. The input at this time is the user's language selection, and the output is the language selection information. Based on this, the server begins preparing the learning content.

[0416] Step 2:

[0417] The server generates learning content using a generative model. Based on the language selection information sent to the server, the generative AI model is used to generate learning content. In this case, the input is the language selection information, and the output is the generated learning content. Specifically, new dialogue scenarios are created while referring to past databases and existing learning materials.

[0418] Step 3:

[0419] The server generates the learning content and sends it to the terminal as text data. The terminal receives this text data and converts it into audio data for the user to hear via a speech synthesis system. Here, the input is the text data from the server, and the output is the audio data played back to the user. The audio data is played back by the terminal through the speaker for the user to hear.

[0420] Step 4:

[0421] The user responds with voice. This response is collected by the device's microphone and converted into text data by speech recognition technology. The input is the user's voice data, and the output is text data. Google's speech recognition API is used for accurate conversion from voice to text.

[0422] Step 5:

[0423] The converted text data is sent back to the server. The server analyzes the text data using emotion recognition tools to identify the user's emotional state. The input in this process is text data, and the output is emotion information. The server recognizes the emotional state using an emotion analysis library.

[0424] Step 6:

[0425] The server adjusts the next dialogue based on the emotional information. Using the obtained emotional information, it generates the next dialogue scenario appropriate to the user's learning state and emotions. The input in this process is emotional information, and the output is the adjusted dialogue content. The generation of prompt sentences prepares the appropriate conversation content.

[0426] Step 7:

[0427] The adjusted dialogue content is sent to the terminal, and the conversation with the user continues. The terminal presents the newly adjusted dialogue content to the user audibly using speech synthesis. The input is the new dialogue content, and the output is the audio data played back to the user. This returns to the first step, and learning progresses as the conversation is smoothly repeated.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] [Third Embodiment]

[0432] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0433] 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.

[0434] 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).

[0435] 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.

[0436] 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.

[0437] 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).

[0438] 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.

[0439] 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.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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".

[0444] This invention is a multilingual learning system that allows users to select the language they wish to learn and provides dialogue practice and lessons in that language.

[0445] At the heart of this system is an AI agent that integrates speech synthesis and speech recognition technologies, with the server and terminal working together. First, the user launches an application on the terminal and selects the language and mode to learn. Based on this selection, the terminal sends a request to the server.

[0446] Upon receiving this request, the server uses a generative AI model to generate learning content based on the selected language. Specifically, it creates learning materials such as dialogue-based scenarios and question-and-answer sets, and stores them on the server in text format. The server then converts this text data into speech data using speech synthesis technology.

[0447] The generated audio data is sent to the device, which plays it back to provide the user with interactive questions and information. By responding to the audio through the device, the user can repeatedly use the learning content for the next step.

[0448] This response is collected by the terminal and converted into text data through speech recognition technology. This text data is then sent back to the server, which generates and provides appropriate feedback and subsequent dialogue based on the user's response. In this way, users can engage in real-time, two-way dialogue, facilitating smooth multilingual learning.

[0449] For example, if a user wants to learn Spanish, the server generates scenarios of everyday Spanish conversation and presents them to the user as audio. When the user answers questions in Spanish, the audio is transcribed into text using speech recognition, and the next questions and content are provided according to the user's level of understanding. This allows users to learn Spanish efficiently at their own pace, without being restricted by time or location.

[0450] The following describes the processing flow.

[0451] Step 1:

[0452] The user launches the application on their device and specifies the language and learning mode they want to learn on the selection screen. The device then retrieves this selection information.

[0453] Step 2:

[0454] The terminal generates request data to send the acquired language and mode information to the server, and then sends that data to the server.

[0455] Step 3:

[0456] The server receives requests from terminals and analyzes their content. Based on the analysis results, it uses a generative AI model to generate learning materials and dialogue scenarios corresponding to the specified language.

[0457] Step 4:

[0458] The server converts the generated text data of teaching materials and scenarios into audio data using speech synthesis technology.

[0459] Step 5:

[0460] The server sends the converted audio data to the terminal.

[0461] Step 6:

[0462] The device plays the received audio data, allowing the user to receive the learning content in audio format. Interactive questions and prompts are presented to the user during this process.

[0463] Step 7:

[0464] The user responds to the presented questions using voice. The user's responses are collected in real time by the device.

[0465] Step 8:

[0466] The device uses speech recognition technology to convert the collected user voice responses into text data.

[0467] Step 9:

[0468] The terminal sends the converted text data to the server, which then parses it.

[0469] Step 10:

[0470] The server initiates a process to generate the next question or feedback based on the user's response. This information is again synthesized into speech and sent to the terminal.

[0471] Step 11:

[0472] The device plays the received audio data again, and the user moves on to the next learning step. This allows the user to continue learning through continuous interaction.

[0473] (Example 1)

[0474] 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."

[0475] In multilingual learning, conventional systems have a problem in that they cannot adequately provide individualized support to users, making it difficult to deliver effective learning. Furthermore, technical limitations in speech recognition and speech synthesis make it difficult to provide a smooth, real-time dialogue environment.

[0476] 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.

[0477] In this invention, the server includes an electronic device for accepting language selection, a configuration for generating learning information based on generative AI technology, a speech synthesis device for presenting the generated learning information as an audio signal, a speech recognition device for converting the user's audio data into text data, and a control mechanism for dynamically generating dialogue based on the user's responses. This enables personalized, responsive multilingual learning for the user.

[0478] An "electronic device that accepts language selection" is a hardware or software mechanism that allows a user to select the language they wish to learn and accepts that information as input.

[0479] "Generative AI technology" is a technology that uses artificial intelligence to generate learning information tailored to the user's purpose and skill level.

[0480] A "speech synthesis device that presents as an audio signal" is a device that uses speech synthesis technology to convert text data into speech and provide it to the user.

[0481] A "speech recognition device" is a device that utilizes technology to convert voice input from a user into text data.

[0482] A "control mechanism" is a system component that dynamically generates dialogue based on user responses and adaptively controls the learning process.

[0483] This invention is a system for supporting multilingual learning, operating through a combination of specific hardware and software. Specifically, it functions effectively through the interaction of a server, terminals, and users.

[0484] The server generates training information using generative AI technology. This generative AI technology takes a prompt as input and generates training information in text format, such as dialogue scenarios and question-and-answer sets, based on that prompt. For example, it might be used as a prompt such as, "Generate a beginner-level scenario about everyday Spanish conversation." Widely used generative models are applied to this generative AI technology.

[0485] The generated training information is converted into speech signals by a speech synthesizer on the server. The speech synthesizer uses cloud-based speech synthesis technology, such as Google Cloud Text-to-Speech or Amazon Polly. This allows the generated text information to be presented to the user in a more intuitive way.

[0486] On the other hand, the terminal plays the role of collecting voice input from the user. The voice responses that the user makes to the terminal are converted into text data by the speech recognition device inside the terminal. For example, speech recognition technology such as Google Speech-to-Text is used. This converted text data is then sent to a server and used to generate the next learning content.

[0487] Through this system, users can experience language learning in real time. For example, if a user wants to learn Spanish, they can select Spanish on their device and proceed with interactive learning. By listening to audio provided by the server and responding with their own voice, they can efficiently acquire the language.

[0488] This invention enables users to learn multiple languages ​​at their own pace, more effectively and efficiently.

[0489] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0490] Step 1:

[0491] The user launches the application on their device and selects the language and mode they wish to learn. This selected information is received by the device's input device. This input information forms the basis of the request data used for subsequent processing.

[0492] Step 2:

[0493] The terminal structures the language and mode information selected by the user and sends it to the server as a request. The request data is transmitted to the server via the HTTP protocol and used as a prompt for the generative AI model. This prompt is necessary to facilitate the generation of the learning scenario.

[0494] Step 3:

[0495] The server launches a generative AI model based on the received request data. The server inputs a command to the generative AI model as a prompt, such as "Generate a learning scenario in the specified language." From this input, the generative AI model outputs conversational text data.

[0496] Step 4:

[0497] The server passes the generated text data to a speech synthesizer, which converts it into an audio signal. The speech synthesizer processes the text data into audio data in a format that is easy for the user to understand. This audio data is then provided to the user in the next step.

[0498] Step 5:

[0499] The server transmits audio data to the terminal. The terminal plays the received audio data through a playback device and presents it to the user. This playback serves as a trigger for the user to answer questions in an interactive format.

[0500] Step 6:

[0501] The user responds verbally to the audio played from the device. The device receives this voice input from the user and converts it into text data using a speech recognition device. The text data generated by the speech recognition process becomes the input for the next step.

[0502] Step 7:

[0503] The device sends text data obtained through speech recognition to the server. The server then uses this data to generate the next learning scenario and feedback. Through this reactive process, a continuous learning cycle for the user is established.

[0504] (Application Example 1)

[0505] 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."

[0506] In multilingual learning, a key challenge is providing an environment where learners can efficiently practice dialogue in their chosen language, without being restricted by time or location. In particular, there is a need to develop a system that enables real-time feedback and continuous conversation, and that supports a variety of languages.

[0507] 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.

[0508] In this invention, the server includes a receiving means for accepting language selection, a generating means for generating learning content based on a generative AI model, and a management means for continuing the dialogue and providing feedback based on the user's response. This enables language learning in a natural dialogue format in multiple languages.

[0509] A "receiving means" is a component that has the function of receiving language information selected by the user as input.

[0510] A "generative AI model" is an artificial intelligence technology that generates appropriate learning content based on language to support users' language learning.

[0511] A "generation method" is a component that has the function of automatically creating learning content to be provided to learners by utilizing a generative AI model.

[0512] "Audio conversion means" refers to a component that has the function of converting generated text data into audio data and presenting it to the user.

[0513] "Voice analysis means" refers to a component that has the function of converting the user's voice into text data.

[0514] A "management device" is a component that has the function of controlling the flow of dialogue based on the user's voice input, enabling continuous conversation, and providing appropriate feedback.

[0515] A "dialogue system" is a system that integrates these methods to realize real-time, interactive language learning in multiple languages.

[0516] In one embodiment of this invention, a dialogue system for supporting language learning is configured so that the user can select a language using a dedicated terminal and learn in a dialogue format. The system basically operates in cooperation between a server and a terminal.

[0517] First, the user launches the application on their device and selects the language they want to learn. The receiving device acquires this information and sends it to the server. The server uses a generative AI model to generate learning materials for the selected language. Specifically, these include conversation scripts and question sets based on various situations. This allows the generating device to provide the user with customized learning content.

[0518] The generated learning content is converted into audio data using an acoustic conversion device. The server sends this to the terminal, which presents it to the user as audio output. When the user responds with audio, the audio is converted into text data via the terminal's audio analysis device and sent back to the server. The server, using a management device, generates the next dialogue based on this text data and provides feedback.

[0519] As a concrete example, if a user wants to learn English, the server creates a script of everyday conversation and provides it as audio through the device. When the user responds in English, the content is transcribed into text, and appropriate feedback and the next question generated by the server are returned to the user as audio. In this way, users can engage in multilingual learning regardless of their location.

[0520] An example of a prompt message would be entered into the server as follows: "Generate a dialogue scenario including basic greetings and everyday conversation phrases in the language selected by the user, and provide the next steps according to the difficulty level." This allows the system to generate appropriate learning content and present it to the user.

[0521] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0522] Step 1:

[0523] The user launches a language learning application on their device and selects the language they want to learn. The input is the language information specified by the user on their device, which is received and sent from the device to the server. The output is the request data sent to the server.

[0524] Step 2:

[0525] Based on the request data received by the server, a generative AI model is used to generate learning content for the selected language. The input is the request data, and by inputting prompt sentences into the generative AI model, it creates text-based dialogue scenarios and question sets. The output is the generated learning content.

[0526] Step 3:

[0527] The generated text-based learning content is converted into audio data by an acoustic conversion device. The input is the generated learning content, and audio data is generated using speech synthesis technology. The output is audio data.

[0528] Step 4:

[0529] The converted audio data is sent from the server to the terminal, which then presents it to the user. The input is the audio data received from the server, which is then played back to the user through the speaker. The output is the audio the user hears.

[0530] Step 5:

[0531] The user responds to the presented audio, and the terminal converts the user's voice into text data using speech analysis. The input is the voice spoken by the user, which is converted into text data using speech recognition technology. The output is text data.

[0532] Step 6:

[0533] Text data is sent to a server, which analyzes this data to generate appropriate feedback and subsequent dialogue. The input is text data obtained from the user's responses, and a generative AI model is used to create dialogue and feedback. The output is new learned information or feedback data.

[0534] 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.

[0535] This invention relates to a multilingual learning system that can recognize a user's emotions during the learning process and adjust the dialogue content accordingly. This system consists of speech synthesis technology, speech recognition technology, and an emotion engine, and the server and terminal work together.

[0536] The user launches the application on their device and selects the language and mode to learn. Based on this selection, the device sends an initial request to the server. The server processes the request and generates learning content and dialogue scenarios using a generative model. This generated text is converted into audio data by a speech synthesis system and sent to the device. The device plays the audio data to the user and begins the dialogue. The user responds to questions using voice.

[0537] The response is collected by the terminal, transcribed into text using speech recognition technology, and then sent back to the server. Furthermore, this speech data is analyzed by an emotion engine to recognize the user's emotional state. The recognized emotion data is then considered by the server when adjusting the content of the next dialogue using a generation mechanism.

[0538] For example, if the emotion engine detects that a user is feeling frustrated while learning French, the server generates easy-to-understand content and encouraging messages. This allows the user to continue learning the language at their own pace and in a relaxed manner. Furthermore, by recording emotions and learning history, individual learning plans are optimized, providing an efficient learning experience.

[0539] In this way, the system of the present invention can not only support language learning but also create an optimal learning environment in response to the user's emotions, thereby more effectively supporting the acquisition of multiple languages.

[0540] The following describes the processing flow.

[0541] Step 1:

[0542] The user launches the application on their device and selects the language they want to learn and the learning mode (e.g., conversational mode) on the displayed screen. The device then retrieves this information.

[0543] Step 2:

[0544] The terminal generates a request to send the acquired information to the server. This request includes language and mode information.

[0545] Step 3:

[0546] The server analyzes requests received from terminals and uses a generative model to generate learning content and dialogue scenarios. This content is stored in text format.

[0547] Step 4:

[0548] The server converts the generated text data into speech data using speech synthesis technology. It then sends the converted speech data to the terminal.

[0549] Step 5:

[0550] The device plays the received audio data and provides the user with learning content in audio format. The user responds to the presented questions and prompts.

[0551] Step 6:

[0552] The user's voice responses are collected through the device's microphone and stored in real time.

[0553] Step 7:

[0554] The device uses speech recognition technology to convert collected voice responses into text data. The converted text data is then sent to the server.

[0555] Step 8:

[0556] The server analyzes the user's text data and uses an emotion engine to identify the user's emotional state.

[0557] Step 9:

[0558] The emotion information identified by the emotion engine is taken into consideration when the server adjusts the content of subsequent interactions and learning.

[0559] Step 10:

[0560] The server synthesizes new learned content, generated in response to the user's emotions, into speech and sends the audio data to the device.

[0561] Step 11:

[0562] The device plays newly received audio data to the user, providing an emotionally sensitive learning experience, and then proceeds to the next dialogue stage.

[0563] This allows users to continue learning a language through flexible, emotion-responsive feedback and dialogue.

[0564] (Example 2)

[0565] 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."

[0566] Traditional language learning systems do not optimize learning based on the user's emotional state, which can lead to dissatisfaction and frustration. As a result, users may find it difficult to continue learning, making efficient acquisition challenging.

[0567] 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.

[0568] In this invention, the server includes a generation means for generating learning content and dialogue scenarios based on a generative model, an emotion analysis means for recognizing the user's emotional state and adjusting the next dialogue content, and a control means for continuing the dialogue based on the user's response. This makes it possible to provide optimal learning content according to the user's emotional state.

[0569] "Input means for accepting language selection" refers to means that provides an interface for users to select the language they wish to learn and has the function of transmitting that selection information to a processing device.

[0570] "Generative means for generating learning content and dialogue scenarios based on a generative model" refers to a means for automatically creating learning content and dialogue scenarios suitable for the user using a pre-configured learning model.

[0571] "A speech synthesis means that presents the generated learning content as audio output" refers to a means equipped with a mechanism for converting generated text into audio data and presenting it to the user.

[0572] "A speech recognition means that converts user voice input into text data" refers to a means that analyzes the pitch of the user's voice, recognizes that information as text, and provides it to a processing device.

[0573] "An emotion analysis tool that recognizes the user's emotional state and adjusts the content of the next conversation" is a tool that analyzes the user's emotions based on data from their voice and behavior, and adjusts the next conversation or learning materials accordingly.

[0574] "Control means for continuing a conversation based on user responses" refers to means that respond in a timely manner to user input and perform the necessary controls to maintain the flow of the conversation.

[0575] The system of the present invention is designed to enable users to effectively learn multiple languages. This system utilizes speech synthesis technology, speech recognition technology, and sentiment analysis technology, with the server and terminal working together.

[0576] server

[0577] The server uses a generative AI model to generate learning content and dialogue scenarios. This employs advanced natural language processing techniques to generate user-appropriate learning material using prompt sentences. This generated text is converted into speech data using speech synthesis technology (e.g., Google Cloud Text-to-Speech). The server further extracts sentiment data from the user's voice using sentiment analysis technology and adjusts the next learning content accordingly.

[0578] terminal

[0579] The terminal is a device for users to input the information necessary for learning. The user starts the application on the terminal and selects the language and mode they wish to learn. During this process, the terminal smoothly plays audio data and records the user's responses. The terminal converts the collected audio into text using speech recognition technology (e.g., Microsoft Azure Speech Service) and sends it to the server.

[0580] User

[0581] Users actively participate in the learning process through their devices. They progress through the learning process in an interactive manner by listening to presented audio materials and responding with voice. An emotion engine recognizes the user's emotional state, and if stress relief is needed, appropriate content is provided.

[0582] Specific examples and prompt statements

[0583] For example, if a user experiences frustration while learning French, the system will generate learning materials using a prompt message such as, "You are experiencing frustration while learning French. Please generate easy-to-understand example sentences and encouraging messages." This creates a flexible learning environment that caters to the individual needs of the user.

[0584] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0585] Step 1:

[0586] The user launches the application on their device and selects the language and mode they want to learn (e.g., beginner, everyday conversation). The device receives information about the language and mode selected by the user as input. The device processes this information and sends it to the server as an initial request.

[0587] Step 2:

[0588] The server analyzes the received request data and generates learning content and dialogue scenarios using a generative AI model. The prompt message is "Generate the optimal learning materials for the mode selected by the user." Natural language processing techniques are used to create the corresponding learning content. The output is the generated text data.

[0589] Step 3:

[0590] The server converts the generated text into audio data using speech synthesis technology. Specifically, it uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert the text data into speech. The output is audio data, which is then sent to the terminal.

[0591] Step 4:

[0592] The terminal plays audio data received from the server to the user. While playback is in progress, the terminal waits for the user's voice response. The input is audio data, and the output is the acquisition of the user's voice.

[0593] Step 5:

[0594] The user responds to voice prompts and engages in dialogue. The user's voice is recorded by the device and converted into text data using speech recognition technology. Specifically, a speech recognition engine (e.g., Microsoft Azure Speech Service) is used to convert the voice to text. The output is text data.

[0595] Step 6:

[0596] The server analyzes the received text and audio data using sentiment analysis tools to recognize the user's emotional state. Using this data, it generates new prompt sentences via a generative AI model to adjust the content of the next dialogue. The output is the adjusted learned content.

[0597] Step 7:

[0598] The server uses the adjusted learning content to generate new audio data and sends it back to the terminal. This allows the conversation session with the user to continue.

[0599] (Application Example 2)

[0600] 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."

[0601] In multilingual learning systems, a challenge exists in optimizing the learning experience due to the inability to engage in appropriate dialogue that responds to the user's emotional state. Furthermore, in systems used in caregiving settings, there is a lack of technical means to adjust dialogue to consider the user's emotions, even though this is necessary.

[0602] 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.

[0603] In this invention, the server includes an input means for accepting language selection, a generation means for generating learning content based on a generative model, a speech synthesis means for presenting the generated learning content as speech output, a speech recognition means for converting the user's speech input into text data, an emotion recognition means for identifying and analyzing the user's emotional state, and an adjustment means for adjusting the dialogue content based on the analyzed emotion information. This makes it possible to realize appropriate dialogue according to the user's emotional state and improve the quality of the learning experience.

[0604] "An input method that accepts language selection" refers to a device or software that provides an interface for users to select the language they wish to learn.

[0605] "Generative means for generating learning content based on a generative model" refers to a device or software that has the function of creating appropriate learning materials and content for the user based on a pre-prepared model.

[0606] "A speech synthesis means that presents the generated learning content as audio output" refers to a device or software that has the function of converting text data into audio data and playing it back as audio through an output device such as a speaker.

[0607] "A speech recognition means that converts a user's voice input into text data" refers to a device or software that has the function of converting voice data obtained through a microphone or the like into text format.

[0608] "An emotion recognition means for identifying and analyzing a user's emotional state" refers to a device or software that has the function of reading and analyzing a user's emotions from voice or text data to interpret that state.

[0609] "Adjustment means for adjusting dialogue content based on analyzed emotional information" refers to a device or software that has the function of appropriately changing the content and tone of dialogue based on information obtained from emotion recognition means.

[0610] The system for realizing this invention primarily involves a server and a terminal working together. The terminal receives language selection from the user and sends this information to the server. The server generates learning content using a generative AI model and sends it to the terminal as text data. On the terminal, a speech synthesis means presents the text data to the user as speech output. This process utilizes software libraries suitable for processing text data and synthesizing speech data. For example, the Google Speech API may be used for speech synthesis.

[0611] The user responds verbally during the learning process. This voice input is collected by the device and converted into text data using speech recognition technology. For example, Google's speech recognition API may be used. The converted text data is sent to a server, which analyzes it using sentiment recognition technology to identify the user's emotional state. Based on this information, the content of the next dialogue is adjusted.

[0612] The system flexibly adjusts the learning experience according to the user's emotions. For example, if a user feels "tired" while learning a particular language, the system generates relaxing interactions and prepares prompts to offer words of encouragement.

[0613] Example of a prompt: "He seems depressed. Please prepare some words of encouragement."

[0614] This allows learners to learn effectively at a pace that suits their own emotions. The system adapts the content and tone of the dialogue in response to changes in the user's emotions, optimizing the learning experience.

[0615] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0616] Step 1:

[0617] The terminal accepts language selection from the user. The user selects the language they wish to learn through the terminal's interface, and this information is sent from the terminal to the server. The input at this time is the user's language selection, and the output is the language selection information. Based on this, the server begins preparing the learning content.

[0618] Step 2:

[0619] The server generates learning content using a generative model. Based on the language selection information sent to the server, the generative AI model is used to generate learning content. In this case, the input is the language selection information, and the output is the generated learning content. Specifically, new dialogue scenarios are created while referring to past databases and existing learning materials.

[0620] Step 3:

[0621] The server generates the learning content and sends it to the terminal as text data. The terminal receives this text data and converts it into audio data for the user to hear via a speech synthesis system. Here, the input is the text data from the server, and the output is the audio data played back to the user. The audio data is played back by the terminal through the speaker for the user to hear.

[0622] Step 4:

[0623] The user responds with voice. This response is collected by the device's microphone and converted into text data by speech recognition technology. The input is the user's voice data, and the output is text data. Google's speech recognition API is used for accurate conversion from voice to text.

[0624] Step 5:

[0625] The converted text data is sent back to the server. The server analyzes the text data using emotion recognition tools to identify the user's emotional state. The input in this process is text data, and the output is emotion information. The server recognizes the emotional state using an emotion analysis library.

[0626] Step 6:

[0627] The server adjusts the next dialogue based on the emotional information. Using the obtained emotional information, it generates the next dialogue scenario appropriate to the user's learning state and emotions. The input in this process is emotional information, and the output is the adjusted dialogue content. The generation of prompt sentences prepares the appropriate conversation content.

[0628] Step 7:

[0629] The adjusted dialogue content is sent to the terminal, and the conversation with the user continues. The terminal presents the newly adjusted dialogue content to the user audibly using speech synthesis. The input is the new dialogue content, and the output is the audio data played back to the user. This returns to the first step, and learning progresses as the conversation is smoothly repeated.

[0630] 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.

[0631] 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.

[0632] 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.

[0633] [Fourth Embodiment]

[0634] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0635] 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.

[0636] 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).

[0637] 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.

[0638] 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.

[0639] 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).

[0640] 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.

[0641] 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.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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".

[0647] This invention is a multilingual learning system that allows users to select the language they wish to learn and provides dialogue practice and lessons in that language.

[0648] At the heart of this system is an AI agent that integrates speech synthesis and speech recognition technologies, with the server and terminal working together. First, the user launches an application on the terminal and selects the language and mode to learn. Based on this selection, the terminal sends a request to the server.

[0649] Upon receiving this request, the server uses a generative AI model to generate learning content based on the selected language. Specifically, it creates learning materials such as dialogue-based scenarios and question-and-answer sets, and stores them on the server in text format. The server then converts this text data into speech data using speech synthesis technology.

[0650] The generated audio data is sent to the device, which plays it back to provide the user with interactive questions and information. By responding to the audio through the device, the user can repeatedly use the learning content for the next step.

[0651] This response is collected by the terminal and converted into text data through speech recognition technology. This text data is then sent back to the server, which generates and provides appropriate feedback and subsequent dialogue based on the user's response. In this way, users can engage in real-time, two-way dialogue, facilitating smooth multilingual learning.

[0652] For example, if a user wants to learn Spanish, the server generates scenarios of everyday Spanish conversation and presents them to the user as audio. When the user answers questions in Spanish, the audio is transcribed into text using speech recognition, and the next questions and content are provided according to the user's level of understanding. This allows users to learn Spanish efficiently at their own pace, without being restricted by time or location.

[0653] The following describes the processing flow.

[0654] Step 1:

[0655] The user launches the application on their device and specifies the language and learning mode they want to learn on the selection screen. The device then retrieves this selection information.

[0656] Step 2:

[0657] The terminal generates request data to send the acquired language and mode information to the server, and then sends that data to the server.

[0658] Step 3:

[0659] The server receives requests from terminals and analyzes their content. Based on the analysis results, it uses a generative AI model to generate learning materials and dialogue scenarios corresponding to the specified language.

[0660] Step 4:

[0661] The server converts the generated text data of teaching materials and scenarios into audio data using speech synthesis technology.

[0662] Step 5:

[0663] The server sends the converted audio data to the terminal.

[0664] Step 6:

[0665] The device plays the received audio data, allowing the user to receive the learning content in audio format. Interactive questions and prompts are presented to the user during this process.

[0666] Step 7:

[0667] The user responds to the presented questions using voice. The user's responses are collected in real time by the device.

[0668] Step 8:

[0669] The device uses speech recognition technology to convert the collected user voice responses into text data.

[0670] Step 9:

[0671] The terminal sends the converted text data to the server, which then parses it.

[0672] Step 10:

[0673] The server initiates a process to generate the next question or feedback based on the user's response. This information is again synthesized into speech and sent to the terminal.

[0674] Step 11:

[0675] The device plays the received audio data again, and the user moves on to the next learning step. This allows the user to continue learning through continuous interaction.

[0676] (Example 1)

[0677] 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".

[0678] In multilingual learning, conventional systems have a problem in that they cannot adequately provide individualized support to users, making it difficult to deliver effective learning. Furthermore, technical limitations in speech recognition and speech synthesis make it difficult to provide a smooth, real-time dialogue environment.

[0679] 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.

[0680] In this invention, the server includes an electronic device for accepting language selection, a configuration for generating learning information based on generative AI technology, a speech synthesis device for presenting the generated learning information as an audio signal, a speech recognition device for converting the user's audio data into text data, and a control mechanism for dynamically generating dialogue based on the user's responses. This enables personalized, responsive multilingual learning for the user.

[0681] An "electronic device that accepts language selection" is a hardware or software mechanism that allows a user to select the language they wish to learn and accepts that information as input.

[0682] "Generative AI technology" is a technology that uses artificial intelligence to generate learning information tailored to the user's purpose and skill level.

[0683] A "speech synthesis device that presents as an audio signal" is a device that uses speech synthesis technology to convert text data into speech and provide it to the user.

[0684] A "speech recognition device" is a device that utilizes technology to convert voice input from a user into text data.

[0685] A "control mechanism" is a system component that dynamically generates dialogue based on user responses and adaptively controls the learning process.

[0686] This invention is a system for supporting multilingual learning, operating through a combination of specific hardware and software. Specifically, it functions effectively through the interaction of a server, terminals, and users.

[0687] The server generates training information using generative AI technology. This generative AI technology takes a prompt as input and generates training information in text format, such as dialogue scenarios and question-and-answer sets, based on that prompt. For example, it might be used as a prompt such as, "Generate a beginner-level scenario about everyday Spanish conversation." Widely used generative models are applied to this generative AI technology.

[0688] The generated training information is converted into speech signals by a speech synthesizer on the server. The speech synthesizer uses cloud-based speech synthesis technology, such as Google Cloud Text-to-Speech or Amazon Polly. This allows the generated text information to be presented to the user in a more intuitive way.

[0689] On the other hand, the terminal plays the role of collecting voice input from the user. The voice responses that the user makes to the terminal are converted into text data by the speech recognition device inside the terminal. For example, speech recognition technology such as Google Speech-to-Text is used. This converted text data is then sent to a server and used to generate the next learning content.

[0690] Through this system, users can experience language learning in real time. For example, if a user wants to learn Spanish, they can select Spanish on their device and proceed with interactive learning. By listening to audio provided by the server and responding with their own voice, they can efficiently acquire the language.

[0691] This invention enables users to learn multiple languages ​​at their own pace, more effectively and efficiently.

[0692] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0693] Step 1:

[0694] The user launches the application on their device and selects the language and mode they wish to learn. This selected information is received by the device's input device. This input information forms the basis of the request data used for subsequent processing.

[0695] Step 2:

[0696] The terminal structures the language and mode information selected by the user and sends it to the server as a request. The request data is transmitted to the server via the HTTP protocol and used as a prompt for the generative AI model. This prompt is necessary to facilitate the generation of the learning scenario.

[0697] Step 3:

[0698] The server launches a generative AI model based on the received request data. The server inputs a command to the generative AI model as a prompt, such as "Generate a learning scenario in the specified language." From this input, the generative AI model outputs conversational text data.

[0699] Step 4:

[0700] The server passes the generated text data to a speech synthesizer, which converts it into an audio signal. The speech synthesizer processes the text data into audio data in a format that is easy for the user to understand. This audio data is then provided to the user in the next step.

[0701] Step 5:

[0702] The server transmits audio data to the terminal. The terminal plays the received audio data through a playback device and presents it to the user. This playback serves as a trigger for the user to answer questions in an interactive format.

[0703] Step 6:

[0704] The user responds verbally to the audio played from the device. The device receives this voice input from the user and converts it into text data using a speech recognition device. The text data generated by the speech recognition process becomes the input for the next step.

[0705] Step 7:

[0706] The device sends text data obtained through speech recognition to the server. The server then uses this data to generate the next learning scenario and feedback. Through this reactive process, a continuous learning cycle for the user is established.

[0707] (Application Example 1)

[0708] 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".

[0709] In multilingual learning, a key challenge is providing an environment where learners can efficiently practice dialogue in their chosen language, without being restricted by time or location. In particular, there is a need to develop a system that enables real-time feedback and continuous conversation, and that supports a variety of languages.

[0710] 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.

[0711] In this invention, the server includes a receiving means for accepting language selection, a generating means for generating learning content based on a generative AI model, and a management means for continuing the dialogue and providing feedback based on the user's response. This enables language learning in a natural dialogue format in multiple languages.

[0712] A "receiving means" is a component that has the function of receiving language information selected by the user as input.

[0713] A "generative AI model" is an artificial intelligence technology that generates appropriate learning content based on language to support users' language learning.

[0714] A "generation method" is a component that has the function of automatically creating learning content to be provided to learners by utilizing a generative AI model.

[0715] "Audio conversion means" refers to a component that has the function of converting generated text data into audio data and presenting it to the user.

[0716] "Voice analysis means" refers to a component that has the function of converting the user's voice into text data.

[0717] A "management device" is a component that has the function of controlling the flow of dialogue based on the user's voice input, enabling continuous conversation, and providing appropriate feedback.

[0718] A "dialogue system" is a system that integrates these methods to realize real-time, interactive language learning in multiple languages.

[0719] In one embodiment of this invention, a dialogue system for supporting language learning is configured so that the user can select a language using a dedicated terminal and learn in a dialogue format. The system basically operates in cooperation between a server and a terminal.

[0720] First, the user launches the application on their device and selects the language they want to learn. The receiving device acquires this information and sends it to the server. The server uses a generative AI model to generate learning materials for the selected language. Specifically, these include conversation scripts and question sets based on various situations. This allows the generating device to provide the user with customized learning content.

[0721] The generated learning content is converted into audio data using an acoustic conversion device. The server sends this to the terminal, which presents it to the user as audio output. When the user responds with audio, the audio is converted into text data via the terminal's audio analysis device and sent back to the server. The server, using a management device, generates the next dialogue based on this text data and provides feedback.

[0722] As a concrete example, if a user wants to learn English, the server creates a script of everyday conversation and provides it as audio through the device. When the user responds in English, the content is transcribed into text, and appropriate feedback and the next question generated by the server are returned to the user as audio. In this way, users can engage in multilingual learning regardless of their location.

[0723] An example of a prompt message would be entered into the server as follows: "Generate a dialogue scenario including basic greetings and everyday conversation phrases in the language selected by the user, and provide the next steps according to the difficulty level." This allows the system to generate appropriate learning content and present it to the user.

[0724] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0725] Step 1:

[0726] The user launches a language learning application on their device and selects the language they want to learn. The input is the language information specified by the user on their device, which is received and sent from the device to the server. The output is the request data sent to the server.

[0727] Step 2:

[0728] Based on the request data received by the server, a generative AI model is used to generate learning content for the selected language. The input is the request data, and by inputting prompt sentences into the generative AI model, it creates text-based dialogue scenarios and question sets. The output is the generated learning content.

[0729] Step 3:

[0730] The generated text-based learning content is converted into audio data by an acoustic conversion device. The input is the generated learning content, and audio data is generated using speech synthesis technology. The output is audio data.

[0731] Step 4:

[0732] The converted audio data is sent from the server to the terminal, which then presents it to the user. The input is the audio data received from the server, which is then played back to the user through the speaker. The output is the audio the user hears.

[0733] Step 5:

[0734] The user responds to the presented audio, and the terminal converts the user's voice into text data using speech analysis. The input is the voice spoken by the user, which is converted into text data using speech recognition technology. The output is text data.

[0735] Step 6:

[0736] Text data is sent to a server, which analyzes this data to generate appropriate feedback and subsequent dialogue. The input is text data obtained from the user's responses, and a generative AI model is used to create dialogue and feedback. The output is new learned information or feedback data.

[0737] 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.

[0738] This invention relates to a multilingual learning system that can recognize a user's emotions during the learning process and adjust the dialogue content accordingly. This system consists of speech synthesis technology, speech recognition technology, and an emotion engine, and the server and terminal work together.

[0739] The user launches the application on their device and selects the language and mode to learn. Based on this selection, the device sends an initial request to the server. The server processes the request and generates learning content and dialogue scenarios using a generative model. This generated text is converted into audio data by a speech synthesis system and sent to the device. The device plays the audio data to the user and begins the dialogue. The user responds to questions using voice.

[0740] The response is collected by the terminal, transcribed into text using speech recognition technology, and then sent back to the server. Furthermore, this speech data is analyzed by an emotion engine to recognize the user's emotional state. The recognized emotion data is then considered by the server when adjusting the content of the next dialogue using a generation mechanism.

[0741] For example, if the emotion engine detects that a user is feeling frustrated while learning French, the server generates easy-to-understand content and encouraging messages. This allows the user to continue learning the language at their own pace and in a relaxed manner. Furthermore, by recording emotions and learning history, individual learning plans are optimized, providing an efficient learning experience.

[0742] In this way, the system of the present invention can not only support language learning but also create an optimal learning environment in response to the user's emotions, thereby more effectively supporting the acquisition of multiple languages.

[0743] The following describes the processing flow.

[0744] Step 1:

[0745] The user launches the application on their device and selects the language they want to learn and the learning mode (e.g., conversational mode) on the displayed screen. The device then retrieves this information.

[0746] Step 2:

[0747] The terminal generates a request to send the acquired information to the server. This request includes language and mode information.

[0748] Step 3:

[0749] The server analyzes requests received from terminals and uses a generative model to generate learning content and dialogue scenarios. This content is stored in text format.

[0750] Step 4:

[0751] The server converts the generated text data into speech data using speech synthesis technology. It then sends the converted speech data to the terminal.

[0752] Step 5:

[0753] The device plays the received audio data and provides the user with learning content in audio format. The user responds to the presented questions and prompts.

[0754] Step 6:

[0755] The user's voice responses are collected through the device's microphone and stored in real time.

[0756] Step 7:

[0757] The device uses speech recognition technology to convert collected voice responses into text data. The converted text data is then sent to the server.

[0758] Step 8:

[0759] The server analyzes the user's text data and uses an emotion engine to identify the user's emotional state.

[0760] Step 9:

[0761] The emotion information identified by the emotion engine is taken into consideration when the server adjusts the content of subsequent interactions and learning.

[0762] Step 10:

[0763] The server synthesizes new learned content, generated in response to the user's emotions, into speech and sends the audio data to the device.

[0764] Step 11:

[0765] The device plays newly received audio data to the user, providing an emotionally sensitive learning experience, and then proceeds to the next dialogue stage.

[0766] This allows users to continue learning a language through flexible, emotion-responsive feedback and dialogue.

[0767] (Example 2)

[0768] 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".

[0769] Traditional language learning systems do not optimize learning based on the user's emotional state, which can lead to dissatisfaction and frustration. As a result, users may find it difficult to continue learning, making efficient acquisition challenging.

[0770] 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.

[0771] In this invention, the server includes a generation means for generating learning content and dialogue scenarios based on a generative model, an emotion analysis means for recognizing the user's emotional state and adjusting the next dialogue content, and a control means for continuing the dialogue based on the user's response. This makes it possible to provide optimal learning content according to the user's emotional state.

[0772] "Input means for accepting language selection" refers to means that provides an interface for users to select the language they wish to learn and has the function of transmitting that selection information to a processing device.

[0773] "Generative means for generating learning content and dialogue scenarios based on a generative model" refers to a means for automatically creating learning content and dialogue scenarios suitable for the user using a pre-configured learning model.

[0774] "A speech synthesis means that presents the generated learning content as audio output" refers to a means equipped with a mechanism for converting generated text into audio data and presenting it to the user.

[0775] "A speech recognition means that converts user voice input into text data" refers to a means that analyzes the pitch of the user's voice, recognizes that information as text, and provides it to a processing device.

[0776] "An emotion analysis tool that recognizes the user's emotional state and adjusts the content of the next conversation" is a tool that analyzes the user's emotions based on data from their voice and behavior, and adjusts the next conversation or learning materials accordingly.

[0777] "Control means for continuing a conversation based on user responses" refers to means that respond in a timely manner to user input and perform the necessary controls to maintain the flow of the conversation.

[0778] The system of the present invention is designed to enable users to effectively learn multiple languages. This system utilizes speech synthesis technology, speech recognition technology, and sentiment analysis technology, with the server and terminal working together.

[0779] server

[0780] The server uses a generative AI model to generate learning content and dialogue scenarios. This employs advanced natural language processing techniques to generate user-appropriate learning material using prompt sentences. This generated text is converted into speech data using speech synthesis technology (e.g., Google Cloud Text-to-Speech). The server further extracts sentiment data from the user's voice using sentiment analysis technology and adjusts the next learning content accordingly.

[0781] terminal

[0782] The terminal is a device for users to input the information necessary for learning. The user starts the application on the terminal and selects the language and mode they wish to learn. During this process, the terminal smoothly plays audio data and records the user's responses. The terminal converts the collected audio into text using speech recognition technology (e.g., Microsoft Azure Speech Service) and sends it to the server.

[0783] User

[0784] Users actively participate in the learning process through their devices. They progress through the learning process in an interactive manner by listening to presented audio materials and responding with voice. An emotion engine recognizes the user's emotional state, and if stress relief is needed, appropriate content is provided.

[0785] Specific examples and prompt statements

[0786] For example, if a user experiences frustration while learning French, the system will generate learning materials using a prompt message such as, "You are experiencing frustration while learning French. Please generate easy-to-understand example sentences and encouraging messages." This creates a flexible learning environment that caters to the individual needs of the user.

[0787] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0788] Step 1:

[0789] The user launches the application on their device and selects the language and mode they want to learn (e.g., beginner, everyday conversation). The device receives information about the language and mode selected by the user as input. The device processes this information and sends it to the server as an initial request.

[0790] Step 2:

[0791] The server analyzes the received request data and generates learning content and dialogue scenarios using a generative AI model. The prompt message is "Generate the optimal learning materials for the mode selected by the user." Natural language processing techniques are used to create the corresponding learning content. The output is the generated text data.

[0792] Step 3:

[0793] The server converts the generated text into audio data using speech synthesis technology. Specifically, it uses a speech synthesis engine (e.g., Google Cloud Text-to-Speech) to convert the text data into speech. The output is audio data, which is then sent to the terminal.

[0794] Step 4:

[0795] The terminal plays audio data received from the server to the user. While playback is in progress, the terminal waits for the user's voice response. The input is audio data, and the output is the acquisition of the user's voice.

[0796] Step 5:

[0797] The user responds to voice prompts and engages in dialogue. The user's voice is recorded by the device and converted into text data using speech recognition technology. Specifically, a speech recognition engine (e.g., Microsoft Azure Speech Service) is used to convert the voice to text. The output is text data.

[0798] Step 6:

[0799] The server analyzes the received text and audio data using sentiment analysis tools to recognize the user's emotional state. Using this data, it generates new prompt sentences via a generative AI model to adjust the content of the next dialogue. The output is the adjusted learned content.

[0800] Step 7:

[0801] The server uses the adjusted learning content to generate new audio data and sends it back to the terminal. This allows the conversation session with the user to continue.

[0802] (Application Example 2)

[0803] 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".

[0804] In multilingual learning systems, a challenge exists in optimizing the learning experience due to the inability to engage in appropriate dialogue that responds to the user's emotional state. Furthermore, in systems used in caregiving settings, there is a lack of technical means to adjust dialogue to consider the user's emotions, even though this is necessary.

[0805] 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.

[0806] In this invention, the server includes an input means for accepting language selection, a generation means for generating learning content based on a generative model, a speech synthesis means for presenting the generated learning content as speech output, a speech recognition means for converting the user's speech input into text data, an emotion recognition means for identifying and analyzing the user's emotional state, and an adjustment means for adjusting the dialogue content based on the analyzed emotion information. This makes it possible to realize appropriate dialogue according to the user's emotional state and improve the quality of the learning experience.

[0807] "An input method that accepts language selection" refers to a device or software that provides an interface for users to select the language they wish to learn.

[0808] "Generative means for generating learning content based on a generative model" refers to a device or software that has the function of creating appropriate learning materials and content for the user based on a pre-prepared model.

[0809] "A speech synthesis means that presents the generated learning content as audio output" refers to a device or software that has the function of converting text data into audio data and playing it back as audio through an output device such as a speaker.

[0810] "A speech recognition means that converts a user's voice input into text data" refers to a device or software that has the function of converting voice data obtained through a microphone or the like into text format.

[0811] "An emotion recognition means for identifying and analyzing a user's emotional state" refers to a device or software that has the function of reading and analyzing a user's emotions from voice or text data to interpret that state.

[0812] "Adjustment means for adjusting dialogue content based on analyzed emotional information" refers to a device or software that has the function of appropriately changing the content and tone of dialogue based on information obtained from emotion recognition means.

[0813] The system for realizing this invention primarily involves a server and a terminal working together. The terminal receives language selection from the user and sends this information to the server. The server generates learning content using a generative AI model and sends it to the terminal as text data. On the terminal, a speech synthesis means presents the text data to the user as speech output. This process utilizes software libraries suitable for processing text data and synthesizing speech data. For example, the Google Speech API may be used for speech synthesis.

[0814] The user responds verbally during the learning process. This voice input is collected by the device and converted into text data using speech recognition technology. For example, Google's speech recognition API may be used. The converted text data is sent to a server, which analyzes it using sentiment recognition technology to identify the user's emotional state. Based on this information, the content of the next dialogue is adjusted.

[0815] The system flexibly adjusts the learning experience according to the user's emotions. For example, if a user feels "tired" while learning a particular language, the system generates relaxing interactions and prepares prompts to offer words of encouragement.

[0816] Example of a prompt: "He seems depressed. Please prepare some words of encouragement."

[0817] This allows learners to learn effectively at a pace that suits their own emotions. The system adapts the content and tone of the dialogue in response to changes in the user's emotions, optimizing the learning experience.

[0818] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0819] Step 1:

[0820] The terminal accepts language selection from the user. The user selects the language they wish to learn through the terminal's interface, and this information is sent from the terminal to the server. The input at this time is the user's language selection, and the output is the language selection information. Based on this, the server begins preparing the learning content.

[0821] Step 2:

[0822] The server generates learning content using a generative model. Based on the language selection information sent to the server, the generative AI model is used to generate learning content. In this case, the input is the language selection information, and the output is the generated learning content. Specifically, new dialogue scenarios are created while referring to past databases and existing learning materials.

[0823] Step 3:

[0824] The server generates the learning content and sends it to the terminal as text data. The terminal receives this text data and converts it into audio data for the user to hear via a speech synthesis system. Here, the input is the text data from the server, and the output is the audio data played back to the user. The audio data is played back by the terminal through the speaker for the user to hear.

[0825] Step 4:

[0826] The user responds with voice. This response is collected by the device's microphone and converted into text data by speech recognition technology. The input is the user's voice data, and the output is text data. Google's speech recognition API is used for accurate conversion from voice to text.

[0827] Step 5:

[0828] The converted text data is sent back to the server. The server analyzes the text data using emotion recognition tools to identify the user's emotional state. The input in this process is text data, and the output is emotion information. The server recognizes the emotional state using an emotion analysis library.

[0829] Step 6:

[0830] The server adjusts the next dialogue based on the emotional information. Using the obtained emotional information, it generates the next dialogue scenario appropriate to the user's learning state and emotions. The input in this process is emotional information, and the output is the adjusted dialogue content. The generation of prompt sentences prepares the appropriate conversation content.

[0831] Step 7:

[0832] The adjusted dialogue content is sent to the terminal, and the conversation with the user continues. The terminal presents the newly adjusted dialogue content to the user audibly using speech synthesis. The input is the new dialogue content, and the output is the audio data played back to the user. This returns to the first step, and learning progresses as the conversation is smoothly repeated.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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."

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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.

[0853] 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.

[0854] The following is further disclosed regarding the embodiments described above.

[0855] (Claim 1)

[0856] An input method that accepts language selection,

[0857] A generation means for generating learning content based on a generative model,

[0858] A speech synthesis means that presents the generated learning content as audio output,

[0859] A speech recognition means that converts the user's voice input into text data,

[0860] A control means that continues the dialogue based on the user's response,

[0861] A system that includes this.

[0862] (Claim 2)

[0863] The system according to claim 1, wherein the speech synthesis means enables multilingual speech synthesis.

[0864] (Claim 3)

[0865] The system according to claim 1, wherein the generation means adjusts the learning content taking into account the learner's past learning history.

[0866] "Example 1"

[0867] (Claim 1)

[0868] An electronic device that accepts language selection,

[0869] A configuration that generates learning information based on generative AI technology,

[0870] A speech synthesis device that presents the generated learning information as an audio signal,

[0871] A speech recognition device that converts user voice data into text data,

[0872] A control mechanism that dynamically generates dialogue based on user responses,

[0873] A learning support system that includes this.

[0874] (Claim 2)

[0875] The learning support system according to claim 1, wherein the speech synthesis device enables speech synthesis in multiple languages.

[0876] (Claim 3)

[0877] The learning support system according to claim 1, wherein the generative AI technology performs processing that takes into account the learner's previous learning history.

[0878] "Application Example 1"

[0879] (Claim 1)

[0880] A receiving method that accepts language selection,

[0881] A generation means for generating learning content based on a generative AI model,

[0882] An acoustic conversion means that presents the generated learning content as an audio output,

[0883] A voice analysis method that converts user voice information into text data,

[0884] A management system that continues the dialogue based on user responses and provides feedback,

[0885] A dialogue system that includes this.

[0886] (Claim 2)

[0887] The dialogue system according to claim 1, wherein the sound conversion means enables multilingual voice output.

[0888] (Claim 3)

[0889] The dialogue system according to claim 1, wherein the generation means adjusts the learning content based on the learner's past learning history and responds in real time to the speech-recognized content.

[0890] "Example 2 of combining an emotion engine"

[0891] (Claim 1)

[0892] An input method that accepts language selection,

[0893] A generation means for generating learning content and dialogue scenarios based on a generative model,

[0894] A speech synthesis means that presents the generated learning content as audio output,

[0895] A speech recognition means that converts the user's voice input into text data,

[0896] A sentiment analysis tool that recognizes the user's emotional state and adjusts the content of the next conversation,

[0897] A control means that continues the dialogue based on the user's response,

[0898] A system that includes this.

[0899] (Claim 2)

[0900] The system according to claim 1, wherein the speech synthesis means enables multilingual speech synthesis.

[0901] (Claim 3)

[0902] The system according to claim 1, wherein the generation means adjusts the learning content taking into account the learner's past learning history and emotional state.

[0903] "Application example 2 when combining with an emotional engine"

[0904] (Claim 1)

[0905] An input method that accepts language selection,

[0906] A generation means for generating learning content based on a generative model,

[0907] A speech synthesis means that presents the generated learning content as audio output,

[0908] A speech recognition means that converts the user's voice input into text data,

[0909] A control means that continues the dialogue based on the user's response,

[0910] An emotion recognition tool that identifies and analyzes the emotional state of the user,

[0911] A means of adjusting the content of the dialogue based on the analyzed emotional information,

[0912] A system that includes this.

[0913] (Claim 2)

[0914] The system according to claim 1, wherein the speech synthesis means enables multilingual speech synthesis and generates a response based on emotional information by the emotion recognition means.

[0915] (Claim 3)

[0916] The system according to claim 1, wherein the generation means adjusts the learning content taking into account the learner's past learning history and emotional information. [Explanation of symbols]

[0917] 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. A receiving method that accepts language selection, A generation means for generating learning content based on a generative AI model, An acoustic conversion means that presents the generated learning content as an audio output, A voice analysis method that converts user voice information into text data, A management system that continues the dialogue based on user responses and provides feedback, A dialogue system that includes this.

2. The dialogue system according to claim 1, wherein the sound conversion means enables multilingual voice output.

3. The dialogue system according to claim 1, wherein the generation means adjusts the learning content based on the learner's past learning history and responds in real time to the speech-recognized content.

Images