System

Abstract

To provide a system capable of providing an environment for a user to daily practice foreign language and efficiently proceed with learning.SOLUTION: A system comprising means for a user to select a language to learn, means for generating a message of a virtual foreigner by a generation AI based on a selection of the user, means for transmitting the generated message to a terminal of the user, means for replying to the message received by the user, means for generating a next message based on a reply of the user by the generation AI, means for transmitting the generated next message to the user again, means for generating a voice in real time and executing a voice chat, means for storing a learning history of the user and evaluating a learning progress, and means for providing feedback based on the evaluation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Many people learn languages, but they face challenges due to limited opportunities to use them in their daily lives, which hinders their progress. They also face challenges due to the lack of a community that speaks a particular language. Furthermore, they lack a proper feedback system to track and evaluate their learning history and progress. These challenges prevent language learners from maximizing their learning. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides the following means.

[0006] The system provides a means for the user to select the language they wish to learn, and includes a means for generating a message from a virtual foreigner using a generation AI based on the user's selection. It also provides a means for sending the generated message to the user's device and replying to messages received by the user. It also includes a generation AI means for generating the next message based on the user's reply, and a means for sending it back to the user. It also includes a means for generating audio in real time and conducting audio chat. Finally, the system includes a means for saving the user's learning history, evaluating the user's learning progress, and providing feedback based on the evaluation.

[0007] "User" refers to a person who uses the system to study a language.

[0008] The "language to learn" refers to a foreign language that the user wishes to learn.

[0009] "Means for selection" refers to the interface through which a user inputs or selects the language they wish to learn into the system.

[0010] "Generative AI" refers to a system that uses artificial intelligence technology to process natural language and generate appropriate messages.

[0011] "Virtual foreigner's message" refers to text generated by generative AI that mimics a message that a native speaker of that language would say.

[0012] "Terminal" refers to a device (smartphone, tablet, PC, etc.) that a user uses to access the system.

[0013] "Means for sending" refers to the communication protocols and infrastructure for sending messages from the server to the user's terminal.

[0014] "Means for replying" refers to an interface that allows a user to input a reply to a received message by text or voice.

[0015] "Means for generating voice" refers to a system that uses generative AI technology to create voice data in real time, making it possible to have a conversation.

[0016] "Voice chat" refers to a function that allows users and virtual foreigners to communicate in real time via voice.

[0017] "Learning history" refers to records of messages, voice chats, etc. that a user makes through the system.

[0018] "Means for assessing learning progress" refers to a function that analyzes how well a user has mastered a language based on the saved learning history.

[0019] "Means for providing feedback" refers to a system that informs users of what they should learn next and areas for improvement based on the evaluation results of their learning progress. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0021] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0023] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0024] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0025] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0026] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0028] [First embodiment]

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

[0030] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0033] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0037] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0040] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0041] This invention relates to a system that allows users to practice foreign languages ​​on a daily basis through communication with virtual foreigners. This system is designed to allow users to select the language they want to learn and to message and voice chat with the virtual foreigners in that language.

[0042] System configuration

[0043] This system consists of a user's device and a server. User devices include smartphones, tablets, and PCs. The server uses a generation AI to generate messages from virtual foreigners and send them to users.

[0044] System Operation

[0045] User registration and language selection

[0046] When a user installs and launches the app, a registration screen appears on the user's device. The user enters basic information such as their name and email address to create an account. A screen is also displayed where the user can select the language they want to learn. For example, if the user selects "French," that information is sent to the server.

[0047] Message Generation

[0048] The server receives the user's selected language information and sends a request to the AI ​​to generate a message in that language. Based on the input, the AI ​​generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?). These messages are designed to include content relevant to the user's daily life.

[0049] Message Delivery and User Response

[0050] The generated message is sent from the server to the user's device. The user's device displays the received message on the screen, and the user can reply to it. For example, if the user replies "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?), the message is sent back to the server.

[0051] The server receives the user's reply and instructs the generation AI to generate the next message. The generation AI generates a new message and sends it back to the user's device. In this way, the message exchange between the user and the virtual alien continues.

[0052] Real-time voice chat

[0053] When a user selects "Voice Chat," a request is sent to the server. The server asks the generation AI to generate voice data in real time. The generation AI generates voice messages such as "Je vais bien, merci!" (I'm fine, thank you!) and sends them to the user's device via the server.

[0054] The user's device plays the received voice data, and the user responds through the microphone. The voice data is then sent back to the server, where the AI ​​generates new voices to continue the communication.

[0055] Learning history and feedback

[0056] The server stores the user's messages and voice chat logs and uses them to evaluate their learning progress. The evaluation results are generated as feedback, including the user's strengths and areas for improvement, and sent to the user's device. By receiving this feedback, the user can check their learning progress and determine which areas they should focus on next.

[0057] Specific examples

[0058] 1. User registration and language selection

[0059] A user opens the app, enters the required registration information, and selects "French" as the language they want to learn.

[0060] The terminal sends information to the server, which receives it.

[0061] 2. Message Creation

[0062] The server asks the generation AI to generate a message in French, and the generation AI generates the message "Bonjour! Comment ça va aujourd'hui?"

[0063] 3. Message Delivery and User Response

[0064] The server sends the generated message to the terminal, and the user receives and replies to the message.

[0065] The device sends a reply to the server, and the server again instructs the generation AI to generate the next message.

[0066] 4. Real-time voice chat

[0067] A user initiates a voice chat and the terminal sends a request to the server.

[0068] The server requests the generation AI to generate voice and sends the generated voice to the user's device.

[0069] 5. Learning history storage and feedback

[0070] The server stores messages and voice chat logs and evaluates learning progress.

[0071] Based on the learning progress, the server generates feedback and sends it to the device.

[0072] In this way, the system of the present invention provides an environment in which users can practice a foreign language on a daily basis and progress in their learning efficiently.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] The user installs and launches the app, and the account registration screen appears on the device screen.

[0076] Step 2:

[0077] A user creates an account by entering basic information such as name and email address, and then selects the language they want to learn.

[0078] Step 3:

[0079] The terminal sends the input information to the server, which receives it and stores it in a database.

[0080] Step 4:

[0081] The server sends a message generation request to the AI ​​based on the user's selected language, and the AI ​​generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?).

[0082] Step 5:

[0083] The server sends the generated message to the user's terminal, and the terminal displays the received message on the user's screen.

[0084] Step 6:

[0085] The user types a reply to the received message (e.g., "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?)) and the terminal sends the reply to the server.

[0086] Step 7:

[0087] The server receives the user's reply and instructs the generation AI to generate the next message. The generation AI generates a new message, which the server then sends to the user's device.

[0088] Step 8:

[0089] The user selects "Voice Chat." The device sends a voice chat start request to the server.

[0090] Step 9:

[0091] The server requests real-time voice generation from the generation AI, the generation AI generates the voice data, and the server sends it to the user's device.

[0092] Step 10:

[0093] The terminal plays the received voice data, the user responds by voice through the microphone, and the terminal transmits the voice data to the server.

[0094] Step 11:

[0095] The server analyzes the received voice data and issues instructions to the generation AI to generate the next voice response. The server then sends the generated voice data back to the user's device.

[0096] Step 12:

[0097] The server stores all messages and voice chat logs in a database, evaluates learning progress, and generates feedback.

[0098] Step 13:

[0099] The device receives feedback from the server and displays it to the user, who then checks the feedback and uses it in their next learning.

[0100] Example 1

[0101] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0102] In language learning, it is effective to practice in everyday communication situations. However, in reality, there are few opportunities to speak a foreign language on a daily basis, making efficient learning difficult. Another issue is that there is no feedback based on individual learning progress, making it unclear which areas need to be strengthened. Furthermore, there are few systems that allow real-time audio interaction, making it difficult to experience actual conversation.

[0103] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0104] In this invention, the server includes a means for allowing a user to select a language they wish to learn, a means for generating a message for a virtual character using a generation AI, a means for sending the generated message to the user's device, and a generation AI means for generating the next message based on the user's reply. This provides users with opportunities to speak a foreign language on a daily basis, allowing them to progress in their studies efficiently. Furthermore, by including a means for generating voice in real time and performing real-time voice communication, it is possible to provide a real conversation experience and enhance the effectiveness of learning. Furthermore, by including a means for saving the user's learning progress data and evaluating the progress, and a means for providing feedback based on the evaluation, it is possible to improve the quality of learning through individualized feedback.

[0105] "Generative AI" is a system that uses artificial intelligence to generate text and speech.

[0106] A "virtual person" is a character that does not exist in reality, but is generated by AI and interacts with the user through messages and voice.

[0107] A "user's terminal" is a device used by a user to access the system, such as a smartphone, tablet, or PC.

[0108] A "message" is text data generated by the generation AI and sent to the user.

[0109] "Audio data" refers to audio data generated by the generation AI and that can be heard by the user.

[0110] "Real-time voice communication" is a communication method in which a user and a virtual character converse in real time through voice.

[0111] "Learning progress data" is a record of the conversations and exercises that a user has conducted through the system.

[0112] "Feedback" is information that indicates the user's learning progress and areas for improvement, and is generated based on the learning progress data.

[0113] "Server means" refers to a server for generating messages from the generation AI and storing and processing data.

[0114] This invention relates to a system that allows users to learn a foreign language through communication with a virtual character. The system consists of a server and a user's terminal. The user's terminal can be a smartphone, tablet, PC, or other device. The server uses a generative AI model to generate messages for the virtual character and send them to the user.

[0115] Basic system configuration

[0116] The system includes the following means:

[0117] 1. A way for users to choose the language they want to learn

[0118] 2. A method for generating messages from virtual characters using generative AI

[0119] 3. A means of sending the generated message to the user's terminal

[0120] 4. A way for users to reply to messages they receive

[0121] 5. Generative AI method to generate the next message based on the user's reply

[0122] 6. A means to send the next generated message back to the user

[0123] 7. Means for generating audio in real time and performing real-time audio communication

[0124] 8. A means of storing user learning progress data and assessing progress

[0125] 9. Means of providing feedback based on the assessment

[0126] Hardware and software used

[0127] The main components of this system include the user's device, a server, and a generative AI model. Specifically, the following hardware and software are used:

[0128] User devices: smartphones, tablets, PCs, etc. These devices run applications and provide an interface with the user.

[0129] Server: A server that stores data, processes data, and invokes generative AI models.

[0130] Generative AI model: An artificial intelligence model such as OpenAI's GPT-4. This model generates text and speech.

[0131] Example of operation

[0132] 1. User registration and language selection

[0133] The user installs and launches the app. The device displays a registration screen where the user enters their name and email address to create an account. The device also displays a screen where the user can select the language they want to learn, and the selection is sent to the server.

[0134] 2. Message Creation

[0135] The server receives the user's selection and sends a request to the AI ​​to generate a message in that language. The AI ​​generates the message based on the prompt.

[0136] Example prompt sentence:

[0137] Prompt: "Ask the user 'Hello, how are you today?' as an everyday greeting in French."

[0138] Produced message: "Bonjour! Comment ça va aujourd'hui?"

[0139] The generated message is sent from the server to the user's terminal.

[0140] 3. Message Delivery and User Response

[0141] The device displays the received message to the user. The user replies to the received message, for example, by typing "Ça va bien, merci! Et toi?" The reply data is sent to the server, which again requests the generation AI to generate the next message.

[0142] 4. Real-time voice chat

[0143] When a user selects voice chat, the request is sent to the server. The server then asks the AI ​​to generate voice data, which is then sent to the device so the user can hear it. The user's response is also sent to the server, and new voice data is generated.

[0144] 5. Learning history storage and feedback

[0145] The server stores the user's messages and voice data, evaluates their progress, and generates feedback based on the evaluation, which is sent to the device for the user to review.

[0146] As a result, this system provides an environment in which users can practice a foreign language on a daily basis and progress their learning efficiently.

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

[0148] Step 1: User registration and language selection

[0149] The user installs and launches the app.

[0150] The device displays the registration screen. The user enters their name and email address. This input data is saved as the user's account information.

[0151] The device displays a language selection screen, and the user selects the language they want to learn. The selected data, e.g., "French," is sent to the server.

[0152] The server receives this information and stores it in a database as the user's language preference. The output is a registration success message and the selected language information.

[0153] Step 2: Message Generation

[0154] After the server receives the user's language selection information, it sends a message generation request to the generative AI model. The input is the prompt sentence "'Hello, how are you today?' as a daily greeting in French."

[0155] The generative AI model generates a message based on the prompt. The generated message, "Bonjour! Comment ça va aujourd'hui?", is output.

[0156] The server receives this generated message and sends it to the user's terminal. The output is the generated message data.

[0157] Step 3: Message Delivery and User Response

[0158] The terminal displays the received message "Bonjour! Comment ça va aujourd'hui?" to the user.

[0159] The user replies to this message. As input, the user types the reply: "Ça va bien, merci! Et toi?"

[0160] The terminal sends this reply data to the server. The output is the reply message data.

[0161] The server receives the reply data and again asks the generative AI model to generate the next message, including the user's reply as input.

[0162] The generative AI model generates a new message, for example, "Je vais bien, merci!" The server receives this generated message data and sends it to the user's device. The output is the new message data.

[0163] Step 4: Real-time voice chat

[0164] The user selects voice chat. As input, a voice chat start request is sent from the device to the server.

[0165] The server asks the generative AI model to generate voice data in real time. As input, the generative AI receives a message prompt such as "Je vais bien, merci!" (I'm fine, thank you!).

[0166] The generative AI model generates voice data, which is then received by the server and sent to the user's device. The output is the generated voice data.

[0167] The terminal plays the received voice data, and the user responds. The user's voice data is included as input.

[0168] The device sends this voice data to the server, which then asks the AI ​​model to generate new voice data. This process is repeated. The output is new voice data.

[0169] Step 5: Learning history and feedback

[0170] The server stores user messages and voice chat logs, which contain past interaction data as input.

[0171] The server evaluates the user's learning progress based on the stored data, and the output is the evaluation result data.

[0172] The server generates feedback based on the evaluation results and sends it to the user's terminal. The output is feedback data.

[0173] The device displays feedback to the user, allowing the user to see their learning progress.

[0174] (Application example 1)

[0175] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0176] Conventional foreign language learning systems lack sufficient support for users to acquire practical language skills that can be used in daily work. Furthermore, there were no systems for customer support in foreign languages ​​that could respond quickly and accurately to user inquiries. As a result, it was difficult to provide efficient support for users learning foreign languages ​​or in business environments where foreign languages ​​are required.

[0177] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0178] In this invention, the server includes means for generating a response to a user's inquiry in a foreign language, means for transmitting the generated response to the user's terminal and resolving the user's inquiry, and means for the user to select a language they wish to learn. This enables the user to efficiently improve their daily work and practical language skills while receiving customer support in a foreign language.

[0179] "Means for user to select a language they wish to learn" means a device or software interface that allows a user to select a particular language they wish to learn.

[0180] "Means for generating messages from virtual foreigners using generation AI" refers to a function or system that uses generation AI to create messages from virtual foreigners in a selected language.

[0181] "Means for sending the generated message to the user's terminal" refers to communication means or software for delivering the generated message to the device used by the user.

[0182] "Means for replying to messages received by a user" refers to a device or software interface that allows a user to respond to a message received by a user.

[0183] "AI generation means for generating the next message based on the user's reply" refers to an AI system that generates a message to continue the next dialogue based on the user's reply.

[0184] The "means for sending the next generated message to the user again" refers to a communication means or software for sending the newly generated message again to the user's terminal.

[0185] "Means for generating voice in real time and conducting voice chat" refers to a function or system for generating voice data in real time and conducting voice chat between a user and a virtual foreigner.

[0186] "Means for saving a user's learning history and evaluating the user's learning progress" refers to a function or system that saves a user's message and voice chat logs and evaluates the user's learning progress based on them.

[0187] "Means for providing feedback based on evaluation" refers to a function or system for evaluating a user's strengths and areas for improvement based on the saved learning history and providing the user with feedback based on that evaluation.

[0188] The "means for generating a response to a user's inquiry in a foreign language" refers to a system or device for generating an appropriate response in a selected foreign language in response to a user's inquiry.

[0189] "Means for sending the generated response to the user's terminal and resolving the user's inquiry" refers to communications means or software for sending the generated response to the user's terminal and resolving the inquiry.

[0190] This invention realizes a system that allows users to practice foreign languages ​​through conversations with virtual foreigners and simultaneously provides user support. This system utilizes a generation AI that generates messages and voice chats in the language selected by the user. It can also respond to user inquiries.

[0191] System configuration

[0192] This system consists of a user's device (smartphone, tablet) and a server. The server uses a generation AI to generate messages and voice messages from virtual foreigners and send them to the user's device.

[0193] Hardware and Software Configuration

[0194] Hardware:

[0195] User devices: smartphones, tablets

[0196] Server: Cloud infrastructure such as AWS (registered trademark), GCP, etc.

[0197] software:

[0198] Generative AI: OpenAI GPT-3 (registered trademark)

[0199] Web framework: Flask

[0200] Data transmission / reception: JSON format

[0201] System Operation

[0202] User registration and language selection

[0203] When a user installs and launches the app, a registration screen appears on the user's device. The user enters basic information such as their name and email address to create an account. A screen is also displayed where the user can select the language they want to learn. For example, if the user selects "French," that information is sent to the server.

[0204] Message Creation and Transmission

[0205] The server receives the user's selected language information and sends a request to the AI ​​to generate a message in that language. Based on the input, the AI ​​generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?). These messages are sent from the server to the user's device and displayed.

[0206] User response and next message generation

[0207] When a user receives a message and replies, the reply is sent to the server. The server receives the user's reply and instructs the generation AI to generate the next message. The generated next message is then sent back to the user's device.

[0208] Real-time voice chat

[0209] When a user selects "Voice Chat," a request is sent to the server. The server asks the generation AI to generate voice data in real time. The generation AI generates voice such as "Je vais bien, merci!" (I'm fine, thank you!) and sends it to the user's device via the server. The user's device then plays back the received voice data.

[0210] Learning history and feedback

[0211] The server stores the user's messages and voice chat logs and evaluates their learning progress based on them. The evaluation results are generated as feedback including the user's strengths and areas for improvement, and are sent back to the user's device.

[0212] Specific examples

[0213] 1. User registration and language selection

[0214] User: Opens the app, fills in the required registration information, and selects "French" as the language they want to learn.

[0215] Terminal: Sends information to the server, which receives it.

[0216] 2. Message Creation and Transmission

[0217] Server: Asks the generation AI to generate a message in French, and the generation AI generates the message "Bonjour! Comment ça va aujourd'hui?"

[0218] 3. User response and next message generation

[0219] User: Receives and replies to messages.

[0220] Server: Receives the reply and asks the generation AI for the next message.

[0221] 4. Real-time voice chat

[0222] User: Starts a voice chat and the device sends a request to the server.

[0223] Server: Requests the generation AI to generate speech and sends the generated speech to the user's device.

[0224] 5. Learning history storage and feedback

[0225] Server: Stores messages and voice chat logs and evaluates learning progress.

[0226] Server: Generates feedback and sends it to the device.

[0227] Prompt Sentence Examples

[0228] Example of a user question: "My payment didn't go through. Can you help me?"

[0229] Example prompt for the AI ​​generator: English: My payment didn't go through. Can you help me?

[0230] This system provides users with an environment in which they can practice foreign languages ​​on a daily basis and progress their learning efficiently, while also enabling them to receive prompt customer support in their foreign language.

[0231] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0232] Step 1: User registration and language selection

[0233] The user installs and launches the app. They enter basic information such as their name and email address to create an account. They are also shown a screen where they can select the language they want to learn. For example, if they select "French," that information is sent from the user's device to the server. The server then stores the received information in a database.

[0234] Input: User's basic information (name, email address), selected language

[0235] Output: User information and selected language are saved on the server side

[0236] Step 2: First message generation

[0237] After receiving the selected language information, the server sends a request to the AI ​​to generate a message in that language. Based on the input, the AI ​​generates a typical message such as "Bonjour! Comment ça va aujourd'hui?" The server then sends the generated message to the user's device.

[0238] Input: User's preferred language information

[0239] Output: The generated message in the selected language

[0240] Step 3: View and reply to messages

[0241] The user's device displays the received message. The user checks the received message and replies. For example, if the user types "Ça va bien, merci! Et toi?", the message is sent from the device to the server. The server saves the received user message and uses it as input data for the next generation request.

[0242] Input: User's reply message

[0243] Output: User's reply message stored on the server

[0244] Step 4: Generate the next message

[0245] The server sends a request to the generation AI to generate the next message based on the user's reply message. The generation AI generates a new message based on the input. For example, a response message such as "Je vais bien, merci!" is generated. This is then sent back to the user's device via the server.

[0246] Input: User's reply message

[0247] Output: The following message generated by the generation AI

[0248] Step 5: Real-time voice chat

[0249] When a user selects "Voice Chat," a request is sent from the user's device to the server. The server asks the generation AI to generate voice data in real time. The generation AI generates voice data such as "Je vais bien, merci!" and sends it to the user's device via the server. The user's device plays the received voice data and sends the voice input from the user's microphone back to the server.

[0250] Input: User's voice request

[0251] Output: Voice data generated by the generative AI

[0252] Step 6: Save your learning history and provide feedback

[0253] The server stores the user's messages and voice chat logs and uses them to evaluate their learning progress. The evaluation results are generated as feedback including the user's strengths and areas for improvement, and are sent back to the user's device. The user can then use this feedback to set their next learning goal.

[0254] Input: User's message history, voice chat log

[0255] Output: Feedback data

[0256] Step 7: Responding to user inquiries

[0257] When a user makes a query, for example, "My payment didn't go through. Can you help me?", the query is sent from the user's device to the server. The server then sends a request to the generation AI to generate a response based on the query. For example, a response such as "Sure, let's check your transaction. Can you provide me with the transaction ID?" is generated and sent to the user's device. The user can then use this response to ask further questions.

[0258] Input: User's query message

[0259] Output: The response message generated by the generation AI

[0260] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0261] This invention relates to a system that recognizes a user's emotions and adapts personalized feedback and conversation content based on those emotions. The system allows users to select the language they want to learn, and by combining an emotion engine with a generation AI that communicates with a virtual foreigner in that language, the system promotes more effective learning.

[0262] System configuration

[0263] This system consists of a user's device, a server, a generation AI, and an emotion engine. User devices include smartphones, tablets, and PCs. The server manages the generation AI and emotion engine, and controls message generation and voice chat for the virtual aliens.

[0264] System Operation

[0265] User registration and language selection

[0266] When a user installs and launches the app, a registration screen appears on the user's device. The user enters their basic information and creates an account. Next, a screen appears asking the user to select the language they want to learn. For example, if the user selects "French," that information is sent to the server.

[0267] Message Generation and Emotion Recognition

[0268] The server receives the user's selected language information and sends a request to the generation AI to generate a message in that language. At that time, the emotion engine recognizes the user's emotional state and provides feedback to the generation AI. The generation AI reflects the feedback from the emotion engine and generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?).

[0269] Message Delivery and User Response

[0270] The generated message is sent from the server to the user's device. The user's device displays the received message on the screen, and the user can reply to it. For example, if the user replies "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?), the message is sent back to the server.

[0271] The server receives the user's reply and analyzes the user's emotional state using the emotion engine. The generation AI generates the next message based on the analysis results from the emotion engine and sends it back to the user.

[0272] Real-time voice chat and emotional adaptation

[0273] When a user selects "Voice Chat," a request is sent to the server. The server uses the generative AI and emotion engine to generate voice data in real time. For example, if the emotion engine recognizes that the user is nervous, the generative AI will generate a voice response with a relaxing tone and content. This allows the user to continue the conversation without stress.

[0274] Learning history and feedback

[0275] The server stores the user's messages and voice chat logs and evaluates their learning progress using an emotion engine. The evaluation results are then generated as feedback that takes into account the user's emotional state and sent to the user's device. By receiving this feedback, the user can check their learning progress and determine which areas they should focus on next.

[0276] Specific examples

[0277] 1. User registration and language selection

[0278] A user opens the app, enters the required registration information, and selects "French" as the language they want to learn.

[0279] The terminal sends information to the server, which receives it.

[0280] 2. Message Generation and Emotion Recognition

[0281] The server asks the generation AI to generate a message in French, and the emotion engine recognizes the user's emotions.

[0282] The generation AI generates the message "Bonjour! Comment ça va aujourd'hui?" and the server sends it to the user's device.

[0283] 3. Message Delivery and User Response

[0284] The device receives the message and displays it to the user.

[0285] The user replied, "Ça va bien, merci! Et toi?"

[0286] The device sends a reply to the server, which then analyzes the user's emotions through an emotion engine.

[0287] 4. Real-time voice chat and emotional adaptation

[0288] A user initiates a voice chat.

[0289] The device sends a request to the server, and the emotion engine recognizes the user's emotions.

[0290] The generating AI generates relaxing sounds, and the server sends the sound data to the user's device.

[0291] 5. Learning history storage and feedback

[0292] The server stores messages and voice chat logs and evaluates learning progress using an emotion engine.

[0293] Based on the evaluation, feedback is generated, received by the device, and displayed to the user.

[0294] In this way, the system of the present invention provides an environment for learning a foreign language more effectively while taking into consideration the user's feelings.

[0295] The processing flow will be explained below.

[0296] Step 1:

[0297] The user installs and launches the app, and the account registration screen appears on the device screen.

[0298] Step 2:

[0299] A user creates an account by entering basic information such as name and email address, and then selects the language they want to learn.

[0300] Step 3:

[0301] The terminal sends the input information to the server, which receives it and stores it in a database.

[0302] Step 4:

[0303] The server sends a message generation request to the AI ​​based on the user's selected language, while the emotion engine recognizes the user's emotional state based on their past history and real-time input.

[0304] Step 5:

[0305] The generative AI reflects feedback from the emotion engine to generate messages such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?).

[0306] Step 6:

[0307] The server sends the generated message to the user's terminal, and the terminal displays the received message on the user's screen.

[0308] Step 7:

[0309] The user types a reply to the received message (e.g., "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?)) and the terminal sends the reply to the server.

[0310] Step 8:

[0311] The server receives the user's reply and analyzes the user's emotional state through the emotion engine. The generation AI generates the next message based on the analysis results from the emotion engine.

[0312] Step 9:

[0313] The server then sends the generated next message back to the user's terminal, which receives the message and displays it to the user.

[0314] Step 10:

[0315] The user selects "Voice Chat." The device sends a voice chat start request to the server.

[0316] Step 11:

[0317] The server uses the generation AI and emotion engine to request real-time voice generation. The generation AI generates the voice data, and the server sends it to the user's device.

[0318] Step 12:

[0319] The terminal plays the received voice data, the user responds by voice through the microphone, and the terminal transmits the voice data to the server.

[0320] Step 13:

[0321] The server analyzes the received voice data using an emotion engine and issues instructions to the generation AI to generate the next voice response. The server then sends the generated voice data back to the user's device.

[0322] Step 14:

[0323] The server stores all messages and voice chat logs in a database, and uses an emotion engine to evaluate learning progress and generate feedback.

[0324] Step 15:

[0325] The device receives feedback from the server and displays it to the user, who then checks the feedback and uses it in their next learning.

[0326] Example 2

[0327] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0328] Conventional language learning systems lack the ability to adapt feedback and communication content to take into account the user's emotional state, making effective learning difficult. Furthermore, real-time voice chat and feedback based on learning progress are limited, making individual optimization insufficient. This can easily discourage users from learning, preventing efficient language acquisition.

[0329] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0330] In this invention, the server includes emotion recognition means for recognizing the user's emotional state and generating messages and voices according to that state, means for saving the user's learning history and evaluating the learning progress, and means for providing feedback based on the evaluation. This makes it possible to provide effective feedback and communication adapted to the user's emotional state and to provide individually optimized learning support through real-time voice chat.

[0331] The "means for the user to select the language they wish to learn" is a function that allows the user to select the language they wish to learn from a list of languages ​​provided within the application.

[0332] "Generative AI" is artificial intelligence that uses natural language processing technology to generate human-like dialogue.

[0333] The "means for generating messages of virtual foreigners" is a function that uses a generation AI to create messages of virtual foreigners in a language selected by the user.

[0334] The "means for transmitting the generated message to the user's terminal" is a function for transferring the message from the server to the user's terminal.

[0335] The "means for replying to a message received by the user" is a function for creating and sending a reply on the terminal in response to a message received by the user.

[0336] The "generative AI means for generating the next message based on the user's reply" is a function that takes the user's reply as input and generates the next dialogue message accordingly.

[0337] "Means for sending the next generated message back to the user" is a function for sending the next message created by the generation AI back to the user's device.

[0338] "Means for generating voice in real time and conducting voice chat" refers to a function that uses generation AI and voice synthesis technology to generate voice in real time and engage in voice conversation with the user.

[0339] "Emotion recognition means that recognizes the user's emotional state and generates messages and voices according to that state" is a function that analyzes emotions from the user's facial expressions and text input, and generates dialogue content according to those emotions.

[0340] The "means for saving the user's learning history and evaluating the learning progress" is a function for saving a record of the user's interactions and activities and evaluating the learning progress based on that record.

[0341] The "means for providing feedback based on evaluation" is a function that uses the evaluation results of the learning progress to provide the user with useful advice and feedback on what they should focus on next.

[0342] This invention relates to a system that recognizes a user's emotions and adapts personalized feedback and conversation content based on those emotions. The system allows users to select the language they want to learn, and by combining an emotion engine with a generation AI that communicates with a virtual foreigner in that language, the system promotes more effective learning.

[0343] System configuration

[0344] This system consists of a user's device, a server, a generation AI, and an emotion engine. User devices include smartphones, tablets, and PCs. The server manages the generation AI and emotion engine, and controls message generation and voice chat for the virtual aliens.

[0345] The specific hardware and software used is as follows:

[0346] Hardware: Smartphones, tablets, computers

[0347] software:

[0348] Generative AI: Natural language processing models such as GPT-4

[0349] Emotion engine: Various emotion analysis APIs (e.g., Microsoft® Azure® emotion recognition API)

[0350] Server: Database and backend server (e.g. AWS EC2 server, Node.js backend)

[0351] System Operation

[0352] User registration and language selection

[0353] When a user installs and launches the app, a registration screen appears on the user's device. The user enters their basic information and creates an account. A screen is then displayed in which the user can select the language they want to learn. For example, if they select "French," that information is sent to the server. The information received by the server is stored in a database.

[0354] Message Generation and Emotion Recognition

[0355] The server requests the generation AI to generate a message based on the language information selected by the user. At that time, the emotion engine recognizes the user's emotional state and provides feedback to the generation AI. Based on the feedback from the emotion engine, the generation AI generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?). The server then sends the generated message to the user's device.

[0356] Message Delivery and User Response

[0357] The device displays the received message on the screen, and the user replies to it. For example, if the user replies "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?), the message is sent to the server again. The server receives the user's reply and analyzes the user's emotional state using an emotion engine. The generation AI generates the next message based on the analysis results from the emotion engine and sends it back to the user.

[0358] Real-time voice chat and emotional adaptation

[0359] When a user selects "Voice Chat," a request is sent to the server. The server uses the generative AI and emotion engine to generate voice data in real time. For example, if the emotion engine recognizes that the user is nervous, the generative AI will generate a voice response with a relaxing tone and content. This allows the user to continue the conversation without stress.

[0360] Learning history and feedback

[0361] The server stores the user's messages and voice chat logs and evaluates their learning progress using an emotion engine. The evaluation results are then generated as feedback that takes into account the user's emotional state and sent to the user's device. By receiving this feedback, the user can check their learning progress and determine which areas they should focus on next.

[0362] Specific examples

[0363] 1. User registration and language selection

[0364] A user opens the app, enters the required registration information, and selects "French" as the language they want to learn.

[0365] The terminal sends information to the server, which receives it.

[0366] 2. Message Generation and Emotion Recognition

[0367] The server asks the generation AI to generate a message in French, and the emotion engine recognizes the user's emotions.

[0368] The generation AI generates the message "Bonjour! Comment ça va aujourd'hui?" and the server sends it to the user's device.

[0369] 3. Message Delivery and User Response

[0370] The device receives the message and displays it to the user.

[0371] The user replied, "Ça va bien, merci! Et toi?"

[0372] The device sends a reply to the server, which then analyzes the user's emotions through an emotion engine.

[0373] 4. Real-time voice chat and emotional adaptation

[0374] A user initiates a voice chat.

[0375] The device sends a request to the server, and the emotion engine recognizes the user's emotions.

[0376] The generating AI generates relaxing sounds, and the server sends the sound data to the user's device.

[0377] 5. Learning history storage and feedback

[0378] The server stores messages and voice chat logs and evaluates learning progress using an emotion engine.

[0379] Based on the evaluation, feedback is generated, received by the device, and displayed to the user.

[0380] This system takes into account the user's emotions and provides an effective dialogue format, enabling a deeper learning experience.

[0381] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0382] Program processing steps

[0383] User registration and language selection

[0384] Step 1: Launch the app

[0385] Input: None

[0386] Output: Display of registration screen

[0387] Specific operation: The user launches the app on their smartphone (or tablet, or PC). The device displays the registration screen.

[0388] Step 2: Enter your registration information

[0389] Input: User's basic information (e.g. name, email address, password)

[0390] Output: User information entered

[0391] Specific behavior: The user enters the basic information displayed on the registration screen.

[0392] Step 3: Language Selection

[0393] Input: Select the language you want to learn (e.g. French)

[0394] Output: Selected language information

[0395] What it does: The user selects the language they want to learn from the displayed list of languages.

[0396] Step 4: Send information

[0397] Input: User basic information and selected language

[0398] Output: Data sent to the server

[0399] Specific operation: The device sends the user's input information and selected language information to the server.

[0400] Step 5: Save Data

[0401] Input: User information and selected language information

[0402] Output: Data stored in the database

[0403] Specific operation: The server stores the received user information and language selection information in a database.

[0404] Message Generation and Emotion Recognition

[0405] Step 6: Message Production Request

[0406] Input: Selected language information

[0407] Output: Message generation request to the generation AI

[0408] Specific behavior: The server requests the generation AI to generate a greeting message in the selected language (e.g., French).

[0409] Step 7: Emotion Recognition

[0410] Input: User history and context

[0411] Output: Evaluation of the user's emotional state

[0412] Specific operation: The server uses the emotion engine to evaluate the user's emotional state. For example, it analyzes the user's typing speed and facial recognition camera.

[0413] Step 8: Send your feedback

[0414] Input: Evaluation result of emotion engine

[0415] Output: Feedback to the generative AI

[0416] Specific behavior: The emotion engine sends feedback to the generative AI based on the user's emotional state.

[0417] Step 9: Message Generation

[0418] Input: Prompt text reflecting feedback

[0419] Output: The generated message

[0420] What it does: The generative AI generates a message based on feedback from the emotion engine. Example: "Bonjour! Comment ça va aujourd'hui?"

[0421] Step 10: Receiving a message

[0422] Input: The generated message

[0423] Output: Data sent to the user's device

[0424] Specific operation: The server sends the generated message to the user's terminal.

[0425] Message Delivery and User Response

[0426] Step 11: Displaying a message

[0427] Input: The message sent

[0428] Output: Message displayed on the screen

[0429] Specific operation: The device displays the received message on the screen.

[0430] Step 12: User response

[0431] Input: User reply (e.g. "Ça va bien, merci! Et toi?")

[0432] Output: User response data

[0433] Specific behavior: The user types a reply to the displayed message.

[0434] Step 13: Send a response message

[0435] Input: User reply data

[0436] Output: Response data sent to the server

[0437] Specific operation: The device sends the user's reply to the server.

[0438] Step 14: Sentiment Analysis

[0439] Input: User reply data

[0440] Output: Evaluation result of emotion engine

[0441] Specific operation: The server analyzes the user's message received by the emotion engine and evaluates the user's emotional state.

[0442] Real-time voice chat and emotional adaptation

[0443] Step 15: Voice Chat Selection

[0444] Input: Voice chat start request

[0445] Output: Request data to the server

[0446] What happens: A user selects the "Voice Chat" option in your app and sends a request.

[0447] Step 16: Receiving a request

[0448] Input: Voice chat start request

[0449] Output: Request processing on the server side

[0450] Specific operation: The terminal sends a request to the server, and the server receives the request.

[0451] Step 17: Real-time audio data generation

[0452] Input: User's emotional state and historical data

[0453] Output: Audio data generation request

[0454] Specific operation: The server uses the generation AI and emotion engine to generate the voice data required for dialogue in real time.

[0455] Step 18: Emotional Adaptation

[0456] Input: Evaluation result of emotion engine

[0457] Output: Feedback to the generative AI

[0458] Specific operation: The emotion engine analyzes the user's emotional state (e.g., nervousness) and provides the corresponding voice tone and content to the generation AI.

[0459] Step 19: Sending audio data

[0460] Input: Generated audio data

[0461] Output: Sends audio data to the user's device

[0462] Specific operation: The generation AI generates a voice response with a relaxing tone and content, and the server sends the voice data to the user's device.

[0463] Learning history and feedback

[0464] Step 20: Logging

[0465] Input: User messages and voice chat data

[0466] Output: Save log data

[0467] What it does: The server stores logs of users' messages and voice chats.

[0468] Step 21: Assess your learning progress

[0469] Input: Saved log data

[0470] Output: Learning progress assessment results

[0471] Specific operation: The emotion engine analyzes the saved logs and evaluates the user's learning progress.

[0472] Step 22: Generate evaluation results

[0473] Input: Learning progress assessment results

[0474] Output: Feedback data

[0475] Specific operation: The generative AI generates feedback based on the evaluation results of the emotion engine.

[0476] Step 23: Send feedback

[0477] Input: Feedback data

[0478] Output: Send feedback to the user's device

[0479] Specific operation: The server sends the generated feedback to the user's device.

[0480] Step 24: Feedback display

[0481] Input: Submitted feedback

[0482] Output: On-screen feedback

[0483] Specific behavior: The device receives the feedback and displays it to the user.

[0484] (Application example 2)

[0485] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0486] Current foreign language learning systems and content distribution services struggle to provide personalized recommendations and interactive educational and entertainment experiences that take into account the user's emotional state. Therefore, there is a need to improve the quality of users' learning motivation and entertainment experiences.

[0487] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional state and providing feedback to the generation AI accordingly, means for recommending content to be played next based on the analyzed emotional data, and means for providing interactive quiz and voting functions based on the user's emotional state. This makes it possible to provide a personalized learning and entertainment experience that adapts to the user's emotions.

[0488] "Means for users to select the information they want to learn" refers to providing an interface that allows users to select specific information or topics that interest them.

[0489] "Means for generating messages for virtual characters using generative AI" refers to a method for using artificial intelligence technology to generate messages for virtual characters based on information selected by a user.

[0490] "Means for transmitting the generated message to the user's terminal" refers to a method for transmitting the message generated by the virtual personality to the user's device using a communication means such as the Internet.

[0491] The "means for a user to reply to a message received" is a method of providing an interface that allows a user to input a response to a message received by the user using text or voice.

[0492] "Generative AI means for generating the next message based on the user's reply" refers to an artificial intelligence technology that analyzes the content of the user's response and generates the next series of dialogue messages based on that.

[0493] The "means for sending the next generated message to the user again" refers to a method for sending the next generated message to the user's device again using a communication means such as the Internet.

[0494] "Means for generating voice in real time and performing voice communication" refers to a method in which a generation AI generates voice messages in real time and uses them as a means of voice communication with the user.

[0495] "Means for saving a user's learning history and evaluating the learning progress" refers to a method for recording the user's progress and analyzing it to evaluate the user's learning situation.

[0496] "Means for providing feedback based on evaluation" refers to a method for presenting constructive advice or next steps to users based on their learning progress and emotional state.

[0497] "Means of analyzing the user's emotional state and providing feedback to the generative AI accordingly" refers to a method of analyzing the user's emotions and facial expressions in real time and reflecting the results in the generative AI.

[0498] "Means for recommending the next content to be played based on analyzed emotional data" is a method for automatically selecting and suggesting the most suitable content to be viewed next based on the user's emotional state.

[0499] "Means for providing an interactive quiz or voting function based on the emotional state of the user" is a method for providing interactive elements such as quizzes or voting that reflect the emotional state of the user in real time.

[0500] A system embodying the present invention analyzes a user's emotions and provides content recommendations and interactive quizzes based on the analyzed emotions, thereby enhancing the user's learning and entertainment experience. The system comprises the following steps:

[0501] System Configuration

[0502] 1. User Device:

[0503] Hardware: Smartphone (including camera and microphone)

[0504] Software: Dedicated application

[0505] Function: Captures the user's face and voice in real time using the camera and microphone and sends the data to a server.

[0506] 2. Server:

[0507] Hardware: Cloud servers, database servers

[0508] Software: Flask (server-side processing), TENSORFLOW (registered trademark) (sentiment analysis), generative AI model

[0509] Function: Analyzes data received from users and uses generative AI to generate content and interactive elements that are sent to the user's device.

[0510] Program processing

[0511] User Registration and Settings

[0512] When a user installs and launches the application on their device, a registration screen is displayed. The user enters basic information, which is then sent to the server. Next, the user selects the genre of interest, and the information is sent to the server.

[0513] Content viewing and sentiment analysis

[0514] When a user plays video content, the device's camera and microphone are used to capture the user's facial expressions and voice. The data is sent to a server and analyzed using TensorFlow and other tools. The results of the emotion analysis are fed into the generative AI.

[0515] Recommendation Generation

[0516] Based on the analysis results, the generative AI recommends the next appropriate content. In this case, the generative AI model generates the most appropriate content based on the user's interests and emotional state. For example, if the user is laughing, it will recommend a comedy movie.

[0517] Providing interactive content

[0518] The generative AI provides interactive quizzes and polls based on the user's emotional state. An example of a prompt might be, "The user is currently watching a romantic comedy movie and is laughing. Please generate the next recommended content and related quiz."

[0519] Learning history and feedback

[0520] The server stores users' viewing history and emotional data, which can then be used to further personalize future recommendations and interactive content. Users can receive this feedback in real time through the app.

[0521] Specific examples

[0522] For example, if a user is laughing while watching a romantic comedy movie, the emotion engine will recognize that laughter and the generative AI will recommend the next comedy movie to watch, or provide a quiz related to that particular scene, allowing the user to continue their learning and entertainment experience while having fun.

[0523] This allows the present invention to respond to the user's emotions and provide a personalized learning and entertainment experience.

[0524] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0525] Step 1:

[0526] The user installs and launches the application. A registration screen appears on the user's device, and the user enters basic information (such as name and email address) and submits it. The entered information is sent to the server via the Internet.

[0527] Input: User basic information

[0528] Output: User information stored in the user database on the server

[0529] Step 2:

[0530] A screen is displayed where the user can select the genre and information they are interested in. The user selects the genre they want to learn about (e.g., comedy, action, etc.) and submits the selected information. The submitted information is received by the server and stored in a database.

[0531] Input: User-selected genre information

[0532] Output: Genre information stored in a database on the server

[0533] Step 3:

[0534] The user plays the video content. When playback starts, the device's camera and microphone are activated to capture the user's facial expressions and voice in real time. This data is then sent to the server.

[0535] Input: User's facial expression and voice data

[0536] Output: User emotion data sent to the server

[0537] Step 4:

[0538] The server uses TensorFlow to analyze the received user facial expression and voice data. The analysis results in the user's emotional state (happiness, surprise, sadness, etc.). The analyzed emotional data is passed to the generation AI.

[0539] Input: User's facial expression and voice data

[0540] Output: Analyzed user emotion data

[0541] Step 5:

[0542] The AI ​​generator recommends the next piece of content to be played based on emotional data and the user's selected genre. The AI ​​generator continues to learn by using appropriate prompts. For example, the prompt might read, "The user is watching a comedy movie and laughing. Please generate the next piece of content to recommend."

[0543] Input: Parsed emotion data, genre information, prompt sentence

[0544] Output: Recommended next content information

[0545] Step 6:

[0546] The server sends the recommended content information to the user's terminal and displays it as a list of content for the user to view next. The user can then select the content to view next.

[0547] Input: Recommended content information

[0548] Output: The following content list displayed on the user's device

[0549] Step 7:

[0550] While the user is watching the next content, the server uses generative AI to generate interactive quizzes and polls, for example, generating quizzes related to specific scenes in a movie and sending them to the user.

[0551] Input: User viewing content information and emotion data

[0552] Output: Interactive quizzes and polls

[0553] Step 8:

[0554] Users participate in interactive quizzes and polls, and the results are sent to the server, which analyzes the results and stores them in the user's learning history.

[0555] Input: User quiz or poll answers

[0556] Output: Saved learning history and analysis data

[0557] Step 9:

[0558] The server uses the stored learning history and emotional data to generate data to further personalize future recommendations and interactive elements, and this feedback is sent to the user in real time.

[0559] Input: Learning history and emotion data

[0560] Output: Personalized feedback

[0561] In this way, the invention allows users to have a personalized learning and entertainment experience that adapts to their emotions.

[0562] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0563] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0564] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0565] [Second embodiment]

[0566] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0567] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0568] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0569] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0570] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0571] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0572] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0573] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0574] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0575] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0576] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0577] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0578] This invention relates to a system that allows users to practice foreign languages ​​on a daily basis through communication with virtual foreigners. This system is designed to allow users to select the language they want to learn and to message and voice chat with the virtual foreigners in that language.

[0579] System configuration

[0580] This system consists of a user's device and a server. User devices include smartphones, tablets, and PCs. The server uses a generation AI to generate messages from virtual foreigners and send them to users.

[0581] System Operation

[0582] User registration and language selection

[0583] When a user installs and launches the app, a registration screen appears on the user's device. The user enters basic information such as their name and email address to create an account. A screen is also displayed where the user can select the language they want to learn. For example, if the user selects "French," that information is sent to the server.

[0584] Message Generation

[0585] The server receives the user's selected language information and sends a request to the AI ​​to generate a message in that language. Based on the input, the AI ​​generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?). These messages are designed to include content relevant to the user's daily life.

[0586] Message Delivery and User Response

[0587] The generated message is sent from the server to the user's device. The user's device displays the received message on the screen, and the user can reply to it. For example, if the user replies "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?), the message is sent back to the server.

[0588] The server receives the user's reply and instructs the generation AI to generate the next message. The generation AI generates a new message and sends it back to the user's device. In this way, the message exchange between the user and the virtual alien continues.

[0589] Real-time voice chat

[0590] When a user selects "Voice Chat," a request is sent to the server. The server asks the generation AI to generate voice data in real time. The generation AI generates voice messages such as "Je vais bien, merci!" (I'm fine, thank you!) and sends them to the user's device via the server.

[0591] The user's device plays the received voice data, and the user responds through the microphone. The voice data is then sent back to the server, where the AI ​​generates new voices to continue the communication.

[0592] Learning history and feedback

[0593] The server stores the user's messages and voice chat logs and uses them to evaluate their learning progress. The evaluation results are generated as feedback, including the user's strengths and areas for improvement, and sent to the user's device. By receiving this feedback, the user can check their learning progress and determine which areas they should focus on next.

[0594] Specific examples

[0595] 1. User registration and language selection

[0596] A user opens the app, enters the required registration information, and selects "French" as the language they want to learn.

[0597] The terminal sends information to the server, which receives it.

[0598] 2. Message Creation

[0599] The server asks the generation AI to generate a message in French, and the generation AI generates the message "Bonjour! Comment ça va aujourd'hui?"

[0600] 3. Message Delivery and User Response

[0601] The server sends the generated message to the terminal, and the user receives and replies to the message.

[0602] The device sends a reply to the server, and the server again instructs the generation AI to generate the next message.

[0603] 4. Real-time voice chat

[0604] A user initiates a voice chat and the terminal sends a request to the server.

[0605] The server requests the generation AI to generate voice and sends the generated voice to the user's device.

[0606] 5. Learning history storage and feedback

[0607] The server stores messages and voice chat logs and evaluates learning progress.

[0608] Based on the learning progress, the server generates feedback and sends it to the device.

[0609] In this way, the system of the present invention provides an environment in which users can practice a foreign language on a daily basis and progress in their learning efficiently.

[0610] The processing flow will be explained below.

[0611] Step 1:

[0612] The user installs and launches the app, and the account registration screen appears on the device screen.

[0613] Step 2:

[0614] A user creates an account by entering basic information such as name and email address, and then selects the language they want to learn.

[0615] Step 3:

[0616] The terminal sends the input information to the server, which receives it and stores it in a database.

[0617] Step 4:

[0618] The server sends a message generation request to the AI ​​based on the user's selected language, and the AI ​​generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?).

[0619] Step 5:

[0620] The server sends the generated message to the user's terminal, and the terminal displays the received message on the user's screen.

[0621] Step 6:

[0622] The user types a reply to the received message (e.g., "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?)) and the terminal sends the reply to the server.

[0623] Step 7:

[0624] The server receives the user's reply and instructs the generation AI to generate the next message. The generation AI generates a new message, which the server then sends to the user's device.

[0625] Step 8:

[0626] The user selects "Voice Chat." The device sends a voice chat start request to the server.

[0627] Step 9:

[0628] The server requests real-time voice generation from the generation AI, the generation AI generates the voice data, and the server sends it to the user's device.

[0629] Step 10:

[0630] The terminal plays the received voice data, the user responds by voice through the microphone, and the terminal transmits the voice data to the server.

[0631] Step 11:

[0632] The server analyzes the received voice data and issues instructions to the generation AI to generate the next voice response. The server then sends the generated voice data back to the user's device.

[0633] Step 12:

[0634] The server stores all messages and voice chat logs in a database, evaluates learning progress, and generates feedback.

[0635] Step 13:

[0636] The device receives feedback from the server and displays it to the user, who then checks the feedback and uses it in their next learning.

[0637] Example 1

[0638] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0639] In language learning, it is effective to practice in everyday communication situations. However, in reality, there are few opportunities to speak a foreign language on a daily basis, making efficient learning difficult. Another issue is that there is no feedback based on individual learning progress, making it unclear which areas need to be strengthened. Furthermore, there are few systems that allow real-time audio interaction, making it difficult to experience actual conversation.

[0640] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0641] In this invention, the server includes a means for allowing a user to select a language they wish to learn, a means for generating a message for a virtual character using a generation AI, a means for sending the generated message to the user's device, and a generation AI means for generating the next message based on the user's reply. This provides users with opportunities to speak a foreign language on a daily basis, allowing them to progress in their studies efficiently. Furthermore, by including a means for generating voice in real time and performing real-time voice communication, it is possible to provide a real conversation experience and enhance the effectiveness of learning. Furthermore, by including a means for saving the user's learning progress data and evaluating the progress, and a means for providing feedback based on the evaluation, it is possible to improve the quality of learning through individualized feedback.

[0642] "Generative AI" is a system that uses artificial intelligence to generate text and speech.

[0643] A "virtual person" is a character that does not exist in reality, but is generated by AI and interacts with the user through messages and voice.

[0644] A "user's terminal" is a device used by a user to access the system, such as a smartphone, tablet, or PC.

[0645] A "message" is text data generated by the generation AI and sent to the user.

[0646] "Audio data" refers to audio data generated by the generation AI and that can be heard by the user.

[0647] "Real-time voice communication" is a communication method in which a user and a virtual character converse in real time through voice.

[0648] "Learning progress data" is a record of the conversations and exercises that a user has conducted through the system.

[0649] "Feedback" is information that indicates the user's learning progress and areas for improvement, and is generated based on the learning progress data.

[0650] "Server means" refers to a server for generating messages from the generation AI and storing and processing data.

[0651] This invention relates to a system that allows users to learn a foreign language through communication with a virtual character. The system consists of a server and a user's terminal. The user's terminal can be a smartphone, tablet, PC, or other device. The server uses a generative AI model to generate messages for the virtual character and send them to the user.

[0652] Basic system configuration

[0653] The system includes the following means:

[0654] 1. A way for users to choose the language they want to learn

[0655] 2. A method for generating messages from virtual characters using generative AI

[0656] 3. A means of sending the generated message to the user's terminal

[0657] 4. A way for users to reply to messages they receive

[0658] 5. Generative AI method to generate the next message based on the user's reply

[0659] 6. A means to send the next generated message back to the user

[0660] 7. Means for generating audio in real time and performing real-time audio communication

[0661] 8. A means of storing user learning progress data and assessing progress

[0662] 9. Means of providing feedback based on the assessment

[0663] Hardware and software used

[0664] The main components of this system include the user's device, a server, and a generative AI model. Specifically, the following hardware and software are used:

[0665] User devices: smartphones, tablets, PCs, etc. These devices run applications and provide an interface with the user.

[0666] Server: A server that stores data, processes data, and invokes generative AI models.

[0667] Generative AI models: Artificial intelligence models such as OpenAI's GPT-4. These models generate text and speech.

[0668] Example of operation

[0669] 1. User registration and language selection

[0670] The user installs and launches the app. The device displays a registration screen where the user enters their name and email address to create an account. The device also displays a screen where the user can select the language they want to learn, and the selection is sent to the server.

[0671] 2. Message Creation

[0672] The server receives the user's selection and sends a request to the AI ​​to generate a message in that language. The AI ​​generates the message based on the prompt.

[0673] Example prompt sentence:

[0674] Prompt: "Ask the user 'Hello, how are you today?' as an everyday greeting in French."

[0675] Produced message: "Bonjour! Comment ça va aujourd'hui?"

[0676] The generated message is sent from the server to the user's terminal.

[0677] 3. Message Delivery and User Response

[0678] The device displays the received message to the user. The user replies to the received message, for example, by typing "Ça va bien, merci! Et toi?" The reply data is sent to the server, which again requests the generation AI to generate the next message.

[0679] 4. Real-time voice chat

[0680] When a user selects voice chat, the request is sent to the server. The server then asks the AI ​​to generate voice data, which is then sent to the device so the user can hear it. The user's response is also sent to the server, and new voice data is generated.

[0681] 5. Learning history storage and feedback

[0682] The server stores the user's messages and voice data, evaluates their progress, and generates feedback based on the evaluation, which is sent to the device for the user to review.

[0683] As a result, this system provides an environment in which users can practice a foreign language on a daily basis and progress their learning efficiently.

[0684] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0685] Step 1: User registration and language selection

[0686] The user installs and launches the app.

[0687] The device displays the registration screen. The user enters their name and email address. This input data is saved as the user's account information.

[0688] The device displays a language selection screen, and the user selects the language they want to learn. The selected data, e.g., "French," is sent to the server.

[0689] The server receives this information and stores it in a database as the user's language preference. The output is a registration success message and the selected language information.

[0690] Step 2: Message Generation

[0691] After the server receives the user's language selection information, it sends a message generation request to the generative AI model. The input is the prompt sentence "'Hello, how are you today?' as a daily greeting in French."

[0692] The generative AI model generates a message based on the prompt. The generated message, "Bonjour! Comment ça va aujourd'hui?", is output.

[0693] The server receives this generated message and sends it to the user's terminal. The output is the generated message data.

[0694] Step 3: Message Delivery and User Response

[0695] The terminal displays the received message "Bonjour! Comment ça va aujourd'hui?" to the user.

[0696] The user replies to this message. As input, the user types the reply: "Ça va bien, merci! Et toi?"

[0697] The terminal sends this reply data to the server. The output is the reply message data.

[0698] The server receives the reply data and again asks the generative AI model to generate the next message, including the user's reply as input.

[0699] The generative AI model generates a new message, for example, "Je vais bien, merci!" The server receives this generated message data and sends it to the user's device. The output is the new message data.

[0700] Step 4: Real-time voice chat

[0701] The user selects voice chat. As input, a voice chat start request is sent from the device to the server.

[0702] The server asks the generative AI model to generate voice data in real time. As input, the generative AI receives a message prompt such as "Je vais bien, merci!" (I'm fine, thank you!).

[0703] The generative AI model generates voice data, which is then received by the server and sent to the user's device. The output is the generated voice data.

[0704] The terminal plays the received voice data, and the user responds. The user's voice data is included as input.

[0705] The device sends this voice data to the server, which then asks the AI ​​model to generate new voice data. This process is repeated. The output is new voice data.

[0706] Step 5: Learning history and feedback

[0707] The server stores user messages and voice chat logs, which contain past interaction data as input.

[0708] The server evaluates the user's learning progress based on the stored data, and the output is the evaluation result data.

[0709] The server generates feedback based on the evaluation results and sends it to the user's terminal. The output is feedback data.

[0710] The device displays feedback to the user, allowing the user to see their learning progress.

[0711] (Application example 1)

[0712] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0713] Conventional foreign language learning systems lack sufficient support for users to acquire practical language skills that can be used in daily work. Furthermore, there were no systems for customer support in foreign languages ​​that could respond quickly and accurately to user inquiries. As a result, it was difficult to provide efficient support for users learning foreign languages ​​or in business environments where foreign languages ​​are required.

[0714] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0715] In this invention, the server includes means for generating a response to a user's inquiry in a foreign language, means for transmitting the generated response to the user's terminal and resolving the user's inquiry, and means for the user to select a language they wish to learn. This enables the user to efficiently improve their daily work and practical language skills while receiving customer support in a foreign language.

[0716] "Means for user to select a language they wish to learn" means a device or software interface that allows a user to select a particular language they wish to learn.

[0717] "Means for generating messages from virtual foreigners using generation AI" refers to a function or system that uses generation AI to create messages from virtual foreigners in a selected language.

[0718] "Means for sending the generated message to the user's terminal" refers to communication means or software for delivering the generated message to the device used by the user.

[0719] "Means for replying to messages received by a user" refers to a device or software interface that allows a user to respond to a message received by a user.

[0720] "AI generation means for generating the next message based on the user's reply" refers to an AI system that generates a message to continue the next dialogue based on the user's reply.

[0721] The "means for sending the next generated message to the user again" refers to a communication means or software for sending the newly generated message again to the user's terminal.

[0722] "Means for generating voice in real time and conducting voice chat" refers to a function or system for generating voice data in real time and conducting voice chat between a user and a virtual foreigner.

[0723] "Means for saving a user's learning history and evaluating the user's learning progress" refers to a function or system that saves a user's message and voice chat logs and evaluates the user's learning progress based on them.

[0724] "Means for providing feedback based on evaluation" refers to a function or system for evaluating a user's strengths and areas for improvement based on the saved learning history and providing the user with feedback based on that evaluation.

[0725] The "means for generating a response to a user's inquiry in a foreign language" refers to a system or device for generating an appropriate response in a selected foreign language in response to a user's inquiry.

[0726] "Means for sending the generated response to the user's terminal and resolving the user's inquiry" refers to communications means or software for sending the generated response to the user's terminal and resolving the inquiry.

[0727] This invention realizes a system that allows users to practice foreign languages ​​through conversations with virtual foreigners and simultaneously provides user support. This system utilizes a generation AI that generates messages and voice chats in the language selected by the user. It can also respond to user inquiries.

[0728] System configuration

[0729] This system consists of a user's device (smartphone, tablet) and a server. The server uses a generation AI to generate messages and voice messages from virtual foreigners and send them to the user's device.

[0730] Hardware and Software Configuration

[0731] Hardware:

[0732] User devices: smartphones, tablets

[0733] Server: Cloud infrastructure such as AWS, GCP, etc.

[0734] software:

[0735] Generation AI: OpenAI GPT-3

[0736] Web framework: Flask

[0737] Data transmission / reception: JSON format

[0738] System Operation

[0739] User registration and language selection

[0740] When a user installs and launches the app, a registration screen appears on the user's device. The user enters basic information such as their name and email address to create an account. A screen is also displayed where the user can select the language they want to learn. For example, if the user selects "French," that information is sent to the server.

[0741] Message Creation and Transmission

[0742] The server receives the user's selected language information and sends a request to the AI ​​to generate a message in that language. Based on the input, the AI ​​generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?). These messages are sent from the server to the user's device and displayed.

[0743] User response and next message generation

[0744] When a user receives a message and replies, the reply is sent to the server. The server receives the user's reply and instructs the generation AI to generate the next message. The generated next message is then sent back to the user's device.

[0745] Real-time voice chat

[0746] When a user selects "Voice Chat," a request is sent to the server. The server asks the generation AI to generate voice data in real time. The generation AI generates voice such as "Je vais bien, merci!" (I'm fine, thank you!) and sends it to the user's device via the server. The user's device then plays back the received voice data.

[0747] Learning history and feedback

[0748] The server stores the user's messages and voice chat logs and evaluates their learning progress based on them. The evaluation results are generated as feedback including the user's strengths and areas for improvement, and are sent back to the user's device.

[0749] Specific examples

[0750] 1. User registration and language selection

[0751] User: Opens the app, fills in the required registration information, and selects "French" as the language they want to learn.

[0752] Terminal: Sends information to the server, which receives it.

[0753] 2. Message Creation and Transmission

[0754] Server: Asks the generation AI to generate a message in French, and the generation AI generates the message "Bonjour! Comment ça va aujourd'hui?"

[0755] 3. User response and next message generation

[0756] User: Receives and replies to messages.

[0757] Server: Receives the reply and asks the generation AI for the next message.

[0758] 4. Real-time voice chat

[0759] User: Starts a voice chat and the device sends a request to the server.

[0760] Server: Requests the generation AI to generate speech and sends the generated speech to the user's device.

[0761] 5. Learning history storage and feedback

[0762] Server: Stores messages and voice chat logs and evaluates learning progress.

[0763] Server: Generates feedback and sends it to the device.

[0764] Prompt Sentence Examples

[0765] Example of a user question: "My payment didn't go through. Can you help me?"

[0766] Example prompt for the AI ​​generator: English: My payment didn't go through. Can you help me?

[0767] This system provides users with an environment in which they can practice foreign languages ​​on a daily basis and progress their learning efficiently, while also enabling them to receive prompt customer support in their foreign language.

[0768] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0769] Step 1: User registration and language selection

[0770] The user installs and launches the app. They enter basic information such as their name and email address to create an account. They are also shown a screen where they can select the language they want to learn. For example, if they select "French," that information is sent from the user's device to the server. The server then stores the received information in a database.

[0771] Input: User's basic information (name, email address), selected language

[0772] Output: User information and selected language are saved on the server side

[0773] Step 2: First message generation

[0774] After receiving the selected language information, the server sends a request to the AI ​​to generate a message in that language. Based on the input, the AI ​​generates a typical message such as "Bonjour! Comment ça va aujourd'hui?" The server then sends the generated message to the user's device.

[0775] Input: User's preferred language information

[0776] Output: The generated message in the selected language

[0777] Step 3: View and reply to messages

[0778] The user's device displays the received message. The user checks the received message and replies. For example, if the user types "Ça va bien, merci! Et toi?", the message is sent from the device to the server. The server saves the received user message and uses it as input data for the next generation request.

[0779] Input: User's reply message

[0780] Output: User's reply message stored on the server

[0781] Step 4: Generate the next message

[0782] The server sends a request to the generation AI to generate the next message based on the user's reply message. The generation AI generates a new message based on the input. For example, a response message such as "Je vais bien, merci!" is generated. This is then sent back to the user's device via the server.

[0783] Input: User's reply message

[0784] Output: The following message generated by the generation AI

[0785] Step 5: Real-time voice chat

[0786] When a user selects "Voice Chat," a request is sent from the user's device to the server. The server asks the generation AI to generate voice data in real time. The generation AI generates voice data such as "Je vais bien, merci!" and sends it to the user's device via the server. The user's device plays the received voice data and sends the voice input from the user's microphone back to the server.

[0787] Input: User's voice request

[0788] Output: Voice data generated by the generative AI

[0789] Step 6: Save your learning history and provide feedback

[0790] The server stores the user's messages and voice chat logs and uses them to evaluate their learning progress. The evaluation results are generated as feedback including the user's strengths and areas for improvement, and are sent back to the user's device. The user can then use this feedback to set their next learning goal.

[0791] Input: User's message history, voice chat log

[0792] Output: Feedback data

[0793] Step 7: Responding to user inquiries

[0794] When a user makes a query, for example, "My payment didn't go through. Can you help me?", the query is sent from the user's device to the server. The server then sends a request to the generation AI to generate a response based on the query. For example, a response such as "Sure, let's check your transaction. Can you provide me with the transaction ID?" is generated and sent to the user's device. The user can then use this response to ask further questions.

[0795] Input: User's query message

[0796] Output: The response message generated by the generation AI

[0797] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0798] This invention relates to a system that recognizes a user's emotions and adapts personalized feedback and conversation content based on those emotions. The system allows users to select the language they want to learn, and by combining an emotion engine with a generation AI that communicates with a virtual foreigner in that language, the system promotes more effective learning.

[0799] System configuration

[0800] This system consists of a user's device, a server, a generation AI, and an emotion engine. User devices include smartphones, tablets, and PCs. The server manages the generation AI and emotion engine, and controls message generation and voice chat for the virtual aliens.

[0801] System Operation

[0802] User registration and language selection

[0803] When a user installs and launches the app, a registration screen appears on the user's device. The user enters their basic information and creates an account. Next, a screen appears asking the user to select the language they want to learn. For example, if the user selects "French," that information is sent to the server.

[0804] Message Generation and Emotion Recognition

[0805] The server receives the user's selected language information and sends a request to the generation AI to generate a message in that language. At that time, the emotion engine recognizes the user's emotional state and provides feedback to the generation AI. The generation AI reflects the feedback from the emotion engine and generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?).

[0806] Message Delivery and User Response

[0807] The generated message is sent from the server to the user's device. The user's device displays the received message on the screen, and the user can reply to it. For example, if the user replies "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?), the message is sent back to the server.

[0808] The server receives the user's reply and analyzes the user's emotional state using the emotion engine. The generation AI generates the next message based on the analysis results from the emotion engine and sends it back to the user.

[0809] Real-time voice chat and emotional adaptation

[0810] When a user selects "Voice Chat," a request is sent to the server. The server uses the generative AI and emotion engine to generate voice data in real time. For example, if the emotion engine recognizes that the user is nervous, the generative AI will generate a voice response with a relaxing tone and content. This allows the user to continue the conversation without stress.

[0811] Learning history and feedback

[0812] The server stores the user's messages and voice chat logs and evaluates their learning progress using an emotion engine. The evaluation results are then generated as feedback that takes into account the user's emotional state and sent to the user's device. By receiving this feedback, the user can check their learning progress and determine which areas they should focus on next.

[0813] Specific examples

[0814] 1. User registration and language selection

[0815] A user opens the app, enters the required registration information, and selects "French" as the language they want to learn.

[0816] The terminal sends information to the server, which receives it.

[0817] 2. Message Generation and Emotion Recognition

[0818] The server asks the generation AI to generate a message in French, and the emotion engine recognizes the user's emotions.

[0819] The generation AI generates the message "Bonjour! Comment ça va aujourd'hui?" and the server sends it to the user's device.

[0820] 3. Message Delivery and User Response

[0821] The device receives the message and displays it to the user.

[0822] The user replied, "Ça va bien, merci! Et toi?"

[0823] The device sends a reply to the server, which then analyzes the user's emotions through an emotion engine.

[0824] 4. Real-time voice chat and emotional adaptation

[0825] A user initiates a voice chat.

[0826] The device sends a request to the server, and the emotion engine recognizes the user's emotions.

[0827] The generating AI generates relaxing sounds, and the server sends the sound data to the user's device.

[0828] 5. Learning history storage and feedback

[0829] The server stores messages and voice chat logs and evaluates learning progress using an emotion engine.

[0830] Based on the evaluation, feedback is generated, received by the device, and displayed to the user.

[0831] In this way, the system of the present invention provides an environment for learning a foreign language more effectively while taking into consideration the user's feelings.

[0832] The processing flow will be explained below.

[0833] Step 1:

[0834] The user installs and launches the app, and the account registration screen appears on the device screen.

[0835] Step 2:

[0836] A user creates an account by entering basic information such as name and email address, and then selects the language they want to learn.

[0837] Step 3:

[0838] The terminal sends the input information to the server, which receives it and stores it in a database.

[0839] Step 4:

[0840] The server sends a message generation request to the AI ​​based on the user's selected language, while the emotion engine recognizes the user's emotional state based on their past history and real-time input.

[0841] Step 5:

[0842] The generative AI reflects feedback from the emotion engine to generate messages such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?).

[0843] Step 6:

[0844] The server sends the generated message to the user's terminal, and the terminal displays the received message on the user's screen.

[0845] Step 7:

[0846] The user types a reply to the received message (e.g., "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?)) and the terminal sends the reply to the server.

[0847] Step 8:

[0848] The server receives the user's reply and analyzes the user's emotional state through the emotion engine. The generation AI generates the next message based on the analysis results from the emotion engine.

[0849] Step 9:

[0850] The server then sends the generated next message back to the user's terminal, which receives the message and displays it to the user.

[0851] Step 10:

[0852] The user selects "Voice Chat." The device sends a voice chat start request to the server.

[0853] Step 11:

[0854] The server uses the generation AI and emotion engine to request real-time voice generation. The generation AI generates the voice data, and the server sends it to the user's device.

[0855] Step 12:

[0856] The terminal plays the received voice data, the user responds by voice through the microphone, and the terminal transmits the voice data to the server.

[0857] Step 13:

[0858] The server analyzes the received voice data using an emotion engine and issues instructions to the generation AI to generate the next voice response. The server then sends the generated voice data back to the user's device.

[0859] Step 14:

[0860] The server stores all messages and voice chat logs in a database, and uses an emotion engine to evaluate learning progress and generate feedback.

[0861] Step 15:

[0862] The device receives feedback from the server and displays it to the user, who then checks the feedback and uses it in their next learning.

[0863] Example 2

[0864] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0865] Conventional language learning systems lack the ability to adapt feedback and communication content to take into account the user's emotional state, making effective learning difficult. Furthermore, real-time voice chat and feedback based on learning progress are limited, making individual optimization insufficient. This can easily discourage users from learning, preventing efficient language acquisition.

[0866] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0867] In this invention, the server includes emotion recognition means for recognizing the user's emotional state and generating messages and voices according to that state, means for saving the user's learning history and evaluating the learning progress, and means for providing feedback based on the evaluation. This makes it possible to provide effective feedback and communication adapted to the user's emotional state and to provide individually optimized learning support through real-time voice chat.

[0868] The "means for the user to select the language they wish to learn" is a function that allows the user to select the language they wish to learn from a list of languages ​​provided within the application.

[0869] "Generative AI" is artificial intelligence that uses natural language processing technology to generate human-like dialogue.

[0870] The "means for generating messages of virtual foreigners" is a function that uses a generation AI to create messages of virtual foreigners in a language selected by the user.

[0871] The "means for transmitting the generated message to the user's terminal" is a function for transferring the message from the server to the user's terminal.

[0872] The "means for replying to a message received by the user" is a function for creating and sending a reply on the terminal in response to a message received by the user.

[0873] The "generative AI means for generating the next message based on the user's reply" is a function that takes the user's reply as input and generates the next dialogue message accordingly.

[0874] "Means for sending the next generated message back to the user" is a function for sending the next message created by the generation AI back to the user's device.

[0875] "Means for generating voice in real time and conducting voice chat" refers to a function that uses generation AI and voice synthesis technology to generate voice in real time and engage in voice conversation with the user.

[0876] "Emotion recognition means that recognizes the user's emotional state and generates messages and voices according to that state" is a function that analyzes emotions from the user's facial expressions and text input, and generates dialogue content according to those emotions.

[0877] The "means for saving the user's learning history and evaluating the learning progress" is a function for saving a record of the user's interactions and activities and evaluating the learning progress based on that record.

[0878] The "means for providing feedback based on evaluation" is a function that uses the evaluation results of the learning progress to provide the user with useful advice and feedback on what they should focus on next.

[0879] This invention relates to a system that recognizes a user's emotions and adapts personalized feedback and conversation content based on those emotions. The system allows users to select the language they want to learn, and by combining an emotion engine with a generation AI that communicates with a virtual foreigner in that language, the system promotes more effective learning.

[0880] System configuration

[0881] This system consists of a user's device, a server, a generation AI, and an emotion engine. User devices include smartphones, tablets, and PCs. The server manages the generation AI and emotion engine, and controls message generation and voice chat for the virtual aliens.

[0882] The specific hardware and software used is as follows:

[0883] Hardware: Smartphones, tablets, computers

[0884] software:

[0885] Generative AI: Natural language processing models such as GPT-4

[0886] Emotion engine: Various emotion analysis APIs (e.g., Microsoft Azure emotion recognition API)

[0887] Server: Database and backend server (e.g. AWS EC2 server, Node.js backend)

[0888] System Operation

[0889] User registration and language selection

[0890] When a user installs and launches the app, a registration screen appears on the user's device. The user enters their basic information and creates an account. A screen is then displayed in which the user can select the language they want to learn. For example, if they select "French," that information is sent to the server. The information received by the server is stored in a database.

[0891] Message Generation and Emotion Recognition

[0892] The server requests the generation AI to generate a message based on the language information selected by the user. At that time, the emotion engine recognizes the user's emotional state and provides feedback to the generation AI. Based on the feedback from the emotion engine, the generation AI generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?). The server then sends the generated message to the user's device.

[0893] Message Delivery and User Response

[0894] The device displays the received message on the screen, and the user replies to it. For example, if the user replies "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?), the message is sent to the server again. The server receives the user's reply and analyzes the user's emotional state using an emotion engine. The generation AI generates the next message based on the analysis results from the emotion engine and sends it back to the user.

[0895] Real-time voice chat and emotional adaptation

[0896] When a user selects "Voice Chat," a request is sent to the server. The server uses the generative AI and emotion engine to generate voice data in real time. For example, if the emotion engine recognizes that the user is nervous, the generative AI will generate a voice response with a relaxing tone and content. This allows the user to continue the conversation without stress.

[0897] Learning history and feedback

[0898] The server stores the user's messages and voice chat logs and evaluates their learning progress using an emotion engine. The evaluation results are then generated as feedback that takes into account the user's emotional state and sent to the user's device. By receiving this feedback, the user can check their learning progress and determine which areas they should focus on next.

[0899] Specific examples

[0900] 1. User registration and language selection

[0901] A user opens the app, enters the required registration information, and selects "French" as the language they want to learn.

[0902] The terminal sends information to the server, which receives it.

[0903] 2. Message Generation and Emotion Recognition

[0904] The server asks the generation AI to generate a message in French, and the emotion engine recognizes the user's emotions.

[0905] The generation AI generates the message "Bonjour! Comment ça va aujourd'hui?" and the server sends it to the user's device.

[0906] 3. Message Delivery and User Response

[0907] The device receives the message and displays it to the user.

[0908] The user replied, "Ça va bien, merci! Et toi?"

[0909] The device sends a reply to the server, which then analyzes the user's emotions through an emotion engine.

[0910] 4. Real-time voice chat and emotional adaptation

[0911] A user initiates a voice chat.

[0912] The device sends a request to the server, and the emotion engine recognizes the user's emotions.

[0913] The generating AI generates relaxing sounds, and the server sends the sound data to the user's device.

[0914] 5. Learning history storage and feedback

[0915] The server stores messages and voice chat logs and evaluates learning progress using an emotion engine.

[0916] Based on the evaluation, feedback is generated, received by the device, and displayed to the user.

[0917] This system takes into account the user's emotions and provides an effective dialogue format, enabling a deeper learning experience.

[0918] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0919] Program processing steps

[0920] User registration and language selection

[0921] Step 1: Launch the app

[0922] Input: None

[0923] Output: Display of registration screen

[0924] Specific operation: The user launches the app on their smartphone (or tablet, or PC). The device displays the registration screen.

[0925] Step 2: Enter your registration information

[0926] Input: User's basic information (e.g. name, email address, password)

[0927] Output: User information entered

[0928] Specific behavior: The user enters the basic information displayed on the registration screen.

[0929] Step 3: Language Selection

[0930] Input: Select the language you want to learn (e.g. French)

[0931] Output: Selected language information

[0932] What it does: The user selects the language they want to learn from the displayed list of languages.

[0933] Step 4: Send information

[0934] Input: User basic information and selected language

[0935] Output: Data sent to the server

[0936] Specific operation: The device sends the user's input information and selected language information to the server.

[0937] Step 5: Save Data

[0938] Input: User information and selected language information

[0939] Output: Data stored in the database

[0940] Specific operation: The server stores the received user information and language selection information in a database.

[0941] Message Generation and Emotion Recognition

[0942] Step 6: Message Production Request

[0943] Input: Selected language information

[0944] Output: Message generation request to the generation AI

[0945] Specific behavior: The server requests the generation AI to generate a greeting message in the selected language (e.g., French).

[0946] Step 7: Emotion Recognition

[0947] Input: User history and context

[0948] Output: Evaluation of the user's emotional state

[0949] Specific operation: The server uses the emotion engine to evaluate the user's emotional state. For example, it analyzes the user's typing speed and facial recognition camera.

[0950] Step 8: Send your feedback

[0951] Input: Evaluation result of emotion engine

[0952] Output: Feedback to the generative AI

[0953] Specific behavior: The emotion engine sends feedback to the generative AI based on the user's emotional state.

[0954] Step 9: Message Generation

[0955] Input: Prompt text reflecting feedback

[0956] Output: The generated message

[0957] What it does: The generative AI generates a message based on feedback from the emotion engine. Example: "Bonjour! Comment ça va aujourd'hui?"

[0958] Step 10: Receiving a message

[0959] Input: The generated message

[0960] Output: Data sent to the user's device

[0961] Specific operation: The server sends the generated message to the user's terminal.

[0962] Message Delivery and User Response

[0963] Step 11: Displaying a message

[0964] Input: The message sent

[0965] Output: Message displayed on the screen

[0966] Specific operation: The device displays the received message on the screen.

[0967] Step 12: User response

[0968] Input: User reply (e.g. "Ça va bien, merci! Et toi?")

[0969] Output: User response data

[0970] Specific behavior: The user types a reply to the displayed message.

[0971] Step 13: Send a response message

[0972] Input: User reply data

[0973] Output: Response data sent to the server

[0974] Specific operation: The device sends the user's reply to the server.

[0975] Step 14: Sentiment Analysis

[0976] Input: User reply data

[0977] Output: Evaluation result of emotion engine

[0978] Specific operation: The server analyzes the user's message received by the emotion engine and evaluates the user's emotional state.

[0979] Real-time voice chat and emotional adaptation

[0980] Step 15: Voice Chat Selection

[0981] Input: Voice chat start request

[0982] Output: Request data to the server

[0983] What happens: A user selects the "Voice Chat" option in your app and sends a request.

[0984] Step 16: Receiving a request

[0985] Input: Voice chat start request

[0986] Output: Request processing on the server side

[0987] Specific operation: The terminal sends a request to the server, and the server receives the request.

[0988] Step 17: Real-time audio data generation

[0989] Input: User's emotional state and historical data

[0990] Output: Audio data generation request

[0991] Specific operation: The server uses the generation AI and emotion engine to generate the voice data required for dialogue in real time.

[0992] Step 18: Emotional Adaptation

[0993] Input: Evaluation result of emotion engine

[0994] Output: Feedback to the generative AI

[0995] Specific operation: The emotion engine analyzes the user's emotional state (e.g., nervousness) and provides the corresponding voice tone and content to the generation AI.

[0996] Step 19: Sending audio data

[0997] Input: Generated audio data

[0998] Output: Sends audio data to the user's device

[0999] Specific operation: The generation AI generates a voice response with a relaxing tone and content, and the server sends the voice data to the user's device.

[1000] Learning history and feedback

[1001] Step 20: Logging

[1002] Input: User messages and voice chat data

[1003] Output: Save log data

[1004] What it does: The server stores logs of users' messages and voice chats.

[1005] Step 21: Assess your learning progress

[1006] Input: Saved log data

[1007] Output: Learning progress assessment results

[1008] Specific operation: The emotion engine analyzes the saved logs and evaluates the user's learning progress.

[1009] Step 22: Generate evaluation results

[1010] Input: Learning progress assessment results

[1011] Output: Feedback data

[1012] Specific operation: The generative AI generates feedback based on the evaluation results of the emotion engine.

[1013] Step 23: Send feedback

[1014] Input: Feedback data

[1015] Output: Send feedback to the user's device

[1016] Specific operation: The server sends the generated feedback to the user's device.

[1017] Step 24: Feedback display

[1018] Input: Submitted feedback

[1019] Output: On-screen feedback

[1020] Specific behavior: The device receives the feedback and displays it to the user.

[1021] (Application example 2)

[1022] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1023] Current foreign language learning systems and content distribution services struggle to provide personalized recommendations and interactive educational and entertainment experiences that take into account the user's emotional state. Therefore, there is a need to improve the quality of users' learning motivation and entertainment experiences.

[1024] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional state and providing feedback to the generation AI accordingly, means for recommending content to be played next based on the analyzed emotional data, and means for providing interactive quiz and voting functions based on the user's emotional state. This makes it possible to provide a personalized learning and entertainment experience that adapts to the user's emotions.

[1025] "Means for users to select the information they want to learn" refers to providing an interface that allows users to select specific information or topics that interest them.

[1026] "Means for generating messages for virtual characters using generative AI" refers to a method for using artificial intelligence technology to generate messages for virtual characters based on information selected by a user.

[1027] "Means for transmitting the generated message to the user's terminal" refers to a method for transmitting the message generated by the virtual personality to the user's device using a communication means such as the Internet.

[1028] The "means for a user to reply to a message received" is a method of providing an interface that allows a user to input a response to a message received by the user using text or voice.

[1029] "Generative AI means for generating the next message based on the user's reply" refers to an artificial intelligence technology that analyzes the content of the user's response and generates the next series of dialogue messages based on that.

[1030] The "means for sending the next generated message to the user again" refers to a method for sending the next generated message to the user's device again using a communication means such as the Internet.

[1031] "Means for generating voice in real time and performing voice communication" refers to a method in which a generation AI generates voice messages in real time and uses them as a means of voice communication with the user.

[1032] "Means for saving a user's learning history and evaluating the learning progress" refers to a method for recording the user's progress and analyzing it to evaluate the user's learning situation.

[1033] "Means for providing feedback based on evaluation" refers to a method for presenting constructive advice or next steps to users based on their learning progress and emotional state.

[1034] "Means of analyzing the user's emotional state and providing feedback to the generative AI accordingly" refers to a method of analyzing the user's emotions and facial expressions in real time and reflecting the results in the generative AI.

[1035] "Means for recommending the next content to be played based on analyzed emotional data" is a method for automatically selecting and suggesting the most suitable content to be viewed next based on the user's emotional state.

[1036] "Means for providing an interactive quiz or voting function based on the emotional state of the user" is a method for providing interactive elements such as quizzes or voting that reflect the emotional state of the user in real time.

[1037] A system embodying the present invention analyzes a user's emotions and provides content recommendations and interactive quizzes based on the analyzed emotions, thereby enhancing the user's learning and entertainment experience. The system comprises the following steps:

[1038] System Configuration

[1039] 1. User Device:

[1040] Hardware: Smartphone (including camera and microphone)

[1041] Software: Dedicated application

[1042] Function: Captures the user's face and voice in real time using the camera and microphone and sends the data to a server.

[1043] 2. Server:

[1044] Hardware: Cloud servers, database servers

[1045] Software: Flask (server-side processing), TensorFlow (sentiment analysis), generative AI model

[1046] Function: Analyzes data received from users and uses generative AI to generate content and interactive elements that are sent to the user's device.

[1047] Program processing

[1048] User Registration and Settings

[1049] When a user installs and launches the application on their device, a registration screen is displayed. The user enters basic information, which is then sent to the server. Next, the user selects the genre of interest, and the information is sent to the server.

[1050] Content viewing and sentiment analysis

[1051] When a user plays video content, the device's camera and microphone are used to capture the user's facial expressions and voice. The data is sent to a server and analyzed using TensorFlow and other tools. The results of the emotion analysis are fed into the generative AI.

[1052] Recommendation Generation

[1053] Based on the analysis results, the generative AI recommends the next appropriate content. In this case, the generative AI model generates the most appropriate content based on the user's interests and emotional state. For example, if the user is laughing, it will recommend a comedy movie.

[1054] Providing interactive content

[1055] The generative AI provides interactive quizzes and polls based on the user's emotional state. An example of a prompt might be, "The user is currently watching a romantic comedy movie and is laughing. Please generate the next recommended content and related quiz."

[1056] Learning history and feedback

[1057] The server stores users' viewing history and emotional data, which can then be used to further personalize future recommendations and interactive content. Users can receive this feedback in real time through the app.

[1058] Specific examples

[1059] For example, if a user is laughing while watching a romantic comedy movie, the emotion engine will recognize that laughter and the generative AI will recommend the next comedy movie to watch, or provide a quiz related to that particular scene, allowing the user to continue their learning and entertainment experience while having fun.

[1060] This allows the present invention to respond to the user's emotions and provide a personalized learning and entertainment experience.

[1061] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1062] Step 1:

[1063] The user installs and launches the application. A registration screen appears on the user's device, and the user enters basic information (such as name and email address) and submits it. The entered information is sent to the server via the Internet.

[1064] Input: User basic information

[1065] Output: User information stored in the user database on the server

[1066] Step 2:

[1067] A screen is displayed where the user can select the genre and information they are interested in. The user selects the genre they want to learn about (e.g., comedy, action, etc.) and submits the selected information. The submitted information is received by the server and stored in a database.

[1068] Input: User-selected genre information

[1069] Output: Genre information stored in a database on the server

[1070] Step 3:

[1071] The user plays the video content. When playback starts, the device's camera and microphone are activated to capture the user's facial expressions and voice in real time. This data is then sent to the server.

[1072] Input: User's facial expression and voice data

[1073] Output: User emotion data sent to the server

[1074] Step 4:

[1075] The server uses TensorFlow to analyze the received user facial expression and voice data. The analysis results in the user's emotional state (happiness, surprise, sadness, etc.). The analyzed emotional data is passed to the generation AI.

[1076] Input: User's facial expression and voice data

[1077] Output: Analyzed user emotion data

[1078] Step 5:

[1079] The AI ​​generator recommends the next piece of content to be played based on emotional data and the user's selected genre. The AI ​​generator continues to learn by using appropriate prompts. For example, the prompt might read, "The user is watching a comedy movie and laughing. Please generate the next piece of content to recommend."

[1080] Input: Parsed emotion data, genre information, prompt sentence

[1081] Output: Recommended next content information

[1082] Step 6:

[1083] The server sends the recommended content information to the user's terminal and displays it as a list of content for the user to view next. The user can then select the content to view next.

[1084] Input: Recommended content information

[1085] Output: The following content list displayed on the user's device

[1086] Step 7:

[1087] While the user is watching the next content, the server uses generative AI to generate interactive quizzes and polls, for example, generating quizzes related to specific scenes in a movie and sending them to the user.

[1088] Input: User viewing content information and emotion data

[1089] Output: Interactive quizzes and polls

[1090] Step 8:

[1091] Users participate in interactive quizzes and polls, and the results are sent to the server, which analyzes the results and stores them in the user's learning history.

[1092] Input: User quiz or poll answers

[1093] Output: Saved learning history and analysis data

[1094] Step 9:

[1095] The server uses the stored learning history and emotional data to generate data to further personalize future recommendations and interactive elements, and this feedback is sent to the user in real time.

[1096] Input: Learning history and emotion data

[1097] Output: Personalized feedback

[1098] In this way, the invention allows users to have a personalized learning and entertainment experience that adapts to their emotions.

[1099] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1100] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1101] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1102] [Third embodiment]

[1103] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1104] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1105] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1106] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1107] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1108] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1109] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1110] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1111] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1112] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1113] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1114] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1115] This invention relates to a system that allows users to practice foreign languages ​​on a daily basis through communication with virtual foreigners. This system is designed to allow users to select the language they want to learn and to message and voice chat with the virtual foreigners in that language.

[1116] System configuration

[1117] This system consists of a user's device and a server. User devices include smartphones, tablets, and PCs. The server uses a generation AI to generate messages from virtual foreigners and send them to users.

[1118] System Operation

[1119] User registration and language selection

[1120] When a user installs and launches the app, a registration screen appears on the user's device. The user enters basic information such as their name and email address to create an account. A screen is also displayed where the user can select the language they want to learn. For example, if the user selects "French," that information is sent to the server.

[1121] Message Generation

[1122] The server receives the user's selected language information and sends a request to the AI ​​to generate a message in that language. Based on the input, the AI ​​generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?). These messages are designed to include content relevant to the user's daily life.

[1123] Message Delivery and User Response

[1124] The generated message is sent from the server to the user's device. The user's device displays the received message on the screen, and the user can reply to it. For example, if the user replies "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?), the message is sent back to the server.

[1125] The server receives the user's reply and instructs the generation AI to generate the next message. The generation AI generates a new message and sends it back to the user's device. In this way, the message exchange between the user and the virtual alien continues.

[1126] Real-time voice chat

[1127] When a user selects "Voice Chat," a request is sent to the server. The server asks the generation AI to generate voice data in real time. The generation AI generates voice messages such as "Je vais bien, merci!" (I'm fine, thank you!) and sends them to the user's device via the server.

[1128] The user's device plays the received voice data, and the user responds through the microphone. The voice data is then sent back to the server, where the AI ​​generates new voices to continue the communication.

[1129] Learning history and feedback

[1130] The server stores the user's messages and voice chat logs and uses them to evaluate their learning progress. The evaluation results are generated as feedback, including the user's strengths and areas for improvement, and sent to the user's device. By receiving this feedback, the user can check their learning progress and determine which areas they should focus on next.

[1131] Specific examples

[1132] 1. User registration and language selection

[1133] A user opens the app, enters the required registration information, and selects "French" as the language they want to learn.

[1134] The terminal sends information to the server, which receives it.

[1135] 2. Message Creation

[1136] The server asks the generation AI to generate a message in French, and the generation AI generates the message "Bonjour! Comment ça va aujourd'hui?"

[1137] 3. Message Delivery and User Response

[1138] The server sends the generated message to the terminal, and the user receives and replies to the message.

[1139] The device sends a reply to the server, and the server again instructs the generation AI to generate the next message.

[1140] 4. Real-time voice chat

[1141] A user initiates a voice chat and the terminal sends a request to the server.

[1142] The server requests the generation AI to generate voice and sends the generated voice to the user's device.

[1143] 5. Learning history storage and feedback

[1144] The server stores messages and voice chat logs and evaluates learning progress.

[1145] Based on the learning progress, the server generates feedback and sends it to the device.

[1146] In this way, the system of the present invention provides an environment in which users can practice a foreign language on a daily basis and progress in their learning efficiently.

[1147] The processing flow will be explained below.

[1148] Step 1:

[1149] The user installs and launches the app, and the account registration screen appears on the device screen.

[1150] Step 2:

[1151] A user creates an account by entering basic information such as name and email address, and then selects the language they want to learn.

[1152] Step 3:

[1153] The terminal sends the input information to the server, which receives it and stores it in a database.

[1154] Step 4:

[1155] The server sends a message generation request to the AI ​​based on the user's selected language, and the AI ​​generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?).

[1156] Step 5:

[1157] The server sends the generated message to the user's terminal, and the terminal displays the received message on the user's screen.

[1158] Step 6:

[1159] The user types a reply to the received message (e.g., "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?)) and the terminal sends the reply to the server.

[1160] Step 7:

[1161] The server receives the user's reply and instructs the generation AI to generate the next message. The generation AI generates a new message, which the server then sends to the user's device.

[1162] Step 8:

[1163] The user selects "Voice Chat." The device sends a voice chat start request to the server.

[1164] Step 9:

[1165] The server requests real-time voice generation from the generation AI, the generation AI generates the voice data, and the server sends it to the user's device.

[1166] Step 10:

[1167] The terminal plays the received voice data, the user responds by voice through the microphone, and the terminal transmits the voice data to the server.

[1168] Step 11:

[1169] The server analyzes the received voice data and issues instructions to the generation AI to generate the next voice response. The server then sends the generated voice data back to the user's device.

[1170] Step 12:

[1171] The server stores all messages and voice chat logs in a database, evaluates learning progress, and generates feedback.

[1172] Step 13:

[1173] The device receives feedback from the server and displays it to the user, who then checks the feedback and uses it in their next learning.

[1174] Example 1

[1175] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1176] In language learning, it is effective to practice in everyday communication situations. However, in reality, there are few opportunities to speak a foreign language on a daily basis, making efficient learning difficult. Another issue is that there is no feedback based on individual learning progress, making it unclear which areas need to be strengthened. Furthermore, there are few systems that allow real-time audio interaction, making it difficult to experience actual conversation.

[1177] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1178] In this invention, the server includes a means for allowing a user to select a language they wish to learn, a means for generating a message for a virtual character using a generation AI, a means for sending the generated message to the user's device, and a generation AI means for generating the next message based on the user's reply. This provides users with opportunities to speak a foreign language on a daily basis, allowing them to progress in their studies efficiently. Furthermore, by including a means for generating voice in real time and performing real-time voice communication, it is possible to provide a real conversation experience and enhance the effectiveness of learning. Furthermore, by including a means for saving the user's learning progress data and evaluating the progress, and a means for providing feedback based on the evaluation, it is possible to improve the quality of learning through individualized feedback.

[1179] "Generative AI" is a system that uses artificial intelligence to generate text and speech.

[1180] A "virtual person" is a character that does not exist in reality, but is generated by AI and interacts with the user through messages and voice.

[1181] A "user's terminal" is a device used by a user to access the system, such as a smartphone, tablet, or PC.

[1182] A "message" is text data generated by the generation AI and sent to the user.

[1183] "Audio data" refers to audio data generated by the generation AI and that can be heard by the user.

[1184] "Real-time voice communication" is a communication method in which a user and a virtual character converse in real time through voice.

[1185] "Learning progress data" is a record of the conversations and exercises that a user has conducted through the system.

[1186] "Feedback" is information that indicates the user's learning progress and areas for improvement, and is generated based on the learning progress data.

[1187] "Server means" refers to a server for generating messages from the generation AI and storing and processing data.

[1188] This invention relates to a system that allows users to learn a foreign language through communication with a virtual character. The system consists of a server and a user's terminal. The user's terminal can be a smartphone, tablet, PC, or other device. The server uses a generative AI model to generate messages for the virtual character and send them to the user.

[1189] Basic system configuration

[1190] The system includes the following means:

[1191] 1. A way for users to choose the language they want to learn

[1192] 2. A method for generating messages from virtual characters using generative AI

[1193] 3. A means of sending the generated message to the user's terminal

[1194] 4. A way for users to reply to messages they receive

[1195] 5. Generative AI method to generate the next message based on the user's reply

[1196] 6. A means to send the next generated message back to the user

[1197] 7. Means for generating audio in real time and performing real-time audio communication

[1198] 8. A means of storing user learning progress data and assessing progress

[1199] 9. Means of providing feedback based on the assessment

[1200] Hardware and software used

[1201] The main components of this system include the user's device, a server, and a generative AI model. Specifically, the following hardware and software are used:

[1202] User devices: smartphones, tablets, PCs, etc. These devices run applications and provide an interface with the user.

[1203] Server: A server that stores data, processes data, and invokes generative AI models.

[1204] Generative AI models: Artificial intelligence models such as OpenAI's GPT-4. These models generate text and speech.

[1205] Example of operation

[1206] 1. User registration and language selection

[1207] The user installs and launches the app. The device displays a registration screen where the user enters their name and email address to create an account. The device also displays a screen where the user can select the language they want to learn, and the selection is sent to the server.

[1208] 2. Message Creation

[1209] The server receives the user's selection and sends a request to the AI ​​to generate a message in that language. The AI ​​generates the message based on the prompt.

[1210] Example prompt sentence:

[1211] Prompt: "Ask the user 'Hello, how are you today?' as an everyday greeting in French."

[1212] Produced message: "Bonjour! Comment ça va aujourd'hui?"

[1213] The generated message is sent from the server to the user's terminal.

[1214] 3. Message Delivery and User Response

[1215] The device displays the received message to the user. The user replies to the received message, for example, by typing "Ça va bien, merci! Et toi?" The reply data is sent to the server, which again requests the generation AI to generate the next message.

[1216] 4. Real-time voice chat

[1217] When a user selects voice chat, the request is sent to the server. The server then asks the AI ​​to generate voice data, which is then sent to the device so the user can hear it. The user's response is also sent to the server, and new voice data is generated.

[1218] 5. Learning history storage and feedback

[1219] The server stores the user's messages and voice data, evaluates their progress, and generates feedback based on the evaluation, which is sent to the device for the user to review.

[1220] As a result, this system provides an environment in which users can practice a foreign language on a daily basis and progress their learning efficiently.

[1221] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1222] Step 1: User registration and language selection

[1223] The user installs and launches the app.

[1224] The device displays the registration screen. The user enters their name and email address. This input data is saved as the user's account information.

[1225] The device displays a language selection screen, and the user selects the language they want to learn. The selected data, e.g., "French," is sent to the server.

[1226] The server receives this information and stores it in a database as the user's language preference. The output is a registration success message and the selected language information.

[1227] Step 2: Message Generation

[1228] After the server receives the user's language selection information, it sends a message generation request to the generative AI model. The input is the prompt sentence "'Hello, how are you today?' as a daily greeting in French."

[1229] The generative AI model generates a message based on the prompt. The generated message, "Bonjour! Comment ça va aujourd'hui?", is output.

[1230] The server receives this generated message and sends it to the user's terminal. The output is the generated message data.

[1231] Step 3: Message Delivery and User Response

[1232] The terminal displays the received message "Bonjour! Comment ça va aujourd'hui?" to the user.

[1233] The user replies to this message. As input, the user types the reply: "Ça va bien, merci! Et toi?"

[1234] The terminal sends this reply data to the server. The output is the reply message data.

[1235] The server receives the reply data and again asks the generative AI model to generate the next message, including the user's reply as input.

[1236] The generative AI model generates a new message, for example, "Je vais bien, merci!" The server receives this generated message data and sends it to the user's device. The output is the new message data.

[1237] Step 4: Real-time voice chat

[1238] The user selects voice chat. As input, a voice chat start request is sent from the device to the server.

[1239] The server asks the generative AI model to generate voice data in real time. As input, the generative AI receives a message prompt such as "Je vais bien, merci!" (I'm fine, thank you!).

[1240] The generative AI model generates voice data, which is then received by the server and sent to the user's device. The output is the generated voice data.

[1241] The terminal plays the received voice data, and the user responds. The user's voice data is included as input.

[1242] The device sends this voice data to the server, which then asks the AI ​​model to generate new voice data. This process is repeated. The output is new voice data.

[1243] Step 5: Learning history and feedback

[1244] The server stores user messages and voice chat logs, which contain past interaction data as input.

[1245] The server evaluates the user's learning progress based on the stored data, and the output is the evaluation result data.

[1246] The server generates feedback based on the evaluation results and sends it to the user's terminal. The output is feedback data.

[1247] The device displays feedback to the user, allowing the user to see their learning progress.

[1248] (Application example 1)

[1249] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1250] Conventional foreign language learning systems lack sufficient support for users to acquire practical language skills that can be used in daily work. Furthermore, there were no systems for customer support in foreign languages ​​that could respond quickly and accurately to user inquiries. As a result, it was difficult to provide efficient support for users learning foreign languages ​​or in business environments where foreign languages ​​are required.

[1251] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1252] In this invention, the server includes means for generating a response to a user's inquiry in a foreign language, means for transmitting the generated response to the user's terminal and resolving the user's inquiry, and means for the user to select a language they wish to learn. This enables the user to efficiently improve their daily work and practical language skills while receiving customer support in a foreign language.

[1253] "Means for user to select a language they wish to learn" means a device or software interface that allows a user to select a particular language they wish to learn.

[1254] "Means for generating messages from virtual foreigners using generation AI" refers to a function or system that uses generation AI to create messages from virtual foreigners in a selected language.

[1255] "Means for sending the generated message to the user's terminal" refers to communication means or software for delivering the generated message to the device used by the user.

[1256] "Means for replying to messages received by a user" refers to a device or software interface that allows a user to respond to a message received by a user.

[1257] "AI generation means for generating the next message based on the user's reply" refers to an AI system that generates a message to continue the next dialogue based on the user's reply.

[1258] The "means for sending the next generated message to the user again" refers to a communication means or software for sending the newly generated message again to the user's terminal.

[1259] "Means for generating voice in real time and conducting voice chat" refers to a function or system for generating voice data in real time and conducting voice chat between a user and a virtual foreigner.

[1260] "Means for saving a user's learning history and evaluating the user's learning progress" refers to a function or system that saves a user's message and voice chat logs and evaluates the user's learning progress based on them.

[1261] "Means for providing feedback based on evaluation" refers to a function or system for evaluating a user's strengths and areas for improvement based on the saved learning history and providing the user with feedback based on that evaluation.

[1262] The "means for generating a response to a user's inquiry in a foreign language" refers to a system or device for generating an appropriate response in a selected foreign language in response to a user's inquiry.

[1263] "Means for sending the generated response to the user's terminal and resolving the user's inquiry" refers to communications means or software for sending the generated response to the user's terminal and resolving the inquiry.

[1264] This invention realizes a system that allows users to practice foreign languages ​​through conversations with virtual foreigners and simultaneously provides user support. This system utilizes a generation AI that generates messages and voice chats in the language selected by the user. It can also respond to user inquiries.

[1265] System configuration

[1266] This system consists of a user's device (smartphone, tablet) and a server. The server uses a generation AI to generate messages and voice messages from virtual foreigners and send them to the user's device.

[1267] Hardware and Software Configuration

[1268] Hardware:

[1269] User devices: smartphones, tablets

[1270] Server: Cloud infrastructure such as AWS, GCP, etc.

[1271] software:

[1272] Generation AI: OpenAI GPT-3

[1273] Web framework: Flask

[1274] Data transmission / reception: JSON format

[1275] System Operation

[1276] User registration and language selection

[1277] When a user installs and launches the app, a registration screen appears on the user's device. The user enters basic information such as their name and email address to create an account. A screen is also displayed where the user can select the language they want to learn. For example, if the user selects "French," that information is sent to the server.

[1278] Message Creation and Transmission

[1279] The server receives the user's selected language information and sends a request to the AI ​​to generate a message in that language. Based on the input, the AI ​​generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?). These messages are sent from the server to the user's device and displayed.

[1280] User response and next message generation

[1281] When a user receives a message and replies, the reply is sent to the server. The server receives the user's reply and instructs the generation AI to generate the next message. The generated next message is then sent back to the user's device.

[1282] Real-time voice chat

[1283] When a user selects "Voice Chat," a request is sent to the server. The server asks the generation AI to generate voice data in real time. The generation AI generates voice such as "Je vais bien, merci!" (I'm fine, thank you!) and sends it to the user's device via the server. The user's device then plays back the received voice data.

[1284] Learning history and feedback

[1285] The server stores the user's messages and voice chat logs and evaluates their learning progress based on them. The evaluation results are generated as feedback including the user's strengths and areas for improvement, and are sent back to the user's device.

[1286] Specific examples

[1287] 1. User registration and language selection

[1288] User: Opens the app, fills in the required registration information, and selects "French" as the language they want to learn.

[1289] Terminal: Sends information to the server, which receives it.

[1290] 2. Message Creation and Transmission

[1291] Server: Asks the generation AI to generate a message in French, and the generation AI generates the message "Bonjour! Comment ça va aujourd'hui?"

[1292] 3. User response and next message generation

[1293] User: Receives and replies to messages.

[1294] Server: Receives the reply and asks the generation AI for the next message.

[1295] 4. Real-time voice chat

[1296] User: Starts a voice chat and the device sends a request to the server.

[1297] Server: Requests the generation AI to generate speech and sends the generated speech to the user's device.

[1298] 5. Learning history storage and feedback

[1299] Server: Stores messages and voice chat logs and evaluates learning progress.

[1300] Server: Generates feedback and sends it to the device.

[1301] Prompt Sentence Examples

[1302] Example of a user question: "My payment didn't go through. Can you help me?"

[1303] Example prompt for the AI ​​generator: English: My payment didn't go through. Can you help me?

[1304] This system provides users with an environment in which they can practice foreign languages ​​on a daily basis and progress their learning efficiently, while also enabling them to receive prompt customer support in their foreign language.

[1305] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1306] Step 1: User registration and language selection

[1307] The user installs and launches the app. They enter basic information such as their name and email address to create an account. They are also shown a screen where they can select the language they want to learn. For example, if they select "French," that information is sent from the user's device to the server. The server then stores the received information in a database.

[1308] Input: User's basic information (name, email address), selected language

[1309] Output: User information and selected language are saved on the server side

[1310] Step 2: First message generation

[1311] After receiving the selected language information, the server sends a request to the AI ​​to generate a message in that language. Based on the input, the AI ​​generates a typical message such as "Bonjour! Comment ça va aujourd'hui?" The server then sends the generated message to the user's device.

[1312] Input: User's preferred language information

[1313] Output: The generated message in the selected language

[1314] Step 3: View and reply to messages

[1315] The user's device displays the received message. The user checks the received message and replies. For example, if the user types "Ça va bien, merci! Et toi?", the message is sent from the device to the server. The server saves the received user message and uses it as input data for the next generation request.

[1316] Input: User's reply message

[1317] Output: User's reply message stored on the server

[1318] Step 4: Generate the next message

[1319] The server sends a request to the generation AI to generate the next message based on the user's reply message. The generation AI generates a new message based on the input. For example, a response message such as "Je vais bien, merci!" is generated. This is then sent back to the user's device via the server.

[1320] Input: User's reply message

[1321] Output: The following message generated by the generation AI

[1322] Step 5: Real-time voice chat

[1323] When a user selects "Voice Chat," a request is sent from the user's device to the server. The server asks the generation AI to generate voice data in real time. The generation AI generates voice data such as "Je vais bien, merci!" and sends it to the user's device via the server. The user's device plays the received voice data and sends the voice input from the user's microphone back to the server.

[1324] Input: User's voice request

[1325] Output: Voice data generated by the generative AI

[1326] Step 6: Save your learning history and provide feedback

[1327] The server stores the user's messages and voice chat logs and uses them to evaluate their learning progress. The evaluation results are generated as feedback including the user's strengths and areas for improvement, and are sent back to the user's device. The user can then use this feedback to set their next learning goal.

[1328] Input: User's message history, voice chat log

[1329] Output: Feedback data

[1330] Step 7: Responding to user inquiries

[1331] When a user makes a query, for example, "My payment didn't go through. Can you help me?", the query is sent from the user's device to the server. The server then sends a request to the generation AI to generate a response based on the query. For example, a response such as "Sure, let's check your transaction. Can you provide me with the transaction ID?" is generated and sent to the user's device. The user can then use this response to ask further questions.

[1332] Input: User's query message

[1333] Output: The response message generated by the generation AI

[1334] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1335] This invention relates to a system that recognizes a user's emotions and adapts personalized feedback and conversation content based on those emotions. The system allows users to select the language they want to learn, and by combining an emotion engine with a generation AI that communicates with a virtual foreigner in that language, the system promotes more effective learning.

[1336] System configuration

[1337] This system consists of a user's device, a server, a generation AI, and an emotion engine. User devices include smartphones, tablets, and PCs. The server manages the generation AI and emotion engine, and controls message generation and voice chat for the virtual aliens.

[1338] System Operation

[1339] User registration and language selection

[1340] When a user installs and launches the app, a registration screen appears on the user's device. The user enters their basic information and creates an account. Next, a screen appears asking the user to select the language they want to learn. For example, if the user selects "French," that information is sent to the server.

[1341] Message Generation and Emotion Recognition

[1342] The server receives the user's selected language information and sends a request to the generation AI to generate a message in that language. At that time, the emotion engine recognizes the user's emotional state and provides feedback to the generation AI. The generation AI reflects the feedback from the emotion engine and generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?).

[1343] Message Delivery and User Response

[1344] The generated message is sent from the server to the user's device. The user's device displays the received message on the screen, and the user can reply to it. For example, if the user replies "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?), the message is sent back to the server.

[1345] The server receives the user's reply and analyzes the user's emotional state using the emotion engine. The generation AI generates the next message based on the analysis results from the emotion engine and sends it back to the user.

[1346] Real-time voice chat and emotional adaptation

[1347] When a user selects "Voice Chat," a request is sent to the server. The server uses the generative AI and emotion engine to generate voice data in real time. For example, if the emotion engine recognizes that the user is nervous, the generative AI will generate a voice response with a relaxing tone and content. This allows the user to continue the conversation without stress.

[1348] Learning history and feedback

[1349] The server stores the user's messages and voice chat logs and evaluates their learning progress using an emotion engine. The evaluation results are then generated as feedback that takes into account the user's emotional state and sent to the user's device. By receiving this feedback, the user can check their learning progress and determine which areas they should focus on next.

[1350] Specific examples

[1351] 1. User registration and language selection

[1352] A user opens the app, enters the required registration information, and selects "French" as the language they want to learn.

[1353] The terminal sends information to the server, which receives it.

[1354] 2. Message Generation and Emotion Recognition

[1355] The server asks the generation AI to generate a message in French, and the emotion engine recognizes the user's emotions.

[1356] The generation AI generates the message "Bonjour! Comment ça va aujourd'hui?" and the server sends it to the user's device.

[1357] 3. Message Delivery and User Response

[1358] The device receives the message and displays it to the user.

[1359] The user replied, "Ça va bien, merci! Et toi?"

[1360] The device sends a reply to the server, which then analyzes the user's emotions through an emotion engine.

[1361] 4. Real-time voice chat and emotional adaptation

[1362] A user initiates a voice chat.

[1363] The device sends a request to the server, and the emotion engine recognizes the user's emotions.

[1364] The generating AI generates relaxing sounds, and the server sends the sound data to the user's device.

[1365] 5. Learning history storage and feedback

[1366] The server stores messages and voice chat logs and evaluates learning progress using an emotion engine.

[1367] Based on the evaluation, feedback is generated, received by the device, and displayed to the user.

[1368] In this way, the system of the present invention provides an environment for learning a foreign language more effectively while taking into consideration the user's feelings.

[1369] The processing flow will be explained below.

[1370] Step 1:

[1371] The user installs and launches the app, and the account registration screen appears on the device screen.

[1372] Step 2:

[1373] A user creates an account by entering basic information such as name and email address, and then selects the language they want to learn.

[1374] Step 3:

[1375] The terminal sends the input information to the server, which receives it and stores it in a database.

[1376] Step 4:

[1377] The server sends a message generation request to the AI ​​based on the user's selected language, while the emotion engine recognizes the user's emotional state based on their past history and real-time input.

[1378] Step 5:

[1379] The generative AI reflects feedback from the emotion engine to generate messages such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?).

[1380] Step 6:

[1381] The server sends the generated message to the user's terminal, and the terminal displays the received message on the user's screen.

[1382] Step 7:

[1383] The user types a reply to the received message (e.g., "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?)) and the terminal sends the reply to the server.

[1384] Step 8:

[1385] The server receives the user's reply and analyzes the user's emotional state through the emotion engine. The generation AI generates the next message based on the analysis results from the emotion engine.

[1386] Step 9:

[1387] The server then sends the generated next message back to the user's terminal, which receives the message and displays it to the user.

[1388] Step 10:

[1389] The user selects "Voice Chat." The device sends a voice chat start request to the server.

[1390] Step 11:

[1391] The server uses the generation AI and emotion engine to request real-time voice generation. The generation AI generates the voice data, and the server sends it to the user's device.

[1392] Step 12:

[1393] The terminal plays the received voice data, the user responds by voice through the microphone, and the terminal transmits the voice data to the server.

[1394] Step 13:

[1395] The server analyzes the received voice data using an emotion engine and issues instructions to the generation AI to generate the next voice response. The server then sends the generated voice data back to the user's device.

[1396] Step 14:

[1397] The server stores all messages and voice chat logs in a database, and uses an emotion engine to evaluate learning progress and generate feedback.

[1398] Step 15:

[1399] The device receives feedback from the server and displays it to the user, who then checks the feedback and uses it in their next learning.

[1400] Example 2

[1401] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1402] Conventional language learning systems lack the ability to adapt feedback and communication content to take into account the user's emotional state, making effective learning difficult. Furthermore, real-time voice chat and feedback based on learning progress are limited, making individual optimization insufficient. This can easily discourage users from learning, preventing efficient language acquisition.

[1403] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1404] In this invention, the server includes emotion recognition means for recognizing the user's emotional state and generating messages and voices according to that state, means for saving the user's learning history and evaluating the learning progress, and means for providing feedback based on the evaluation. This makes it possible to provide effective feedback and communication adapted to the user's emotional state and to provide individually optimized learning support through real-time voice chat.

[1405] The "means for the user to select the language they wish to learn" is a function that allows the user to select the language they wish to learn from a list of languages ​​provided within the application.

[1406] "Generative AI" is artificial intelligence that uses natural language processing technology to generate human-like dialogue.

[1407] The "means for generating messages of virtual foreigners" is a function that uses a generation AI to create messages of virtual foreigners in a language selected by the user.

[1408] The "means for transmitting the generated message to the user's terminal" is a function for transferring the message from the server to the user's terminal.

[1409] The "means for replying to a message received by the user" is a function for creating and sending a reply on the terminal in response to a message received by the user.

[1410] The "generative AI means for generating the next message based on the user's reply" is a function that takes the user's reply as input and generates the next dialogue message accordingly.

[1411] "Means for sending the next generated message back to the user" is a function for sending the next message created by the generation AI back to the user's device.

[1412] "Means for generating voice in real time and conducting voice chat" refers to a function that uses generation AI and voice synthesis technology to generate voice in real time and engage in voice conversation with the user.

[1413] "Emotion recognition means that recognizes the user's emotional state and generates messages and voices according to that state" is a function that analyzes emotions from the user's facial expressions and text input, and generates dialogue content according to those emotions.

[1414] The "means for saving the user's learning history and evaluating the learning progress" is a function for saving a record of the user's interactions and activities and evaluating the learning progress based on that record.

[1415] The "means for providing feedback based on evaluation" is a function that uses the evaluation results of the learning progress to provide the user with useful advice and feedback on what they should focus on next.

[1416] This invention relates to a system that recognizes a user's emotions and adapts personalized feedback and conversation content based on those emotions. The system allows users to select the language they want to learn, and by combining an emotion engine with a generation AI that communicates with a virtual foreigner in that language, the system promotes more effective learning.

[1417] System configuration

[1418] This system consists of a user's device, a server, a generation AI, and an emotion engine. User devices include smartphones, tablets, and PCs. The server manages the generation AI and emotion engine, and controls message generation and voice chat for the virtual aliens.

[1419] The specific hardware and software used is as follows:

[1420] Hardware: Smartphones, tablets, computers

[1421] software:

[1422] Generative AI: Natural language processing models such as GPT-4

[1423] Emotion engine: Various emotion analysis APIs (e.g., Microsoft Azure emotion recognition API)

[1424] Server: Database and backend server (e.g. AWS EC2 server, Node.js backend)

[1425] System Operation

[1426] User registration and language selection

[1427] When a user installs and launches the app, a registration screen appears on the user's device. The user enters their basic information and creates an account. A screen is then displayed in which the user can select the language they want to learn. For example, if they select "French," that information is sent to the server. The information received by the server is stored in a database.

[1428] Message Generation and Emotion Recognition

[1429] The server requests the generation AI to generate a message based on the language information selected by the user. At that time, the emotion engine recognizes the user's emotional state and provides feedback to the generation AI. Based on the feedback from the emotion engine, the generation AI generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?). The server then sends the generated message to the user's device.

[1430] Message Delivery and User Response

[1431] The device displays the received message on the screen, and the user replies to it. For example, if the user replies "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?), the message is sent to the server again. The server receives the user's reply and analyzes the user's emotional state using an emotion engine. The generation AI generates the next message based on the analysis results from the emotion engine and sends it back to the user.

[1432] Real-time voice chat and emotional adaptation

[1433] When a user selects "Voice Chat," a request is sent to the server. The server uses the generative AI and emotion engine to generate voice data in real time. For example, if the emotion engine recognizes that the user is nervous, the generative AI will generate a voice response with a relaxing tone and content. This allows the user to continue the conversation without stress.

[1434] Learning history and feedback

[1435] The server stores the user's messages and voice chat logs and evaluates their learning progress using an emotion engine. The evaluation results are then generated as feedback that takes into account the user's emotional state and sent to the user's device. By receiving this feedback, the user can check their learning progress and determine which areas they should focus on next.

[1436] Specific examples

[1437] 1. User registration and language selection

[1438] A user opens the app, enters the required registration information, and selects "French" as the language they want to learn.

[1439] The terminal sends information to the server, which receives it.

[1440] 2. Message Generation and Emotion Recognition

[1441] The server asks the generation AI to generate a message in French, and the emotion engine recognizes the user's emotions.

[1442] The generation AI generates the message "Bonjour! Comment ça va aujourd'hui?" and the server sends it to the user's device.

[1443] 3. Message Delivery and User Response

[1444] The device receives the message and displays it to the user.

[1445] The user replied, "Ça va bien, merci! Et toi?"

[1446] The device sends a reply to the server, which then analyzes the user's emotions through an emotion engine.

[1447] 4. Real-time voice chat and emotional adaptation

[1448] A user initiates a voice chat.

[1449] The device sends a request to the server, and the emotion engine recognizes the user's emotions.

[1450] The generating AI generates relaxing sounds, and the server sends the sound data to the user's device.

[1451] 5. Learning history storage and feedback

[1452] The server stores messages and voice chat logs and evaluates learning progress using an emotion engine.

[1453] Based on the evaluation, feedback is generated, received by the device, and displayed to the user.

[1454] This system takes into account the user's emotions and provides an effective dialogue format, enabling a deeper learning experience.

[1455] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1456] Program processing steps

[1457] User registration and language selection

[1458] Step 1: Launch the app

[1459] Input: None

[1460] Output: Display of registration screen

[1461] Specific operation: The user launches the app on their smartphone (or tablet, or PC). The device displays the registration screen.

[1462] Step 2: Enter your registration information

[1463] Input: User's basic information (e.g. name, email address, password)

[1464] Output: User information entered

[1465] Specific behavior: The user enters the basic information displayed on the registration screen.

[1466] Step 3: Language Selection

[1467] Input: Select the language you want to learn (e.g. French)

[1468] Output: Selected language information

[1469] What it does: The user selects the language they want to learn from the displayed list of languages.

[1470] Step 4: Send information

[1471] Input: User basic information and selected language

[1472] Output: Data sent to the server

[1473] Specific operation: The device sends the user's input information and selected language information to the server.

[1474] Step 5: Save Data

[1475] Input: User information and selected language information

[1476] Output: Data stored in the database

[1477] Specific operation: The server stores the received user information and language selection information in a database.

[1478] Message Generation and Emotion Recognition

[1479] Step 6: Message Production Request

[1480] Input: Selected language information

[1481] Output: Message generation request to the generation AI

[1482] Specific behavior: The server requests the generation AI to generate a greeting message in the selected language (e.g., French).

[1483] Step 7: Emotion Recognition

[1484] Input: User history and context

[1485] Output: Evaluation of the user's emotional state

[1486] Specific operation: The server uses the emotion engine to evaluate the user's emotional state. For example, it analyzes the user's typing speed and facial recognition camera.

[1487] Step 8: Send your feedback

[1488] Input: Evaluation result of emotion engine

[1489] Output: Feedback to the generative AI

[1490] Specific behavior: The emotion engine sends feedback to the generative AI based on the user's emotional state.

[1491] Step 9: Message Generation

[1492] Input: Prompt text reflecting feedback

[1493] Output: The generated message

[1494] What it does: The generative AI generates a message based on feedback from the emotion engine. Example: "Bonjour! Comment ça va aujourd'hui?"

[1495] Step 10: Receiving a message

[1496] Input: The generated message

[1497] Output: Data sent to the user's device

[1498] Specific operation: The server sends the generated message to the user's terminal.

[1499] Message Delivery and User Response

[1500] Step 11: Displaying a message

[1501] Input: The message sent

[1502] Output: Message displayed on the screen

[1503] Specific operation: The device displays the received message on the screen.

[1504] Step 12: User response

[1505] Input: User reply (e.g. "Ça va bien, merci! Et toi?")

[1506] Output: User response data

[1507] Specific behavior: The user types a reply to the displayed message.

[1508] Step 13: Send a response message

[1509] Input: User reply data

[1510] Output: Response data sent to the server

[1511] Specific operation: The device sends the user's reply to the server.

[1512] Step 14: Sentiment Analysis

[1513] Input: User reply data

[1514] Output: Evaluation result of emotion engine

[1515] Specific operation: The server analyzes the user's message received by the emotion engine and evaluates the user's emotional state.

[1516] Real-time voice chat and emotional adaptation

[1517] Step 15: Voice Chat Selection

[1518] Input: Voice chat start request

[1519] Output: Request data to the server

[1520] What happens: A user selects the "Voice Chat" option in your app and sends a request.

[1521] Step 16: Receiving a request

[1522] Input: Voice chat start request

[1523] Output: Request processing on the server side

[1524] Specific operation: The terminal sends a request to the server, and the server receives the request.

[1525] Step 17: Real-time audio data generation

[1526] Input: User's emotional state and historical data

[1527] Output: Audio data generation request

[1528] Specific operation: The server uses the generation AI and emotion engine to generate the voice data required for dialogue in real time.

[1529] Step 18: Emotional Adaptation

[1530] Input: Evaluation result of emotion engine

[1531] Output: Feedback to the generative AI

[1532] Specific operation: The emotion engine analyzes the user's emotional state (e.g., nervousness) and provides the corresponding voice tone and content to the generation AI.

[1533] Step 19: Sending audio data

[1534] Input: Generated audio data

[1535] Output: Sends audio data to the user's device

[1536] Specific operation: The generation AI generates a voice response with a relaxing tone and content, and the server sends the voice data to the user's device.

[1537] Learning history and feedback

[1538] Step 20: Logging

[1539] Input: User messages and voice chat data

[1540] Output: Save log data

[1541] What it does: The server stores logs of users' messages and voice chats.

[1542] Step 21: Assess your learning progress

[1543] Input: Saved log data

[1544] Output: Learning progress assessment results

[1545] Specific operation: The emotion engine analyzes the saved logs and evaluates the user's learning progress.

[1546] Step 22: Generate evaluation results

[1547] Input: Learning progress assessment results

[1548] Output: Feedback data

[1549] Specific operation: The generative AI generates feedback based on the evaluation results of the emotion engine.

[1550] Step 23: Send feedback

[1551] Input: Feedback data

[1552] Output: Send feedback to the user's device

[1553] Specific operation: The server sends the generated feedback to the user's device.

[1554] Step 24: Feedback display

[1555] Input: Submitted feedback

[1556] Output: On-screen feedback

[1557] Specific behavior: The device receives the feedback and displays it to the user.

[1558] (Application example 2)

[1559] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1560] Current foreign language learning systems and content distribution services struggle to provide personalized recommendations and interactive educational and entertainment experiences that take into account the user's emotional state. Therefore, there is a need to improve the quality of users' learning motivation and entertainment experiences.

[1561] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional state and providing feedback to the generation AI accordingly, means for recommending content to be played next based on the analyzed emotional data, and means for providing interactive quiz and voting functions based on the user's emotional state. This makes it possible to provide a personalized learning and entertainment experience that adapts to the user's emotions.

[1562] "Means for users to select the information they want to learn" refers to providing an interface that allows users to select specific information or topics that interest them.

[1563] "Means for generating messages for virtual characters using generative AI" refers to a method for using artificial intelligence technology to generate messages for virtual characters based on information selected by a user.

[1564] "Means for transmitting the generated message to the user's terminal" refers to a method for transmitting the message generated by the virtual personality to the user's device using a communication means such as the Internet.

[1565] The "means for a user to reply to a message received" is a method of providing an interface that allows a user to input a response to a message received by the user using text or voice.

[1566] "Generative AI means for generating the next message based on the user's reply" refers to an artificial intelligence technology that analyzes the content of the user's response and generates the next series of dialogue messages based on that.

[1567] The "means for sending the next generated message to the user again" refers to a method for sending the next generated message to the user's device again using a communication means such as the Internet.

[1568] "Means for generating voice in real time and performing voice communication" refers to a method in which a generation AI generates voice messages in real time and uses them as a means of voice communication with the user.

[1569] "Means for saving a user's learning history and evaluating the learning progress" refers to a method for recording the user's progress and analyzing it to evaluate the user's learning situation.

[1570] "Means for providing feedback based on evaluation" refers to a method for presenting constructive advice or next steps to users based on their learning progress and emotional state.

[1571] "Means of analyzing the user's emotional state and providing feedback to the generative AI accordingly" refers to a method of analyzing the user's emotions and facial expressions in real time and reflecting the results in the generative AI.

[1572] "Means for recommending the next content to be played based on analyzed emotional data" is a method for automatically selecting and suggesting the most suitable content to be viewed next based on the user's emotional state.

[1573] "Means for providing an interactive quiz or voting function based on the emotional state of the user" is a method for providing interactive elements such as quizzes or voting that reflect the emotional state of the user in real time.

[1574] A system embodying the present invention analyzes a user's emotions and provides content recommendations and interactive quizzes based on the analyzed emotions, thereby enhancing the user's learning and entertainment experience. The system comprises the following steps:

[1575] System Configuration

[1576] 1. User Device:

[1577] Hardware: Smartphone (including camera and microphone)

[1578] Software: Dedicated application

[1579] Function: Captures the user's face and voice in real time using the camera and microphone and sends the data to a server.

[1580] 2. Server:

[1581] Hardware: Cloud servers, database servers

[1582] Software: Flask (server-side processing), TensorFlow (sentiment analysis), generative AI model

[1583] Function: Analyzes data received from users and uses generative AI to generate content and interactive elements that are sent to the user's device.

[1584] Program processing

[1585] User Registration and Settings

[1586] When a user installs and launches the application on their device, a registration screen is displayed. The user enters basic information, which is then sent to the server. Next, the user selects the genre of interest, and the information is sent to the server.

[1587] Content viewing and sentiment analysis

[1588] When a user plays video content, the device's camera and microphone are used to capture the user's facial expressions and voice. The data is sent to a server and analyzed using TensorFlow and other tools. The results of the emotion analysis are fed into the generative AI.

[1589] Recommendation Generation

[1590] Based on the analysis results, the generative AI recommends the next appropriate content. In this case, the generative AI model generates the most appropriate content based on the user's interests and emotional state. For example, if the user is laughing, it will recommend a comedy movie.

[1591] Providing interactive content

[1592] The generative AI provides interactive quizzes and polls based on the user's emotional state. An example of a prompt might be, "The user is currently watching a romantic comedy movie and is laughing. Please generate the next recommended content and related quiz."

[1593] Learning history and feedback

[1594] The server stores users' viewing history and emotional data, which can then be used to further personalize future recommendations and interactive content. Users can receive this feedback in real time through the app.

[1595] Specific examples

[1596] For example, if a user is laughing while watching a romantic comedy movie, the emotion engine will recognize that laughter and the generative AI will recommend the next comedy movie to watch, or provide a quiz related to that particular scene, allowing the user to continue their learning and entertainment experience while having fun.

[1597] This allows the present invention to respond to the user's emotions and provide a personalized learning and entertainment experience.

[1598] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1599] Step 1:

[1600] The user installs and launches the application. A registration screen appears on the user's device, and the user enters basic information (such as name and email address) and submits it. The entered information is sent to the server via the Internet.

[1601] Input: User basic information

[1602] Output: User information stored in the user database on the server

[1603] Step 2:

[1604] A screen is displayed where the user can select the genre and information they are interested in. The user selects the genre they want to learn about (e.g., comedy, action, etc.) and submits the selected information. The submitted information is received by the server and stored in a database.

[1605] Input: User-selected genre information

[1606] Output: Genre information stored in a database on the server

[1607] Step 3:

[1608] The user plays the video content. When playback starts, the device's camera and microphone are activated to capture the user's facial expressions and voice in real time. This data is then sent to the server.

[1609] Input: User's facial expression and voice data

[1610] Output: User emotion data sent to the server

[1611] Step 4:

[1612] The server uses TensorFlow to analyze the received user facial expression and voice data. The analysis results in the user's emotional state (happiness, surprise, sadness, etc.). The analyzed emotional data is passed to the generation AI.

[1613] Input: User's facial expression and voice data

[1614] Output: Analyzed user emotion data

[1615] Step 5:

[1616] The AI ​​generator recommends the next piece of content to be played based on emotional data and the user's selected genre. The AI ​​generator continues to learn by using appropriate prompts. For example, the prompt might read, "The user is watching a comedy movie and laughing. Please generate the next piece of content to recommend."

[1617] Input: Parsed emotion data, genre information, prompt sentence

[1618] Output: Recommended next content information

[1619] Step 6:

[1620] The server sends the recommended content information to the user's terminal and displays it as a list of content for the user to view next. The user can then select the content to view next.

[1621] Input: Recommended content information

[1622] Output: The following content list displayed on the user's device

[1623] Step 7:

[1624] While the user is watching the next content, the server uses generative AI to generate interactive quizzes and polls, for example, generating quizzes related to specific scenes in a movie and sending them to the user.

[1625] Input: User viewing content information and emotion data

[1626] Output: Interactive quizzes and polls

[1627] Step 8:

[1628] Users participate in interactive quizzes and polls, and the results are sent to the server, which analyzes the results and stores them in the user's learning history.

[1629] Input: User quiz or poll answers

[1630] Output: Saved learning history and analysis data

[1631] Step 9:

[1632] The server uses the stored learning history and emotional data to generate data to further personalize future recommendations and interactive elements, and this feedback is sent to the user in real time.

[1633] Input: Learning history and emotion data

[1634] Output: Personalized feedback

[1635] In this way, the invention allows users to have a personalized learning and entertainment experience that adapts to their emotions.

[1636] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1637] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1638] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1639] [Fourth embodiment]

[1640] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1641] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1642] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1643] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1644] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1645] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1646] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1647] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1648] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1649] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1650] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1651] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1652] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1653] This invention relates to a system that allows users to practice foreign languages ​​on a daily basis through communication with virtual foreigners. This system is designed to allow users to select the language they want to learn and to message and voice chat with the virtual foreigners in that language.

[1654] System configuration

[1655] This system consists of a user's device and a server. User devices include smartphones, tablets, and PCs. The server uses a generation AI to generate messages from virtual foreigners and send them to users.

[1656] System Operation

[1657] User registration and language selection

[1658] When a user installs and launches the app, a registration screen appears on the user's device. The user enters basic information such as their name and email address to create an account. A screen is also displayed where the user can select the language they want to learn. For example, if the user selects "French," that information is sent to the server.

[1659] Message Generation

[1660] The server receives the user's selected language information and sends a request to the AI ​​to generate a message in that language. Based on the input, the AI ​​generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?). These messages are designed to include content relevant to the user's daily life.

[1661] Message Delivery and User Response

[1662] The generated message is sent from the server to the user's device. The user's device displays the received message on the screen, and the user can reply to it. For example, if the user replies "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?), the message is sent back to the server.

[1663] The server receives the user's reply and instructs the generation AI to generate the next message. The generation AI generates a new message and sends it back to the user's device. In this way, the message exchange between the user and the virtual alien continues.

[1664] Real-time voice chat

[1665] When a user selects "Voice Chat," a request is sent to the server. The server asks the generation AI to generate voice data in real time. The generation AI generates voice messages such as "Je vais bien, merci!" (I'm fine, thank you!) and sends them to the user's device via the server.

[1666] The user's device plays the received voice data, and the user responds through the microphone. The voice data is then sent back to the server, where the AI ​​generates new voices to continue the communication.

[1667] Learning history and feedback

[1668] The server stores the user's messages and voice chat logs and uses them to evaluate their learning progress. The evaluation results are generated as feedback, including the user's strengths and areas for improvement, and sent to the user's device. By receiving this feedback, the user can check their learning progress and determine which areas they should focus on next.

[1669] Specific examples

[1670] 1. User registration and language selection

[1671] A user opens the app, enters the required registration information, and selects "French" as the language they want to learn.

[1672] The terminal sends information to the server, which receives it.

[1673] 2. Message Creation

[1674] The server asks the generation AI to generate a message in French, and the generation AI generates the message "Bonjour! Comment ça va aujourd'hui?"

[1675] 3. Message Delivery and User Response

[1676] The server sends the generated message to the terminal, and the user receives and replies to the message.

[1677] The device sends a reply to the server, and the server again instructs the generation AI to generate the next message.

[1678] 4. Real-time voice chat

[1679] A user initiates a voice chat and the terminal sends a request to the server.

[1680] The server requests the generation AI to generate voice and sends the generated voice to the user's device.

[1681] 5. Learning history storage and feedback

[1682] The server stores messages and voice chat logs and evaluates learning progress.

[1683] Based on the learning progress, the server generates feedback and sends it to the device.

[1684] In this way, the system of the present invention provides an environment in which users can practice a foreign language on a daily basis and progress in their learning efficiently.

[1685] The processing flow will be explained below.

[1686] Step 1:

[1687] The user installs and launches the app, and the account registration screen appears on the device screen.

[1688] Step 2:

[1689] A user creates an account by entering basic information such as name and email address, and then selects the language they want to learn.

[1690] Step 3:

[1691] The terminal sends the input information to the server, which receives it and stores it in a database.

[1692] Step 4:

[1693] The server sends a message generation request to the AI ​​based on the user's selected language, and the AI ​​generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?).

[1694] Step 5:

[1695] The server sends the generated message to the user's terminal, and the terminal displays the received message on the user's screen.

[1696] Step 6:

[1697] The user types a reply to the received message (e.g., "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?)) and the terminal sends the reply to the server.

[1698] Step 7:

[1699] The server receives the user's reply and instructs the generation AI to generate the next message. The generation AI generates a new message, which the server then sends to the user's device.

[1700] Step 8:

[1701] The user selects "Voice Chat." The device sends a voice chat start request to the server.

[1702] Step 9:

[1703] The server requests real-time voice generation from the generation AI, the generation AI generates the voice data, and the server sends it to the user's device.

[1704] Step 10:

[1705] The terminal plays the received voice data, the user responds by voice through the microphone, and the terminal transmits the voice data to the server.

[1706] Step 11:

[1707] The server analyzes the received voice data and issues instructions to the generation AI to generate the next voice response. The server then sends the generated voice data back to the user's device.

[1708] Step 12:

[1709] The server stores all messages and voice chat logs in a database, evaluates learning progress, and generates feedback.

[1710] Step 13:

[1711] The device receives feedback from the server and displays it to the user, who then checks the feedback and uses it in their next learning.

[1712] Example 1

[1713] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1714] In language learning, it is effective to practice in everyday communication situations. However, in reality, there are few opportunities to speak a foreign language on a daily basis, making efficient learning difficult. Another issue is that there is no feedback based on individual learning progress, making it unclear which areas need to be strengthened. Furthermore, there are few systems that allow real-time audio interaction, making it difficult to experience actual conversation.

[1715] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1716] In this invention, the server includes a means for allowing a user to select a language they wish to learn, a means for generating a message for a virtual character using a generation AI, a means for sending the generated message to the user's device, and a generation AI means for generating the next message based on the user's reply. This provides users with opportunities to speak a foreign language on a daily basis, allowing them to progress in their studies efficiently. Furthermore, by including a means for generating voice in real time and performing real-time voice communication, it is possible to provide a real conversation experience and enhance the effectiveness of learning. Furthermore, by including a means for saving the user's learning progress data and evaluating the progress, and a means for providing feedback based on the evaluation, it is possible to improve the quality of learning through individualized feedback.

[1717] "Generative AI" is a system that uses artificial intelligence to generate text and speech.

[1718] A "virtual person" is a character that does not exist in reality, but is generated by AI and interacts with the user through messages and voice.

[1719] A "user's terminal" is a device used by a user to access the system, such as a smartphone, tablet, or PC.

[1720] A "message" is text data generated by the generation AI and sent to the user.

[1721] "Audio data" refers to audio data generated by the generation AI and that can be heard by the user.

[1722] "Real-time voice communication" is a communication method in which a user and a virtual character converse in real time through voice.

[1723] "Learning progress data" is a record of the conversations and exercises that a user has conducted through the system.

[1724] "Feedback" is information that indicates the user's learning progress and areas for improvement, and is generated based on the learning progress data.

[1725] "Server means" refers to a server for generating messages from the generation AI and storing and processing data.

[1726] This invention relates to a system that allows users to learn a foreign language through communication with a virtual character. The system consists of a server and a user's terminal. The user's terminal can be a smartphone, tablet, PC, or other device. The server uses a generative AI model to generate messages for the virtual character and send them to the user.

[1727] Basic system configuration

[1728] The system includes the following means:

[1729] 1. A way for users to choose the language they want to learn

[1730] 2. A method for generating messages from virtual characters using generative AI

[1731] 3. A means of sending the generated message to the user's terminal

[1732] 4. A way for users to reply to messages they receive

[1733] 5. Generative AI method to generate the next message based on the user's reply

[1734] 6. A means to send the next generated message back to the user

[1735] 7. Means for generating audio in real time and performing real-time audio communication

[1736] 8. A means of storing user learning progress data and assessing progress

[1737] 9. Means of providing feedback based on the assessment

[1738] Hardware and software used

[1739] The main components of this system include the user's device, a server, and a generative AI model. Specifically, the following hardware and software are used:

[1740] User devices: smartphones, tablets, PCs, etc. These devices run applications and provide an interface with the user.

[1741] Server: A server that stores data, processes data, and invokes generative AI models.

[1742] Generative AI models: Artificial intelligence models such as OpenAI's GPT-4. These models generate text and speech.

[1743] Example of operation

[1744] 1. User registration and language selection

[1745] The user installs and launches the app. The device displays a registration screen where the user enters their name and email address to create an account. The device also displays a screen where the user can select the language they want to learn, and the selection is sent to the server.

[1746] 2. Message Creation

[1747] The server receives the user's selection and sends a request to the AI ​​to generate a message in that language. The AI ​​generates the message based on the prompt.

[1748] Example prompt sentence:

[1749] Prompt: "Ask the user 'Hello, how are you today?' as an everyday greeting in French."

[1750] Produced message: "Bonjour! Comment ça va aujourd'hui?"

[1751] The generated message is sent from the server to the user's terminal.

[1752] 3. Message Delivery and User Response

[1753] The device displays the received message to the user. The user replies to the received message, for example, by typing "Ça va bien, merci! Et toi?" The reply data is sent to the server, which again requests the generation AI to generate the next message.

[1754] 4. Real-time voice chat

[1755] When a user selects voice chat, the request is sent to the server. The server then asks the AI ​​to generate voice data, which is then sent to the device so the user can hear it. The user's response is also sent to the server, and new voice data is generated.

[1756] 5. Learning history storage and feedback

[1757] The server stores the user's messages and voice data, evaluates their progress, and generates feedback based on the evaluation, which is sent to the device for the user to review.

[1758] As a result, this system provides an environment in which users can practice a foreign language on a daily basis and progress their learning efficiently.

[1759] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1760] Step 1: User registration and language selection

[1761] The user installs and launches the app.

[1762] The device displays the registration screen. The user enters their name and email address. This input data is saved as the user's account information.

[1763] The device displays a language selection screen, and the user selects the language they want to learn. The selected data, e.g., "French," is sent to the server.

[1764] The server receives this information and stores it in a database as the user's language preference. The output is a registration success message and the selected language information.

[1765] Step 2: Message Generation

[1766] After the server receives the user's language selection information, it sends a message generation request to the generative AI model. The input is the prompt sentence "'Hello, how are you today?' as a daily greeting in French."

[1767] The generative AI model generates a message based on the prompt. The generated message, "Bonjour! Comment ça va aujourd'hui?", is output.

[1768] The server receives this generated message and sends it to the user's terminal. The output is the generated message data.

[1769] Step 3: Message Delivery and User Response

[1770] The terminal displays the received message "Bonjour! Comment ça va aujourd'hui?" to the user.

[1771] The user replies to this message. As input, the user types the reply: "Ça va bien, merci! Et toi?"

[1772] The terminal sends this reply data to the server. The output is the reply message data.

[1773] The server receives the reply data and again asks the generative AI model to generate the next message, including the user's reply as input.

[1774] The generative AI model generates a new message, for example, "Je vais bien, merci!" The server receives this generated message data and sends it to the user's device. The output is the new message data.

[1775] Step 4: Real-time voice chat

[1776] The user selects voice chat. As input, a voice chat start request is sent from the device to the server.

[1777] The server asks the generative AI model to generate voice data in real time. As input, the generative AI receives a message prompt such as "Je vais bien, merci!" (I'm fine, thank you!).

[1778] The generative AI model generates voice data, which is then received by the server and sent to the user's device. The output is the generated voice data.

[1779] The terminal plays the received voice data, and the user responds. The user's voice data is included as input.

[1780] The device sends this voice data to the server, which then asks the AI ​​model to generate new voice data. This process is repeated. The output is new voice data.

[1781] Step 5: Learning history and feedback

[1782] The server stores user messages and voice chat logs, which contain past interaction data as input.

[1783] The server evaluates the user's learning progress based on the stored data, and the output is the evaluation result data.

[1784] The server generates feedback based on the evaluation results and sends it to the user's terminal. The output is feedback data.

[1785] The device displays feedback to the user, allowing the user to see their learning progress.

[1786] (Application example 1)

[1787] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1788] Conventional foreign language learning systems lack sufficient support for users to acquire practical language skills that can be used in daily work. Furthermore, there were no systems for customer support in foreign languages ​​that could respond quickly and accurately to user inquiries. As a result, it was difficult to provide efficient support for users learning foreign languages ​​or in business environments where foreign languages ​​are required.

[1789] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1790] In this invention, the server includes means for generating a response to a user's inquiry in a foreign language, means for transmitting the generated response to the user's terminal and resolving the user's inquiry, and means for the user to select a language they wish to learn. This enables the user to efficiently improve their daily work and practical language skills while receiving customer support in a foreign language.

[1791] "Means for user to select a language they wish to learn" means a device or software interface that allows a user to select a particular language they wish to learn.

[1792] "Means for generating messages from virtual foreigners using generation AI" refers to a function or system that uses generation AI to create messages from virtual foreigners in a selected language.

[1793] "Means for sending the generated message to the user's terminal" refers to communication means or software for delivering the generated message to the device used by the user.

[1794] "Means for replying to messages received by a user" refers to a device or software interface that allows a user to respond to a message received by a user.

[1795] "AI generation means for generating the next message based on the user's reply" refers to an AI system that generates a message to continue the next dialogue based on the user's reply.

[1796] The "means for sending the next generated message to the user again" refers to a communication means or software for sending the newly generated message again to the user's terminal.

[1797] "Means for generating voice in real time and conducting voice chat" refers to a function or system for generating voice data in real time and conducting voice chat between a user and a virtual foreigner.

[1798] "Means for saving a user's learning history and evaluating the user's learning progress" refers to a function or system that saves a user's message and voice chat logs and evaluates the user's learning progress based on them.

[1799] "Means for providing feedback based on evaluation" refers to a function or system for evaluating a user's strengths and areas for improvement based on the saved learning history and providing the user with feedback based on that evaluation.

[1800] The "means for generating a response to a user's inquiry in a foreign language" refers to a system or device for generating an appropriate response in a selected foreign language in response to a user's inquiry.

[1801] "Means for sending the generated response to the user's terminal and resolving the user's inquiry" refers to communications means or software for sending the generated response to the user's terminal and resolving the inquiry.

[1802] This invention realizes a system that allows users to practice foreign languages ​​through conversations with virtual foreigners and simultaneously provides user support. This system utilizes a generation AI that generates messages and voice chats in the language selected by the user. It can also respond to user inquiries.

[1803] System configuration

[1804] This system consists of a user's device (smartphone, tablet) and a server. The server uses a generation AI to generate messages and voice messages from virtual foreigners and send them to the user's device.

[1805] Hardware and Software Configuration

[1806] Hardware:

[1807] User devices: smartphones, tablets

[1808] Server: Cloud infrastructure such as AWS, GCP, etc.

[1809] software:

[1810] Generation AI: OpenAI GPT-3

[1811] Web framework: Flask

[1812] Data transmission / reception: JSON format

[1813] System Operation

[1814] User registration and language selection

[1815] When a user installs and launches the app, a registration screen appears on the user's device. The user enters basic information such as their name and email address to create an account. A screen is also displayed where the user can select the language they want to learn. For example, if the user selects "French," that information is sent to the server.

[1816] Message Creation and Transmission

[1817] The server receives the user's selected language information and sends a request to the AI ​​to generate a message in that language. Based on the input, the AI ​​generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?). These messages are sent from the server to the user's device and displayed.

[1818] User response and next message generation

[1819] When a user receives a message and replies, the reply is sent to the server. The server receives the user's reply and instructs the generation AI to generate the next message. The generated next message is then sent back to the user's device.

[1820] Real-time voice chat

[1821] When a user selects "Voice Chat," a request is sent to the server. The server asks the generation AI to generate voice data in real time. The generation AI generates voice such as "Je vais bien, merci!" (I'm fine, thank you!) and sends it to the user's device via the server. The user's device then plays back the received voice data.

[1822] Learning history and feedback

[1823] The server stores the user's messages and voice chat logs and evaluates their learning progress based on them. The evaluation results are generated as feedback including the user's strengths and areas for improvement, and are sent back to the user's device.

[1824] Specific examples

[1825] 1. User registration and language selection

[1826] User: Opens the app, fills in the required registration information, and selects "French" as the language they want to learn.

[1827] Terminal: Sends information to the server, which receives it.

[1828] 2. Message Creation and Transmission

[1829] Server: Asks the generation AI to generate a message in French, and the generation AI generates the message "Bonjour! Comment ça va aujourd'hui?"

[1830] 3. User response and next message generation

[1831] User: Receives and replies to messages.

[1832] Server: Receives the reply and asks the generation AI for the next message.

[1833] 4. Real-time voice chat

[1834] User: Starts a voice chat and the device sends a request to the server.

[1835] Server: Requests the generation AI to generate speech and sends the generated speech to the user's device.

[1836] 5. Learning history storage and feedback

[1837] Server: Stores messages and voice chat logs and evaluates learning progress.

[1838] Server: Generates feedback and sends it to the device.

[1839] Prompt Sentence Examples

[1840] Example of a user question: "My payment didn't go through. Can you help me?"

[1841] Example prompt for the AI ​​generator: English: My payment didn't go through. Can you help me?

[1842] This system provides users with an environment in which they can practice foreign languages ​​on a daily basis and progress their learning efficiently, while also enabling them to receive prompt customer support in their foreign language.

[1843] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1844] Step 1: User registration and language selection

[1845] The user installs and launches the app. They enter basic information such as their name and email address to create an account. They are also shown a screen where they can select the language they want to learn. For example, if they select "French," that information is sent from the user's device to the server. The server then stores the received information in a database.

[1846] Input: User's basic information (name, email address), selected language

[1847] Output: User information and selected language are saved on the server side

[1848] Step 2: First message generation

[1849] After receiving the selected language information, the server sends a request to the AI ​​to generate a message in that language. Based on the input, the AI ​​generates a typical message such as "Bonjour! Comment ça va aujourd'hui?" The server then sends the generated message to the user's device.

[1850] Input: User's preferred language information

[1851] Output: The generated message in the selected language

[1852] Step 3: View and reply to messages

[1853] The user's device displays the received message. The user checks the received message and replies. For example, if the user types "Ça va bien, merci! Et toi?", the message is sent from the device to the server. The server saves the received user message and uses it as input data for the next generation request.

[1854] Input: User's reply message

[1855] Output: User's reply message stored on the server

[1856] Step 4: Generate the next message

[1857] The server sends a request to the generation AI to generate the next message based on the user's reply message. The generation AI generates a new message based on the input. For example, a response message such as "Je vais bien, merci!" is generated. This is then sent back to the user's device via the server.

[1858] Input: User's reply message

[1859] Output: The following message generated by the generation AI

[1860] Step 5: Real-time voice chat

[1861] When a user selects "Voice Chat," a request is sent from the user's device to the server. The server asks the generation AI to generate voice data in real time. The generation AI generates voice data such as "Je vais bien, merci!" and sends it to the user's device via the server. The user's device plays the received voice data and sends the voice input from the user's microphone back to the server.

[1862] Input: User's voice request

[1863] Output: Voice data generated by the generative AI

[1864] Step 6: Save your learning history and provide feedback

[1865] The server stores the user's messages and voice chat logs and uses them to evaluate their learning progress. The evaluation results are generated as feedback including the user's strengths and areas for improvement, and are sent back to the user's device. The user can then use this feedback to set their next learning goal.

[1866] Input: User's message history, voice chat log

[1867] Output: Feedback data

[1868] Step 7: Responding to user inquiries

[1869] When a user makes a query, for example, "My payment didn't go through. Can you help me?", the query is sent from the user's device to the server. The server then sends a request to the generation AI to generate a response based on the query. For example, a response such as "Sure, let's check your transaction. Can you provide me with the transaction ID?" is generated and sent to the user's device. The user can then use this response to ask further questions.

[1870] Input: User's query message

[1871] Output: The response message generated by the generation AI

[1872] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1873] This invention relates to a system that recognizes a user's emotions and adapts personalized feedback and conversation content based on those emotions. The system allows users to select the language they want to learn, and by combining an emotion engine with a generation AI that communicates with a virtual foreigner in that language, the system promotes more effective learning.

[1874] System configuration

[1875] This system consists of a user's device, a server, a generation AI, and an emotion engine. User devices include smartphones, tablets, and PCs. The server manages the generation AI and emotion engine, and controls message generation and voice chat for the virtual aliens.

[1876] System Operation

[1877] User registration and language selection

[1878] When a user installs and launches the app, a registration screen appears on the user's device. The user enters their basic information and creates an account. Next, a screen appears asking the user to select the language they want to learn. For example, if the user selects "French," that information is sent to the server.

[1879] Message Generation and Emotion Recognition

[1880] The server receives the user's selected language information and sends a request to the generation AI to generate a message in that language. At that time, the emotion engine recognizes the user's emotional state and provides feedback to the generation AI. The generation AI reflects the feedback from the emotion engine and generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?).

[1881] Message Delivery and User Response

[1882] The generated message is sent from the server to the user's device. The user's device displays the received message on the screen, and the user can reply to it. For example, if the user replies "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?), the message is sent back to the server.

[1883] The server receives the user's reply and analyzes the user's emotional state using the emotion engine. The generation AI generates the next message based on the analysis results from the emotion engine and sends it back to the user.

[1884] Real-time voice chat and emotional adaptation

[1885] When a user selects "Voice Chat," a request is sent to the server. The server uses the generative AI and emotion engine to generate voice data in real time. For example, if the emotion engine recognizes that the user is nervous, the generative AI will generate a voice response with a relaxing tone and content. This allows the user to continue the conversation without stress.

[1886] Learning history and feedback

[1887] The server stores the user's messages and voice chat logs and evaluates their learning progress using an emotion engine. The evaluation results are then generated as feedback that takes into account the user's emotional state and sent to the user's device. By receiving this feedback, the user can check their learning progress and determine which areas they should focus on next.

[1888] Specific examples

[1889] 1. User registration and language selection

[1890] A user opens the app, enters the required registration information, and selects "French" as the language they want to learn.

[1891] The terminal sends information to the server, which receives it.

[1892] 2. Message Generation and Emotion Recognition

[1893] The server asks the generation AI to generate a message in French, and the emotion engine recognizes the user's emotions.

[1894] The generation AI generates the message "Bonjour! Comment ça va aujourd'hui?" and the server sends it to the user's device.

[1895] 3. Message Delivery and User Response

[1896] The device receives the message and displays it to the user.

[1897] The user replied, "Ça va bien, merci! Et toi?"

[1898] The device sends a reply to the server, which then analyzes the user's emotions through an emotion engine.

[1899] 4. Real-time voice chat and emotional adaptation

[1900] A user initiates a voice chat.

[1901] The device sends a request to the server, and the emotion engine recognizes the user's emotions.

[1902] The generating AI generates relaxing sounds, and the server sends the sound data to the user's device.

[1903] 5. Learning history storage and feedback

[1904] The server stores messages and voice chat logs and evaluates learning progress using an emotion engine.

[1905] Based on the evaluation, feedback is generated, received by the device, and displayed to the user.

[1906] In this way, the system of the present invention provides an environment for learning a foreign language more effectively while taking into consideration the user's feelings.

[1907] The processing flow will be explained below.

[1908] Step 1:

[1909] The user installs and launches the app, and the account registration screen appears on the device screen.

[1910] Step 2:

[1911] A user creates an account by entering basic information such as name and email address, and then selects the language they want to learn.

[1912] Step 3:

[1913] The terminal sends the input information to the server, which receives it and stores it in a database.

[1914] Step 4:

[1915] The server sends a message generation request to the AI ​​based on the user's selected language, while the emotion engine recognizes the user's emotional state based on their past history and real-time input.

[1916] Step 5:

[1917] The generative AI reflects feedback from the emotion engine to generate messages such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?).

[1918] Step 6:

[1919] The server sends the generated message to the user's terminal, and the terminal displays the received message on the user's screen.

[1920] Step 7:

[1921] The user types a reply to the received message (e.g., "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?)) and the terminal sends the reply to the server.

[1922] Step 8:

[1923] The server receives the user's reply and analyzes the user's emotional state through the emotion engine. The generation AI generates the next message based on the analysis results from the emotion engine.

[1924] Step 9:

[1925] The server then sends the generated next message back to the user's terminal, which receives the message and displays it to the user.

[1926] Step 10:

[1927] The user selects "Voice Chat." The device sends a voice chat start request to the server.

[1928] Step 11:

[1929] The server uses the generation AI and emotion engine to request real-time voice generation. The generation AI generates the voice data, and the server sends it to the user's device.

[1930] Step 12:

[1931] The terminal plays the received voice data, the user responds by voice through the microphone, and the terminal transmits the voice data to the server.

[1932] Step 13:

[1933] The server analyzes the received voice data using an emotion engine and issues instructions to the generation AI to generate the next voice response. The server then sends the generated voice data back to the user's device.

[1934] Step 14:

[1935] The server stores all messages and voice chat logs in a database, and uses an emotion engine to evaluate learning progress and generate feedback.

[1936] Step 15:

[1937] The device receives feedback from the server and displays it to the user, who then checks the feedback and uses it in their next learning.

[1938] Example 2

[1939] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1940] Conventional language learning systems lack the ability to adapt feedback and communication content to take into account the user's emotional state, making effective learning difficult. Furthermore, real-time voice chat and feedback based on learning progress are limited, making individual optimization insufficient. This can easily discourage users from learning, preventing efficient language acquisition.

[1941] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1942] In this invention, the server includes emotion recognition means for recognizing the user's emotional state and generating messages and voices according to that state, means for saving the user's learning history and evaluating the learning progress, and means for providing feedback based on the evaluation. This makes it possible to provide effective feedback and communication adapted to the user's emotional state and to provide individually optimized learning support through real-time voice chat.

[1943] The "means for the user to select the language they wish to learn" is a function that allows the user to select the language they wish to learn from a list of languages ​​provided within the application.

[1944] "Generative AI" is artificial intelligence that uses natural language processing technology to generate human-like dialogue.

[1945] The "means for generating messages of virtual foreigners" is a function that uses a generation AI to create messages of virtual foreigners in a language selected by the user.

[1946] The "means for transmitting the generated message to the user's terminal" is a function for transferring the message from the server to the user's terminal.

[1947] The "means for replying to a message received by the user" is a function for creating and sending a reply on the terminal in response to a message received by the user.

[1948] The "generative AI means for generating the next message based on the user's reply" is a function that takes the user's reply as input and generates the next dialogue message accordingly.

[1949] "Means for sending the next generated message back to the user" is a function for sending the next message created by the generation AI back to the user's device.

[1950] "Means for generating voice in real time and conducting voice chat" refers to a function that uses generation AI and voice synthesis technology to generate voice in real time and engage in voice conversation with the user.

[1951] "Emotion recognition means that recognizes the user's emotional state and generates messages and voices according to that state" is a function that analyzes emotions from the user's facial expressions and text input, and generates dialogue content according to those emotions.

[1952] The "means for saving the user's learning history and evaluating the learning progress" is a function for saving a record of the user's interactions and activities and evaluating the learning progress based on that record.

[1953] The "means for providing feedback based on evaluation" is a function that uses the evaluation results of the learning progress to provide the user with useful advice and feedback on what they should focus on next.

[1954] This invention relates to a system that recognizes a user's emotions and adapts personalized feedback and conversation content based on those emotions. The system allows users to select the language they want to learn, and by combining an emotion engine with a generation AI that communicates with a virtual foreigner in that language, the system promotes more effective learning.

[1955] System configuration

[1956] This system consists of a user's device, a server, a generation AI, and an emotion engine. User devices include smartphones, tablets, and PCs. The server manages the generation AI and emotion engine, and controls message generation and voice chat for the virtual aliens.

[1957] The specific hardware and software used is as follows:

[1958] Hardware: Smartphones, tablets, computers

[1959] software:

[1960] Generative AI: Natural language processing models such as GPT-4

[1961] Emotion engine: Various emotion analysis APIs (e.g., Microsoft Azure emotion recognition API)

[1962] Server: Database and backend server (e.g. AWS EC2 server, Node.js backend)

[1963] System Operation

[1964] User registration and language selection

[1965] When a user installs and launches the app, a registration screen appears on the user's device. The user enters their basic information and creates an account. A screen is then displayed in which the user can select the language they want to learn. For example, if they select "French," that information is sent to the server. The information received by the server is stored in a database.

[1966] Message Generation and Emotion Recognition

[1967] The server requests the generation AI to generate a message based on the language information selected by the user. At that time, the emotion engine recognizes the user's emotional state and provides feedback to the generation AI. Based on the feedback from the emotion engine, the generation AI generates a message such as "Bonjour! Comment ça va aujourd'hui?" (Hello, how are you today?). The server then sends the generated message to the user's device.

[1968] Message Delivery and User Response

[1969] The device displays the received message on the screen, and the user replies to it. For example, if the user replies "Ça va bien, merci! Et toi?" (I'm fine, thank you! How about you?), the message is sent to the server again. The server receives the user's reply and analyzes the user's emotional state using an emotion engine. The generation AI generates the next message based on the analysis results from the emotion engine and sends it back to the user.

[1970] Real-time voice chat and emotional adaptation

[1971] When a user selects "Voice Chat," a request is sent to the server. The server uses the generative AI and emotion engine to generate voice data in real time. For example, if the emotion engine recognizes that the user is nervous, the generative AI will generate a voice response with a relaxing tone and content. This allows the user to continue the conversation without stress.

[1972] Learning history and feedback

[1973] The server stores the user's messages and voice chat logs and evaluates their learning progress using an emotion engine. The evaluation results are then generated as feedback that takes into account the user's emotional state and sent to the user's device. By receiving this feedback, the user can check their learning progress and determine which areas they should focus on next.

[1974] Specific examples

[1975] 1. User registration and language selection

[1976] A user opens the app, enters the required registration information, and selects "French" as the language they want to learn.

[1977] The terminal sends information to the server, which receives it.

[1978] 2. Message Generation and Emotion Recognition

[1979] The server asks the generation AI to generate a message in French, and the emotion engine recognizes the user's emotions.

[1980] The generation AI generates the message "Bonjour! Comment ça va aujourd'hui?" and the server sends it to the user's device.

[1981] 3. Message Delivery and User Response

[1982] The device receives the message and displays it to the user.

[1983] The user replied, "Ça va bien, merci! Et toi?"

[1984] The device sends a reply to the server, which then analyzes the user's emotions through an emotion engine.

[1985] 4. Real-time voice chat and emotional adaptation

[1986] A user initiates a voice chat.

[1987] The device sends a request to the server, and the emotion engine recognizes the user's emotions.

[1988] The generating AI generates relaxing sounds, and the server sends the sound data to the user's device.

[1989] 5. Learning history storage and feedback

[1990] The server stores messages and voice chat logs and evaluates learning progress using an emotion engine.

[1991] Based on the evaluation, feedback is generated, received by the device, and displayed to the user.

[1992] This system takes into account the user's emotions and provides an effective dialogue format, enabling a deeper learning experience.

[1993] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1994] Program processing steps

[1995] User registration and language selection

[1996] Step 1: Launch the app

[1997] Input: None

[1998] Output: Display of registration screen

[1999] Specific operation: The user launches the app on their smartphone (or tablet, or PC). The device displays the registration screen.

[2000] Step 2: Enter your registration information

[2001] Input: User's basic information (e.g. name, email address, password)

[2002] Output: User information entered

[2003] Specific behavior: The user enters the basic information displayed on the registration screen.

[2004] Step 3: Language Selection

[2005] Input: Select the language you want to learn (e.g. French)

[2006] Output: Selected language information

[2007] What it does: The user selects the language they want to learn from the displayed list of languages.

[2008] Step 4: Send information

[2009] Input: User basic information and selected language

[2010] Output: Data sent to the server

[2011] Specific operation: The device sends the user's input information and selected language information to the server.

[2012] Step 5: Save Data

[2013] Input: User information and selected language information

[2014] Output: Data stored in the database

[2015] Specific operation: The server stores the received user information and language selection information in a database.

[2016] Message Generation and Emotion Recognition

[2017] Step 6: Message Production Request

[2018] Input: Selected language information

[2019] Output: Message generation request to the generation AI

[2020] Specific behavior: The server requests the generation AI to generate a greeting message in the selected language (e.g., French).

[2021] Step 7: Emotion Recognition

[2022] Input: User history and context

[2023] Output: Evaluation of the user's emotional state

[2024] Specific operation: The server uses the emotion engine to evaluate the user's emotional state. For example, it analyzes the user's typing speed and facial recognition camera.

[2025] Step 8: Send your feedback

[2026] Input: Evaluation result of emotion engine

[2027] Output: Feedback to the generative AI

[2028] Specific behavior: The emotion engine sends feedback to the generative AI based on the user's emotional state.

[2029] Step 9: Message Generation

[2030] Input: Prompt text reflecting feedback

[2031] Output: The generated message

[2032] What it does: The generative AI generates a message based on feedback from the emotion engine. Example: "Bonjour! Comment ça va aujourd'hui?"

[2033] Step 10: Receiving a message

[2034] Input: The generated message

[2035] Output: Data sent to the user's device

[2036] Specific operation: The server sends the generated message to the user's terminal.

[2037] Message Delivery and User Response

[2038] Step 11: Displaying a message

[2039] Input: The message sent

[2040] Output: Message displayed on the screen

[2041] Specific operation: The device displays the received message on the screen.

[2042] Step 12: User response

[2043] Input: User reply (e.g. "Ça va bien, merci! Et toi?")

[2044] Output: User response data

[2045] Specific behavior: The user types a reply to the displayed message.

[2046] Step 13: Send a response message

[2047] Input: User reply data

[2048] Output: Response data sent to the server

[2049] Specific operation: The device sends the user's reply to the server.

[2050] Step 14: Sentiment Analysis

[2051] Input: User reply data

[2052] Output: Evaluation result of emotion engine

[2053] Specific operation: The server analyzes the user's message received by the emotion engine and evaluates the user's emotional state.

[2054] Real-time voice chat and emotional adaptation

[2055] Step 15: Voice Chat Selection

[2056] Input: Voice chat start request

[2057] Output: Request data to the server

[2058] What happens: A user selects the "Voice Chat" option in your app and sends a request.

[2059] Step 16: Receiving a request

[2060] Input: Voice chat start request

[2061] Output: Request processing on the server side

[2062] Specific operation: The terminal sends a request to the server, and the server receives the request.

[2063] Step 17: Real-time audio data generation

[2064] Input: User's emotional state and historical data

[2065] Output: Audio data generation request

[2066] Specific operation: The server uses the generation AI and emotion engine to generate the voice data required for dialogue in real time.

[2067] Step 18: Emotional Adaptation

[2068] Input: Evaluation result of emotion engine

[2069] Output: Feedback to the generative AI

[2070] Specific operation: The emotion engine analyzes the user's emotional state (e.g., nervousness) and provides the corresponding voice tone and content to the generation AI.

[2071] Step 19: Sending audio data

[2072] Input: Generated audio data

[2073] Output: Sends audio data to the user's device

[2074] Specific operation: The generation AI generates a voice response with a relaxing tone and content, and the server sends the voice data to the user's device.

[2075] Learning history and feedback

[2076] Step 20: Logging

[2077] Input: User messages and voice chat data

[2078] Output: Save log data

[2079] What it does: The server stores logs of users' messages and voice chats.

[2080] Step 21: Assess your learning progress

[2081] Input: Saved log data

[2082] Output: Learning progress assessment results

[2083] Specific operation: The emotion engine analyzes the saved logs and evaluates the user's learning progress.

[2084] Step 22: Generate evaluation results

[2085] Input: Learning progress assessment results

[2086] Output: Feedback data

[2087] Specific operation: The generative AI generates feedback based on the evaluation results of the emotion engine.

[2088] Step 23: Send feedback

[2089] Input: Feedback data

[2090] Output: Send feedback to the user's device

[2091] Specific operation: The server sends the generated feedback to the user's device.

[2092] Step 24: Feedback display

[2093] Input: Submitted feedback

[2094] Output: On-screen feedback

[2095] Specific behavior: The device receives the feedback and displays it to the user.

[2096] (Application example 2)

[2097] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2098] Current foreign language learning systems and content distribution services struggle to provide personalized recommendations and interactive educational and entertainment experiences that take into account the user's emotional state. Therefore, there is a need to improve the quality of users' learning motivation and entertainment experiences.

[2099] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotional state and providing feedback to the generation AI accordingly, means for recommending content to be played next based on the analyzed emotional data, and means for providing interactive quiz and voting functions based on the user's emotional state. This makes it possible to provide a personalized learning and entertainment experience that adapts to the user's emotions.

[2100] "Means for users to select the information they want to learn" refers to providing an interface that allows users to select specific information or topics that interest them.

[2101] "Means for generating messages for virtual characters using generative AI" refers to a method for using artificial intelligence technology to generate messages for virtual characters based on information selected by a user.

[2102] "Means for transmitting the generated message to the user's terminal" refers to a method for transmitting the message generated by the virtual personality to the user's device using a communication means such as the Internet.

[2103] The "means for a user to reply to a message received" is a method of providing an interface that allows a user to input a response to a message received by the user using text or voice.

[2104] "Generative AI means for generating the next message based on the user's reply" refers to an artificial intelligence technology that analyzes the content of the user's response and generates the next series of dialogue messages based on that.

[2105] The "means for sending the next generated message to the user again" refers to a method for sending the next generated message to the user's device again using a communication means such as the Internet.

[2106] "Means for generating voice in real time and performing voice communication" refers to a method in which a generation AI generates voice messages in real time and uses them as a means of voice communication with the user.

[2107] "Means for saving a user's learning history and evaluating the learning progress" refers to a method for recording the user's progress and analyzing it to evaluate the user's learning situation.

[2108] "Means for providing feedback based on evaluation" refers to a method for presenting constructive advice or next steps to users based on their learning progress and emotional state.

[2109] "Means of analyzing the user's emotional state and providing feedback to the generative AI accordingly" refers to a method of analyzing the user's emotions and facial expressions in real time and reflecting the results in the generative AI.

[2110] "Means for recommending the next content to be played based on analyzed emotional data" is a method for automatically selecting and suggesting the most suitable content to be viewed next based on the user's emotional state.

[2111] "Means for providing an interactive quiz or voting function based on the emotional state of the user" is a method for providing interactive elements such as quizzes or voting that reflect the emotional state of the user in real time.

[2112] A system embodying the present invention analyzes a user's emotions and provides content recommendations and interactive quizzes based on the analyzed emotions, thereby enhancing the user's learning and entertainment experience. The system comprises the following steps:

[2113] System Configuration

[2114] 1. User Device:

[2115] Hardware: Smartphone (including camera and microphone)

[2116] Software: Dedicated application

[2117] Function: Captures the user's face and voice in real time using the camera and microphone and sends the data to a server.

[2118] 2. Server:

[2119] Hardware: Cloud servers, database servers

[2120] Software: Flask (server-side processing), TensorFlow (sentiment analysis), generative AI model

[2121] Function: Analyzes data received from users and uses generative AI to generate content and interactive elements that are sent to the user's device.

[2122] Program processing

[2123] User Registration and Settings

[2124] When a user installs and launches the application on their device, a registration screen is displayed. The user enters basic information, which is then sent to the server. Next, the user selects the genre of interest, and the information is sent to the server.

[2125] Content viewing and sentiment analysis

[2126] When a user plays video content, the device's camera and microphone are used to capture the user's facial expressions and voice. The data is sent to a server and analyzed using TensorFlow and other tools. The results of the emotion analysis are fed into the generative AI.

[2127] Recommendation Generation

[2128] Based on the analysis results, the generative AI recommends the next appropriate content. In this case, the generative AI model generates the most appropriate content based on the user's interests and emotional state. For example, if the user is laughing, it will recommend a comedy movie.

[2129] Providing interactive content

[2130] The generative AI provides interactive quizzes and polls based on the user's emotional state. An example of a prompt might be, "The user is currently watching a romantic comedy movie and is laughing. Please generate the next recommended content and related quiz."

[2131] Learning history and feedback

[2132] The server stores users' viewing history and emotional data, which can then be used to further personalize future recommendations and interactive content. Users can receive this feedback in real time through the app.

[2133] Specific examples

[2134] For example, if a user is laughing while watching a romantic comedy movie, the emotion engine will recognize that laughter and the generative AI will recommend the next comedy movie to watch, or provide a quiz related to that particular scene, allowing the user to continue their learning and entertainment experience while having fun.

[2135] This allows the present invention to respond to the user's emotions and provide a personalized learning and entertainment experience.

[2136] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2137] Step 1:

[2138] The user installs and launches the application. A registration screen appears on the user's device, and the user enters basic information (such as name and email address) and submits it. The entered information is sent to the server via the Internet.

[2139] Input: User basic information

[2140] Output: User information stored in the user database on the server

[2141] Step 2:

[2142] A screen is displayed where the user can select the genre and information they are interested in. The user selects the genre they want to learn about (e.g., comedy, action, etc.) and submits the selected information. The submitted information is received by the server and stored in a database.

[2143] Input: User-selected genre information

[2144] Output: Genre information stored in a database on the server

[2145] Step 3:

[2146] The user plays the video content. When playback starts, the device's camera and microphone are activated to capture the user's facial expressions and voice in real time. This data is then sent to the server.

[2147] Input: User's facial expression and voice data

[2148] Output: User emotion data sent to the server

[2149] Step 4:

[2150] The server uses TensorFlow to analyze the received user facial expression and voice data. The analysis results in the user's emotional state (happiness, surprise, sadness, etc.). The analyzed emotional data is passed to the generation AI.

[2151] Input: User's facial expression and voice data

[2152] Output: Analyzed user emotion data

[2153] Step 5:

[2154] The AI ​​generator recommends the next piece of content to be played based on emotional data and the user's selected genre. The AI ​​generator continues to learn by using appropriate prompts. For example, the prompt might read, "The user is watching a comedy movie and laughing. Please generate the next piece of content to recommend."

[2155] Input: Parsed emotion data, genre information, prompt sentence

[2156] Output: Recommended next content information

[2157] Step 6:

[2158] The server sends the recommended content information to the user's terminal and displays it as a list of content for the user to view next. The user can then select the content to view next.

[2159] Input: Recommended content information

[2160] Output: The following content list displayed on the user's device

[2161] Step 7:

[2162] While the user is watching the next content, the server uses generative AI to generate interactive quizzes and polls, for example, generating quizzes related to specific scenes in a movie and sending them to the user.

[2163] Input: User viewing content information and emotion data

[2164] Output: Interactive quizzes and polls

[2165] Step 8:

[2166] Users participate in interactive quizzes and polls, and the results are sent to the server, which analyzes the results and stores them in the user's learning history.

[2167] Input: User quiz or poll answers

[2168] Output: Saved learning history and analysis data

[2169] Step 9:

[2170] The server uses the stored learning history and emotional data to generate data to further personalize future recommendations and interactive elements, and this feedback is sent to the user in real time.

[2171] Input: Learning history and emotion data

[2172] Output: Personalized feedback

[2173] In this way, the invention allows users to have a personalized learning and entertainment experience that adapts to their emotions.

[2174] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2175] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2176] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2177] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2178] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2179] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2180] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2181] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2182] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2183] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2184] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2185] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2186] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2187] 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.

[2188] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2189] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2190] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2191] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2192] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2193] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustration...

Claims

1. a means for the user to select the language they wish to learn; A means for generating a message of a virtual foreigner by a generating AI based on a user's selection; means for transmitting the generated message to a user's terminal; a means for the user to reply to a message received; A generation AI means for generating the next message based on the user's reply; means for sending the next generated message back to the user; means for generating audio in real time and conducting audio chat; means for storing a user's learning history and assessing their learning progress; a means of providing feedback based on the evaluation; A system including:

2. 10. The system of claim 1, further comprising a voice generating means for conducting real-time voice chat.

3. The system of claim 1 , further comprising means for providing personalized feedback based on the user's learning history.

Images