System

Abstract

A system is provided.SOLUTION: A system comprising: means for generating language learning content for a user using generative artificial intelligence; means for accumulating and analyzing logs of conversations with the user; means for providing feedback according to a learning progress of the user based on a result of the analysis; and means for communicating with various devices to allow the user to access from different devices.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] Interest in language learning is on the rise these days, but continuation rates remain low. Traditional online English conversation services require learners to coordinate schedules with instructors, placing time constraints and increasing mental strain on them. Another issue is the difficulty of receiving optimal feedback tailored to individual learning progress. Furthermore, in many cases, there is a lack of seamless learning methods across a variety of devices, not just smartphones and PCs. There is a need to resolve these issues and provide learners with a more effective and efficient language learning environment. [Means for solving the problem]

[0005] The present invention provides an online language learning system using generative artificial intelligence. This system includes a means for generating language learning content for a user, where the generative artificial intelligence generates optimal conversation content in real time based on the user's registration information and past learning log. It also includes a means for accumulating and analyzing conversation logs with the user, and a means for providing feedback based on the analysis results according to the user's learning progress. It also includes a means for communicating with various devices, allowing users to seamlessly access the system from different devices. This solves conventional problems and makes it possible to provide effective language learning 24 hours a day, 365 days a year.

[0006] "Generative AI" is a system that uses artificial intelligence technology to generate new data and content based on user input and requests.

[0007] "User" refers to a user who uses this system to learn a language.

[0008] "Language learning content" refers to data such as learning materials and conversation content for users to use in their studies, and is generated by generative artificial intelligence.

[0009] A "conversation log" is a record of a conversation between a user and a system during language learning, and includes text and audio data.

[0010] "Analysis" refers to the process of evaluating a user's learning progress and challenges based on accumulated conversation log data.

[0011] "Feedback" refers to suggestions and evaluations provided to users based on the analysis results, helping them progress in their learning.

[0012] "Device" broadly refers to any hardware device that a user uses to access this system, such as a smartphone, PC, or tablet.

[0013] "Accessible from different devices" means that users can seamlessly access the system using multiple types of devices and continue their language learning.

[0014] "Real-time" refers to near-instant data processing and response, meaning there is little delay in generating learning content or providing feedback. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] MODE FOR CARRYING OUT THE INVENTION

[0037] This invention is an online system that uses generative artificial intelligence to support users' language learning. This system uses generative artificial intelligence to automatically generate content based on the user's learning level and preferences, and accumulates and analyzes conversation logs with the user to provide individually optimized feedback. The system is also designed to allow users to access it seamlessly from different devices.

[0038] The operation of this system will be explained below with specific examples.

[0039] 1. User Registration and Login

[0040] The user opens the application and enters information such as name, email address, desired password, and desired language to learn on the new account registration screen. The device sends this information to the server, which validates the information. If validation is successful, the server saves the user information in the database and returns a message to the device indicating registration is complete.

[0041] 2. Start learning conversation

[0042] The user presses the "Start Conversation Learning" button on the application's home screen. The device sends this request to the server. The server retrieves the user's learning level from the database and uses generative artificial intelligence to generate conversation content based on the user's level. This generated conversation content is sent to the device and displayed to the user.

[0043] 3. Conversation progress and log accumulation

[0044] Users can initiate conversations with their avatars and respond via text or voice. The device sends the user's responses in real time to the server, which then stores the responses in a database as a conversation log. This ensures that all conversations are recorded and stored as data for later analysis.

[0045] 4. Analysis and Feedback

[0046] After the conversation ends, the server analyzes the accumulated conversation log. The analysis evaluates the user's pronunciation, grammatical accuracy, and vocabulary used. Based on the analysis results, the server generates feedback and suggestions for the next lesson. This feedback includes specific advice such as "your pronunciation was good" or "review this grammar." The device displays this feedback to the user.

[0047] 5. Device connectivity and seamless access

[0048] The system can be accessed from a variety of devices, including smartphones, PCs, and tablets. No matter which device a user uses, their previous learning log and current progress are all synchronized, allowing them to continue their language learning seamlessly. The server manages communication between these devices and provides consistent session information across devices.

[0049] Specific examples

[0050] For example, suppose an English learner wants to use this system to learn new grammar. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation that incorporates appropriate grammar points. The generated conversation might be a question such as "What did you do yesterday?" If the user responds with "I went to the supermarket," the conversation is saved in the log. After the conversation is completed, analysis is performed and feedback is provided to the user, such as "Your use of the past tense is correct."

[0051] In this way, users receive a personalized learning experience, helping them learn a language more efficiently.

[0052] The processing flow will be explained below.

[0053] 1. User Registration and Login

[0054] Step 1:

[0055] A user opens the application and enters information such as their name, email address, desired password, and desired language of study on the new account registration screen.

[0056] Step 2:

[0057] The terminal transmits the entered registration information to the server.

[0058] Step 3:

[0059] The server validates the received registration information, specifically checking that the email address is formatted correctly and that the password meets the required criteria.

[0060] Step 4:

[0061] The server stores the user information in the database after successful validation.

[0062] Step 5:

[0063] The server returns a message to the terminal indicating that registration is complete, and the terminal displays this to the user.

[0064] 2. Start learning conversation

[0065] Step 1:

[0066] The user presses the "Start Conversation Learning" button on the application's home screen.

[0067] Step 2:

[0068] The terminal sends a "conversation learning start" request to the server.

[0069] Step 3:

[0070] The server retrieves the user's learning level from the database.

[0071] Step 4:

[0072] The server generates conversation content using generative artificial intelligence based on the acquired learning level.

[0073] Step 5:

[0074] The server transmits the generated conversation content to the terminal, which then displays it to the user.

[0075] 3. Conversation progress and log accumulation

[0076] Step 1:

[0077] The user responds to the conversation content displayed on the terminal by text or voice.

[0078] Step 2:

[0079] The terminal transmits the user's response to the server in real time.

[0080] Step 3:

[0081] The server stores the received responses in a database as a conversation log, which includes not only the user's responses but also the time the conversation occurred.

[0082] 4. Analysis and Feedback

[0083] Step 1:

[0084] After the conversation ends, the server analyzes the accumulated conversation log.

[0085] Step 2:

[0086] The server identifies the user's learning progress and areas for improvement based on the results of the analysis, which includes pronunciation, grammatical accuracy, and the variety of vocabulary used.

[0087] Step 3:

[0088] The server generates feedback based on the analysis, including specific advice such as "Use the past tense correctly" or "Use a more diverse vocabulary."

[0089] Step 4:

[0090] The server sends the generated feedback to the terminal, which displays it to the user.

[0091] 5. Device connectivity and seamless access

[0092] Step 1:

[0093] When a user accesses the system from a different device, the terminal sends the login information to the server.

[0094] Step 2:

[0095] The server verifies the authentication information and verifies that the user is authorized to access the site.

[0096] Step 3:

[0097] The server sends the latest learning log and progress information to the new device, which then displays it to the user, allowing the user to check their previous learning content and progress and continue their learning smoothly.

[0098] This series of steps allows users to continue learning a language 24 hours a day, 365 days a year, regardless of location.

[0099] Example 1

[0100] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0101] Conventional language learning systems have struggled to provide feedback tailored to each user's individual learning progress and optimal learning content. It has also been difficult to seamlessly synchronize learning data across different devices. This has resulted in an inefficient learning experience for users, slowing down their language acquisition progress.

[0102] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0103] In this invention, the server includes means for generating language learning content for a user using generative artificial intelligence, means for accumulating and analyzing conversation logs with the user, means for providing feedback according to the user's learning progress based on the analysis results, means for communicating with various devices and allowing the user to access the content from different devices, means for inputting and validating user information, means for saving the user information in a database, means for providing prompts for generating conversation content based on the user's learning level, means for transmitting and saving user responses in real time, and means for analyzing the conversation logs and generating suggestions for next learning content and feedback, thereby providing an optimal learning experience according to the user's individual learning progress and enabling effective language acquisition.

[0104] "Generative AI" is an AI technology that generates new content and data based on user input information.

[0105] "Language learning content" refers to teaching and practice materials that help users learn a particular language.

[0106] A "conversation log" refers to a record of a conversation between a user and a system, and is saved as text or audio data.

[0107] "Feedback" refers to the advice and evaluation provided by the system regarding the user's learning progress and performance.

[0108] "Various devices" refers to different hardware platforms such as smartphones, PCs, and tablets.

[0109] A "database" is a system for systematically storing and managing data such as user information and conversation logs.

[0110] A "prompt sentence" is an input sentence that serves as the basis for generative artificial intelligence to generate conversation content.

[0111] "User response" refers to the reply or input given by the user to the system.

[0112] "Real-time" refers to the situation where user input is processed the instant it is made, with little time delay.

[0113] This invention is an online system that uses generative artificial intelligence to support users' language learning. The system uses generative artificial intelligence to automatically generate content based on the user's learning level and preferences, and accumulates and analyzes conversation logs with the user to provide individually optimized feedback. The system is designed to be seamlessly accessible from various devices, including smartphones, PCs, and tablets.

[0114] User Registration and Login

[0115] The user opens the application and enters information such as name, email address, desired password, and desired language to learn on the new account registration screen. The device sends this information to the server. The server validates the information, and if validation is successful, saves the user information in a database (e.g., MySQL). A message indicating registration completion is returned to the device and displayed to the user.

[0116] Start learning conversation

[0117] The user presses the "Start Conversation Learning" button on the application's home screen. The device sends this request to the server. The server retrieves the user's learning level from the database and uses generative artificial intelligence (e.g., GPT-3 using the OpenAI API) to generate conversation content based on the user's level. The generated conversation content is sent to the device and displayed to the user.

[0118] Conversation progress and log accumulation

[0119] Users can initiate conversations with their avatars and respond via text or voice. The device sends the user's responses in real time to the server, which then stores the responses in a database as a conversation log. This ensures that all conversations are recorded and stored as data for later analysis.

[0120] Analysis and feedback

[0121] After the conversation ends, the server analyzes the accumulated conversation log. This analysis evaluates the user's pronunciation, grammatical accuracy, and vocabulary used. Based on the analysis results, the server generates feedback and suggestions for the next lesson. This feedback includes specific advice such as "your pronunciation was good" or "review this grammar." The device displays this feedback to the user.

[0122] Device Connectivity and Seamless Access

[0123] The system can be accessed from a variety of devices, including smartphones, PCs, and tablets. No matter which device a user uses, previous learning logs and current progress are all synchronized, allowing for seamless language learning. The server manages communication between these devices and provides consistent session information across devices.

[0124] Specific examples

[0125] For example, suppose an English learner wants to use this system to learn new grammar. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation incorporating appropriate grammar points. The generated conversation might be a question such as "What did you do yesterday?" If the user responds with "I went to the supermarket," the conversation is saved in the log. After the conversation is completed, analysis is performed and feedback is provided to the user, such as "Your use of the past tense is correct." In this way, users can receive an individually optimized learning experience and acquire languages ​​more efficiently.

[0126] Example prompts for generative AI models

[0127] The user's current learning level is beginner. Please generate conversation content appropriate for that level. The theme should be "daily life" and should include practice of past tense.

[0128] User Information:

[0129] Language of study: English

[0130] Learning level: Beginner

[0131] Example of a conversation to generate:

[0132] Question: What did you do yesterday?

[0133] Expected Answer: I went to the supermarket.

[0134] Based on this prompt, the generative AI generates conversational content appropriate to the user's learning progress, allowing the user to learn the language effectively.

[0135] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0136] Step 1:

[0137] A user opens the application and enters their name, email address, password, and language of study on the new account registration screen. This information is sent as input to the device, and then sent from the device to the server. The server validates the information, specifically checking the format of the email address, the strength of the password, etc. The output of this step is that if validation is successful, the user information is saved in a database (e.g. MySQL). If validation fails, an error message is returned to the device.

[0138] Step 2:

[0139] When a user presses the "Start Conversation Learning" button, the terminal sends this request to the server. The input is the conversation learning start request, and the server obtains the user's learning level from the database. Specifically, it extracts level information from the learning log table based on the user ID. The output of this step is the user's learning level information.

[0140] Step 3:

[0141] The server generates a prompt based on the acquired learning level information. The prompt is sent as input to a generative artificial intelligence (e.g., GPT-3 using the OpenAI API), which generates conversation content appropriate for the user's level. Specifically, the prompt includes instructions such as, "The user's current learning level is beginner. Please generate content about 'daily life' that includes practice in the past tense." The output of this step is the generated conversation content.

[0142] Step 4:

[0143] The generated conversation content is sent from the server to the terminal, which then displays it to the user. The input is the generated conversation content from the server, and through this display, the user can start conversation learning. The output of this step is the conversation content displayed to the user.

[0144] Step 5:

[0145] The user initiates a conversation with the avatar and responds with text or voice. This response is sent by the device to the server in real time. The input is text or voice data from the user. The server stores this as a conversation log in the database. Specifically, it stores the text data in a conversation log table and the voice data in audio file format. The output of this step is the conversation log stored in the database.

[0146] Step 6:

[0147] After the conversation ends, the server analyzes the accumulated conversation log. The input is the stored conversation log data, and the analysis evaluates the user's pronunciation, grammatical accuracy, and vocabulary used. Specifically, natural language processing tools are used to analyze the text data, and speech recognition technology is used for the audio data. The output of this step is the analysis results.

[0148] Step 7:

[0149] The server generates feedback and suggestions for the next learning content based on the analysis results. Specifically, it automatically generates feedback sentences that include specific advice such as "your pronunciation was good" or "review this grammar." The input is the analysis results, and the generated feedback sentences are the output of this step.

[0150] Step 8:

[0151] The server generates feedback sentences, which are sent to the terminal and displayed by the terminal to the user. The input is the feedback sentences from the server, which the user can use to proceed to the next learning step. The output of this step is the feedback sentences displayed to the user.

[0152] Points to note

[0153] Data transmission and reception at each step is performed via the Internet.

[0154] Access to the database and storage of data is done securely.

[0155] Appropriate security measures are in place to protect user privacy.

[0156] (Application example 1)

[0157] 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."

[0158] Modern factories often employ workers from multiple countries, and language differences can have a serious impact on work efficiency and safety. In particular, serious problems can occur if work instructions and safety precautions are not communicated accurately. Furthermore, as robots and automation systems are widely used in factories, these devices must be able to communicate smoothly with humans. However, while current language learning systems provide optimal learning content tailored to individual learning situations, they are not specialized for the unique work environment of a factory. Therefore, there is a need for systems that facilitate communication in factory environments and strengthen collaboration between workers and machines.

[0159] 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.

[0160] In this invention, the server includes means for generating language learning content for a user using generative artificial intelligence, means for accumulating and analyzing conversation logs with the user, means for providing feedback according to the user's learning progress based on the analysis results, means for communicating with various devices and enabling the user to access the server from different devices, means for linking with equipment used in a factory environment and generating dialogues for language learning, and means for analyzing the conversation logs based on the dialogues and providing feedback related to factory work. This enables efficient and safe communication between multinational workers working in factories and robots.

[0161] "Generative artificial intelligence" refers to an artificial intelligence system that has the ability to automatically generate new data and content based on given data and conditions.

[0162] "User" refers to the person or device that uses this system to learn a language.

[0163] "Language learning content" refers to learning materials, interactive exercises, and other learning materials used by users to study.

[0164] "Conversation log" refers to a record of the conversation between the user and the system.

[0165] "Analysis results" refers to the data and evaluations obtained by analyzing the conversation logs.

[0166] "Feedback" refers to advice and evaluation provided to users based on their learning progress.

[0167] "Various devices" refers to devices that can access the system, such as smartphones, tablets, PCs, smart glasses, and head-mounted displays.

[0168] "Factory environment" refers to the physical location where products are manufactured and assembled, and the working conditions therein.

[0169] "Device" refers to a device such as a robot or automation system that operates in conjunction with the language learning system.

[0170] "Dialogue" refers to conversational communication between a user and a system.

[0171] This invention is a system for supporting language learning for robots in a factory environment. This system uses generative artificial intelligence to generate learning content for users (here, robots), accumulates and analyzes conversation logs with the users, and provides feedback based on the analysis results. This system also communicates with various devices (smartphones, tablets, PCs, smart glasses, head-mounted displays, etc.), allowing users to access the system from different devices. This system also works in conjunction with equipment used in the factory environment.

[0172] System Program

[0173] The server implements a program with the following functions:

[0174] 1. Language learning content generation:

[0175] The server uses generative artificial intelligence to generate optimal conversation content in real time based on the user's registration information and past learning logs. For this purpose, a generative AI model is used.

[0176] 2. Conversation log storage and analysis:

[0177] The server stores conversation logs with users in the form of text and audio data, analyzes them, and automatically evaluates the user's learning progress. Natural language processing (NLP) algorithms are used to analyze the conversation logs.

[0178] 3. Providing Feedback:

[0179] Based on the analysis results, the server provides feedback based on the user's learning progress, including accuracy of pronunciation, proper use of grammar, and vocabulary use.

[0180] 4. Communication between devices:

[0181] The server communicates seamlessly with various devices, allowing users to access the content from different devices, using a cloud-based synchronization mechanism.

[0182] 5. Collaboration in a factory environment:

[0183] The server interacts with the equipment used in the factory environment and generates dialogues for language learning that simulate specific situations related to factory work.

[0184] Processing Description

[0185] The server receives the user's registration information (first name, last name, email address, password, and language to learn) and stores it in a database. When the robot presses the "Start Learning" button, the server generates the optimal conversation content based on the registration information and past learning logs. This conversation content is sent to the robot, and the robot proceeds with its work based on the received content.

[0186] Conversation logs are stored as text and audio data for analysis and feedback. The server analyzes these logs and generates feedback based on the robot's learning progress. This feedback is displayed on the robot's display and can be used to improve the robot's next task.

[0187] For example, consider a scenario in which a factory robot responds to the Japanese question, "Please tell me what you did yesterday," with "I did welding yesterday." In this case, the server stores the content of this dialogue and evaluates the accuracy of pronunciation and grammar.

[0188] Example prompt sentence:

[0189] "Create a language learning dialogue for a factory robot to learn Japanese at its current skill level. The robot should practice sentences it might use during daily operations, such as greetings and task descriptions."

[0190] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0191] Step 1:

[0192] A user launches an application from their device and enters information such as their name, email address, password, and preferred language into the new account registration screen. This information is then sent from the device to the server, where it is validated.

[0193] Input: User information (name, email address, password, preferred language)

[0194] Data processing / calculation: Validation of input information

[0195] Output: Validation results, saved to database

[0196] Step 2:

[0197] The server stores the user information whose validation has been successful in the database and sends a message to the terminal indicating that the user registration has been completed.

[0198] Input: Validation result

[0199] Data processing / calculation: Saving user information to a database

[0200] Output: Registration complete message

[0201] Step 3:

[0202] The user presses the "Start Conversation Learning" button on the application's home screen. This request is sent from the device to the server, which retrieves the user's registration information and past learning logs from the database.

[0203] Input: User's "Start conversation learning" request

[0204] Data processing / calculation: Retrieving information from a database

[0205] Output: User information, past learning logs

[0206] Step 4:

[0207] The server uses a generative AI model to generate conversation content appropriate for the user's level based on the acquired user information and past learning logs, and uses appropriate prompts for this generation.

[0208] Input: User information, past learning log

[0209] Data processing / calculation: Generating conversation content using generative AI models

[0210] Output: Generated conversation

[0211] Step 5:

[0212] The generated conversation is sent to the device and displayed to the user, who can then initiate a conversation with the avatar and respond with text or voice, which is then sent to the server in real time.

[0213] Input: Generated conversation

[0214] Data processing / calculation: Display to user

[0215] Output: User response (text or voice data)

[0216] Step 6:

[0217] The server stores the received user responses in a database as a conversation log, which is then accumulated as data for analysis.

[0218] Input: User response (text or voice data)

[0219] Data processing / calculation: Accumulation as conversation log

[0220] Output: Saved conversation logs

[0221] Step 7:

[0222] After the conversation ends, the server analyzes the accumulated conversation log and generates feedback based on the analysis results, including corrections to pronunciation and grammar, as well as compliments.

[0223] Input: Saved Conversation Log

[0224] Data processing / calculation: Analysis of conversation logs, generation of feedback

[0225] Output: Analysis results, feedback

[0226] Step 8:

[0227] The generated feedback is sent to the terminal and displayed to the user, who then uses the feedback to improve their next conversation practice.

[0228] Input: Analysis results, feedback

[0229] Data processing / calculation: Display to user

[0230] Output: Displayed feedback

[0231] Step 9:

[0232] The server communicates with various devices, allowing users to seamlessly access the app from different devices, allowing them to check their learning progress from any device.

[0233] Input: Device connection request

[0234] Data processing / calculation: Communication management between devices

[0235] Output:Seamless Access

[0236] 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.

[0237] MODE FOR CARRYING OUT THE INVENTION

[0238] This invention is an online language learning system that combines generative artificial intelligence and an emotion engine. This system is designed to allow users to learn languages ​​at any time and in an optimal environment, and can be accessed from a variety of devices. The operation of this system is described in detail below.

[0239] 1. User Registration and Login

[0240] A user opens a language learning application and enters their name, email address, desired password, and desired language into the new account registration screen. The device sends this information to the server. The server validates the received information and stores information that is deemed correct in a database. Once registration is complete, the server sends a confirmation message to the device, which displays it to the user.

[0241] 2. Start learning conversation

[0242] The user presses the "Start Conversation Learning" button on the application's home screen. The device sends this request to the server. The server retrieves the user's learning level from the database and uses generative artificial intelligence to generate optimal conversation content based on the user's level. The generated conversation content is sent to the device, which then displays it to the user.

[0243] 3. Emotion Recognition and Log Accumulation

[0244] When a user responds to a conversation, the device sends the user's voice and text data to the server. The server then stores the received data in a database as a conversation log. The device's built-in emotion engine also analyzes the user's response data and identifies their emotional state (e.g., joy, sadness, surprise, etc.). The emotion identification results are also saved along with the conversation log.

[0245] 4. Analysis and Feedback

[0246] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data. The emotion engine evaluates the user's emotional state as they study and generates feedback based on this. For example, if the user is feeling stressed, it can provide feedback on how to study in a relaxed manner. Based on the analysis, the server also identifies the user's learning progress and areas for improvement, generating feedback suggesting the next course of study.

[0247] 5. Device connectivity and seamless access

[0248] This system can be accessed from various devices such as smartphones, PCs, and tablets. When a user logs in using a different device, the device sends authentication information to the server, which then verifies the authentication information. If authentication is successful, the server sends the latest learning log and progress information to the new device, which then displays it to the user. This allows users to check their previous learning content and progress, and continue learning seamlessly from any device.

[0249] Specific examples

[0250] For example, suppose an English learner wants to learn a new word. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation that includes the new word. The generated conversation might be a question such as, "Where did you go today?" If the user responds, "I went to the library," the conversation is saved in the log in real time. Furthermore, an emotion engine analyzes the user's voice to determine whether the user is relaxed or stressed. After the conversation ends, the system generates feedback such as, "Your pronunciation is accurate, and you seem to be learning in a relaxed manner. Next, let's review past tense grammar," and the device displays this to the user.

[0251] In this way, users can get a learning experience that is individually optimized to their mood and level of understanding on that day.

[0252] The processing flow will be explained below.

[0253] 1. User Registration and Login

[0254] Step 1:

[0255] A user opens a language learning application and enters information such as their name, email address, desired password, and language to learn on the new account registration screen.

[0256] Step 2:

[0257] The terminal transmits the input information to the server.

[0258] Step 3:

[0259] The server validates the received information and stores the information that is determined to be correct in a database.

[0260] Step 4:

[0261] The server sends a registration completion message to the terminal, which the terminal displays to the user.

[0262] 2. Start learning conversation

[0263] Step 1:

[0264] The user presses the "Start Conversation Learning" button on the application's home screen.

[0265] Step 2:

[0266] The terminal sends a learning start request to the server.

[0267] Step 3:

[0268] The server retrieves the user's learning level from the database.

[0269] Step 4:

[0270] The server generates conversation content using generative artificial intelligence based on the acquired learning level.

[0271] Step 5:

[0272] The server transmits the generated conversation content to the terminal, which then displays it to the user.

[0273] 3. Emotion Recognition and Log Accumulation

[0274] Step 1:

[0275] The user responds to the displayed conversation content by text or voice.

[0276] Step 2:

[0277] The terminal transmits the user's response to the server in real time.

[0278] Step 3:

[0279] The server stores the received response data in a database as a conversation log.

[0280] Step 4:

[0281] The server uses an emotion engine to analyze the response data and identify the user's emotional state.

[0282] Step 5:

[0283] The server also stores the identified emotion data along with the conversation log.

[0284] 4. Analysis and Feedback

[0285] Step 1:

[0286] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data.

[0287] Step 2:

[0288] Based on the analysis results, the server evaluates the user's learning progress and identifies areas for improvement.

[0289] Step 3:

[0290] The server generates feedback based on the evaluation results, including specific advice on learning progress and suggestions for next learning content.

[0291] Step 4:

[0292] The server sends the generated feedback to the terminal, which displays it to the user.

[0293] 5. Device connectivity and seamless access

[0294] Step 1:

[0295] When a user logs in from a different device, the terminal sends the login information to the server.

[0296] Step 2:

[0297] The server authenticates the received login information and verifies the user's access rights.

[0298] Step 3:

[0299] After successful authentication, the server sends the latest learning log and progress information to the new device.

[0300] Step 4:

[0301] The device displays this information to the user, allowing them to check their previous learning content and progress and continue their learning seamlessly.

[0302] Specific examples

[0303] For example, when an English learner presses the "Start Conversation Learning" button, the server reads the user's learning log and generates new conversation content. If the generated conversation content is "How was your day?", the user might respond with "I went to the park." The device sends this response to the server, which analyzes and saves the "enjoying" state along with the conversation log using its emotion engine. After the conversation ends, the server generates feedback such as "Your pronunciation is good and you seem to be learning in a relaxed manner. Let's move on," and the device displays this to the user. In this way, users can obtain an optimal learning experience that also takes their emotions into consideration.

[0304] Example 2

[0305] 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."

[0306] Language learning systems need to effectively assess users' learning progress and provide optimal feedback. It is also important to make the learning environment more flexible by allowing users to easily access the learning environment from any device. Furthermore, it is desirable to analyze users' emotional states and more individually tailor the learning experience.

[0307] 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.

[0308] In this invention, the server includes: a means for generating language learning content for a user using generative artificial intelligence; a means for accumulating and analyzing conversation logs with the user; a means for providing feedback according to the user's learning progress based on the analysis results; a means for analyzing the user's response data using an emotion engine and identifying their emotional state; and a means for communicating with various devices and allowing the user to access the content from different devices. This allows for effective evaluation of the user's learning progress and provides optimal feedback. Furthermore, by analyzing the user's emotional state in real time and reflecting this in the feedback, the learning experience can be more personalized and an environment can be realized where the content can be seamlessly accessed from different devices.

[0309] "Generative AI" is an AI technology that generates language learning content in real time based on user input.

[0310] A "conversation log" is data that records the content of a conversation between a user and a system, and includes text data and voice data.

[0311] An "emotion engine" is a software component that analyzes user response data to identify the user's emotional state.

[0312] "Feedback" refers to evaluations and advice provided based on a user's learning progress, including information suggesting improvements to learning content and next steps.

[0313] "Learning progress" is an index that indicates the degree of progress of a user's language learning, and is evaluated based on the results of analysis of conversation logs and emotion data.

[0314] "Storage means" is a function for saving conversation logs and emotional data in a database.

[0315] "Analysis" refers to the process of using accumulated data to evaluate the user's learning progress and emotional state.

[0316] "Device" refers to any electronic device used by a user to access the system, including a smartphone, PC, tablet, etc.

[0317] "Communication" refers to the process of exchanging data between different devices over a network.

[0318] "Real-time" refers to data being generated and processed instantly.

[0319] This invention is an online language learning system that combines generative artificial intelligence and an emotion engine. This system is designed to allow users to learn languages ​​at any time and in an optimal environment, and can be accessed from a variety of devices. The operation of this system is described in detail below.

[0320] 1. User Registration and Login

[0321] A user opens a language learning application and enters their name, email address, desired password, desired language, etc. into the new account registration screen.

[0322] The terminal sends this information to the server.

[0323] The server validates the received information and stores the information that is deemed correct in a database (e.g., MySQL or PostgreSQL).

[0324] Once registration is complete, the server sends a confirmation message to the terminal, which the terminal displays to the user.

[0325] 2. Start learning conversation

[0326] The user presses the "Start Conversation Learning" button on the application's home screen.

[0327] The terminal sends this request to the server.

[0328] The server retrieves the user's learning level from the database and generates optimal conversation content based on the user's level using generative artificial intelligence (e.g., GPT-4 model). The generated conversation content is sent to the device, which then displays it to the user.

[0329] 3. Emotion Recognition and Log Accumulation

[0330] When the user responds to the conversation, the terminal transmits the user's voice data and text data to the server.

[0331] The server stores the received data in a database as a conversation log. The built-in emotion engine analyzes the user's response data and identifies their emotional state (e.g., joy, sadness, surprise, etc.). The emotion identification results are also stored along with the conversation log.

[0332] 4. Analysis and Feedback

[0333] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data. The emotion engine evaluates the user's emotional state as they study and generates feedback based on this. For example, if the user is feeling stressed, it will provide feedback on how to study in a relaxed manner. Based on the analysis, the server also identifies the user's learning progress and areas for improvement, and generates feedback suggesting the next course of study.

[0334] 5. Device connectivity and seamless access

[0335] The system can be accessed from a variety of devices, including smartphones, PCs, and tablets.

[0336] When a user logs in using a different device, the terminal sends the authentication information to the server.

[0337] The server verifies the authentication information and, if successful, sends the latest learning log and progress information to the new device.

[0338] The device displays this to the user, allowing them to check their previous learning content and progress, and continue learning seamlessly from any device.

[0339] Specific examples

[0340] For example, suppose an English learner wants to learn new words. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation that includes the new words. The generated conversation might include questions such as "Where did you go today?"

[0341] When the user responds, "I went to the library," the conversation is logged in real time. Furthermore, an emotion engine analyzes the user's voice to determine whether they are relaxed or stressed. After the conversation ends, the system generates feedback such as, "Your pronunciation is accurate, and you seem to be learning in a relaxed manner. Next, let's review past tense grammar," and the device displays this to the user.

[0342] Prompt Sentence Examples

[0343] Specific conversation content can be generated by writing prompts to the generative AI model as follows:

[0344] For users who click the "Start Conversation Learning" button, generate a conversation appropriate to their level. The language of study is English, and the learner is at beginner level. Generate a conversation that includes questions to teach the learner new vocabulary.

[0345] This prompt allows the generative AI model to generate appropriate conversational content and provide it to the user.

[0346] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0347] Processing Steps

[0348] Step 1: User Registration and Login

[0349] 1. Enter information

[0350] A user opens a language learning application and enters their name, email address, desired password, and the language they wish to learn.

[0351] Input: Name, Email Address, Password, Language

[0352] Output: Request to send input data

[0353] 2. Data Transmission

[0354] The terminal transmits the information entered by the user to the server.

[0355] Input: Input data

[0356] Output: Send data to the server

[0357] 3. Validation and Storage

[0358] The server validates the submitted data and stores it in a database if it is deemed correct, for example by checking the format of the email address or the strength of the password.

[0359] Input: Input data

[0360] Output: Validation success or failure

[0361] 4. Sending a registration completion message

[0362] If validation is successful, the server sends the user a registration completion message, which the terminal displays to the user.

[0363] Input: Validation successful

[0364] Output: Display a confirmation message

[0365] Step 2: Start learning conversations

[0366] 1. Send a lesson start request

[0367] The user presses the "Start Conversation Learning" button on the application's home screen.

[0368] Input: Start learning request

[0369] Output: Request sent to server

[0370] 2. Obtaining user level and generating conversation content

[0371] The server obtains the user's learning level from the database and generates optimal conversation content using generative artificial intelligence (e.g., GPT-4).

[0372] Input: User learning level

[0373] Output: Generated conversation

[0374] 3. Display of conversation contents

[0375] The generated conversation content is sent to the terminal, which displays it to the user.

[0376] Input: Generated conversation

[0377] Output: Display of conversation

[0378] Step 3: Emotion recognition and logging

[0379] 1. Sending conversation response data

[0380] When the user responds to the conversation, the terminal transmits the voice data and text data to the server.

[0381] Input: Response data (audio or text)

[0382] Output: Send data to the server

[0383] 2. Save conversation logs

[0384] The server stores the received data in a database as a conversation log.

[0385] Input: Response data

[0386] Output: Save to database

[0387] 3. Emotional state analysis

[0388] The built-in emotion engine analyzes the user's response data and identifies their emotional state, such as joy, sadness, or surprise, based on their voice data.

[0389] Input: Response data

[0390] Output: Save the sentiment analysis results

[0391] Step 4: Analyze and provide feedback

[0392] 1. Log and emotion data analysis

[0393] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data.

[0394] Input: Conversation logs, emotion data

[0395] Output: Analysis results

[0396] 2. Generate feedback

[0397] The emotion engine generates optimal feedback for the user based on the analysis results. For example, if the user is relaxed, it generates feedback such as "You are able to study in a relaxed state."

[0398] Input: Analysis results

[0399] Output: Feedback message

[0400] 3. Viewing Feedback

[0401] The generated feedback is sent to the terminal, which displays it to the user.

[0402] Input: Feedback message

[0403] Output: Display feedback

[0404] Step 5: Device connection and seamless access

[0405] 1. Log in from your device

[0406] When a user logs in on a different device, the terminal sends authentication information to the server.

[0407] Input: Credentials

[0408] Output: Authentication request to the server

[0409] 2. Verify your credentials and synchronize your data

[0410] The server verifies the authentication information and, if successful, sends the latest learning log and progress information to the new device.

[0411] Input: Credentials

[0412] Output: Send training data

[0413] 3. View your learning log and progress information

[0414] The device displays this to the user, allowing them to check their previous learning content and progress, and continue learning seamlessly from any device.

[0415] Input: Training data

[0416] Output: Display of learning information

[0417] (Application example 2)

[0418] 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."

[0419] Conventional language learning systems were unable to provide learning content that took the user's emotional state into consideration, resulting in issues with learning efficiency and continuity. Furthermore, because appetite is significantly influenced by emotions, it was also unable to simultaneously provide meal suggestions based on the user's emotions. This created a need for a way to reduce learning stress and improve the overall learning experience.

[0420] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0421] In this invention, the server includes means for generating language learning content for a user using generative artificial intelligence, means for accumulating and analyzing conversation logs with the user, means for providing feedback according to the user's learning progress based on the analysis results, means for communicating with various devices and allowing the user to access the server from different devices, and means for analyzing the user's emotional data and recommending optimal meals based on the analysis results, thereby making it possible to provide content and suggest optimal meals that take the user's emotional state into consideration.

[0422] "Generative AI" is an AI technology that creates appropriate content and suggestions in real time based on the user's learning and emotional state.

[0423] "Conversation log" refers to recorded data that collects and stores the contents of conversations users have as text and audio data.

[0424] "Emotional data" is information that indicates the emotional state of a user obtained by analyzing the user's voice or text.

[0425] "Feedback" is advice or information about next steps or areas for improvement that is provided based on the user's learning progress and emotional state.

[0426] "Various devices" refers to the various devices that users use to access the site, such as smartphones, PCs, and tablets.

[0427] "Communication means" refers to the network means used by users to continuously access the service from different devices.

[0428] "Method of recommending meals" is a technology that suggests optimal meals based on the user's emotional data.

[0429] This invention is a system that combines generative artificial intelligence and an emotion engine to optimize an online language learning system and a food delivery application. Specific embodiments of this system are described below.

[0430] Basic Features

[0431] The system works on various devices, including smartphones, PCs, and tablets. Users can register and log in to receive optimal content and feedback based on their learning progress and emotional state. The system also supports seamless access across different devices.

[0432] Program Generation and Processing Description

[0433] The server first generates appropriate learning content using generative artificial intelligence based on the information and emotional state entered by the user, using specific software libraries called EmotionEngine and FoodRecommendationAI.

[0434] 1. The server receives the user information

[0435] When a user logs in to their account through their device, the server retrieves the user's profile information and past learning logs.

[0436] 2. Emotion Data Analysis

[0437] The user inputs their current emotional state and sends it to the server, which then uses the EmotionEngine to analyze this data and determine the user's emotional state.

[0438] 3. Generating learning content and feedback

[0439] The server uses generative artificial intelligence to generate optimal conversation content based on the user's learning progress, and also analyzes the user's stress level and relaxation state based on emotional data, providing appropriate feedback.

[0440] 4. Dietary Recommendations

[0441] Furthermore, it uses generative artificial intelligence to recommend optimal meals based on emotional data: for example, if the user is stressed, it will recommend relaxing meals, and if they are relaxed, it will recommend nutritious meals.

[0442] Usage example

[0443] If a user logs in to a food delivery app and enters "stress" as their emotional state, the server will analyze this information using the Emotion Engine and use Food Recommendation AI to recommend "meals that have a relaxing effect." Specific recommendations include a "Japanese meal set" and "chamomile tea."

[0444] Example prompts to be input to the generative AI model

[0445] An example prompt might have the following format:

[0446] User Emotion: Stress

[0447] User preference: Japanese food

[0448] Output format: Suggest a relaxing meal.

[0449] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0450] Step 1:

[0451] The user opens the smartphone app and enters login information (user ID and password). The device sends this information to the server, which then authenticates the user. If authentication is successful, the server retrieves the user's profile information and past learning logs and sends them to the device. In this process, the input is the user's login information, and the output is the user's profile information and past learning logs. Data processing and data calculation involve authentication and retrieval of data from the database.

[0452] Step 2:

[0453] The user inputs their current emotional state. For example, emotions such as "stressed" or "relaxed" are input into a smartphone app. The device sends this emotional information to the server, which then analyzes the data using the Emotion Engine. The input is the user's emotional state, and the output is the analyzed emotional data. Data processing and data calculation are emotion analysis.

[0454] Step 3:

[0455] The server uses generative artificial intelligence to generate appropriate learning content in real time based on emotional data and past learning logs. Optimal conversation content is generated based on the user's learning progress and level. The input is emotional data and learning logs, and the output is the generated learning content. Data processing and data calculation are used to generate learning content.

[0456] Step 4:

[0457] The generated learning content is sent to the terminal and displayed to the user. The user practices the conversation and responds in voice or text format. The terminal sends this response data to the server. The input is the generated learning content, and the output is the user's response data. Data processing and data calculation involve receiving the user's input.

[0458] Step 5:

[0459] The server receives and stores the user's conversation log as text and audio data. It also analyzes the conversation log to automatically evaluate learning progress. The input is the user's response data, and the output is the analyzed learning progress data. Data processing and data calculation involve the analysis and storage of the conversation log.

[0460] Step 6:

[0461] Based on the analysis results, the server provides feedback according to the user's learning progress. This feedback is sent to the terminal and displayed to the user. The input is learning progress data, and the output is feedback. Data processing and data calculation are used to generate feedback.

[0462] Step 7:

[0463] Based on the emotion data, the server uses Food Recommendation AI to recommend the most suitable meal. This recommendation is also sent to the device and displayed to the user. The input is emotion data, and the output is the meal recommendation. Data processing and data calculation are used to generate the meal recommendation.

[0464] 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.

[0465] 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.

[0466] 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.

[0467] [Second embodiment]

[0468] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0469] 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.

[0470] 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).

[0471] 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.

[0472] 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.

[0473] 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).

[0474] 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.

[0475] 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.

[0476] 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.

[0477] 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.

[0478] 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.

[0479] 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."

[0480] MODE FOR CARRYING OUT THE INVENTION

[0481] This invention is an online system that uses generative artificial intelligence to support users' language learning. The system uses generative artificial intelligence to automatically generate content based on the user's learning level and preferences, and accumulates and analyzes conversation logs with the user to provide individually optimized feedback. The system is also designed to allow users to access the system seamlessly from different devices.

[0482] The operation of this system will be explained below with specific examples.

[0483] 1. User Registration and Login

[0484] The user opens the application and enters information such as name, email address, desired password, and desired language to learn on the new account registration screen. The device sends this information to the server, which validates the information. If validation is successful, the server saves the user information in the database and returns a message to the device indicating registration is complete.

[0485] 2. Start learning conversation

[0486] The user presses the "Start Conversation Learning" button on the application's home screen. The device sends this request to the server. The server retrieves the user's learning level from the database and uses generative artificial intelligence to generate conversation content based on the user's level. This generated conversation content is sent to the device and displayed to the user.

[0487] 3. Conversation progress and log accumulation

[0488] Users can initiate conversations with their avatars and respond via text or voice. The device sends the user's responses in real time to the server, which then stores the responses in a database as a conversation log. This ensures that all conversations are recorded and stored as data for later analysis.

[0489] 4. Analysis and Feedback

[0490] After the conversation ends, the server analyzes the accumulated conversation log. The analysis evaluates the user's pronunciation, grammatical accuracy, and vocabulary used. Based on the analysis results, the server generates feedback and suggestions for the next lesson. This feedback includes specific advice such as "your pronunciation was good" or "review this grammar." The device displays this feedback to the user.

[0491] 5. Device connectivity and seamless access

[0492] The system can be accessed from a variety of devices, including smartphones, PCs, and tablets. No matter which device a user uses, their previous learning log and current progress are all synchronized, allowing them to continue their language learning seamlessly. The server manages communication between these devices and provides consistent session information across devices.

[0493] Specific examples

[0494] For example, suppose an English learner wants to use this system to learn new grammar. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation that incorporates appropriate grammar points. The generated conversation might be a question such as "What did you do yesterday?" If the user responds with "I went to the supermarket," the conversation is saved in the log. After the conversation is completed, analysis is performed and feedback is provided to the user, such as "Your use of the past tense is correct."

[0495] In this way, users receive a personalized learning experience, helping them learn a language more efficiently.

[0496] The processing flow will be explained below.

[0497] 1. User Registration and Login

[0498] Step 1:

[0499] A user opens the application and enters information such as their name, email address, desired password, and desired language of study on the new account registration screen.

[0500] Step 2:

[0501] The terminal transmits the entered registration information to the server.

[0502] Step 3:

[0503] The server validates the received registration information, specifically checking that the email address is formatted correctly and that the password meets the required criteria.

[0504] Step 4:

[0505] The server stores the user information in the database after successful validation.

[0506] Step 5:

[0507] The server returns a message to the terminal indicating that registration is complete, and the terminal displays this to the user.

[0508] 2. Start learning conversation

[0509] Step 1:

[0510] The user presses the "Start Conversation Learning" button on the application's home screen.

[0511] Step 2:

[0512] The terminal sends a "conversation learning start" request to the server.

[0513] Step 3:

[0514] The server retrieves the user's learning level from the database.

[0515] Step 4:

[0516] The server generates conversation content using generative artificial intelligence based on the acquired learning level.

[0517] Step 5:

[0518] The server transmits the generated conversation content to the terminal, which then displays it to the user.

[0519] 3. Conversation progress and log accumulation

[0520] Step 1:

[0521] The user responds to the conversation content displayed on the terminal by text or voice.

[0522] Step 2:

[0523] The terminal transmits the user's response to the server in real time.

[0524] Step 3:

[0525] The server stores the received responses in a database as a conversation log, which includes not only the user's responses but also the time the conversation occurred.

[0526] 4. Analysis and Feedback

[0527] Step 1:

[0528] After the conversation ends, the server analyzes the accumulated conversation log.

[0529] Step 2:

[0530] The server identifies the user's learning progress and areas for improvement based on the results of the analysis, which includes pronunciation, grammatical accuracy, and the variety of vocabulary used.

[0531] Step 3:

[0532] The server generates feedback based on the analysis, including specific advice such as "Use the past tense correctly" or "Use a more diverse vocabulary."

[0533] Step 4:

[0534] The server sends the generated feedback to the terminal, which displays it to the user.

[0535] 5. Device connectivity and seamless access

[0536] Step 1:

[0537] When a user accesses the system from a different device, the terminal sends the login information to the server.

[0538] Step 2:

[0539] The server verifies the authentication information and verifies that the user is authorized to access the site.

[0540] Step 3:

[0541] The server sends the latest learning log and progress information to the new device, which then displays it to the user, allowing the user to check their previous learning content and progress and continue their learning smoothly.

[0542] This series of steps allows users to continue learning a language 24 hours a day, 365 days a year, regardless of location.

[0543] Example 1

[0544] 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."

[0545] Conventional language learning systems have struggled to provide feedback tailored to each user's individual learning progress and optimal learning content. It has also been difficult to seamlessly synchronize learning data across different devices. This has resulted in an inefficient learning experience for users, slowing down their language acquisition progress.

[0546] 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.

[0547] In this invention, the server includes means for generating language learning content for a user using generative artificial intelligence, means for accumulating and analyzing conversation logs with the user, means for providing feedback according to the user's learning progress based on the analysis results, means for communicating with various devices and allowing the user to access the content from different devices, means for inputting and validating user information, means for saving the user information in a database, means for providing prompts for generating conversation content based on the user's learning level, means for transmitting and saving user responses in real time, and means for analyzing the conversation logs and generating suggestions for next learning content and feedback, thereby providing an optimal learning experience according to the user's individual learning progress and enabling effective language acquisition.

[0548] "Generative AI" is an AI technology that generates new content and data based on user input information.

[0549] "Language learning content" refers to teaching and practice materials that help users learn a particular language.

[0550] A "conversation log" refers to a record of a conversation between a user and a system, and is saved as text or audio data.

[0551] "Feedback" refers to the advice and evaluation provided by the system regarding the user's learning progress and performance.

[0552] "Various devices" refers to different hardware platforms such as smartphones, PCs, and tablets.

[0553] A "database" is a system for systematically storing and managing data such as user information and conversation logs.

[0554] A "prompt sentence" is an input sentence that serves as the basis for generative artificial intelligence to generate conversation content.

[0555] "User response" refers to the reply or input given by the user to the system.

[0556] "Real-time" refers to the situation where user input is processed the instant it is made, with little time delay.

[0557] This invention is an online system that uses generative artificial intelligence to support users' language learning. The system uses generative artificial intelligence to automatically generate content based on the user's learning level and preferences, and accumulates and analyzes conversation logs with the user to provide individually optimized feedback. The system is designed to be seamlessly accessible from various devices, including smartphones, PCs, and tablets.

[0558] User Registration and Login

[0559] The user opens the application and enters information such as name, email address, desired password, and desired language to learn on the new account registration screen. The device sends this information to the server. The server validates the information, and if validation is successful, saves the user information in a database (e.g., MySQL). A message indicating registration completion is returned to the device and displayed to the user.

[0560] Start learning conversation

[0561] The user presses the "Start Conversation Learning" button on the application's home screen. The device sends this request to the server. The server retrieves the user's learning level from the database and uses generative artificial intelligence (e.g., GPT-3 using the OpenAI API) to generate conversation content based on the user's level. The generated conversation content is sent to the device and displayed to the user.

[0562] Conversation progress and log accumulation

[0563] Users can initiate conversations with their avatars and respond via text or voice. The device sends the user's responses in real time to the server, which then stores the responses in a database as a conversation log. This ensures that all conversations are recorded and stored as data for later analysis.

[0564] Analysis and feedback

[0565] After the conversation ends, the server analyzes the accumulated conversation log. This analysis evaluates the user's pronunciation, grammatical accuracy, and vocabulary used. Based on the analysis results, the server generates feedback and suggestions for the next lesson. This feedback includes specific advice such as "your pronunciation was good" or "review this grammar." The device displays this feedback to the user.

[0566] Device Connectivity and Seamless Access

[0567] The system can be accessed from a variety of devices, including smartphones, PCs, and tablets. No matter which device a user uses, previous learning logs and current progress are all synchronized, allowing for seamless language learning. The server manages communication between these devices and provides consistent session information across devices.

[0568] Specific examples

[0569] For example, suppose an English learner wants to use this system to learn new grammar. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation incorporating appropriate grammar points. The generated conversation might be a question such as "What did you do yesterday?" If the user responds with "I went to the supermarket," the conversation is saved in the log. After the conversation is completed, analysis is performed and feedback is provided to the user, such as "Your use of the past tense is correct." In this way, users can receive an individually optimized learning experience and acquire languages ​​more efficiently.

[0570] Example prompts for generative AI models

[0571] The user's current learning level is beginner. Please generate conversation content appropriate for that level. The theme should be "daily life" and should include practice of past tense.

[0572] User Information:

[0573] Language of study: English

[0574] Learning level: Beginner

[0575] Example of a conversation to generate:

[0576] Question: What did you do yesterday?

[0577] Expected Answer: I went to the supermarket.

[0578] Based on this prompt, the generative AI generates conversational content appropriate to the user's learning progress, allowing the user to learn the language effectively.

[0579] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0580] Step 1:

[0581] A user opens the application and enters their name, email address, password, and language of study on the new account registration screen. This information is sent as input to the device, and then sent from the device to the server. The server validates the information, specifically checking the format of the email address, the strength of the password, etc. The output of this step is that if validation is successful, the user information is saved in a database (e.g. MySQL). If validation fails, an error message is returned to the device.

[0582] Step 2:

[0583] When a user presses the "Start Conversation Learning" button, the terminal sends this request to the server. The input is the conversation learning start request, and the server obtains the user's learning level from the database. Specifically, it extracts level information from the learning log table based on the user ID. The output of this step is the user's learning level information.

[0584] Step 3:

[0585] The server generates a prompt based on the acquired learning level information. The prompt is sent as input to a generative artificial intelligence (e.g., GPT-3 using the OpenAI API), which generates conversation content appropriate for the user's level. Specifically, the prompt includes instructions such as, "The user's current learning level is beginner. Please generate content about 'daily life' that includes practice in the past tense." The output of this step is the generated conversation content.

[0586] Step 4:

[0587] The generated conversation content is sent from the server to the terminal, which then displays it to the user. The input is the generated conversation content from the server, and through this display, the user can start conversation learning. The output of this step is the conversation content displayed to the user.

[0588] Step 5:

[0589] The user initiates a conversation with the avatar and responds with text or voice. This response is sent by the device to the server in real time. The input is text or voice data from the user. The server stores this as a conversation log in the database. Specifically, it stores the text data in a conversation log table and the voice data in audio file format. The output of this step is the conversation log stored in the database.

[0590] Step 6:

[0591] After the conversation ends, the server analyzes the accumulated conversation log. The input is the stored conversation log data, and the analysis evaluates the user's pronunciation, grammatical accuracy, and vocabulary used. Specifically, natural language processing tools are used to analyze the text data, and speech recognition technology is used for the audio data. The output of this step is the analysis results.

[0592] Step 7:

[0593] The server generates feedback and suggestions for the next learning content based on the analysis results. Specifically, it automatically generates feedback sentences that include specific advice such as "your pronunciation was good" or "review this grammar." The input is the analysis results, and the generated feedback sentences are the output of this step.

[0594] Step 8:

[0595] The server generates feedback sentences, which are sent to the terminal and displayed by the terminal to the user. The input is the feedback sentences from the server, which the user can use to proceed to the next learning step. The output of this step is the feedback sentences displayed to the user.

[0596] Points to note

[0597] Data transmission and reception at each step is performed via the Internet.

[0598] Access to the database and storage of data is done securely.

[0599] Appropriate security measures are in place to protect user privacy.

[0600] (Application example 1)

[0601] 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."

[0602] Modern factories often employ workers from multiple countries, and language differences can have a serious impact on work efficiency and safety. In particular, serious problems can arise if work instructions and safety precautions are not communicated accurately. Furthermore, as robots and automation systems are widely used in factories, these devices must be able to communicate smoothly with humans. However, while current language learning systems provide optimal learning content tailored to individual learning situations, they are not specialized for the unique work environment of a factory. Therefore, there is a need for systems that facilitate communication in factory environments and strengthen collaboration between workers and machines.

[0603] 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.

[0604] In this invention, the server includes means for generating language learning content for a user using generative artificial intelligence, means for accumulating and analyzing conversation logs with the user, means for providing feedback according to the user's learning progress based on the analysis results, means for communicating with various devices and enabling the user to access the server from different devices, means for linking with equipment used in a factory environment and generating dialogues for language learning, and means for analyzing the conversation logs based on the dialogues and providing feedback related to factory work. This enables efficient and safe communication between multinational workers working in factories and robots.

[0605] "Generative artificial intelligence" refers to an artificial intelligence system that has the ability to automatically generate new data and content based on given data and conditions.

[0606] "User" refers to the person or device that uses this system to learn a language.

[0607] "Language learning content" refers to learning materials, interactive exercises, and other learning materials used by users to study.

[0608] "Conversation log" refers to a record of the conversation between the user and the system.

[0609] "Analysis results" refers to the data and evaluations obtained by analyzing the conversation logs.

[0610] "Feedback" refers to advice and evaluation provided to users based on their learning progress.

[0611] "Various devices" refers to devices that can access the system, such as smartphones, tablets, PCs, smart glasses, and head-mounted displays.

[0612] "Factory environment" refers to the physical location where products are manufactured and assembled, and the working conditions therein.

[0613] "Device" refers to a device such as a robot or automation system that operates in conjunction with the language learning system.

[0614] "Dialogue" refers to conversational communication between a user and a system.

[0615] This invention is a system for supporting language learning for robots in a factory environment. This system uses generative artificial intelligence to generate learning content for users (here, robots), accumulates and analyzes conversation logs with the users, and provides feedback based on the analysis results. This system also communicates with various devices (smartphones, tablets, PCs, smart glasses, head-mounted displays, etc.), allowing users to access the system from different devices. This system also works in conjunction with equipment used in the factory environment.

[0616] System Program

[0617] The server implements a program with the following functions:

[0618] 1. Language learning content generation:

[0619] The server uses generative artificial intelligence to generate optimal conversation content in real time based on the user's registration information and past learning logs. For this purpose, a generative AI model is used.

[0620] 2. Conversation log storage and analysis:

[0621] The server stores conversation logs with users in the form of text and audio data, analyzes them, and automatically evaluates the user's learning progress. Natural language processing (NLP) algorithms are used to analyze the conversation logs.

[0622] 3. Providing Feedback:

[0623] Based on the analysis results, the server provides feedback based on the user's learning progress, including accuracy of pronunciation, proper use of grammar, and vocabulary use.

[0624] 4. Communication between devices:

[0625] The server communicates seamlessly with various devices, allowing users to access the content from different devices, using a cloud-based synchronization mechanism.

[0626] 5. Collaboration in a factory environment:

[0627] The server interacts with the equipment used in the factory environment and generates dialogues for language learning that simulate specific situations related to factory work.

[0628] Processing Description

[0629] The server receives the user's registration information (first name, last name, email address, password, and language to learn) and stores it in a database. When the robot presses the "Start Learning" button, the server generates the optimal conversation content based on the registration information and past learning logs. This conversation content is sent to the robot, and the robot proceeds with its work based on the received content.

[0630] Conversation logs are stored as text and audio data for analysis and feedback. The server analyzes these logs and generates feedback based on the robot's learning progress. This feedback is displayed on the robot's display and can be used to improve the robot's next task.

[0631] For example, consider a scenario in which a factory robot responds to the Japanese question, "Please tell me what you did yesterday," with "I did welding yesterday." In this case, the server stores the content of this dialogue and evaluates the accuracy of pronunciation and grammar.

[0632] Example prompt sentence:

[0633] "Create a language learning dialogue for a factory robot to learn Japanese at its current skill level. The robot should practice sentences it might use during daily operations, such as greetings and task descriptions."

[0634] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0635] Step 1:

[0636] A user launches an application from their device and enters information such as their name, email address, password, and preferred language into the new account registration screen. This information is then sent from the device to the server, where it is validated.

[0637] Input: User information (name, email address, password, preferred language)

[0638] Data processing / calculation: Validation of input information

[0639] Output: Validation results, saved to database

[0640] Step 2:

[0641] The server stores the user information whose validation has been successful in the database and sends a message to the terminal indicating that the user registration has been completed.

[0642] Input: Validation result

[0643] Data processing / calculation: Saving user information to a database

[0644] Output: Registration complete message

[0645] Step 3:

[0646] The user presses the "Start Conversation Learning" button on the application's home screen. This request is sent from the device to the server, which retrieves the user's registration information and past learning logs from the database.

[0647] Input: User's "Start conversation learning" request

[0648] Data processing / calculation: Retrieving information from a database

[0649] Output: User information, past learning logs

[0650] Step 4:

[0651] The server uses a generative AI model to generate conversation content appropriate for the user's level based on the acquired user information and past learning logs, and uses appropriate prompts for this generation.

[0652] Input: User information, past learning log

[0653] Data processing / calculation: Generating conversation content using generative AI models

[0654] Output: Generated conversation

[0655] Step 5:

[0656] The generated conversation is sent to the device and displayed to the user, who can then initiate a conversation with the avatar and respond with text or voice, which is then sent to the server in real time.

[0657] Input: Generated conversation

[0658] Data processing / calculation: Display to user

[0659] Output: User response (text or voice data)

[0660] Step 6:

[0661] The server stores the received user responses in a database as a conversation log, which is then accumulated as data for analysis.

[0662] Input: User response (text or voice data)

[0663] Data processing / calculation: Accumulation as conversation log

[0664] Output: Saved conversation logs

[0665] Step 7:

[0666] After the conversation ends, the server analyzes the accumulated conversation log and generates feedback based on the analysis results, including corrections to pronunciation and grammar, as well as compliments.

[0667] Input: Saved Conversation Log

[0668] Data processing / calculation: Analysis of conversation logs, generation of feedback

[0669] Output: Analysis results, feedback

[0670] Step 8:

[0671] The generated feedback is sent to the terminal and displayed to the user, who then uses the feedback to improve their next conversation practice.

[0672] Input: Analysis results, feedback

[0673] Data processing / calculation: Display to user

[0674] Output: Displayed feedback

[0675] Step 9:

[0676] The server communicates with various devices, allowing users to seamlessly access the app from different devices, allowing them to check their learning progress from any device.

[0677] Input: Device connection request

[0678] Data processing / calculation: Communication management between devices

[0679] Output:Seamless Access

[0680] 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.

[0681] MODE FOR CARRYING OUT THE INVENTION

[0682] This invention is an online language learning system that combines generative artificial intelligence and an emotion engine. This system is designed to allow users to learn languages ​​at any time and in an optimal environment, and can be accessed from a variety of devices. The operation of this system is described in detail below.

[0683] 1. User Registration and Login

[0684] A user opens a language learning application and enters their name, email address, desired password, and desired language into the new account registration screen. The device sends this information to the server. The server validates the received information and stores information that is deemed correct in a database. Once registration is complete, the server sends a confirmation message to the device, which displays it to the user.

[0685] 2. Start learning conversation

[0686] The user presses the "Start Conversation Learning" button on the application's home screen. The device sends this request to the server. The server retrieves the user's learning level from the database and uses generative artificial intelligence to generate optimal conversation content based on the user's level. The generated conversation content is sent to the device, which then displays it to the user.

[0687] 3. Emotion Recognition and Log Accumulation

[0688] When a user responds to a conversation, the device sends the user's voice and text data to the server. The server then stores the received data in a database as a conversation log. The device's built-in emotion engine also analyzes the user's response data and identifies their emotional state (e.g., joy, sadness, surprise, etc.). The emotion identification results are also saved along with the conversation log.

[0689] 4. Analysis and Feedback

[0690] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data. The emotion engine evaluates the user's emotional state as they study and generates feedback based on this. For example, if the user is feeling stressed, it can provide feedback on how to study in a relaxed manner. Based on the analysis, the server also identifies the user's learning progress and areas for improvement, generating feedback suggesting the next course of study.

[0691] 5. Device connectivity and seamless access

[0692] This system can be accessed from various devices such as smartphones, PCs, and tablets. When a user logs in using a different device, the device sends authentication information to the server, which then verifies the authentication information. If authentication is successful, the server sends the latest learning log and progress information to the new device, which then displays it to the user. This allows users to check their previous learning content and progress, and continue learning seamlessly from any device.

[0693] Specific examples

[0694] For example, suppose an English learner wants to learn a new word. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation that includes the new word. The generated conversation might be a question such as, "Where did you go today?" If the user responds, "I went to the library," the conversation is saved in the log in real time. Furthermore, an emotion engine analyzes the user's voice to determine whether the user is relaxed or stressed. After the conversation ends, the system generates feedback such as, "Your pronunciation is accurate, and you seem to be learning in a relaxed manner. Next, let's review past tense grammar," and the device displays this to the user.

[0695] In this way, users can get a learning experience that is individually optimized to their mood and level of understanding on that day.

[0696] The processing flow will be explained below.

[0697] 1. User Registration and Login

[0698] Step 1:

[0699] A user opens a language learning application and enters information such as their name, email address, desired password, and language to learn on the new account registration screen.

[0700] Step 2:

[0701] The terminal transmits the input information to the server.

[0702] Step 3:

[0703] The server validates the received information and stores the information that is determined to be correct in a database.

[0704] Step 4:

[0705] The server sends a registration completion message to the terminal, which the terminal displays to the user.

[0706] 2. Start learning conversation

[0707] Step 1:

[0708] The user presses the "Start Conversation Learning" button on the application's home screen.

[0709] Step 2:

[0710] The terminal sends a learning start request to the server.

[0711] Step 3:

[0712] The server retrieves the user's learning level from the database.

[0713] Step 4:

[0714] The server generates conversation content using generative artificial intelligence based on the acquired learning level.

[0715] Step 5:

[0716] The server transmits the generated conversation content to the terminal, which then displays it to the user.

[0717] 3. Emotion Recognition and Log Accumulation

[0718] Step 1:

[0719] The user responds to the displayed conversation content by text or voice.

[0720] Step 2:

[0721] The terminal transmits the user's response to the server in real time.

[0722] Step 3:

[0723] The server stores the received response data in a database as a conversation log.

[0724] Step 4:

[0725] The server uses an emotion engine to analyze the response data and identify the user's emotional state.

[0726] Step 5:

[0727] The server also stores the identified emotion data along with the conversation log.

[0728] 4. Analysis and Feedback

[0729] Step 1:

[0730] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data.

[0731] Step 2:

[0732] Based on the analysis results, the server evaluates the user's learning progress and identifies areas for improvement.

[0733] Step 3:

[0734] The server generates feedback based on the evaluation results, including specific advice on learning progress and suggestions for next learning content.

[0735] Step 4:

[0736] The server sends the generated feedback to the terminal, which displays it to the user.

[0737] 5. Device connectivity and seamless access

[0738] Step 1:

[0739] When a user logs in from a different device, the terminal sends the login information to the server.

[0740] Step 2:

[0741] The server authenticates the received login information and verifies the user's access rights.

[0742] Step 3:

[0743] After successful authentication, the server sends the latest learning log and progress information to the new device.

[0744] Step 4:

[0745] The device displays this information to the user, allowing them to check their previous learning content and progress and continue their learning seamlessly.

[0746] Specific examples

[0747] For example, when an English learner presses the "Start Conversation Learning" button, the server reads the user's learning log and generates new conversation content. If the generated conversation content is "How was your day?", the user might respond with "I went to the park." The device sends this response to the server, which analyzes and saves the "enjoying" state along with the conversation log using its emotion engine. After the conversation ends, the server generates feedback such as "Your pronunciation is good and you seem to be learning in a relaxed manner. Let's move on," and the device displays this to the user. In this way, users can obtain an optimal learning experience that also takes their emotions into consideration.

[0748] Example 2

[0749] 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."

[0750] Language learning systems need to effectively assess users' learning progress and provide optimal feedback. It is also important to make the learning environment more flexible by allowing users to easily access the learning environment from any device. Furthermore, it is desirable to analyze users' emotional states and more individually tailor the learning experience.

[0751] 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.

[0752] In this invention, the server includes: a means for generating language learning content for a user using generative artificial intelligence; a means for accumulating and analyzing conversation logs with the user; a means for providing feedback according to the user's learning progress based on the analysis results; a means for analyzing the user's response data using an emotion engine and identifying their emotional state; and a means for communicating with various devices and allowing the user to access the content from different devices. This allows for effective evaluation of the user's learning progress and provides optimal feedback. Furthermore, by analyzing the user's emotional state in real time and reflecting this in the feedback, the learning experience can be more personalized and an environment can be realized where the content can be seamlessly accessed from different devices.

[0753] "Generative AI" is an AI technology that generates language learning content in real time based on user input.

[0754] A "conversation log" is data that records the content of a conversation between a user and a system, and includes text data and voice data.

[0755] An "emotion engine" is a software component that analyzes user response data to identify the user's emotional state.

[0756] "Feedback" refers to evaluations and advice provided based on a user's learning progress, including information suggesting improvements to learning content and next steps.

[0757] "Learning progress" is an index that indicates the degree of progress of a user's language learning, and is evaluated based on the results of analysis of conversation logs and emotion data.

[0758] "Storage means" is a function for saving conversation logs and emotional data in a database.

[0759] "Analysis" refers to the process of using accumulated data to evaluate the user's learning progress and emotional state.

[0760] "Device" refers to any electronic device used by a user to access the system, including a smartphone, PC, tablet, etc.

[0761] "Communication" refers to the process of exchanging data between different devices over a network.

[0762] "Real-time" refers to data being generated and processed instantly.

[0763] This invention is an online language learning system that combines generative artificial intelligence and an emotion engine. This system is designed to allow users to learn languages ​​at any time and in an optimal environment, and can be accessed from a variety of devices. The operation of this system is described in detail below.

[0764] 1. User Registration and Login

[0765] A user opens a language learning application and enters their name, email address, desired password, desired language, etc. into the new account registration screen.

[0766] The terminal sends this information to the server.

[0767] The server validates the received information and stores the information that is deemed correct in a database (e.g., MySQL or PostgreSQL).

[0768] Once registration is complete, the server sends a confirmation message to the terminal, which the terminal displays to the user.

[0769] 2. Start learning conversation

[0770] The user presses the "Start Conversation Learning" button on the application's home screen.

[0771] The terminal sends this request to the server.

[0772] The server retrieves the user's learning level from the database and generates optimal conversation content based on the user's level using generative artificial intelligence (e.g., GPT-4 model). The generated conversation content is sent to the device, which then displays it to the user.

[0773] 3. Emotion Recognition and Log Accumulation

[0774] When the user responds to the conversation, the terminal transmits the user's voice data and text data to the server.

[0775] The server stores the received data in a database as a conversation log. The built-in emotion engine analyzes the user's response data and identifies their emotional state (e.g., joy, sadness, surprise, etc.). The emotion identification results are also stored along with the conversation log.

[0776] 4. Analysis and Feedback

[0777] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data. The emotion engine evaluates the user's emotional state as they study and generates feedback based on this. For example, if the user is feeling stressed, it will provide feedback on how to study in a relaxed manner. Based on the analysis, the server also identifies the user's learning progress and areas for improvement, and generates feedback suggesting the next course of study.

[0778] 5. Device connectivity and seamless access

[0779] The system can be accessed from a variety of devices, including smartphones, PCs, and tablets.

[0780] When a user logs in using a different device, the terminal sends the authentication information to the server.

[0781] The server verifies the authentication information and, if successful, sends the latest learning log and progress information to the new device.

[0782] The device displays this to the user, allowing them to check their previous learning content and progress, and continue learning seamlessly from any device.

[0783] Specific examples

[0784] For example, suppose an English learner wants to learn new words. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation that includes the new words. The generated conversation might include questions such as "Where did you go today?"

[0785] When the user responds, "I went to the library," the conversation is logged in real time. Furthermore, an emotion engine analyzes the user's voice to determine whether they are relaxed or stressed. After the conversation ends, the system generates feedback such as, "Your pronunciation is accurate, and you seem to be learning in a relaxed manner. Next, let's review past tense grammar," and the device displays this to the user.

[0786] Prompt Sentence Examples

[0787] Specific conversation content can be generated by writing prompts to the generative AI model as follows:

[0788] For users who click the "Start Conversation Learning" button, generate a conversation appropriate to their level. The language of study is English, and the learner is at beginner level. Generate a conversation that includes questions to teach the learner new vocabulary.

[0789] This prompt allows the generative AI model to generate appropriate conversational content and provide it to the user.

[0790] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0791] Processing Steps

[0792] Step 1: User Registration and Login

[0793] 1. Enter information

[0794] A user opens a language learning application and enters their name, email address, desired password, and the language they wish to learn.

[0795] Input: Name, Email Address, Password, Language

[0796] Output: Request to send input data

[0797] 2. Data Transmission

[0798] The terminal transmits the information entered by the user to the server.

[0799] Input: Input data

[0800] Output: Send data to the server

[0801] 3. Validation and Storage

[0802] The server validates the submitted data and stores it in a database if it is deemed correct, for example by checking the format of the email address or the strength of the password.

[0803] Input: Input data

[0804] Output: Validation success or failure

[0805] 4. Sending a registration completion message

[0806] If validation is successful, the server sends the user a registration completion message, which the terminal displays to the user.

[0807] Input: Validation successful

[0808] Output: Display a confirmation message

[0809] Step 2: Start learning conversations

[0810] 1. Send a lesson start request

[0811] The user presses the "Start Conversation Learning" button on the application's home screen.

[0812] Input: Start learning request

[0813] Output: Request sent to server

[0814] 2. Obtaining user level and generating conversation content

[0815] The server obtains the user's learning level from the database and generates optimal conversation content using generative artificial intelligence (e.g., GPT-4).

[0816] Input: User learning level

[0817] Output: Generated conversation

[0818] 3. Display of conversation contents

[0819] The generated conversation content is sent to the terminal, which displays it to the user.

[0820] Input: Generated conversation

[0821] Output: Display of conversation

[0822] Step 3: Emotion recognition and logging

[0823] 1. Sending conversation response data

[0824] When the user responds to the conversation, the terminal transmits the voice data and text data to the server.

[0825] Input: Response data (audio or text)

[0826] Output: Send data to the server

[0827] 2. Save conversation logs

[0828] The server stores the received data in a database as a conversation log.

[0829] Input: Response data

[0830] Output: Save to database

[0831] 3. Emotional state analysis

[0832] The built-in emotion engine analyzes the user's response data and identifies their emotional state, such as joy, sadness, or surprise, based on their voice data.

[0833] Input: Response data

[0834] Output: Save the sentiment analysis results

[0835] Step 4: Analyze and provide feedback

[0836] 1. Log and emotion data analysis

[0837] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data.

[0838] Input: Conversation logs, emotion data

[0839] Output: Analysis results

[0840] 2. Generate feedback

[0841] The emotion engine generates optimal feedback for the user based on the analysis results. For example, if the user is relaxed, it generates feedback such as "You are able to study in a relaxed state."

[0842] Input: Analysis results

[0843] Output: Feedback message

[0844] 3. Viewing Feedback

[0845] The generated feedback is sent to the terminal, which displays it to the user.

[0846] Input: Feedback message

[0847] Output: Display feedback

[0848] Step 5: Device connection and seamless access

[0849] 1. Log in from your device

[0850] When a user logs in on a different device, the terminal sends authentication information to the server.

[0851] Input: Credentials

[0852] Output: Authentication request to the server

[0853] 2. Verify your credentials and synchronize your data

[0854] The server verifies the authentication information and, if successful, sends the latest learning log and progress information to the new device.

[0855] Input: Credentials

[0856] Output: Send training data

[0857] 3. View your learning log and progress information

[0858] The device displays this to the user, allowing them to check their previous learning content and progress, and continue learning seamlessly from any device.

[0859] Input: Training data

[0860] Output: Display of learning information

[0861] (Application example 2)

[0862] 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."

[0863] Conventional language learning systems were unable to provide learning content that took the user's emotional state into consideration, resulting in issues with learning efficiency and continuity. Furthermore, because appetite is significantly influenced by emotions, it was also unable to simultaneously provide meal suggestions based on the user's emotions. This created a need for a way to reduce learning stress and improve the overall learning experience.

[0864] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0865] In this invention, the server includes means for generating language learning content for a user using generative artificial intelligence, means for accumulating and analyzing conversation logs with the user, means for providing feedback according to the user's learning progress based on the analysis results, means for communicating with various devices and allowing the user to access the server from different devices, and means for analyzing the user's emotional data and recommending optimal meals based on the analysis results, thereby making it possible to provide content and suggest optimal meals that take the user's emotional state into consideration.

[0866] "Generative AI" is an AI technology that creates appropriate content and suggestions in real time based on the user's learning and emotional state.

[0867] "Conversation log" refers to recorded data that collects and stores the contents of conversations users have as text and audio data.

[0868] "Emotional data" is information that indicates the emotional state of a user obtained by analyzing the user's voice or text.

[0869] "Feedback" is advice or information about next steps or areas for improvement that is provided based on the user's learning progress and emotional state.

[0870] "Various devices" refers to the various devices that users use to access the site, such as smartphones, PCs, and tablets.

[0871] "Communication means" refers to the network means used by users to continuously access the service from different devices.

[0872] "Method of recommending meals" is a technology that suggests optimal meals based on the user's emotional data.

[0873] This invention is a system that combines generative artificial intelligence and an emotion engine to optimize an online language learning system and a food delivery application. Specific embodiments of this system are described below.

[0874] Basic Features

[0875] The system works on various devices, including smartphones, PCs, and tablets. Users can register and log in to receive optimal content and feedback based on their learning progress and emotional state. The system also supports seamless access across different devices.

[0876] Program Generation and Processing Description

[0877] The server first generates appropriate learning content using generative artificial intelligence based on the information and emotional state entered by the user, using specific software libraries called EmotionEngine and FoodRecommendationAI.

[0878] 1. The server receives the user information

[0879] When a user logs in to their account through their device, the server retrieves the user's profile information and past learning logs.

[0880] 2. Emotion Data Analysis

[0881] The user inputs their current emotional state and sends it to the server, which then uses the EmotionEngine to analyze this data and determine the user's emotional state.

[0882] 3. Generating learning content and feedback

[0883] The server uses generative artificial intelligence to generate optimal conversation content based on the user's learning progress, and also analyzes the user's stress level and relaxation state based on emotional data, providing appropriate feedback.

[0884] 4. Dietary Recommendations

[0885] Furthermore, it uses generative artificial intelligence to recommend optimal meals based on emotional data: for example, if the user is stressed, it will recommend relaxing meals, and if they are relaxed, it will recommend nutritious meals.

[0886] Usage example

[0887] If a user logs in to a food delivery app and enters "stress" as their emotional state, the server will analyze this information using the Emotion Engine and use Food Recommendation AI to recommend "meals that have a relaxing effect." Specific recommendations include a "Japanese meal set" and "chamomile tea."

[0888] Example prompts to be input to the generative AI model

[0889] An example prompt might have the following format:

[0890] User Emotion: Stress

[0891] User preference: Japanese food

[0892] Output format: Suggest a relaxing meal.

[0893] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0894] Step 1:

[0895] The user opens the smartphone app and enters login information (user ID and password). The device sends this information to the server, which then authenticates the user. If authentication is successful, the server retrieves the user's profile information and past learning logs and sends them to the device. In this process, the input is the user's login information, and the output is the user's profile information and past learning logs. Data processing and data calculation involve authentication and retrieval of data from the database.

[0896] Step 2:

[0897] The user inputs their current emotional state. For example, emotions such as "stressed" or "relaxed" are input into a smartphone app. The device sends this emotional information to the server, which then analyzes the data using the Emotion Engine. The input is the user's emotional state, and the output is the analyzed emotional data. Data processing and data calculation are emotion analysis.

[0898] Step 3:

[0899] The server uses generative artificial intelligence to generate appropriate learning content in real time based on emotional data and past learning logs. Optimal conversation content is generated based on the user's learning progress and level. The input is emotional data and learning logs, and the output is the generated learning content. Data processing and data calculation are used to generate learning content.

[0900] Step 4:

[0901] The generated learning content is sent to the terminal and displayed to the user. The user practices the conversation and responds in voice or text format. The terminal sends this response data to the server. The input is the generated learning content, and the output is the user's response data. Data processing and data calculation involve receiving the user's input.

[0902] Step 5:

[0903] The server receives and stores the user's conversation log as text and audio data. It also analyzes the conversation log to automatically evaluate learning progress. The input is the user's response data, and the output is the analyzed learning progress data. Data processing and data calculation involve the analysis and storage of the conversation log.

[0904] Step 6:

[0905] Based on the analysis results, the server provides feedback according to the user's learning progress. This feedback is sent to the terminal and displayed to the user. The input is learning progress data, and the output is feedback. Data processing and data calculation are used to generate feedback.

[0906] Step 7:

[0907] Based on the emotion data, the server uses Food Recommendation AI to recommend the most suitable meal. This recommendation is also sent to the device and displayed to the user. The input is emotion data, and the output is the meal recommendation. Data processing and data calculation are used to generate the meal recommendation.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] [Third embodiment]

[0912] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0913] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0914] 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).

[0915] 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.

[0916] 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.

[0917] 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).

[0918] 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.

[0919] 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.

[0920] 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.

[0921] 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.

[0922] 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.

[0923] 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."

[0924] MODE FOR CARRYING OUT THE INVENTION

[0925] This invention is an online system that uses generative artificial intelligence to support users' language learning. This system uses generative artificial intelligence to automatically generate content based on the user's learning level and preferences, and accumulates and analyzes conversation logs with the user to provide individually optimized feedback. The system is also designed to allow users to access it seamlessly from different devices.

[0926] The operation of this system will be explained below with specific examples.

[0927] 1. User Registration and Login

[0928] The user opens the application and enters information such as name, email address, desired password, and desired language to learn on the new account registration screen. The device sends this information to the server, which validates the information. If validation is successful, the server saves the user information in the database and returns a message to the device indicating registration is complete.

[0929] 2. Start learning conversation

[0930] The user presses the "Start Conversation Learning" button on the application's home screen. The device sends this request to the server. The server retrieves the user's learning level from the database and uses generative artificial intelligence to generate conversation content based on the user's level. This generated conversation content is sent to the device and displayed to the user.

[0931] 3. Conversation progress and log accumulation

[0932] Users can initiate conversations with their avatars and respond via text or voice. The device sends the user's responses in real time to the server, which then stores the responses in a database as a conversation log. This ensures that all conversations are recorded and stored as data for later analysis.

[0933] 4. Analysis and Feedback

[0934] After the conversation ends, the server analyzes the accumulated conversation log. The analysis evaluates the user's pronunciation, grammatical accuracy, and vocabulary used. Based on the analysis results, the server generates feedback and suggestions for the next lesson. This feedback includes specific advice such as "your pronunciation was good" or "review this grammar." The device displays this feedback to the user.

[0935] 5. Device connectivity and seamless access

[0936] The system can be accessed from a variety of devices, including smartphones, PCs, and tablets. No matter which device a user uses, their previous learning log and current progress are all synchronized, allowing them to continue their language learning seamlessly. The server manages communication between these devices and provides consistent session information across devices.

[0937] Specific examples

[0938] For example, suppose an English learner wants to use this system to learn new grammar. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation that incorporates appropriate grammar points. The generated conversation might be a question such as "What did you do yesterday?" If the user responds with "I went to the supermarket," the conversation is saved in the log. After the conversation is completed, analysis is performed and feedback is provided to the user, such as "Your use of the past tense is correct."

[0939] In this way, users receive a personalized learning experience, helping them learn a language more efficiently.

[0940] The processing flow will be explained below.

[0941] 1. User Registration and Login

[0942] Step 1:

[0943] A user opens the application and enters information such as their name, email address, desired password, and desired language of study on the new account registration screen.

[0944] Step 2:

[0945] The terminal transmits the entered registration information to the server.

[0946] Step 3:

[0947] The server validates the received registration information, specifically checking that the email address is formatted correctly and that the password meets the required criteria.

[0948] Step 4:

[0949] The server stores the user information in the database after successful validation.

[0950] Step 5:

[0951] The server returns a message to the terminal indicating that registration is complete, and the terminal displays this to the user.

[0952] 2. Start learning conversation

[0953] Step 1:

[0954] The user presses the "Start Conversation Learning" button on the application's home screen.

[0955] Step 2:

[0956] The terminal sends a "conversation learning start" request to the server.

[0957] Step 3:

[0958] The server retrieves the user's learning level from the database.

[0959] Step 4:

[0960] The server generates conversation content using generative artificial intelligence based on the acquired learning level.

[0961] Step 5:

[0962] The server transmits the generated conversation content to the terminal, which then displays it to the user.

[0963] 3. Conversation progress and log accumulation

[0964] Step 1:

[0965] The user responds to the conversation content displayed on the terminal by text or voice.

[0966] Step 2:

[0967] The terminal transmits the user's response to the server in real time.

[0968] Step 3:

[0969] The server stores the received responses in a database as a conversation log, which includes not only the user's responses but also the time the conversation occurred.

[0970] 4. Analysis and Feedback

[0971] Step 1:

[0972] After the conversation ends, the server analyzes the accumulated conversation log.

[0973] Step 2:

[0974] The server identifies the user's learning progress and areas for improvement based on the results of the analysis, which includes pronunciation, grammatical accuracy, and the variety of vocabulary used.

[0975] Step 3:

[0976] The server generates feedback based on the analysis, including specific advice such as "Use the past tense correctly" or "Use a more diverse vocabulary."

[0977] Step 4:

[0978] The server sends the generated feedback to the terminal, which displays it to the user.

[0979] 5. Device connectivity and seamless access

[0980] Step 1:

[0981] When a user accesses the system from a different device, the terminal sends the login information to the server.

[0982] Step 2:

[0983] The server verifies the authentication information and verifies that the user is authorized to access the site.

[0984] Step 3:

[0985] The server sends the latest learning log and progress information to the new device, which then displays it to the user, allowing the user to check their previous learning content and progress and continue their learning smoothly.

[0986] This series of steps allows users to continue learning a language 24 hours a day, 365 days a year, regardless of location.

[0987] Example 1

[0988] 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."

[0989] Conventional language learning systems have struggled to provide feedback tailored to each user's individual learning progress and optimal learning content. It has also been difficult to seamlessly synchronize learning data across different devices. This has resulted in an inefficient learning experience for users, slowing down their language acquisition progress.

[0990] 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.

[0991] In this invention, the server includes means for generating language learning content for a user using generative artificial intelligence, means for accumulating and analyzing conversation logs with the user, means for providing feedback according to the user's learning progress based on the analysis results, means for communicating with various devices and allowing the user to access the content from different devices, means for inputting and validating user information, means for saving the user information in a database, means for providing prompts for generating conversation content based on the user's learning level, means for transmitting and saving user responses in real time, and means for analyzing the conversation logs and generating suggestions for next learning content and feedback, thereby providing an optimal learning experience according to the user's individual learning progress and enabling effective language acquisition.

[0992] "Generative AI" is an AI technology that generates new content and data based on user input information.

[0993] "Language learning content" refers to teaching and practice materials that help users learn a particular language.

[0994] A "conversation log" refers to a record of a conversation between a user and a system, and is saved as text or audio data.

[0995] "Feedback" refers to the advice and evaluation provided by the system regarding the user's learning progress and performance.

[0996] "Various devices" refers to different hardware platforms such as smartphones, PCs, and tablets.

[0997] A "database" is a system for systematically storing and managing data such as user information and conversation logs.

[0998] A "prompt sentence" is an input sentence that serves as the basis for generative artificial intelligence to generate conversation content.

[0999] "User response" refers to the reply or input given by the user to the system.

[1000] "Real-time" refers to the situation where user input is processed the instant it is made, with little time delay.

[1001] This invention is an online system that uses generative artificial intelligence to support users' language learning. The system uses generative artificial intelligence to automatically generate content based on the user's learning level and preferences, and accumulates and analyzes conversation logs with the user to provide individually optimized feedback. The system is designed to be seamlessly accessible from various devices, including smartphones, PCs, and tablets.

[1002] User Registration and Login

[1003] The user opens the application and enters information such as name, email address, desired password, and desired language to learn on the new account registration screen. The device sends this information to the server. The server validates the information, and if validation is successful, saves the user information in a database (e.g., MySQL). A message indicating registration completion is returned to the device and displayed to the user.

[1004] Start learning conversation

[1005] The user presses the "Start Conversation Learning" button on the application's home screen. The device sends this request to the server. The server retrieves the user's learning level from the database and uses generative artificial intelligence (e.g., GPT-3 using the OpenAI API) to generate conversation content based on the user's level. The generated conversation content is sent to the device and displayed to the user.

[1006] Conversation progress and log accumulation

[1007] Users can initiate conversations with their avatars and respond via text or voice. The device sends the user's responses in real time to the server, which then stores the responses in a database as a conversation log. This ensures that all conversations are recorded and stored as data for later analysis.

[1008] Analysis and feedback

[1009] After the conversation ends, the server analyzes the accumulated conversation log. This analysis evaluates the user's pronunciation, grammatical accuracy, and vocabulary used. Based on the analysis results, the server generates feedback and suggestions for the next lesson. This feedback includes specific advice such as "your pronunciation was good" or "review this grammar." The device displays this feedback to the user.

[1010] Device Connectivity and Seamless Access

[1011] The system can be accessed from a variety of devices, including smartphones, PCs, and tablets. No matter which device a user uses, previous learning logs and current progress are all synchronized, allowing for seamless language learning. The server manages communication between these devices and provides consistent session information across devices.

[1012] Specific examples

[1013] For example, suppose an English learner wants to use this system to learn new grammar. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation incorporating appropriate grammar points. The generated conversation might be a question such as "What did you do yesterday?" If the user responds with "I went to the supermarket," the conversation is saved in the log. After the conversation is completed, analysis is performed and feedback is provided to the user, such as "Your use of the past tense is correct." In this way, users can receive an individually optimized learning experience and acquire languages ​​more efficiently.

[1014] Example prompts for generative AI models

[1015] The user's current learning level is beginner. Please generate conversation content appropriate for that level. The theme should be "daily life" and should include practice of past tense.

[1016] User Information:

[1017] Language of study: English

[1018] Learning level: Beginner

[1019] Example of a conversation to generate:

[1020] Question: What did you do yesterday?

[1021] Expected Answer: I went to the supermarket.

[1022] Based on this prompt, the generative AI generates conversational content appropriate to the user's learning progress, allowing the user to learn the language effectively.

[1023] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1024] Step 1:

[1025] A user opens the application and enters their name, email address, password, and language of study on the new account registration screen. This information is sent as input to the device, and then sent from the device to the server. The server validates the information, specifically checking the format of the email address, the strength of the password, etc. The output of this step is that if validation is successful, the user information is saved in a database (e.g. MySQL). If validation fails, an error message is returned to the device.

[1026] Step 2:

[1027] When a user presses the "Start Conversation Learning" button, the terminal sends this request to the server. The input is the conversation learning start request, and the server obtains the user's learning level from the database. Specifically, it extracts level information from the learning log table based on the user ID. The output of this step is the user's learning level information.

[1028] Step 3:

[1029] The server generates a prompt based on the acquired learning level information. The prompt is sent as input to a generative artificial intelligence (e.g., GPT-3 using the OpenAI API), which generates conversation content appropriate for the user's level. Specifically, the prompt includes instructions such as, "The user's current learning level is beginner. Please generate content about 'daily life' that includes practice in the past tense." The output of this step is the generated conversation content.

[1030] Step 4:

[1031] The generated conversation content is sent from the server to the terminal, which then displays it to the user. The input is the generated conversation content from the server, and through this display, the user can start conversation learning. The output of this step is the conversation content displayed to the user.

[1032] Step 5:

[1033] The user initiates a conversation with the avatar and responds with text or voice. This response is sent by the device to the server in real time. The input is text or voice data from the user. The server stores this as a conversation log in the database. Specifically, it stores the text data in a conversation log table and the voice data in audio file format. The output of this step is the conversation log stored in the database.

[1034] Step 6:

[1035] After the conversation ends, the server analyzes the accumulated conversation log. The input is the stored conversation log data, and the analysis evaluates the user's pronunciation, grammatical accuracy, and vocabulary used. Specifically, natural language processing tools are used to analyze the text data, and speech recognition technology is used for the audio data. The output of this step is the analysis results.

[1036] Step 7:

[1037] The server generates feedback and suggestions for the next learning content based on the analysis results. Specifically, it automatically generates feedback sentences that include specific advice such as "your pronunciation was good" or "review this grammar." The input is the analysis results, and the generated feedback sentences are the output of this step.

[1038] Step 8:

[1039] The server generates feedback sentences, which are sent to the terminal and displayed by the terminal to the user. The input is the feedback sentences from the server, which the user can use to proceed to the next learning step. The output of this step is the feedback sentences displayed to the user.

[1040] Points to note

[1041] Data transmission and reception at each step is performed via the Internet.

[1042] Access to the database and storage of data is done securely.

[1043] Appropriate security measures are in place to protect user privacy.

[1044] (Application example 1)

[1045] 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."

[1046] Modern factories often employ workers from multiple countries, and language differences can have a serious impact on work efficiency and safety. In particular, serious problems can arise if work instructions and safety precautions are not communicated accurately. Furthermore, as robots and automation systems are widely used in factories, these devices must be able to communicate smoothly with humans. However, while current language learning systems provide optimal learning content tailored to individual learning situations, they are not specialized for the unique work environment of a factory. Therefore, there is a need for systems that facilitate communication in factory environments and strengthen collaboration between workers and machines.

[1047] 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.

[1048] In this invention, the server includes means for generating language learning content for a user using generative artificial intelligence, means for accumulating and analyzing conversation logs with the user, means for providing feedback according to the user's learning progress based on the analysis results, means for communicating with various devices and enabling the user to access the server from different devices, means for linking with equipment used in a factory environment and generating dialogues for language learning, and means for analyzing the conversation logs based on the dialogues and providing feedback related to factory work. This enables efficient and safe communication between multinational workers working in factories and robots.

[1049] "Generative artificial intelligence" refers to an artificial intelligence system that has the ability to automatically generate new data and content based on given data and conditions.

[1050] "User" refers to the person or device that uses this system to learn a language.

[1051] "Language learning content" refers to learning materials, interactive exercises, and other learning materials used by users to study.

[1052] "Conversation log" refers to a record of the conversation between the user and the system.

[1053] "Analysis results" refers to the data and evaluations obtained by analyzing the conversation logs.

[1054] "Feedback" refers to advice and evaluation provided to users based on their learning progress.

[1055] "Various devices" refers to devices that can access the system, such as smartphones, tablets, PCs, smart glasses, and head-mounted displays.

[1056] "Factory environment" refers to the physical location where products are manufactured and assembled, and the working conditions therein.

[1057] "Device" refers to a device such as a robot or automation system that operates in conjunction with the language learning system.

[1058] "Dialogue" refers to conversational communication between a user and a system.

[1059] This invention is a system for supporting language learning for robots in a factory environment. This system uses generative artificial intelligence to generate learning content for users (here, robots), accumulates and analyzes conversation logs with the users, and provides feedback based on the analysis results. This system also communicates with various devices (smartphones, tablets, PCs, smart glasses, head-mounted displays, etc.), allowing users to access the system from different devices. This system also works in conjunction with equipment used in the factory environment.

[1060] System Program

[1061] The server implements a program with the following functions:

[1062] 1. Language learning content generation:

[1063] The server uses generative artificial intelligence to generate optimal conversation content in real time based on the user's registration information and past learning logs. For this purpose, a generative AI model is used.

[1064] 2. Conversation log storage and analysis:

[1065] The server stores conversation logs with users in the form of text and audio data, analyzes them, and automatically evaluates the user's learning progress. Natural language processing (NLP) algorithms are used to analyze the conversation logs.

[1066] 3. Providing Feedback:

[1067] Based on the analysis results, the server provides feedback based on the user's learning progress, including accuracy of pronunciation, proper use of grammar, and vocabulary use.

[1068] 4. Communication between devices:

[1069] The server communicates seamlessly with various devices, allowing users to access the content from different devices, using a cloud-based synchronization mechanism.

[1070] 5. Collaboration in a factory environment:

[1071] The server interacts with the equipment used in the factory environment and generates dialogues for language learning that simulate specific situations related to factory work.

[1072] Processing Description

[1073] The server receives the user's registration information (first name, last name, email address, password, and language to learn) and stores it in a database. When the robot presses the "Start Learning" button, the server generates the optimal conversation content based on the registration information and past learning logs. This conversation content is sent to the robot, and the robot proceeds with its work based on the received content.

[1074] Conversation logs are stored as text and audio data for analysis and feedback. The server analyzes these logs and generates feedback based on the robot's learning progress. This feedback is displayed on the robot's display and can be used to improve the robot's next task.

[1075] For example, consider a scenario in which a factory robot responds to the Japanese question, "Please tell me what you did yesterday," with "I did welding yesterday." In this case, the server stores the content of this dialogue and evaluates the accuracy of pronunciation and grammar.

[1076] Example prompt sentence:

[1077] "Create a language learning dialogue for a factory robot to learn Japanese at its current skill level. The robot should practice sentences it might use during daily operations, such as greetings and task descriptions."

[1078] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1079] Step 1:

[1080] A user launches an application from their device and enters information such as their name, email address, password, and preferred language into the new account registration screen. This information is then sent from the device to the server, where it is validated.

[1081] Input: User information (name, email address, password, preferred language)

[1082] Data processing / calculation: Validation of input information

[1083] Output: Validation results, saved to database

[1084] Step 2:

[1085] The server stores the user information whose validation has been successful in the database and sends a message to the terminal indicating that the user registration has been completed.

[1086] Input: Validation result

[1087] Data processing / calculation: Saving user information to a database

[1088] Output: Registration complete message

[1089] Step 3:

[1090] The user presses the "Start Conversation Learning" button on the application's home screen. This request is sent from the device to the server, which retrieves the user's registration information and past learning logs from the database.

[1091] Input: User's "Start conversation learning" request

[1092] Data processing / calculation: Retrieving information from a database

[1093] Output: User information, past learning logs

[1094] Step 4:

[1095] The server uses a generative AI model to generate conversation content appropriate for the user's level based on the acquired user information and past learning logs, and uses appropriate prompts for this generation.

[1096] Input: User information, past learning log

[1097] Data processing / calculation: Generating conversation content using generative AI models

[1098] Output: Generated conversation

[1099] Step 5:

[1100] The generated conversation is sent to the device and displayed to the user, who can then initiate a conversation with the avatar and respond with text or voice, which is then sent to the server in real time.

[1101] Input: Generated conversation

[1102] Data processing / calculation: Display to user

[1103] Output: User response (text or voice data)

[1104] Step 6:

[1105] The server stores the received user responses in a database as a conversation log, which is then accumulated as data for analysis.

[1106] Input: User response (text or voice data)

[1107] Data processing / calculation: Accumulation as conversation log

[1108] Output: Saved conversation logs

[1109] Step 7:

[1110] After the conversation ends, the server analyzes the accumulated conversation log and generates feedback based on the analysis results, including corrections to pronunciation and grammar, as well as compliments.

[1111] Input: Saved Conversation Log

[1112] Data processing / calculation: Analysis of conversation logs, generation of feedback

[1113] Output: Analysis results, feedback

[1114] Step 8:

[1115] The generated feedback is sent to the terminal and displayed to the user, who then uses the feedback to improve their next conversation practice.

[1116] Input: Analysis results, feedback

[1117] Data processing / calculation: Display to user

[1118] Output: Displayed feedback

[1119] Step 9:

[1120] The server communicates with various devices, allowing users to seamlessly access the app from different devices, allowing them to check their learning progress from any device.

[1121] Input: Device connection request

[1122] Data processing / calculation: Communication management between devices

[1123] Output:Seamless Access

[1124] 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.

[1125] MODE FOR CARRYING OUT THE INVENTION

[1126] This invention is an online language learning system that combines generative artificial intelligence and an emotion engine. This system is designed to allow users to learn languages ​​at any time and in an optimal environment, and can be accessed from a variety of devices. The operation of this system is described in detail below.

[1127] 1. User Registration and Login

[1128] A user opens a language learning application and enters their name, email address, desired password, and desired language into the new account registration screen. The device sends this information to the server. The server validates the received information and stores information that is deemed correct in a database. Once registration is complete, the server sends a confirmation message to the device, which displays it to the user.

[1129] 2. Start learning conversation

[1130] The user presses the "Start Conversation Learning" button on the application's home screen. The device sends this request to the server. The server retrieves the user's learning level from the database and uses generative artificial intelligence to generate optimal conversation content based on the user's level. The generated conversation content is sent to the device, which then displays it to the user.

[1131] 3. Emotion Recognition and Log Accumulation

[1132] When a user responds to a conversation, the device sends the user's voice and text data to the server. The server then stores the received data in a database as a conversation log. The device's built-in emotion engine also analyzes the user's response data and identifies their emotional state (e.g., joy, sadness, surprise, etc.). The emotion identification results are also saved along with the conversation log.

[1133] 4. Analysis and Feedback

[1134] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data. The emotion engine evaluates the user's emotional state as they study and generates feedback based on this. For example, if the user is feeling stressed, it can provide feedback on how to study in a relaxed manner. Based on the analysis, the server also identifies the user's learning progress and areas for improvement, generating feedback suggesting the next course of study.

[1135] 5. Device connectivity and seamless access

[1136] This system can be accessed from various devices such as smartphones, PCs, and tablets. When a user logs in using a different device, the device sends authentication information to the server, which then verifies the authentication information. If authentication is successful, the server sends the latest learning log and progress information to the new device, which then displays it to the user. This allows users to check their previous learning content and progress, and continue learning seamlessly from any device.

[1137] Specific examples

[1138] For example, suppose an English learner wants to learn a new word. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation that includes the new word. The generated conversation might be a question such as, "Where did you go today?" If the user responds, "I went to the library," the conversation is saved in the log in real time. Furthermore, an emotion engine analyzes the user's voice to determine whether the user is relaxed or stressed. After the conversation ends, the system generates feedback such as, "Your pronunciation is accurate, and you seem to be learning in a relaxed manner. Next, let's review past tense grammar," and the device displays this to the user.

[1139] In this way, users can get a learning experience that is individually optimized to their mood and level of understanding on that day.

[1140] The processing flow will be explained below.

[1141] 1. User Registration and Login

[1142] Step 1:

[1143] A user opens a language learning application and enters information such as their name, email address, desired password, and language to learn on the new account registration screen.

[1144] Step 2:

[1145] The terminal transmits the input information to the server.

[1146] Step 3:

[1147] The server validates the received information and stores the information that is determined to be correct in a database.

[1148] Step 4:

[1149] The server sends a registration completion message to the terminal, which the terminal displays to the user.

[1150] 2. Start learning conversation

[1151] Step 1:

[1152] The user presses the "Start Conversation Learning" button on the application's home screen.

[1153] Step 2:

[1154] The terminal sends a learning start request to the server.

[1155] Step 3:

[1156] The server retrieves the user's learning level from the database.

[1157] Step 4:

[1158] The server generates conversation content using generative artificial intelligence based on the acquired learning level.

[1159] Step 5:

[1160] The server transmits the generated conversation content to the terminal, which then displays it to the user.

[1161] 3. Emotion Recognition and Log Accumulation

[1162] Step 1:

[1163] The user responds to the displayed conversation content by text or voice.

[1164] Step 2:

[1165] The terminal transmits the user's response to the server in real time.

[1166] Step 3:

[1167] The server stores the received response data in a database as a conversation log.

[1168] Step 4:

[1169] The server uses an emotion engine to analyze the response data and identify the user's emotional state.

[1170] Step 5:

[1171] The server also stores the identified emotion data along with the conversation log.

[1172] 4. Analysis and Feedback

[1173] Step 1:

[1174] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data.

[1175] Step 2:

[1176] Based on the analysis results, the server evaluates the user's learning progress and identifies areas for improvement.

[1177] Step 3:

[1178] The server generates feedback based on the evaluation results, including specific advice on learning progress and suggestions for next learning content.

[1179] Step 4:

[1180] The server sends the generated feedback to the terminal, which displays it to the user.

[1181] 5. Device connectivity and seamless access

[1182] Step 1:

[1183] When a user logs in from a different device, the terminal sends the login information to the server.

[1184] Step 2:

[1185] The server authenticates the received login information and verifies the user's access rights.

[1186] Step 3:

[1187] After successful authentication, the server sends the latest learning log and progress information to the new device.

[1188] Step 4:

[1189] The device displays this information to the user, allowing them to check their previous learning content and progress and continue their learning seamlessly.

[1190] Specific examples

[1191] For example, when an English learner presses the "Start Conversation Learning" button, the server reads the user's learning log and generates new conversation content. If the generated conversation content is "How was your day?", the user might respond with "I went to the park." The device sends this response to the server, which analyzes and saves the "enjoying" state along with the conversation log using its emotion engine. After the conversation ends, the server generates feedback such as "Your pronunciation is good and you seem to be learning in a relaxed manner. Let's move on," and the device displays this to the user. In this way, users can obtain an optimal learning experience that also takes their emotions into consideration.

[1192] Example 2

[1193] 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."

[1194] Language learning systems need to effectively assess users' learning progress and provide optimal feedback. It is also important to make the learning environment more flexible by allowing users to easily access the learning environment from any device. Furthermore, it is desirable to analyze users' emotional states and more individually tailor the learning experience.

[1195] 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.

[1196] In this invention, the server includes: a means for generating language learning content for a user using generative artificial intelligence; a means for accumulating and analyzing conversation logs with the user; a means for providing feedback according to the user's learning progress based on the analysis results; a means for analyzing the user's response data using an emotion engine and identifying their emotional state; and a means for communicating with various devices and allowing the user to access the content from different devices. This allows for effective evaluation of the user's learning progress and provides optimal feedback. Furthermore, by analyzing the user's emotional state in real time and reflecting this in the feedback, the learning experience can be more personalized and an environment can be realized where the content can be seamlessly accessed from different devices.

[1197] "Generative AI" is an AI technology that generates language learning content in real time based on user input.

[1198] A "conversation log" is data that records the content of a conversation between a user and a system, and includes text data and voice data.

[1199] An "emotion engine" is a software component that analyzes user response data to identify the user's emotional state.

[1200] "Feedback" refers to evaluations and advice provided based on a user's learning progress, including information suggesting improvements to learning content and next steps.

[1201] "Learning progress" is an index that indicates the degree of progress of a user's language learning, and is evaluated based on the results of analysis of conversation logs and emotion data.

[1202] "Storage means" is a function for saving conversation logs and emotional data in a database.

[1203] "Analysis" refers to the process of using accumulated data to evaluate the user's learning progress and emotional state.

[1204] "Device" refers to any electronic device used by a user to access the system, including a smartphone, PC, tablet, etc.

[1205] "Communication" refers to the process of exchanging data between different devices over a network.

[1206] "Real-time" refers to data being generated and processed instantly.

[1207] This invention is an online language learning system that combines generative artificial intelligence and an emotion engine. This system is designed to allow users to learn languages ​​at any time and in an optimal environment, and can be accessed from a variety of devices. The operation of this system is described in detail below.

[1208] 1. User Registration and Login

[1209] A user opens a language learning application and enters their name, email address, desired password, desired language, etc. into the new account registration screen.

[1210] The terminal sends this information to the server.

[1211] The server validates the received information and stores the information that is deemed correct in a database (e.g., MySQL or PostgreSQL).

[1212] Once registration is complete, the server sends a confirmation message to the terminal, which the terminal displays to the user.

[1213] 2. Start learning conversation

[1214] The user presses the "Start Conversation Learning" button on the application's home screen.

[1215] The terminal sends this request to the server.

[1216] The server retrieves the user's learning level from the database and generates optimal conversation content based on the user's level using generative artificial intelligence (e.g., GPT-4 model). The generated conversation content is sent to the device, which then displays it to the user.

[1217] 3. Emotion Recognition and Log Accumulation

[1218] When the user responds to the conversation, the terminal transmits the user's voice data and text data to the server.

[1219] The server stores the received data in a database as a conversation log. The built-in emotion engine analyzes the user's response data and identifies their emotional state (e.g., joy, sadness, surprise, etc.). The emotion identification results are also stored along with the conversation log.

[1220] 4. Analysis and Feedback

[1221] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data. The emotion engine evaluates the user's emotional state as they study and generates feedback based on this. For example, if the user is feeling stressed, it will provide feedback on how to study in a relaxed manner. Based on the analysis, the server also identifies the user's learning progress and areas for improvement, and generates feedback suggesting the next course of study.

[1222] 5. Device connectivity and seamless access

[1223] The system can be accessed from a variety of devices, including smartphones, PCs, and tablets.

[1224] When a user logs in using a different device, the terminal sends the authentication information to the server.

[1225] The server verifies the authentication information and, if successful, sends the latest learning log and progress information to the new device.

[1226] The device displays this to the user, allowing them to check their previous learning content and progress, and continue learning seamlessly from any device.

[1227] Specific examples

[1228] For example, suppose an English learner wants to learn new words. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation that includes the new words. The generated conversation might include questions such as "Where did you go today?"

[1229] When the user responds, "I went to the library," the conversation is logged in real time. Furthermore, an emotion engine analyzes the user's voice to determine whether they are relaxed or stressed. After the conversation ends, the system generates feedback such as, "Your pronunciation is accurate, and you seem to be learning in a relaxed manner. Next, let's review past tense grammar," and the device displays this to the user.

[1230] Prompt Sentence Examples

[1231] Specific conversation content can be generated by writing prompts to the generative AI model as follows:

[1232] For users who click the "Start Conversation Learning" button, generate a conversation appropriate to their level. The language of study is English, and the learner is at beginner level. Generate a conversation that includes questions to teach the learner new vocabulary.

[1233] This prompt allows the generative AI model to generate appropriate conversational content and provide it to the user.

[1234] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1235] Processing Steps

[1236] Step 1: User Registration and Login

[1237] 1. Enter information

[1238] A user opens a language learning application and enters their name, email address, desired password, and the language they wish to learn.

[1239] Input: Name, Email Address, Password, Language

[1240] Output: Request to send input data

[1241] 2. Data Transmission

[1242] The terminal transmits the information entered by the user to the server.

[1243] Input: Input data

[1244] Output: Send data to the server

[1245] 3. Validation and Storage

[1246] The server validates the submitted data and stores it in a database if it is deemed correct, for example by checking the format of the email address or the strength of the password.

[1247] Input: Input data

[1248] Output: Validation success or failure

[1249] 4. Sending a registration completion message

[1250] If validation is successful, the server sends the user a registration completion message, which the terminal displays to the user.

[1251] Input: Validation successful

[1252] Output: Display a confirmation message

[1253] Step 2: Start learning conversations

[1254] 1. Send a lesson start request

[1255] The user presses the "Start Conversation Learning" button on the application's home screen.

[1256] Input: Start learning request

[1257] Output: Request sent to server

[1258] 2. Obtaining user level and generating conversation content

[1259] The server obtains the user's learning level from the database and generates optimal conversation content using generative artificial intelligence (e.g., GPT-4).

[1260] Input: User learning level

[1261] Output: Generated conversation

[1262] 3. Display of conversation contents

[1263] The generated conversation content is sent to the terminal, which displays it to the user.

[1264] Input: Generated conversation

[1265] Output: Display of conversation

[1266] Step 3: Emotion recognition and logging

[1267] 1. Sending conversation response data

[1268] When the user responds to the conversation, the terminal transmits the voice data and text data to the server.

[1269] Input: Response data (audio or text)

[1270] Output: Send data to the server

[1271] 2. Save conversation logs

[1272] The server stores the received data in a database as a conversation log.

[1273] Input: Response data

[1274] Output: Save to database

[1275] 3. Emotional state analysis

[1276] The built-in emotion engine analyzes the user's response data and identifies their emotional state, such as joy, sadness, or surprise, based on their voice data.

[1277] Input: Response data

[1278] Output: Save the sentiment analysis results

[1279] Step 4: Analyze and provide feedback

[1280] 1. Log and emotion data analysis

[1281] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data.

[1282] Input: Conversation logs, emotion data

[1283] Output: Analysis results

[1284] 2. Generate feedback

[1285] The emotion engine generates optimal feedback for the user based on the analysis results. For example, if the user is relaxed, it generates feedback such as "You are able to study in a relaxed state."

[1286] Input: Analysis results

[1287] Output: Feedback message

[1288] 3. Viewing Feedback

[1289] The generated feedback is sent to the terminal, which displays it to the user.

[1290] Input: Feedback message

[1291] Output: Display feedback

[1292] Step 5: Device connection and seamless access

[1293] 1. Log in from your device

[1294] When a user logs in on a different device, the terminal sends authentication information to the server.

[1295] Input: Credentials

[1296] Output: Authentication request to the server

[1297] 2. Verify your credentials and synchronize your data

[1298] The server verifies the authentication information and, if successful, sends the latest learning log and progress information to the new device.

[1299] Input: Credentials

[1300] Output: Send training data

[1301] 3. View your learning log and progress information

[1302] The device displays this to the user, allowing them to check their previous learning content and progress, and continue learning seamlessly from any device.

[1303] Input: Training data

[1304] Output: Display of learning information

[1305] (Application example 2)

[1306] 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."

[1307] Conventional language learning systems were unable to provide learning content that took the user's emotional state into consideration, resulting in issues with learning efficiency and continuity. Furthermore, because appetite is significantly influenced by emotions, it was also unable to simultaneously provide meal suggestions based on the user's emotions. This created a need for a way to reduce learning stress and improve the overall learning experience.

[1308] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1309] In this invention, the server includes means for generating language learning content for a user using generative artificial intelligence, means for accumulating and analyzing conversation logs with the user, means for providing feedback according to the user's learning progress based on the analysis results, means for communicating with various devices and allowing the user to access the server from different devices, and means for analyzing the user's emotional data and recommending optimal meals based on the analysis results, thereby making it possible to provide content and suggest optimal meals that take the user's emotional state into consideration.

[1310] "Generative AI" is an AI technology that creates appropriate content and suggestions in real time based on the user's learning and emotional state.

[1311] "Conversation log" refers to recorded data that collects and stores the contents of conversations users have as text and audio data.

[1312] "Emotional data" is information that indicates the emotional state of a user obtained by analyzing the user's voice or text.

[1313] "Feedback" is advice or information about next steps or areas for improvement that is provided based on the user's learning progress and emotional state.

[1314] "Various devices" refers to the various devices that users use to access the site, such as smartphones, PCs, and tablets.

[1315] "Communication means" refers to the network means used by users to continuously access the service from different devices.

[1316] "Method of recommending meals" is a technology that suggests optimal meals based on the user's emotional data.

[1317] This invention is a system that combines generative artificial intelligence and an emotion engine to optimize an online language learning system and a food delivery application. Specific embodiments of this system are described below.

[1318] Basic Features

[1319] The system works on various devices, including smartphones, PCs, and tablets. Users can register and log in to receive optimal content and feedback based on their learning progress and emotional state. The system also supports seamless access across different devices.

[1320] Program Generation and Processing Description

[1321] The server first generates appropriate learning content using generative artificial intelligence based on the information and emotional state entered by the user, using specific software libraries called EmotionEngine and FoodRecommendationAI.

[1322] 1. The server receives the user information

[1323] When a user logs in to their account through their device, the server retrieves the user's profile information and past learning logs.

[1324] 2. Emotion Data Analysis

[1325] The user inputs their current emotional state and sends it to the server, which then uses the EmotionEngine to analyze this data and determine the user's emotional state.

[1326] 3. Generating learning content and feedback

[1327] The server uses generative artificial intelligence to generate optimal conversation content based on the user's learning progress, and also analyzes the user's stress level and relaxation state based on emotional data, providing appropriate feedback.

[1328] 4. Dietary Recommendations

[1329] Furthermore, it uses generative artificial intelligence to recommend optimal meals based on emotional data: for example, if the user is stressed, it will recommend relaxing meals, and if they are relaxed, it will recommend nutritious meals.

[1330] Usage example

[1331] If a user logs in to a food delivery app and enters "stress" as their emotional state, the server will analyze this information using the Emotion Engine and use Food Recommendation AI to recommend "meals that have a relaxing effect." Specific recommendations include a "Japanese meal set" and "chamomile tea."

[1332] Example prompts to be input to the generative AI model

[1333] An example prompt might have the following format:

[1334] User Emotion: Stress

[1335] User preference: Japanese food

[1336] Output format: Suggest a relaxing meal.

[1337] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1338] Step 1:

[1339] The user opens the smartphone app and enters login information (user ID and password). The device sends this information to the server, which then authenticates the user. If authentication is successful, the server retrieves the user's profile information and past learning logs and sends them to the device. In this process, the input is the user's login information, and the output is the user's profile information and past learning logs. Data processing and data calculation involve authentication and retrieval of data from the database.

[1340] Step 2:

[1341] The user inputs their current emotional state. For example, emotions such as "stressed" or "relaxed" are input into a smartphone app. The device sends this emotional information to the server, which then analyzes the data using the Emotion Engine. The input is the user's emotional state, and the output is the analyzed emotional data. Data processing and data calculation are emotion analysis.

[1342] Step 3:

[1343] The server uses generative artificial intelligence to generate appropriate learning content in real time based on emotional data and past learning logs. Optimal conversation content is generated based on the user's learning progress and level. The input is emotional data and learning logs, and the output is the generated learning content. Data processing and data calculation are used to generate learning content.

[1344] Step 4:

[1345] The generated learning content is sent to the terminal and displayed to the user. The user practices the conversation and responds in voice or text format. The terminal sends this response data to the server. The input is the generated learning content, and the output is the user's response data. Data processing and data calculation involve receiving the user's input.

[1346] Step 5:

[1347] The server receives and stores the user's conversation log as text and audio data. It also analyzes the conversation log to automatically evaluate learning progress. The input is the user's response data, and the output is the analyzed learning progress data. Data processing and data calculation involve the analysis and storage of the conversation log.

[1348] Step 6:

[1349] Based on the analysis results, the server provides feedback according to the user's learning progress. This feedback is sent to the terminal and displayed to the user. The input is learning progress data, and the output is feedback. Data processing and data calculation are used to generate feedback.

[1350] Step 7:

[1351] Based on the emotion data, the server uses Food Recommendation AI to recommend the most suitable meal. This recommendation is also sent to the device and displayed to the user. The input is emotion data, and the output is the meal recommendation. Data processing and data calculation are used to generate the meal recommendation.

[1352] 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.

[1353] 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.

[1354] 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.

[1355] [Fourth embodiment]

[1356] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1357] 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.

[1358] 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).

[1359] 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.

[1360] 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.

[1361] 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).

[1362] 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.

[1363] 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.

[1364] 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.

[1365] 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.

[1366] 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.

[1367] 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.

[1368] 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."

[1369] MODE FOR CARRYING OUT THE INVENTION

[1370] This invention is an online system that uses generative artificial intelligence to support users' language learning. This system uses generative artificial intelligence to automatically generate content based on the user's learning level and preferences, and accumulates and analyzes conversation logs with the user to provide individually optimized feedback. The system is also designed to allow users to access it seamlessly from different devices.

[1371] The operation of this system will be explained below with specific examples.

[1372] 1. User Registration and Login

[1373] The user opens the application and enters information such as name, email address, desired password, and desired language to learn on the new account registration screen. The device sends this information to the server, which validates the information. If validation is successful, the server saves the user information in the database and returns a message to the device indicating registration is complete.

[1374] 2. Start learning conversation

[1375] The user presses the "Start Conversation Learning" button on the application's home screen. The device sends this request to the server. The server retrieves the user's learning level from the database and uses generative artificial intelligence to generate conversation content based on the user's level. This generated conversation content is sent to the device and displayed to the user.

[1376] 3. Conversation progress and log accumulation

[1377] Users can initiate conversations with their avatars and respond via text or voice. The device sends the user's responses in real time to the server, which then stores the responses in a database as a conversation log. This ensures that all conversations are recorded and stored as data for later analysis.

[1378] 4. Analysis and Feedback

[1379] After the conversation ends, the server analyzes the accumulated conversation log. The analysis evaluates the user's pronunciation, grammatical accuracy, and vocabulary used. Based on the analysis results, the server generates feedback and suggestions for the next lesson. This feedback includes specific advice such as "your pronunciation was good" or "review this grammar." The device displays this feedback to the user.

[1380] 5. Device connectivity and seamless access

[1381] The system can be accessed from a variety of devices, including smartphones, PCs, and tablets. No matter which device a user uses, their previous learning log and current progress are all synchronized, allowing them to continue their language learning seamlessly. The server manages communication between these devices and provides consistent session information across devices.

[1382] Specific examples

[1383] For example, suppose an English learner wants to use this system to learn new grammar. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation that incorporates appropriate grammar points. The generated conversation might be a question such as "What did you do yesterday?" If the user responds with "I went to the supermarket," the conversation is saved in the log. After the conversation is completed, analysis is performed and feedback is provided to the user, such as "Your use of the past tense is correct."

[1384] In this way, users receive a personalized learning experience, helping them learn a language more efficiently.

[1385] The processing flow will be explained below.

[1386] 1. User Registration and Login

[1387] Step 1:

[1388] A user opens the application and enters information such as their name, email address, desired password, and desired language of study on the new account registration screen.

[1389] Step 2:

[1390] The terminal transmits the entered registration information to the server.

[1391] Step 3:

[1392] The server validates the received registration information, specifically checking that the email address is formatted correctly and that the password meets the required criteria.

[1393] Step 4:

[1394] The server stores the user information in the database after successful validation.

[1395] Step 5:

[1396] The server returns a message to the terminal indicating that registration is complete, and the terminal displays this to the user.

[1397] 2. Start learning conversation

[1398] Step 1:

[1399] The user presses the "Start Conversation Learning" button on the application's home screen.

[1400] Step 2:

[1401] The terminal sends a "conversation learning start" request to the server.

[1402] Step 3:

[1403] The server retrieves the user's learning level from the database.

[1404] Step 4:

[1405] The server generates conversation content using generative artificial intelligence based on the acquired learning level.

[1406] Step 5:

[1407] The server transmits the generated conversation content to the terminal, which then displays it to the user.

[1408] 3. Conversation progress and log accumulation

[1409] Step 1:

[1410] The user responds to the conversation content displayed on the terminal by text or voice.

[1411] Step 2:

[1412] The terminal transmits the user's response to the server in real time.

[1413] Step 3:

[1414] The server stores the received responses in a database as a conversation log, which includes not only the user's responses but also the time the conversation occurred.

[1415] 4. Analysis and Feedback

[1416] Step 1:

[1417] After the conversation ends, the server analyzes the accumulated conversation log.

[1418] Step 2:

[1419] The server identifies the user's learning progress and areas for improvement based on the results of the analysis, which includes pronunciation, grammatical accuracy, and the variety of vocabulary used.

[1420] Step 3:

[1421] The server generates feedback based on the analysis, including specific advice such as "Use the past tense correctly" or "Use a more diverse vocabulary."

[1422] Step 4:

[1423] The server sends the generated feedback to the terminal, which displays it to the user.

[1424] 5. Device connectivity and seamless access

[1425] Step 1:

[1426] When a user accesses the system from a different device, the terminal sends the login information to the server.

[1427] Step 2:

[1428] The server verifies the authentication information and verifies that the user is authorized to access the site.

[1429] Step 3:

[1430] The server sends the latest learning log and progress information to the new device, which then displays it to the user, allowing the user to check their previous learning content and progress and continue their learning smoothly.

[1431] This series of steps allows users to continue learning a language 24 hours a day, 365 days a year, regardless of location.

[1432] Example 1

[1433] 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."

[1434] Conventional language learning systems have struggled to provide feedback tailored to each user's individual learning progress and optimal learning content. It has also been difficult to seamlessly synchronize learning data across different devices. This has resulted in an inefficient learning experience for users, slowing down their language acquisition progress.

[1435] 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.

[1436] In this invention, the server includes means for generating language learning content for a user using generative artificial intelligence, means for accumulating and analyzing conversation logs with the user, means for providing feedback according to the user's learning progress based on the analysis results, means for communicating with various devices and allowing the user to access the content from different devices, means for inputting and validating user information, means for saving the user information in a database, means for providing prompts for generating conversation content based on the user's learning level, means for transmitting and saving user responses in real time, and means for analyzing the conversation logs and generating suggestions for next learning content and feedback, thereby providing an optimal learning experience according to the user's individual learning progress and enabling effective language acquisition.

[1437] "Generative AI" is an AI technology that generates new content and data based on user input information.

[1438] "Language learning content" refers to teaching and practice materials that help users learn a particular language.

[1439] A "conversation log" refers to a record of a conversation between a user and a system, and is saved as text or audio data.

[1440] "Feedback" refers to the advice and evaluation provided by the system regarding the user's learning progress and performance.

[1441] "Various devices" refers to different hardware platforms such as smartphones, PCs, and tablets.

[1442] A "database" is a system for systematically storing and managing data such as user information and conversation logs.

[1443] A "prompt sentence" is an input sentence that serves as the basis for generative artificial intelligence to generate conversation content.

[1444] "User response" refers to the reply or input given by the user to the system.

[1445] "Real-time" refers to the situation where user input is processed the instant it is made, with little time delay.

[1446] This invention is an online system that uses generative artificial intelligence to support users' language learning. The system uses generative artificial intelligence to automatically generate content based on the user's learning level and preferences, and accumulates and analyzes conversation logs with the user to provide individually optimized feedback. The system is designed to be seamlessly accessible from various devices, including smartphones, PCs, and tablets.

[1447] User Registration and Login

[1448] The user opens the application and enters information such as name, email address, desired password, and desired language to learn on the new account registration screen. The device sends this information to the server. The server validates the information, and if validation is successful, saves the user information in a database (e.g., MySQL). A message indicating registration completion is returned to the device and displayed to the user.

[1449] Start learning conversation

[1450] The user presses the "Start Conversation Learning" button on the application's home screen. The device sends this request to the server. The server retrieves the user's learning level from the database and uses generative artificial intelligence (e.g., GPT-3 using the OpenAI API) to generate conversation content based on the user's level. The generated conversation content is sent to the device and displayed to the user.

[1451] Conversation progress and log accumulation

[1452] Users can initiate conversations with their avatars and respond via text or voice. The device sends the user's responses in real time to the server, which then stores the responses in a database as a conversation log. This ensures that all conversations are recorded and stored as data for later analysis.

[1453] Analysis and feedback

[1454] After the conversation ends, the server analyzes the accumulated conversation log. This analysis evaluates the user's pronunciation, grammatical accuracy, and vocabulary used. Based on the analysis results, the server generates feedback and suggestions for the next lesson. This feedback includes specific advice such as "your pronunciation was good" or "review this grammar." The device displays this feedback to the user.

[1455] Device Connectivity and Seamless Access

[1456] The system can be accessed from a variety of devices, including smartphones, PCs, and tablets. No matter which device a user uses, previous learning logs and current progress are all synchronized, allowing for seamless language learning. The server manages communication between these devices and provides consistent session information across devices.

[1457] Specific examples

[1458] For example, suppose an English learner wants to use this system to learn new grammar. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation incorporating appropriate grammar points. The generated conversation might be a question such as "What did you do yesterday?" If the user responds with "I went to the supermarket," the conversation is saved in the log. After the conversation is completed, analysis is performed and feedback is provided to the user, such as "Your use of the past tense is correct." In this way, users can receive an individually optimized learning experience and acquire languages ​​more efficiently.

[1459] Example prompts for generative AI models

[1460] The user's current learning level is beginner. Please generate conversation content appropriate for that level. The theme should be "daily life" and should include practice of past tense.

[1461] User Information:

[1462] Language of study: English

[1463] Learning level: Beginner

[1464] Example of a conversation to generate:

[1465] Question: What did you do yesterday?

[1466] Expected Answer: I went to the supermarket.

[1467] Based on this prompt, the generative AI generates conversational content appropriate to the user's learning progress, allowing the user to learn the language effectively.

[1468] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1469] Step 1:

[1470] A user opens the application and enters their name, email address, password, and language of study on the new account registration screen. This information is sent as input to the device, and then sent from the device to the server. The server validates the information, specifically checking the format of the email address, the strength of the password, etc. The output of this step is that if validation is successful, the user information is saved in a database (e.g. MySQL). If validation fails, an error message is returned to the device.

[1471] Step 2:

[1472] When a user presses the "Start Conversation Learning" button, the terminal sends this request to the server. The input is the conversation learning start request, and the server obtains the user's learning level from the database. Specifically, it extracts level information from the learning log table based on the user ID. The output of this step is the user's learning level information.

[1473] Step 3:

[1474] The server generates a prompt based on the acquired learning level information. The prompt is sent as input to a generative artificial intelligence (e.g., GPT-3 using the OpenAI API), which generates conversation content appropriate for the user's level. Specifically, the prompt includes instructions such as, "The user's current learning level is beginner. Please generate content about 'daily life' that includes practice in the past tense." The output of this step is the generated conversation content.

[1475] Step 4:

[1476] The generated conversation content is sent from the server to the terminal, which then displays it to the user. The input is the generated conversation content from the server, and through this display, the user can start conversation learning. The output of this step is the conversation content displayed to the user.

[1477] Step 5:

[1478] The user initiates a conversation with the avatar and responds with text or voice. This response is sent by the device to the server in real time. The input is text or voice data from the user. The server stores this as a conversation log in the database. Specifically, it stores the text data in a conversation log table and the voice data in audio file format. The output of this step is the conversation log stored in the database.

[1479] Step 6:

[1480] After the conversation ends, the server analyzes the accumulated conversation log. The input is the stored conversation log data, and the analysis evaluates the user's pronunciation, grammatical accuracy, and vocabulary used. Specifically, natural language processing tools are used to analyze the text data, and speech recognition technology is used for the audio data. The output of this step is the analysis results.

[1481] Step 7:

[1482] The server generates feedback and suggestions for the next learning content based on the analysis results. Specifically, it automatically generates feedback sentences that include specific advice such as "your pronunciation was good" or "review this grammar." The input is the analysis results, and the generated feedback sentences are the output of this step.

[1483] Step 8:

[1484] The server generates feedback sentences, which are sent to the terminal and displayed by the terminal to the user. The input is the feedback sentences from the server, which the user can use to proceed to the next learning step. The output of this step is the feedback sentences displayed to the user.

[1485] Points to note

[1486] Data transmission and reception at each step is performed via the Internet.

[1487] Access to the database and storage of data is done securely.

[1488] Appropriate security measures are in place to protect user privacy.

[1489] (Application example 1)

[1490] 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."

[1491] Modern factories often employ workers from multiple countries, and language differences can have a serious impact on work efficiency and safety. In particular, serious problems can arise if work instructions and safety precautions are not communicated accurately. Furthermore, as robots and automation systems are widely used in factories, these devices must be able to communicate smoothly with humans. However, while current language learning systems provide optimal learning content tailored to individual learning situations, they are not specialized for the unique work environment of a factory. Therefore, there is a need for systems that facilitate communication in factory environments and strengthen collaboration between workers and machines.

[1492] 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.

[1493] In this invention, the server includes means for generating language learning content for a user using generative artificial intelligence, means for accumulating and analyzing conversation logs with the user, means for providing feedback according to the user's learning progress based on the analysis results, means for communicating with various devices and enabling the user to access the server from different devices, means for linking with equipment used in a factory environment and generating dialogues for language learning, and means for analyzing the conversation logs based on the dialogues and providing feedback related to factory work. This enables efficient and safe communication between multinational workers working in factories and robots.

[1494] "Generative artificial intelligence" refers to an artificial intelligence system that has the ability to automatically generate new data and content based on given data and conditions.

[1495] "User" refers to the person or device that uses this system to learn a language.

[1496] "Language learning content" refers to learning materials, interactive exercises, and other learning materials used by users to study.

[1497] "Conversation log" refers to a record of the conversation between the user and the system.

[1498] "Analysis results" refers to the data and evaluations obtained by analyzing the conversation logs.

[1499] "Feedback" refers to advice and evaluation provided to users based on their learning progress.

[1500] "Various devices" refers to devices that can access the system, such as smartphones, tablets, PCs, smart glasses, and head-mounted displays.

[1501] "Factory environment" refers to the physical location where products are manufactured and assembled, and the working conditions therein.

[1502] "Device" refers to a device such as a robot or automation system that operates in conjunction with the language learning system.

[1503] "Dialogue" refers to conversational communication between a user and a system.

[1504] This invention is a system for supporting language learning for robots in a factory environment. This system uses generative artificial intelligence to generate learning content for users (here, robots), accumulates and analyzes conversation logs with the users, and provides feedback based on the analysis results. This system also communicates with various devices (smartphones, tablets, PCs, smart glasses, head-mounted displays, etc.), allowing users to access the system from different devices. This system also works in conjunction with equipment used in the factory environment.

[1505] System Program

[1506] The server implements a program with the following functions:

[1507] 1. Language learning content generation:

[1508] The server uses generative artificial intelligence to generate optimal conversation content in real time based on the user's registration information and past learning logs. For this purpose, a generative AI model is used.

[1509] 2. Conversation log storage and analysis:

[1510] The server stores conversation logs with users in the form of text and audio data, analyzes them, and automatically evaluates the user's learning progress. Natural language processing (NLP) algorithms are used to analyze the conversation logs.

[1511] 3. Providing Feedback:

[1512] Based on the analysis results, the server provides feedback based on the user's learning progress, including accuracy of pronunciation, proper use of grammar, and vocabulary use.

[1513] 4. Communication between devices:

[1514] The server communicates seamlessly with various devices, allowing users to access the content from different devices, using a cloud-based synchronization mechanism.

[1515] 5. Collaboration in a factory environment:

[1516] The server interacts with the equipment used in the factory environment and generates dialogues for language learning that simulate specific situations related to factory work.

[1517] Processing Description

[1518] The server receives the user's registration information (first name, last name, email address, password, and language to learn) and stores it in a database. When the robot presses the "Start Learning" button, the server generates the optimal conversation content based on the registration information and past learning logs. This conversation content is sent to the robot, and the robot proceeds with its work based on the received content.

[1519] Conversation logs are stored as text and audio data for analysis and feedback. The server analyzes these logs and generates feedback based on the robot's learning progress. This feedback is displayed on the robot's display and can be used to improve the robot's next task.

[1520] For example, consider a scenario in which a factory robot responds to the Japanese question, "Please tell me what you did yesterday," with "I did welding yesterday." In this case, the server stores the content of this dialogue and evaluates the accuracy of pronunciation and grammar.

[1521] Example prompt sentence:

[1522] "Create a language learning dialogue for a factory robot to learn Japanese at its current skill level. The robot should practice sentences it might use during daily operations, such as greetings and task descriptions."

[1523] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1524] Step 1:

[1525] A user launches an application from their device and enters information such as their name, email address, password, and preferred language into the new account registration screen. This information is then sent from the device to the server, where it is validated.

[1526] Input: User information (name, email address, password, preferred language)

[1527] Data processing / calculation: Validation of input information

[1528] Output: Validation results, saved to database

[1529] Step 2:

[1530] The server stores the user information whose validation has been successful in the database and sends a message to the terminal indicating that the user registration has been completed.

[1531] Input: Validation result

[1532] Data processing / calculation: Saving user information to a database

[1533] Output: Registration complete message

[1534] Step 3:

[1535] The user presses the "Start Conversation Learning" button on the application's home screen. This request is sent from the device to the server, which retrieves the user's registration information and past learning logs from the database.

[1536] Input: User's "Start conversation learning" request

[1537] Data processing / calculation: Retrieving information from a database

[1538] Output: User information, past learning logs

[1539] Step 4:

[1540] The server uses a generative AI model to generate conversation content appropriate for the user's level based on the acquired user information and past learning logs, and uses appropriate prompts for this generation.

[1541] Input: User information, past learning log

[1542] Data processing / calculation: Generating conversation content using generative AI models

[1543] Output: Generated conversation

[1544] Step 5:

[1545] The generated conversation is sent to the device and displayed to the user, who can then initiate a conversation with the avatar and respond with text or voice, which is then sent to the server in real time.

[1546] Input: Generated conversation

[1547] Data processing / calculation: Display to user

[1548] Output: User response (text or voice data)

[1549] Step 6:

[1550] The server stores the received user responses in a database as a conversation log, which is then accumulated as data for analysis.

[1551] Input: User response (text or voice data)

[1552] Data processing / calculation: Accumulation as conversation log

[1553] Output: Saved conversation logs

[1554] Step 7:

[1555] After the conversation ends, the server analyzes the accumulated conversation log and generates feedback based on the analysis results, including corrections to pronunciation and grammar, as well as compliments.

[1556] Input: Saved Conversation Log

[1557] Data processing / calculation: Analysis of conversation logs, generation of feedback

[1558] Output: Analysis results, feedback

[1559] Step 8:

[1560] The generated feedback is sent to the terminal and displayed to the user, who then uses the feedback to improve their next conversation practice.

[1561] Input: Analysis results, feedback

[1562] Data processing / calculation: Display to user

[1563] Output: Displayed feedback

[1564] Step 9:

[1565] The server communicates with various devices, allowing users to seamlessly access the app from different devices, allowing them to check their learning progress from any device.

[1566] Input: Device connection request

[1567] Data processing / calculation: Communication management between devices

[1568] Output:Seamless Access

[1569] 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.

[1570] MODE FOR CARRYING OUT THE INVENTION

[1571] This invention is an online language learning system that combines generative artificial intelligence and an emotion engine. This system is designed to allow users to learn languages ​​at any time and in an optimal environment, and can be accessed from a variety of devices. The operation of this system is described in detail below.

[1572] 1. User Registration and Login

[1573] A user opens a language learning application and enters their name, email address, desired password, and desired language into the new account registration screen. The device sends this information to the server. The server validates the received information and stores information that is deemed correct in a database. Once registration is complete, the server sends a confirmation message to the device, which displays it to the user.

[1574] 2. Start learning conversation

[1575] The user presses the "Start Conversation Learning" button on the application's home screen. The device sends this request to the server. The server retrieves the user's learning level from the database and uses generative artificial intelligence to generate optimal conversation content based on the user's level. The generated conversation content is sent to the device, which then displays it to the user.

[1576] 3. Emotion Recognition and Log Accumulation

[1577] When a user responds to a conversation, the device sends the user's voice and text data to the server. The server then stores the received data in a database as a conversation log. The device's built-in emotion engine also analyzes the user's response data and identifies their emotional state (e.g., joy, sadness, surprise, etc.). The emotion identification results are also saved along with the conversation log.

[1578] 4. Analysis and Feedback

[1579] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data. The emotion engine evaluates the user's emotional state as they study and generates feedback based on this. For example, if the user is feeling stressed, it can provide feedback on how to study in a relaxed manner. Based on the analysis, the server also identifies the user's learning progress and areas for improvement, generating feedback suggesting the next course of study.

[1580] 5. Device connectivity and seamless access

[1581] This system can be accessed from various devices such as smartphones, PCs, and tablets. When a user logs in using a different device, the device sends authentication information to the server, which then verifies the authentication information. If authentication is successful, the server sends the latest learning log and progress information to the new device, which then displays it to the user. This allows users to check their previous learning content and progress, and continue learning seamlessly from any device.

[1582] Specific examples

[1583] For example, suppose an English learner wants to learn a new word. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation that includes the new word. The generated conversation might be a question such as, "Where did you go today?" If the user responds, "I went to the library," the conversation is saved in the log in real time. Furthermore, an emotion engine analyzes the user's voice to determine whether the user is relaxed or stressed. After the conversation ends, the system generates feedback such as, "Your pronunciation is accurate, and you seem to be learning in a relaxed manner. Next, let's review past tense grammar," and the device displays this to the user.

[1584] In this way, users can get a learning experience that is individually optimized to their mood and level of understanding on that day.

[1585] The processing flow will be explained below.

[1586] 1. User Registration and Login

[1587] Step 1:

[1588] A user opens a language learning application and enters information such as their name, email address, desired password, and language to learn on the new account registration screen.

[1589] Step 2:

[1590] The terminal transmits the input information to the server.

[1591] Step 3:

[1592] The server validates the received information and stores the information that is determined to be correct in a database.

[1593] Step 4:

[1594] The server sends a registration completion message to the terminal, which the terminal displays to the user.

[1595] 2. Start learning conversation

[1596] Step 1:

[1597] The user presses the "Start Conversation Learning" button on the application's home screen.

[1598] Step 2:

[1599] The terminal sends a learning start request to the server.

[1600] Step 3:

[1601] The server retrieves the user's learning level from the database.

[1602] Step 4:

[1603] The server generates conversation content using generative artificial intelligence based on the acquired learning level.

[1604] Step 5:

[1605] The server transmits the generated conversation content to the terminal, which then displays it to the user.

[1606] 3. Emotion Recognition and Log Accumulation

[1607] Step 1:

[1608] The user responds to the displayed conversation content by text or voice.

[1609] Step 2:

[1610] The terminal transmits the user's response to the server in real time.

[1611] Step 3:

[1612] The server stores the received response data in a database as a conversation log.

[1613] Step 4:

[1614] The server uses an emotion engine to analyze the response data and identify the user's emotional state.

[1615] Step 5:

[1616] The server also stores the identified emotion data along with the conversation log.

[1617] 4. Analysis and Feedback

[1618] Step 1:

[1619] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data.

[1620] Step 2:

[1621] Based on the analysis results, the server evaluates the user's learning progress and identifies areas for improvement.

[1622] Step 3:

[1623] The server generates feedback based on the evaluation results, including specific advice on learning progress and suggestions for next learning content.

[1624] Step 4:

[1625] The server sends the generated feedback to the terminal, which displays it to the user.

[1626] 5. Device connectivity and seamless access

[1627] Step 1:

[1628] When a user logs in from a different device, the terminal sends the login information to the server.

[1629] Step 2:

[1630] The server authenticates the received login information and verifies the user's access rights.

[1631] Step 3:

[1632] After successful authentication, the server sends the latest learning log and progress information to the new device.

[1633] Step 4:

[1634] The device displays this information to the user, allowing them to check their previous learning content and progress and continue their learning seamlessly.

[1635] Specific examples

[1636] For example, when an English learner presses the "Start Conversation Learning" button, the server reads the user's learning log and generates new conversation content. If the generated conversation content is "How was your day?", the user might respond with "I went to the park." The device sends this response to the server, which analyzes and saves the "enjoying" state along with the conversation log using its emotion engine. After the conversation ends, the server generates feedback such as "Your pronunciation is good and you seem to be learning in a relaxed manner. Let's move on," and the device displays this to the user. In this way, users can obtain an optimal learning experience that also takes their emotions into consideration.

[1637] Example 2

[1638] 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."

[1639] Language learning systems need to effectively assess users' learning progress and provide optimal feedback. It is also important to make the learning environment more flexible by allowing users to easily access the learning environment from any device. Furthermore, it is desirable to analyze users' emotional states and more individually tailor the learning experience.

[1640] 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.

[1641] In this invention, the server includes: a means for generating language learning content for a user using generative artificial intelligence; a means for accumulating and analyzing conversation logs with the user; a means for providing feedback according to the user's learning progress based on the analysis results; a means for analyzing the user's response data using an emotion engine and identifying their emotional state; and a means for communicating with various devices and allowing the user to access the content from different devices. This allows for effective evaluation of the user's learning progress and provides optimal feedback. Furthermore, by analyzing the user's emotional state in real time and reflecting this in the feedback, the learning experience can be more personalized and an environment can be realized where the content can be seamlessly accessed from different devices.

[1642] "Generative AI" is an AI technology that generates language learning content in real time based on user input.

[1643] A "conversation log" is data that records the content of a conversation between a user and a system, and includes text data and voice data.

[1644] An "emotion engine" is a software component that analyzes user response data to identify the user's emotional state.

[1645] "Feedback" refers to evaluations and advice provided based on a user's learning progress, including information suggesting improvements to learning content and next steps.

[1646] "Learning progress" is an index that indicates the degree of progress of a user's language learning, and is evaluated based on the results of analysis of conversation logs and emotion data.

[1647] "Storage means" is a function for saving conversation logs and emotional data in a database.

[1648] "Analysis" refers to the process of using accumulated data to evaluate the user's learning progress and emotional state.

[1649] "Device" refers to any electronic device used by a user to access the system, including a smartphone, PC, tablet, etc.

[1650] "Communication" refers to the process of exchanging data between different devices over a network.

[1651] "Real-time" refers to data being generated and processed instantly.

[1652] This invention is an online language learning system that combines generative artificial intelligence and an emotion engine. This system is designed to allow users to learn languages ​​at any time and in an optimal environment, and can be accessed from a variety of devices. The operation of this system is described in detail below.

[1653] 1. User Registration and Login

[1654] A user opens a language learning application and enters their name, email address, desired password, desired language, etc. into the new account registration screen.

[1655] The terminal sends this information to the server.

[1656] The server validates the received information and stores the information that is deemed correct in a database (e.g., MySQL or PostgreSQL).

[1657] Once registration is complete, the server sends a confirmation message to the terminal, which the terminal displays to the user.

[1658] 2. Start learning conversation

[1659] The user presses the "Start Conversation Learning" button on the application's home screen.

[1660] The terminal sends this request to the server.

[1661] The server retrieves the user's learning level from the database and generates optimal conversation content based on the user's level using generative artificial intelligence (e.g., GPT-4 model). The generated conversation content is sent to the device, which then displays it to the user.

[1662] 3. Emotion Recognition and Log Accumulation

[1663] When the user responds to the conversation, the terminal transmits the user's voice data and text data to the server.

[1664] The server stores the received data in a database as a conversation log. The built-in emotion engine analyzes the user's response data and identifies their emotional state (e.g., joy, sadness, surprise, etc.). The emotion identification results are also stored along with the conversation log.

[1665] 4. Analysis and Feedback

[1666] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data. The emotion engine evaluates the user's emotional state as they study and generates feedback based on this. For example, if the user is feeling stressed, it will provide feedback on how to study in a relaxed manner. Based on the analysis, the server also identifies the user's learning progress and areas for improvement, and generates feedback suggesting the next course of study.

[1667] 5. Device connectivity and seamless access

[1668] The system can be accessed from a variety of devices, including smartphones, PCs, and tablets.

[1669] When a user logs in using a different device, the terminal sends the authentication information to the server.

[1670] The server verifies the authentication information and, if successful, sends the latest learning log and progress information to the new device.

[1671] The device displays this to the user, allowing them to check their previous learning content and progress, and continue learning seamlessly from any device.

[1672] Specific examples

[1673] For example, suppose an English learner wants to learn new words. When the user presses the "Start Conversation Learning" button, the server checks the user's current learning log and generates a conversation that includes the new words. The generated conversation might include questions such as "Where did you go today?"

[1674] When the user responds, "I went to the library," the conversation is logged in real time. Furthermore, an emotion engine analyzes the user's voice to determine whether they are relaxed or stressed. After the conversation ends, the system generates feedback such as, "Your pronunciation is accurate, and you seem to be learning in a relaxed manner. Next, let's review past tense grammar," and the device displays this to the user.

[1675] Prompt Sentence Examples

[1676] Specific conversation content can be generated by writing prompts to the generative AI model as follows:

[1677] For users who click the "Start Conversation Learning" button, generate a conversation appropriate to their level. The language of study is English, and the learner is at beginner level. Generate a conversation that includes questions to teach the learner new vocabulary.

[1678] This prompt allows the generative AI model to generate appropriate conversational content and provide it to the user.

[1679] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1680] Processing Steps

[1681] Step 1: User Registration and Login

[1682] 1. Enter information

[1683] A user opens a language learning application and enters their name, email address, desired password, and the language they wish to learn.

[1684] Input: Name, Email Address, Password, Language

[1685] Output: Request to send input data

[1686] 2. Data Transmission

[1687] The terminal transmits the information entered by the user to the server.

[1688] Input: Input data

[1689] Output: Send data to the server

[1690] 3. Validation and Storage

[1691] The server validates the submitted data and stores it in a database if it is deemed correct, for example by checking the format of the email address or the strength of the password.

[1692] Input: Input data

[1693] Output: Validation success or failure

[1694] 4. Sending a registration completion message

[1695] If validation is successful, the server sends the user a registration completion message, which the terminal displays to the user.

[1696] Input: Validation successful

[1697] Output: Display a confirmation message

[1698] Step 2: Start learning conversations

[1699] 1. Send a lesson start request

[1700] The user presses the "Start Conversation Learning" button on the application's home screen.

[1701] Input: Start learning request

[1702] Output: Request sent to server

[1703] 2. Obtaining user level and generating conversation content

[1704] The server obtains the user's learning level from the database and generates optimal conversation content using generative artificial intelligence (e.g., GPT-4).

[1705] Input: User learning level

[1706] Output: Generated conversation

[1707] 3. Display of conversation contents

[1708] The generated conversation content is sent to the terminal, which displays it to the user.

[1709] Input: Generated conversation

[1710] Output: Display of conversation

[1711] Step 3: Emotion recognition and logging

[1712] 1. Sending conversation response data

[1713] When the user responds to the conversation, the terminal transmits the voice data and text data to the server.

[1714] Input: Response data (audio or text)

[1715] Output: Send data to the server

[1716] 2. Save conversation logs

[1717] The server stores the received data in a database as a conversation log.

[1718] Input: Response data

[1719] Output: Save to database

[1720] 3. Emotional state analysis

[1721] The built-in emotion engine analyzes the user's response data and identifies their emotional state, such as joy, sadness, or surprise, based on their voice data.

[1722] Input: Response data

[1723] Output: Save the sentiment analysis results

[1724] Step 4: Analyze and provide feedback

[1725] 1. Log and emotion data analysis

[1726] Once the conversation session ends, the server analyzes the accumulated conversation log and emotional data.

[1727] Input: Conversation logs, emotion data

[1728] Output: Analysis results

[1729] 2. Generate feedback

[1730] The emotion engine generates optimal feedback for the user based on the analysis results. For example, if the user is relaxed, it generates feedback such as "You are able to study in a relaxed state."

[1731] Input: Analysis results

[1732] Output: Feedback message

[1733] 3. Viewing Feedback

[1734] The generated feedback is sent to the terminal, which displays it to the user.

[1735] Input: Feedback message

[1736] Output: Display feedback

[1737] Step 5: Device connection and seamless access

[1738] 1. Log in from your device

[1739] When a user logs in on a different device, the terminal sends authentication information to the server.

[1740] Input: Credentials

[1741] Output: Authentication request to the server

[1742] 2. Verify your credentials and synchronize your data

[1743] The server verifies the authentication information and, if successful, sends the latest learning log and progress information to the new device.

[1744] Input: Credentials

[1745] Output: Send training data

[1746] 3. View your learning log and progress information

[1747] The device displays this to the user, allowing them to check their previous learning content and progress, and continue learning seamlessly from any device.

[1748] Input: Training data

[1749] Output: Display of learning information

[1750] (Application example 2)

[1751] 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."

[1752] Conventional language learning systems were unable to provide learning content that took the user's emotional state into consideration, resulting in issues with learning efficiency and continuity. Furthermore, because appetite is significantly influenced by emotions, it was also unable to simultaneously provide meal suggestions based on the user's emotions. This created a need for a way to reduce learning stress and improve the overall learning experience.

[1753] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1754] In this invention, the server includes means for generating language learning content for a user using generative artificial intelligence, means for accumulating and analyzing conversation logs with the user, means for providing feedback according to the user's learning progress based on the analysis results, means for communicating with various devices and allowing the user to access the server from different devices, and means for analyzing the user's emotional data and recommending optimal meals based on the analysis results, thereby making it possible to provide content and suggest optimal meals that take the user's emotional state into consideration.

[1755] "Generative AI" is an AI technology that creates appropriate content and suggestions in real time based on the user's learning and emotional state.

[1756] "Conversation log" refers to recorded data that collects and stores the contents of conversations users have as text and audio data.

[1757] "Emotional data" is information that indicates the emotional state of a user obtained by analyzing the user's voice or text.

[1758] "Feedback" is advice or information about next steps or areas for improvement that is provided based on the user's learning progress and emotional state.

[1759] "Various devices" refers to the various devices that users use to access the site, such as smartphones, PCs, and tablets.

[1760] "Communication means" refers to the network means used by users to continuously access the service from different devices.

[1761] "Method of recommending meals" is a technology that suggests optimal meals based on the user's emotional data.

[1762] This invention is a system that combines generative artificial intelligence and an emotion engine to optimize an online language learning system and a food delivery application. Specific embodiments of this system are described below.

[1763] Basic Features

[1764] The system works on various devices, including smartphones, PCs, and tablets. Users can register and log in to receive optimal content and feedback based on their learning progress and emotional state. The system also supports seamless access across different devices.

[1765] Program Generation and Processing Description

[1766] The server first generates appropriate learning content using generative artificial intelligence based on the information and emotional state entered by the user, using specific software libraries called EmotionEngine and FoodRecommendationAI.

[1767] 1. The server receives the user information

[1768] When a user logs in to their account through their device, the server retrieves the user's profile information and past learning logs.

[1769] 2. Emotion Data Analysis

[1770] The user inputs their current emotional state and sends it to the server, which then uses the EmotionEngine to analyze this data and determine the user's emotional state.

[1771] 3. Generating learning content and feedback

[1772] The server uses generative artificial intelligence to generate optimal conversation content based on the user's learning progress, and also analyzes the user's stress level and relaxation state based on emotional data, providing appropriate feedback.

[1773] 4. Dietary Recommendations

[1774] Furthermore, it uses generative artificial intelligence to recommend optimal meals based on emotional data: for example, if the user is stressed, it will recommend relaxing meals, and if they are relaxed, it will recommend nutritious meals.

[1775] Usage example

[1776] If a user logs in to a food delivery app and enters "stress" as their emotional state, the server will analyze this information using the Emotion Engine and use Food Recommendation AI to recommend "meals that have a relaxing effect." Specific recommendations include a "Japanese meal set" and "chamomile tea."

[1777] Example prompts to be input to the generative AI model

[1778] An example prompt might have the following format:

[1779] User Emotion: Stress

[1780] User preference: Japanese food

[1781] Output format: Suggest a relaxing meal.

[1782] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1783] Step 1:

[1784] The user opens the smartphone app and enters login information (user ID and password). The device sends this information to the server, which then authenticates the user. If authentication is successful, the server retrieves the user's profile information and past learning logs and sends them to the device. In this process, the input is the user's login information, and the output is the user's profile information and past learning logs. Data processing and data calculation involve authentication and retrieval of data from the database.

[1785] Step 2:

[1786] The user inputs their current emotional state. For example, emotions such as "stressed" or "relaxed" are input into a smartphone app. The device sends this emotional information to the server, which then analyzes the data using the Emotion Engine. The input is the user's emotional state, and the output is the analyzed emotional data. Data processing and data calculation are emotion analysis.

[1787] Step 3:

[1788] The server uses generative artificial intelligence to generate appropriate learning content in real time based on emotional data and past learning logs. Optimal conversation content is generated based on the user's learning progress and level. The input is emotional data and learning logs, and the output is the generated learning content. Data processing and data calculation are used to generate learning content.

[1789] Step 4:

[1790] The generated learning content is sent to the terminal and displayed to the user. The user practices the conversation and responds in voice or text format. The terminal sends this response data to the server. The input is the generated learning content, and the output is the user's response data. Data processing and data calculation involve receiving the user's input.

[1791] Step 5:

[1792] The server receives and stores the user's conversation log as text and audio data. It also analyzes the conversation log to automatically evaluate learning progress. The input is the user's response data, and the output is the analyzed learning progress data. Data processing and data calculation involve the analysis and storage of the conversation log.

[1793] Step 6:

[1794] Based on the analysis results, the server provides feedback according to the user's learning progress. This feedback is sent to the terminal and displayed to the user. The input is learning progress data, and the output is feedback. Data processing and data calculation are used to generate feedback.

[1795] Step 7:

[1796] Based on the emotion data, the server uses Food Recommendation AI to recommend the most suitable meal. This recommendation is also sent to the device and displayed to the user. The input is emotion data, and the output is the meal recommendation. Data processing and data calculation are used to generate the meal recommendation.

[1797] 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.

[1798] 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.

[1799] 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.

[1800] 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.

[1801] 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.

[1802] 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.

[1803] 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).

[1804] 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.

[1805] 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."

[1806] 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.

[1807] 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).

[1808] 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.

[1809] 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.

[1810] 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.

[1811] 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.

[1812] 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.

[1813] 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.

[1814] 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.

[1815] 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.

[1816] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1817] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1818] The following is further disclosed regarding the above embodiment.

[1819] (Claim 1)

[1820] A means for generating language learning content for a user using generative artificial intelligence;

[1821] means for accumulating and analyzing a conversation log with the user;

[1822] a means for providing feedback according to the user's learning progress based on the analysis results;

[1823] means for communicating with various devices to allow said user to access from different devices;

[1824] A system including:

[1825] (Claim 2)

[1826] The system according to claim 1, characterized in that the generative artificial intelligence generates optimal conversation content in real time based on the user's registration information and past learning log.

[1827] (Claim 3)

[1828] 2. The system according to claim 1, wherein the storage means stores the user's conversation log as text and voice data, and analyzes the data to automatically evaluate the user's learning progress.

[1829] "Example 1"

[1830] (Claim 1)

[1831] A means for generating language learning content for a user using generative artificial intelligence;

[1832] means for accumulating and analyzing a conversation log with the user;

[1833] a means for providing feedback according to the user's learning progress based on the analysis results;

[1834] means for communicating with various devices to allow said user to access from different devices;

[1835] a means for entering and validating user information;

[1836] a means for storing user information in a database;

[1837] means for providing prompt sentences for generating conversational content based on the user's learning level;

[1838] a means for transmitting and storing user responses in real time;

[1839] A means of analyzing conversation logs and generating suggestions and feedback for the next learning content;

[1840] A system including:

[1841] (Claim 2)

[1842] The system according to claim 1, characterized in that the generative artificial intelligence generates optimal conversation content in real time based on the user's registration information and past learning log.

[1843] (Claim 3)

[1844] 2. The system according to claim 1, wherein the storage means stores the user's conversation log as text and voice data, and analyzes the data to automatically evaluate the user's learning progress.

[1845] "Application Example 1"

[1846] (Claim 1)

[1847] A means for generating language learning content for a user using generative artificial intelligence;

[1848] means for accumulating and analyzing a conversation log with the user;

[1849] a means for providing feedback according to the user's learning progress based on the analysis results;

[1850] means for communicating with various devices to allow said user to access from different devices;

[1851] a means for generating dialogues for language learning in conjunction with devices used in a factory environment;

[1852] means for analyzing a conversation log based on the dialogue and providing feedback related to factory work;

[1853] A system including:

[1854] (Claim 2)

[1855] The system according to claim 1, characterized in that the generative artificial intelligence generates optimal conversation content in real time based on the user's registration information and past learning log.

[1856] (Claim 3)

[1857] 2. The system according to claim 1, wherein the storage means stores the user's conversation log as text and voice data, and analyzes the data to automatically evaluate the user's learning progress.

[1858] "Example 2: Combining Emotion Engines"

[1859] (Claim 1)

[1860] A means for generating language learning content for a user using generative artificial intelligence;

[1861] means for accumulating and analyzing a conversation log with the user;

[1862] a means for providing feedback according to the user's learning progress based on the analysis results;

[1863] means for analyzing the user's response data using an emotion engine to identify an emotional state;

[1864] means for communicating with various devices to allow said user to access from different devices;

[1865] A system including:

[1866] (Claim 2)

[1867] The system according to claim 1, characterized in that the generative artificial intelligence generates optimal conversation content in real time based on the user's registration information and past learning log.

[1868] (Claim 3)

[1869] 2. The system according to claim 1, wherein the storage means stores the user's conversation log as text and voice data, and analyzes the data to automatically evaluate the user's learning progress.

[1870] "Application example 2 when combining emotion engines"

[1871] (Claim 1)

[1872] A means for generating language learning content for a user using generative artificial intelligence;

[1873] means for accumulating and analyzing a conversation log with the user;

[1874] a means for providing feedback according to the user's learning progress based on the analysis results;

[1875] means for communicating with various devices to allow said user to access from different devices;

[1876] means for analyzing the emotion data of the user and recommending an optimal meal based on the analysis results;

[1877] A system including:

[1878] (Claim 2)

[1879] The system according to claim 1, characterized in that the generative artificial intelligence generates optimal conversation content in real time based on the user's registration information and past learning log.

[1880] (Claim 3)

[1881] 2. The system according to claim 1, wherein the storage means stores the user's conversation log as text and voice data, and analyzes the data to automatically evaluate the user's learning progress. [Explanation of symbols]

[1882] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for generating language learning content for a user using generative artificial intelligence; means for accumulating and analyzing a conversation log with the user; a means for providing feedback according to the user's learning progress based on the analysis results; means for communicating with various devices to allow said user to access from different devices; A system including:

2. 2. The system according to claim 1, wherein the generative artificial intelligence generates optimal conversation content in real time based on the user's registration information and past learning log.

3. 2. The system according to claim 1, wherein said storage means stores the user's conversation log as text and voice data, and analyzes the log to automatically evaluate the user's learning progress.

Images