system

Abstract

We provide the system. [Solution] A means for analyzing the user's learning goals and skill level, A means for automatically generating a learning plan based on the analysis results, A means for providing interactive voice dialogue using means for analyzing the user's pronunciation and language use in real time, A means of automatically generating visual teaching materials using image generation technology and presenting them to the user, A means for generating a video and providing a simulation based on a specified scenario, A means of analyzing the user's learning progress and providing individualized feedback, A system that includes this.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] There is a need to solve the difficulties in maintaining self-learning motivation and evaluating progress faced by language learners and corporate employees. Conventional language learning methods do not fully consider the individual needs of learners and rely on uniform teaching materials and methods, which is one of the factors hindering the improvement of learning efficiency. In addition, there is a lack of opportunities for real-time pronunciation and conversation practice, and it is difficult to apply the learning results in the real world. Furthermore, due to limited means of visualizing progress and receiving specific feedback, self-evaluation is difficult and there is a lack of guidance in continuous learning.

Means for Solving the Problems

[0005] This invention solves these problems by providing a multimodal language learning agent that combines text reading, speech recognition, image generation, and video generation technologies. Specifically, it includes means for analyzing the user's learning goals and skill level and automatically generating an individualized learning plan based on them. It also includes means for analyzing the user's pronunciation and grammar in real time and providing interactive feedback. Furthermore, it deepens the learner's understanding by automatically generating visual learning materials using image generation technology. In addition, it includes means for providing simulation videos based on specific situations using video generation technology to support practical learning. Finally, by performing progress evaluation and feedback, it constructs a system that enables learners to grasp specific areas for improvement and learn efficiently.

[0006] A "user" is an individual or group that uses the system to learn a language.

[0007] A "learning plan" is a personalized learning guide created based on the user's learning goals and current skill level.

[0008] "Voice dialogue" is an interactive form of communication that takes place in real time by analyzing the user's pronunciation and grammar.

[0009] "Image generation technology" refers to algorithms and processes that automatically create visual materials based on text or a theme.

[0010] "Video generation technology" refers to algorithms and processes that automatically create video content based on specific scenarios or situations.

[0011] "Progress evaluation" is a process that tracks users' learning activities and analyzes their level of achievement and areas for improvement.

[0012] "Feedback" refers to analyzing a user's learning activities and providing specific advice and evaluations for improvement.

[0013] "System" refers to a comprehensive platform that combines multiple technologies and processes defined in the claims of this patent to provide language learning services to users. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] The multimodal language learning system of the present invention provides users with an individualized learning experience through the cooperation of the server, terminal, and user elements. This system operates in the following manner, with each element working in coordination.

[0036] First, the user uses their device to input their learning objectives and current skill level. The device sends this information to a server, which uses natural language processing technology to analyze the user's needs and automatically generate a personalized learning plan. This plan is tailored to the user's requirements and can be specialized in specific areas, such as business English or travel English.

[0037] Next, users can improve their language skills using the voice interaction function. The device records the user's voice and sends it to the server. The server analyzes the user's speech using speech recognition technology and provides real-time feedback on pronunciation and grammar using speech synthesis technology. For example, if it is necessary to distinguish between the pronunciation of "r" and "l," the server will point out the difference and provide an example of the correct pronunciation.

[0038] Furthermore, in the generation of visual learning materials, illustrations and scenario images are automatically generated by the server using image generation technology. The terminal then presents these to the user. This makes it easier for the user to visually understand the meaning of new words. For example, in a lesson themed on "airport," an image of boarding procedures is generated and provided.

[0039] The video simulation is conducted based on a specific scenario, and the server uses video generation technology to generate relevant videos. Users can observe these videos through their devices and hone their practical skills. For example, when practicing conversation in a restaurant, videos are provided that include ordering methods and customer service interactions.

[0040] Finally, the progress evaluation and feedback function allows the server to analyze the user's learning data and provide personalized evaluations. This enables users to understand their strengths and areas for improvement, allowing them to learn more efficiently.

[0041] Based on the above configuration, the present invention provides flexible and effective support for language learning that meets the user's needs. This system is expected to solve the challenges of maintaining motivation and evaluating progress in language learning, thereby improving learning efficiency.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user uses a device to input their learning objectives and current skill level. The device then sends this information to the server.

[0045] Step 2:

[0046] The server analyzes the received user information using natural language processing technology to understand the user's needs. Based on those needs, the server generates a personalized learning plan.

[0047] Step 3:

[0048] The server sends the generated learning plan to the device, and the device displays the plan details to the user. The user then begins learning based on this plan.

[0049] Step 4:

[0050] The user initiates a voice interaction using the device's microphone. The device records the user's voice and sends the audio data to the server.

[0051] Step 5:

[0052] The server uses speech recognition technology to analyze the audio data and evaluate the user's pronunciation and grammar. The server then generates feedback using speech synthesis technology and sends it to the terminal.

[0053] Step 6:

[0054] The device provides real-time feedback to the user in voice or text. The user then uses this feedback to improve their pronunciation and grammar.

[0055] Step 7:

[0056] When a user requests visual learning materials, the device sends the request to the server. The server uses image generation technology to generate relevant illustrations and scenario images.

[0057] Step 8:

[0058] The server sends the generated visual learning materials to the terminal, which then displays them to the user. The user uses the visual learning materials to gain a deeper understanding of vocabulary and grammar.

[0059] Step 9:

[0060] When a user requests a video simulation, the device sends scenario information to the server. The server uses video generation technology to generate a video based on the specified scenario.

[0061] Step 10:

[0062] The server sends the generated video to the terminal, and the terminal plays the video for the user. The user practices practical skills through simulation videos that mimic realistic situations.

[0063] Step 11:

[0064] The device tracks the user's learning activities and periodically sends progress data to the server. The server analyzes the data and evaluates the user's learning progress.

[0065] Step 12:

[0066] The server generates personalized feedback based on learning assessments and sends it to the device. The device presents the feedback to the user, who then identifies areas for improvement and uses them to further their learning.

[0067] (Example 1)

[0068] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0069] A challenge with conventional language learning systems was the insufficient generation of personalized learning plans tailored to the user's learning goals and skill level. Furthermore, the lack of real-time feedback on pronunciation and grammar, coupled with the manual generation of visual learning materials and simulation videos, resulted in an inconsistent and inefficient learning experience for the learner.

[0070] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0071] In this invention, the server includes means for analyzing user information and automatically generating a learning plan using a generative AI model; means for analyzing the user's pronunciation and language use in real time using speech recognition technology and speech synthesis technology and providing feedback; and means for automatically generating visual learning materials and simulation videos using image generation technology and video generation technology. This enables the user to receive a personalized learning experience and improves learning efficiency through real-time voice feedback and automatically generated visual learning materials and videos.

[0072] "User information" refers to data that learners input via a device to define their own learning goals and skill levels.

[0073] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze user information and automatically generate personalized learning plans.

[0074] A "learning plan" is a plan of specific learning activities and content that is automatically generated according to the user's learning goals and skill level.

[0075] "Speech recognition technology" is a technology that analyzes voice data input by a user and identifies and recognizes the linguistic elements within it.

[0076] "Speech synthesis technology" is a technology that generates speech data and provides real-time feedback.

[0077] "Visual teaching materials" are visual educational resources presented to learners using image generation technology.

[0078] "Video generation technology" is a technology that generates video content based on a specified scenario and provides learners with a simulation.

[0079] "Feedback" refers to evaluations and improvement suggestions provided for a user's learning activities, often specifically pointing out aspects such as pronunciation and progress.

[0080] The language learning system of the present invention provides personalized learning through the coordinated operation of the user, terminal, and server. In this system, the user first inputs their learning objectives and skill level using a terminal. This input process is performed via a user interface and can be done using common devices such as tablets and smartphones.

[0081] The terminal transmits user input information to the server via the internet. The server operates on a cloud platform with high computing power and analyzes user information using natural language processing technology. The server uses a generative AI model to generate a personalized learning plan tailored to the user's learning needs. This plan includes daily learning content and progress goals.

[0082] Furthermore, users can practice pronunciation through voice input. The device records the user's speech and sends the data to a server. The server analyzes the user's pronunciation using speech recognition technology and provides immediate feedback using speech synthesis technology. This allows users to receive specific advice on the accuracy of their pronunciation and grammatical errors.

[0083] To aid in visual learning, the server uses image generation technology to create illustrations and scene diagrams, which are then presented to the user via the terminal. This feature supports the visual understanding of new words and concepts. In particular, video generation technology is used for scenario-based video simulations, allowing users to acquire practical skills while watching them on their terminals.

[0084] The server also analyzes the user's learning progress and provides personalized feedback using machine learning algorithms. This feedback includes clear areas for improvement and specific learning advice.

[0085] For example, if a user enters "I want to practice English conversation for business meetings" into the terminal, the server will propose a corresponding learning plan and provide practical learning through voice dialogue and video simulations. An example of a prompt sentence is "Please teach me a conversation about ordering at a restaurant." Through this system, users can learn a language effectively and efficiently.

[0086] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0087] Step 1:

[0088] The user uses a device to input their learning objectives and current skill level. This input data includes the target language, learning level, and specific needs (e.g., travel conversation). The device then formats this information and prepares it for transmission to the server.

[0089] Step 2:

[0090] The terminal transmits user input data to the server via the internet. During this process, the data is encrypted to ensure security. The server registers the received data in a database for analysis.

[0091] Step 3:

[0092] The server uses natural language processing technology to analyze user information. Based on the analysis, a generative AI model creates a personalized learning plan tailored to the user. This plan includes recommended lessons, materials, and practice methods. The generated plan is temporarily stored on the server and prepared for transmission to the user's device.

[0093] Step 4:

[0094] The user uses the voice input function on their device to speak phrases or words they want to practice. The device records the voice data from the microphone and converts it into digital data for transmission to the server.

[0095] Step 5:

[0096] The server uses speech recognition technology to analyze the user's voice data. It converts the voice data into text and detects pronunciation and grammatical errors. Based on this analysis, it uses speech synthesis technology to generate feedback data that includes correct pronunciation and suggested corrections.

[0097] Step 6:

[0098] The device displays feedback data received from the server to the user. The feedback is provided in audio or text format and includes specific areas for improvement and advice. The user then uses this information to practice pronunciation.

[0099] Step 7:

[0100] The server uses image generation technology to generate visual learning materials related to the learning plan. These materials are designed to help with understanding new words and scenarios. The generated image data is sent to the terminal.

[0101] Step 8:

[0102] The server uses video generation technology to create a simulated video based on a specified scenario. This video is designed to simulate a real-life conversation and is provided to the user's device so that they can watch it repeatedly for learning.

[0103] Step 9:

[0104] The server continuously records the user's learning progress and analyzes it using machine learning algorithms. Based on this analysis, it generates data to provide personalized feedback and advice on goal achievement, and sends it to the user's device.

[0105] <|ipynb_marker|> Code

[0106] There is no code provided to execute or demonstrate.

[0107] (Application Example 1)

[0108] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0109] Traditional systems have limitations in terms of personalization and interactivity when it comes to effective language learning tailored to individual user needs. Furthermore, the lack of effective means to provide visual learning materials and simulation videos restricts the user's learning experience. This makes it difficult to maintain learning efficiency and motivation.

[0110] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0111] In this invention, the server includes means for analyzing the user's learning goals and ability level, means for automatically generating a training plan based on the analysis results, and means for providing interactive voice conversation using means for analyzing the user's pronunciation and vocabulary use in real time. This enables the automatic generation of personalized training plans and an improved learning experience through advanced interactive functions.

[0112] A "user" is a person who uses the system to learn a language.

[0113] "Learning objectives" refer to the specific language abilities and skills that the user wants to achieve.

[0114] "Proficiency level" is an indicator that represents the user's current language skill level.

[0115] "Means of analysis" refers to technologies that process user input information to understand its intent and content.

[0116] A "training plan" is a learning process designed based on the user's learning goals and skill level.

[0117] "Automatic generation methods" refer to technologies that automatically create optimal training plans from user information.

[0118] "Pronunciation" refers to the accuracy of the phonetic aspects of words.

[0119] "Vocabulary usage" refers to the selection and use of words and expressions by the user.

[0120] "Real-time analysis" refers to technology that processes and analyzes user voice instantly.

[0121] "Means of providing interactive voice conversations" refers to a system that enables interactive communication with users through voice.

[0122] "Visual learning materials" are teaching materials that use images and visuals to support learning.

[0123] "Image generation technology" is a technology that uses algorithms to create visual content.

[0124] "Scene" is a term that refers to a specific situation or scenario.

[0125] "Means of generating and providing videos" refers to technologies that create and present scene-based video content to users.

[0126] "Learning progress" indicates the degree to which the user's language ability is improving.

[0127] "Feedback" refers to information that provides evaluations of user performance and suggestions for improvement.

[0128] A "robot" is an electronic device that operates based on a program and can interact with a user.

[0129] The system for implementing this invention consists of a server, a terminal, and a user. First, the user operates the terminal to input their learning goals and current ability level. Based on this, the terminal sends data to the server. The server receives this information and analyzes it using natural language processing technology. Based on the results of this analysis, the system automatically generates an optimal training plan for the user.

[0130] Next, the user engages in an interactive voice conversation through the robot. The robot incorporates speech recognition and speech synthesis technologies to analyze the user's pronunciation and vocabulary usage in real time. For example, if areas for improvement in pronunciation are detected, feedback is provided immediately.

[0131] Furthermore, the server utilizes image generation technology to create visual learning materials tailored to the user's learning situation and presents them to the user via the terminal. Simulation videos are also generated in a similar manner, making it easier for users to visualize the actual situation.

[0132] The user's learning progress is periodically evaluated by the server, and detailed feedback is provided. This process is implemented using various hardware and software. For example, Google Cloud Speech-to-Text is used for speech processing, and OpenAI's GPT model is used for natural language processing. Stable Diffusion can be used for image generation, and the Pexels API can be used for video generation.

[0133] As a concrete example, consider a scenario where a user practices conversation in a restaurant. The robot acts as the waiter, taking orders and providing real-time feedback on pronunciation. Furthermore, the learning effect can be enhanced by presenting images and simulation videos related to the order.

[0134] An example of a prompt for a generative AI model is: "A user places an order at a restaurant. As a waiter, check the pronunciation and grammar, point out areas for improvement, and provide correct examples. Generate and present an image based on the situation."

[0135] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0136] Step 1:

[0137] The user inputs their learning goals and current proficiency level via a terminal. The input data is then sent to the server by the terminal. In this step, the input is the user's learning goals and proficiency level, and the output is the data sent to the server. The terminal's operation involves receiving user input and sending data.

[0138] Step 2:

[0139] The server uses natural language processing techniques to analyze the data it receives. The input is user data sent from the terminal, and the output is information about the analyzed learning needs. The server processes this data to automatically generate an optimal learning plan for the user.

[0140] Step 3:

[0141] The server automatically generates a learning plan and sends it to the terminal. The input is the learning plan generated by the server, and the output is the terminal that received it. The server's operation is to format and send the plan data.

[0142] Step 4:

[0143] The user initiates an interactive voice conversation with the robot using a terminal. The input is the user's voice, which is analyzed in real time by the robot. The output is either voice or text, including feedback on pronunciation and grammar. The terminal and robot's actions are voice recognition and feedback provision.

[0144] Step 5:

[0145] The server uses image generation technology to generate visual learning materials related to the user's learning content and sends them to the terminal. The input is scene information based on the learning plan, and the output is the generated image. The server's operation consists of generating and sending image data.

[0146] Step 6:

[0147] The server generates video content based on a specified scenario and provides the simulation to the terminal. The input is scenario information from the learning plan, and the output is the generated simulation video. The server's operation consists of executing the video generation algorithm and sending data.

[0148] Step 7:

[0149] The server analyzes the user's learning progress and provides personalized feedback to the terminal. The input is the user's learning history data, and the output is progress evaluation feedback information. The server's operation consists of data analysis and feedback generation.

[0150] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0151] This invention provides a multimodal language learning system that combines an emotion engine, thereby enabling further personalization of the user's learning experience. The system operates as follows, with the server, terminal, and user each playing a specific role.

[0152] First, the user inputs their learning goals and skill level through their device, and the device sends this information to the server. The server uses natural language processing technology to analyze the user's needs and automatically generates a personalized learning plan. In this process, the user's learning history and emotional state are also taken into consideration to provide a more appropriate plan.

[0153] When using the voice interaction function, the user speaks into the device's microphone, and the voice data is sent to the server. The server analyzes the spoken content based on speech recognition technology and evaluates the user's emotional state using an emotion engine. This evaluation result is reflected in the feedback generated using speech synthesis technology, providing advice tailored to the user's state in real time. For example, if the server detects that the user is feeling dissatisfied or stressed, it can offer encouraging messages or simple tasks.

[0154] Furthermore, the emotion engine is also used when generating visual learning materials and video simulations. The server generates content tailored to the user's interests and emotions using image and video generation technologies and presents it through the device. When the user is relaxed, a more challenging scenario is presented, and when they feel tense or anxious, easier exercises are presented, designed to gradually improve their skills.

[0155] Furthermore, the emotion engine is also used in progress evaluation. The server analyzes the user's learning activities and emotional changes, and generates emotion-based feedback. This feedback allows users to better understand their own learning process and maintain motivation as they continue learning.

[0156] Through the embodiments described above, the present invention aims to realize a personalized language learning experience that takes emotions into consideration, thereby maximizing the user's learning effectiveness. This system is expected to not only improve language skills but also support the user's psychological aspects.

[0157] The following describes the processing flow.

[0158] Step 1:

[0159] The user uses a device to input their learning goals, current skill level, and emotional state. The device then sends this information to the server.

[0160] Step 2:

[0161] The server analyzes the received user data using natural language processing technology. Based on the user's needs, it automatically generates a learning plan, taking their emotional state into consideration.

[0162] Step 3:

[0163] The server sends the generated learning plan to the device. The device displays the plan details to the user and presents learning content tailored to their emotions.

[0164] Step 4:

[0165] The user activates the voice interaction function through the device and begins speaking. The device records the voice data and sends it to the server.

[0166] Step 5:

[0167] The server uses speech recognition technology to convert the audio data into text and analyzes its content. Furthermore, it uses an emotion engine to evaluate the user's emotions and generate feedback.

[0168] Step 6:

[0169] The server generates customized feedback using speech synthesis technology and sends it to the terminal. The terminal provides the user with real-time feedback in either voice or text.

[0170] Step 7:

[0171] When a user requests visual learning materials, the device sends a request to the server. The server uses image generation technology to generate learning materials that respond to the user's emotions.

[0172] Step 8:

[0173] The server sends the generated visual learning materials to the device. The device displays the materials to the user, supporting emotionally sensitive learning.

[0174] Step 9:

[0175] When a user requests a video simulation, the device sends the scenario to the server. The server generates a video using video generation technology and incorporates the user's emotions into it.

[0176] Step 10:

[0177] The server sends the generated video to the device. The device plays the video for the user, assisting in the practice of practical skills. The practice is provided at a pace that suits the user's mood.

[0178] Step 11:

[0179] The device tracks the user's learning activities and emotional changes, and sends the data to the server. The server performs progress and emotional assessments and manages the user's learning status.

[0180] Step 12:

[0181] The server generates personalized feedback based on training data and sentiment evaluations. The terminal presents the feedback to the user and suggests a learning direction that takes sentiment into account.

[0182] (Example 2)

[0183] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0184] Current language learning systems suffer from insufficient personalization that takes into account each user's individual learning progress and emotional state, making it difficult to maximize learning effectiveness. Furthermore, they sometimes fail to provide adequate feedback to maintain user motivation. In addition, it is difficult to integrate and utilize diverse forms of learning materials, preventing the provision of a learning experience tailored to each individual user.

[0185] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0186] In this invention, the server includes means for analyzing the user's learning goals and skill level, means for automatically generating a learning plan based on the analysis results, and means for analyzing the user's emotional state and reflecting it in the learning content. This makes it possible to respond to the user's individual needs and provide a personalized learning experience based on their emotional state. Furthermore, this allows the user to maintain their motivation while learning effectively.

[0187] "User learning objectives" refer to the specific language learning goals that learners wish to achieve.

[0188] "Skill level" is an indicator that shows the degree of language proficiency a user currently possesses.

[0189] "Means of analysis" refers to the process by which a system understands the input information and gains appropriate insights.

[0190] "Automatic generation methods" refer to the function of a system that generates content and plans without human intervention, based on pre-set rules and algorithms.

[0191] "Interactive voice communication" is a feature that allows users to communicate in real time using natural language.

[0192] "Visual learning materials" are educational media provided to learners to acquire information through visual means.

[0193] "Virtual experience" is a method of providing users with realistic experiences through computer-generated content.

[0194] "Learning progress" is an indicator that measures the degree of progress made towards the goals set by the user.

[0195] "Emotional state" refers to a learner's psychological and emotional condition and is a factor that influences their learning activities.

[0196] "Feedback" refers to information provided by a system in response to user input and activities, such as opinions and evaluations, that helps improve the learning process.

[0197] This invention is a multimodal language learning system that integrates an emotion engine and aims to optimize the individual learning experience of each user. The system mainly consists of three elements: a server, a terminal, and the user.

[0198] First, the user uses a device to input information about their learning goals and skill level. The device securely transmits this information to a server via the internet. The device can operate using a browser application or a dedicated application.

[0199] Next, the server analyzes the received data using natural language processing (NLP) techniques. This analysis utilizes Python NLP libraries (such as SpaCy or NLTK). Based on the analysis results, a personalized learning plan tailored to the user's learning needs is automatically generated by an AI model. This AI model is designed to take into account the user's past data and emotional state.

[0200] Furthermore, when using the voice interaction function, the user inputs voice using the device's microphone. This voice is sent from the device to the server. The server uses a speech recognition API (for example, Google Cloud Speech-to-Text) to analyze the utterance and evaluates the user's emotions using an emotion engine. This emotion evaluation is reflected in the feedback generated by speech synthesis technology and presented to the user in real time.

[0201] Furthermore, the server automatically generates visual learning materials and video content using image and video generation technologies. This allows for the creation of learning materials tailored to the user's chosen learning goals and emotional state, enriching the learning experience.

[0202] For example, if a user enters "I want to improve my French conversation skills" into the device, the system will consider the user's skill level and emotional state, and then provide appropriate conversation practice and learning materials to help them understand the emotions of French. Another example of a prompt sentence for the generating AI model is, "Please suggest ways for the user to efficiently learn new vocabulary."

[0203] Based on the above, the system of the present invention aims to make user learning a comprehensive educational experience that includes emotional support, rather than merely the acquisition of knowledge.

[0204] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0205] Step 1:

[0206] The user inputs learning goals and skill levels into the device. The user text-inputs the language to be learned and their goals through the device's interface. This input information is treated as basic data necessary for customizing the learning content. The device processes this input data, formats it, and then sends it to the server.

[0207] Step 2:

[0208] The device sends input data to the server. The device uses a secure communication protocol (e.g., HTTPS) to send formatted data to the server. This ensures user privacy. The data includes learning objectives, skill level, and timestamps.

[0209] Step 3:

[0210] The server receives data from the user and analyzes it using natural language processing (NLP) techniques. Based on the received data, the server uses Python's NLP library to identify the user's needs. The input for the analysis is the user's learning goals and skill level, and the output includes insights necessary for designing a personalized learning plan.

[0211] Step 4:

[0212] The server automatically generates a learning plan using a generated AI model. In this step, the server inputs the analysis results into the generated AI model to precisely determine the content and stages of learning. The input also includes the user's learning history and emotional state, and the output is a learning plan tailored to the user.

[0213] Step 5:

[0214] The device receives the learning plan from the server and presents it to the user. The learning plan is displayed on the screen in a user-friendly format. Upon receiving the plan, the device decrypts its contents and provides it to the user as appropriately formatted information.

[0215] Step 6:

[0216] The user uses the voice interaction function to input speech into the device. The user speaks into the device's microphone, and the audio is converted into a digital format and sent to the server. This data is treated as a voice input prompt and is analyzed in the next step.

[0217] Step 7:

[0218] The server analyzes audio data using speech recognition technology and evaluates it using an emotion engine. The server uses a speech recognition API to convert user speech into text. Then, the emotion engine evaluates the user's emotional state. The input is audio data, and the output is the analyzed text and the emotion evaluation result.

[0219] Step 8:

[0220] The server generates feedback and delivers it to the user via speech synthesis. The server uses speech synthesis technology to generate feedback messages tailored to the user's emotional state. The final output is in audio format, which is provided to the user in real time through the device.

[0221] Step 9:

[0222] The user receives feedback and decides on their next learning action. Based on the feedback provided, the user chooses the next step. This process allows the user to learn efficiently.

[0223] (Application Example 2)

[0224] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0225] Modern language learning demands flexible learning approaches tailored to each learner's ability level and emotional state. However, traditional systems fail to adequately address individual needs, posing challenges in maintaining motivation and efficient learning. Furthermore, standardized feedback makes it difficult to maximize learning effectiveness, and insufficient psychological support for users is also a problem.

[0226] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0227] In this invention, the server includes means for analyzing the user's learning goals and ability level; means for automatically generating a learning plan based on the analysis results; means for analyzing the user's pronunciation and language use in real time; means for automatically generating and presenting visual learning materials to the user using image generation technology; means for generating videos and providing simulations based on specified situations; means for analyzing the user's learning progress and providing individual feedback; and means for analyzing the user's emotional state and providing voice encouragement and learning adjustments according to that situation. This makes it possible to provide a personalized learning experience tailored to each user and improve learning efficiency and motivation.

[0228] A "user" is an individual learner who utilizes a language learning system.

[0229] A "learning objective" is the specific language skill or knowledge level that the user wants to achieve.

[0230] "Proficiency level" is an indicator that shows the degree of language knowledge and skills a user currently possesses.

[0231] "Analysis" is the process of thoroughly examining information and data to reveal its structure and characteristics.

[0232] A "learning plan" refers to a chronologically organized set of steps and strategies aimed at helping a user achieve their goals.

[0233] "Real-time analysis" means processing phenomena and data as they occur and reflecting the results immediately.

[0234] "Interactive voice communication" is a process in which the user and the system exchange information bidirectionally through voice.

[0235] "Visual learning materials" are educational content created to provide information to users through visual means.

[0236] "Image generation technology" refers to the technology of creating new images within a computer using algorithms and software.

[0237] "Generating video based on context" means automatically creating appropriate video content according to specific conditions or context.

[0238] "Simulation" is a method of imitating real-world phenomena and predicting or analyzing their states and changes.

[0239] "Analyzing a user's learning progress" means evaluating how close a learner is to achieving their goals.

[0240] "Providing individualized feedback" means offering optimal advice and suggestions for improvement based on the user's situation and progress.

[0241] "Analyzing emotional states" is the process of understanding a user's psychological state and emotions, and comprehending their characteristics.

[0242] "Voice encouragement" is the act of sending messages through voice to support a user's motivation and mental state.

[0243] "Adjusting the learning plan" is the process of reviewing the learning plan and making adjustments in the optimal direction according to the user's progress and circumstances.

[0244] This invention is based on a system that analyzes emotional states and learning progress in real time to personalize the user's learning experience and provides a learning plan based on that analysis.

[0245] The server uses natural language processing technology and sentiment analysis engines to analyze the learning goals and ability levels provided by the user. Based on the results of these analyses, an algorithm is used to select the most suitable content for generating the learning plan. In this process, the user's past learning history and sentiment data are utilized to establish a personalized plan.

[0246] On the device side, speech recognition technology is used to collect the user's speech and instantly transmit it to the server. The server analyzes the received audio data and evaluates the emotional state. For example, if it is detected that the user is feeling anxious, the server uses speech synthesis technology to generate encouraging feedback and presents it to the user through the device.

[0247] Furthermore, the server combines image and video generation technologies to create visual learning materials and simulation videos tailored to the user's interests and situation. This makes the learning content easier to understand intuitively.

[0248] For example, if a user is struggling with a particular topic during their learning process, the server can create a simple scenario based on that topic and present practice problems in a way that alleviates the user's anxiety.

[0249] An example of a prompt based on a generative AI model is: "After the user expresses their feelings, show how to support their motivation and adjust their learning. Include specific encouraging messages in case the user becomes frustrated."

[0250] Overall, this system aims to enhance learning effectiveness by providing individual users with a learning pace and method tailored to their needs.

[0251] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0252] Step 1:

[0253] The device receives input from the user regarding learning goals and ability levels. This information is sent to a server to build a database of personalized learning plans. The input information serves as foundational data for analyzing the user's specific learning needs.

[0254] Step 2:

[0255] The server uses natural language processing techniques to analyze the user's learning goals and ability level based on the received data. This analysis prepares the data necessary to generate a learning plan tailored to the user. The analyzed data is then passed to the learning planning algorithm, which leads to the design of an individualized plan.

[0256] Step 3:

[0257] When a user speaks into the device, voice data is collected. The device sends this voice data to a server, which uses speech recognition technology to analyze the content of the speech. As a result, the user's emotional state based on the speech is evaluated. In this step, the input voice is processed as digital data, and the corresponding text and emotional state are output.

[0258] Step 4:

[0259] The server generates appropriate feedback using speech synthesis technology based on the user's emotional state. If the emotion is determined to be dissatisfaction or anxiety, an encouraging message is created. The generated voice feedback is delivered to the user through the terminal. In this step, voice data corresponding to the analysis results is output.

[0260] Step 5:

[0261] The server utilizes image and video generation technologies to create visual learning materials and simulation videos tailored to the user's interests and emotions. These materials are designed to enhance the user's learning experience. The generated visual content is displayed to the user via their device. The generated materials serve as supplementary content for the learning plan.

[0262] Step 6:

[0263] The server analyzes the user's learning progress and provides personalized feedback based on the analysis results. This allows users to understand their own learning progress and make necessary improvements and adjustments. The feedback based on the analysis results contributes to maintaining the user's learning motivation.

[0264] This entire process provides users with an optimal learning environment tailored to their needs, enabling efficient language acquisition.

[0265] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0266] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0267] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0268] [Second Embodiment]

[0269] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0270] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0271] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0272] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0273] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0274] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0275] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0276] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0277] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0278] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0279] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0280] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0281] The multimodal language learning system of the present invention provides users with an individualized learning experience through the cooperation of the server, terminal, and user elements. This system operates in the following manner, with each element working in coordination.

[0282] First, the user uses their device to input their learning objectives and current skill level. The device sends this information to a server, which uses natural language processing technology to analyze the user's needs and automatically generate a personalized learning plan. This plan is tailored to the user's requirements and can be specialized in specific areas, such as business English or travel English.

[0283] Next, the user can use the voice interaction function to improve their language skills. The terminal records the user's voice and sends it to the server. The server analyzes the user's speech using speech recognition technology and provides real-time feedback on pronunciation and grammar through speech synthesis technology. For example, when it is necessary to distinguish between the pronunciations of "r" and "l", the server points out that point and provides examples of correct pronunciation.

[0284] Also, in the generation of visual teaching materials, illustrations and scenario images using image generation technology are automatically generated by the server. Then the terminal presents it to the user. This makes it easier for the user to visually understand the meaning of new words. For example, in a lesson themed on "airport", images of the boarding procedures are generated and provided.

[0285] Video simulations are carried out based on specific scenarios, and the server utilizes video generation technology to generate related videos. The user can observe this video through the terminal and hone practical skills. For example, when practicing conversations in a restaurant, videos including the order-taking method and the interaction with customers are provided.

[0286] Finally, in the function of progress evaluation and feedback, the server analyzes the user's learning data and conducts personalized evaluations. This enables the user to grasp their strengths and areas for improvement and proceed with learning efficiently.

[0287] Based on the above forms, the present invention realizes flexible and effective support for language learning according to the needs of users. It is expected that this system will solve the problems of maintaining motivation for language learning and progress evaluation, and improve learning efficiency.

[0288] Next, the processing flow will be described.

[0289] Step 1:

[0290] The user uses a device to input their learning objectives and current skill level. The device then sends this information to the server.

[0291] Step 2:

[0292] The server analyzes the received user information using natural language processing technology to understand the user's needs. Based on those needs, the server generates a personalized learning plan.

[0293] Step 3:

[0294] The server sends the generated learning plan to the device, and the device displays the plan details to the user. The user then begins learning based on this plan.

[0295] Step 4:

[0296] The user initiates a voice interaction using the device's microphone. The device records the user's voice and sends the audio data to the server.

[0297] Step 5:

[0298] The server uses speech recognition technology to analyze the audio data and evaluate the user's pronunciation and grammar. The server then generates feedback using speech synthesis technology and sends it to the terminal.

[0299] Step 6:

[0300] The device provides real-time feedback to the user in voice or text. The user then uses this feedback to improve their pronunciation and grammar.

[0301] Step 7:

[0302] When a user requests visual learning materials, the device sends the request to the server. The server uses image generation technology to generate relevant illustrations and scenario images.

[0303] Step 8:

[0304] The server sends the generated visual teaching materials to the terminal, and the terminal displays them to the user. The user uses the visual teaching materials to understand vocabulary and grammar more deeply.

[0305] Step 9:

[0306] When the user requests a video simulation, the terminal sends scenario information to the server. The server uses video generation technology to generate a video based on the specified scenario.

[0307] Step 10:

[0308] The server sends the generated video to the terminal, and the terminal plays the video for the user. The user practices practical skills through a simulation video that mimics a realistic situation.

[0309] Step 11:

[0310] The terminal tracks the user's learning activities and periodically sends progress data to the server. The server analyzes the data and evaluates the user's learning progress.

[0311] Step 12:

[0312] The server generates personalized feedback based on the learning evaluation and sends it to the terminal. The terminal presents the feedback to the user, and the user grasps the areas for improvement and applies them to learning.

[0313] (Example 1)

[0314] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0315] A challenge with conventional language learning systems was the insufficient generation of personalized learning plans tailored to the user's learning goals and skill level. Furthermore, the lack of real-time feedback on pronunciation and grammar, coupled with the manual generation of visual learning materials and simulation videos, resulted in an inconsistent and inefficient learning experience for the learner.

[0316] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0317] In this invention, the server includes means for analyzing user information and automatically generating a learning plan using a generative AI model; means for analyzing the user's pronunciation and language use in real time using speech recognition technology and speech synthesis technology and providing feedback; and means for automatically generating visual learning materials and simulation videos using image generation technology and video generation technology. This enables the user to receive a personalized learning experience and improves learning efficiency through real-time voice feedback and automatically generated visual learning materials and videos.

[0318] "User information" refers to data that learners input via a device to define their own learning goals and skill levels.

[0319] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze user information and automatically generate personalized learning plans.

[0320] A "learning plan" is a plan of specific learning activities and content that is automatically generated according to the user's learning goals and skill level.

[0321] "Speech recognition technology" is a technology that analyzes voice data input by a user and identifies and recognizes the linguistic elements within it.

[0322] "Speech synthesis technology" is a technology that generates speech data and provides real-time feedback.

[0323] "Visual teaching materials" are visual educational resources presented to learners using image generation technology.

[0324] "Video generation technology" is a technology that generates video content based on a specified scenario and provides learners with a simulation.

[0325] "Feedback" refers to evaluations and improvement suggestions provided for a user's learning activities, often specifically pointing out aspects such as pronunciation and progress.

[0326] The language learning system of the present invention provides personalized learning through the coordinated operation of the user, terminal, and server. In this system, the user first inputs their learning objectives and skill level using a terminal. This input process is performed via a user interface and can be done using common devices such as tablets and smartphones.

[0327] The terminal transmits user input information to the server via the internet. The server operates on a cloud platform with high computing power and analyzes user information using natural language processing technology. The server uses a generative AI model to generate a personalized learning plan tailored to the user's learning needs. This plan includes daily learning content and progress goals.

[0328] Furthermore, users can practice pronunciation through voice input. The device records the user's speech and sends the data to a server. The server analyzes the user's pronunciation using speech recognition technology and provides immediate feedback using speech synthesis technology. This allows users to receive specific advice on the accuracy of their pronunciation and grammatical errors.

[0329] To aid in visual learning, the server uses image generation technology to create illustrations and scene diagrams, which are then presented to the user via the terminal. This feature supports the visual understanding of new words and concepts. In particular, video generation technology is used for scenario-based video simulations, allowing users to acquire practical skills while watching them on their terminals.

[0330] The server also analyzes the user's learning progress and provides personalized feedback using machine learning algorithms. This feedback includes clear areas for improvement and specific learning advice.

[0331] For example, if a user enters "I want to practice English conversation for business meetings" into the terminal, the server will propose a corresponding learning plan and provide practical learning through voice dialogue and video simulations. An example of a prompt sentence is "Please teach me a conversation about ordering at a restaurant." Through this system, users can learn a language effectively and efficiently.

[0332] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0333] Step 1:

[0334] The user uses a device to input their learning objectives and current skill level. This input data includes the target language, learning level, and specific needs (e.g., travel conversation). The device then formats this information and prepares it for transmission to the server.

[0335] Step 2:

[0336] The terminal transmits user input data to the server via the internet. During this process, the data is encrypted to ensure security. The server registers the received data in a database for analysis.

[0337] Step 3:

[0338] The server uses natural language processing technology to analyze user information. Based on the analysis, a generative AI model creates a personalized learning plan tailored to the user. This plan includes recommended lessons, materials, and practice methods. The generated plan is temporarily stored on the server and prepared for transmission to the user's device.

[0339] Step 4:

[0340] The user uses the voice input function on their device to speak phrases or words they want to practice. The device records the voice data from the microphone and converts it into digital data for transmission to the server.

[0341] Step 5:

[0342] The server uses speech recognition technology to analyze the user's voice data. It converts the voice data into text and detects pronunciation and grammatical errors. Based on this analysis, it uses speech synthesis technology to generate feedback data that includes correct pronunciation and suggested corrections.

[0343] Step 6:

[0344] The device displays feedback data received from the server to the user. The feedback is provided in audio or text format and includes specific areas for improvement and advice. The user then uses this information to practice pronunciation.

[0345] Step 7:

[0346] The server uses image generation technology to generate visual learning materials related to the learning plan. These materials are designed to help with understanding new words and scenarios. The generated image data is sent to the terminal.

[0347] Step 8:

[0348] The server uses video generation technology to create a simulated video based on a specified scenario. This video is designed to simulate a real-life conversation and is provided to the user's device so that they can watch it repeatedly for learning.

[0349] Step 9:

[0350] The server continuously records the user's learning progress and analyzes it using machine learning algorithms. Based on this analysis, it generates data to provide personalized feedback and advice on goal achievement, and sends it to the user's device.

[0351] <|ipynb_marker|> Code

[0352] There is no code provided to execute or demonstrate.

[0353] (Application Example 1)

[0354] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0355] Traditional systems have limitations in terms of personalization and interactivity when it comes to effective language learning tailored to individual user needs. Furthermore, the lack of effective means to provide visual learning materials and simulation videos restricts the user's learning experience. This makes it difficult to maintain learning efficiency and motivation.

[0356] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0357] In this invention, the server includes means for analyzing the user's learning goals and ability level, means for automatically generating a training plan based on the analysis results, and means for providing interactive voice conversation using means for analyzing the user's pronunciation and vocabulary use in real time. This enables the automatic generation of personalized training plans and an improved learning experience through advanced interactive functions.

[0358] A "user" is a person who uses the system to learn a language.

[0359] "Learning objectives" refer to the specific language abilities and skills that the user wants to achieve.

[0360] "Proficiency level" is an indicator that represents the user's current language skill level.

[0361] "Means of analysis" refers to technologies that process user input information to understand its intent and content.

[0362] A "training plan" is a learning process designed based on the user's learning goals and skill level.

[0363] "Automatic generation methods" refer to technologies that automatically create optimal training plans from user information.

[0364] "Pronunciation" refers to the accuracy of the phonetic aspects of words.

[0365] "Vocabulary usage" refers to the selection and use of words and expressions by the user.

[0366] "Real-time analysis" refers to technology that processes and analyzes user voice instantly.

[0367] "Means of providing interactive voice conversations" refers to a system that enables interactive communication with users through voice.

[0368] "Visual learning materials" are teaching materials that use images and visuals to support learning.

[0369] "Image generation technology" is a technology that uses algorithms to create visual content.

[0370] "Scene" is a term that refers to a specific situation or scenario.

[0371] "Means of generating and providing videos" refers to technologies that create and present scene-based video content to users.

[0372] "Learning progress" indicates the degree to which the user's language ability is improving.

[0373] "Feedback" refers to information that provides evaluations of user performance and suggestions for improvement.

[0374] A "robot" is an electronic device that operates based on a program and can interact with a user.

[0375] The system for implementing this invention consists of a server, a terminal, and a user. First, the user operates the terminal to input their learning goals and current ability level. Based on this, the terminal sends data to the server. The server receives this information and analyzes it using natural language processing technology. Based on the results of this analysis, the system automatically generates an optimal training plan for the user.

[0376] Next, the user engages in an interactive voice conversation through the robot. The robot incorporates speech recognition and speech synthesis technologies to analyze the user's pronunciation and vocabulary usage in real time. For example, if areas for improvement in pronunciation are detected, feedback is provided immediately.

[0377] Furthermore, the server utilizes image generation technology to create visual learning materials tailored to the user's learning situation and presents them to the user via the terminal. Simulation videos are also generated in a similar manner, making it easier for users to visualize the actual situation.

[0378] The user's learning progress is periodically evaluated by the server, and detailed feedback is provided. This process is implemented using various hardware and software. For example, Google Cloud Speech-to-Text is used for speech processing, and OpenAI's GPT model is used for natural language processing. Stable Diffusion can be used for image generation, and the Pexels API can be used for video generation.

[0379] As a concrete example, consider a scenario where a user practices conversation in a restaurant. The robot acts as the waiter, taking orders and providing real-time feedback on pronunciation. Furthermore, the learning effect can be enhanced by presenting images and simulation videos related to the order.

[0380] An example of a prompt for a generative AI model is: "A user places an order at a restaurant. As a waiter, check the pronunciation and grammar, point out areas for improvement, and provide correct examples. Generate and present an image based on the situation."

[0381] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0382] Step 1:

[0383] The user inputs their learning goals and current proficiency level via a terminal. The input data is then sent to the server by the terminal. In this step, the input is the user's learning goals and proficiency level, and the output is the data sent to the server. The terminal's operation involves receiving user input and sending data.

[0384] Step 2:

[0385] The server uses natural language processing techniques to analyze the data it receives. The input is user data sent from the terminal, and the output is information about the analyzed learning needs. The server processes this data to automatically generate an optimal learning plan for the user.

[0386] Step 3:

[0387] The server automatically generates a learning plan and sends it to the terminal. The input is the learning plan generated by the server, and the output is the terminal that received it. The server's operation is to format and send the plan data.

[0388] Step 4:

[0389] The user initiates an interactive voice conversation with the robot using a terminal. The input is the user's voice, which is analyzed in real time by the robot. The output is either voice or text, including feedback on pronunciation and grammar. The terminal and robot's actions are voice recognition and feedback provision.

[0390] Step 5:

[0391] The server uses image generation technology to generate visual learning materials related to the user's learning content and sends them to the terminal. The input is scene information based on the learning plan, and the output is the generated image. The server's operation consists of generating and sending image data.

[0392] Step 6:

[0393] The server generates video content based on a specified scenario and provides the simulation to the terminal. The input is scenario information from the learning plan, and the output is the generated simulation video. The server's operation consists of executing the video generation algorithm and sending data.

[0394] Step 7:

[0395] The server analyzes the user's learning progress and provides personalized feedback to the terminal. The input is the user's learning history data, and the output is progress evaluation feedback information. The server's operation consists of data analysis and feedback generation.

[0396] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0397] This invention provides a multimodal language learning system that combines an emotion engine, thereby enabling further personalization of the user's learning experience. The system operates as follows, with the server, terminal, and user each playing a specific role.

[0398] First, the user inputs their learning goals and skill level through their device, and the device sends this information to the server. The server uses natural language processing technology to analyze the user's needs and automatically generates a personalized learning plan. In this process, the user's learning history and emotional state are also taken into consideration to provide a more appropriate plan.

[0399] When using the voice interaction function, the user speaks into the device's microphone, and the voice data is sent to the server. The server analyzes the spoken content based on speech recognition technology and evaluates the user's emotional state using an emotion engine. This evaluation result is reflected in the feedback generated using speech synthesis technology, providing advice tailored to the user's state in real time. For example, if the server detects that the user is feeling dissatisfied or stressed, it can offer encouraging messages or simple tasks.

[0400] Furthermore, the emotion engine is also used when generating visual learning materials and video simulations. The server generates content tailored to the user's interests and emotions using image and video generation technologies and presents it through the device. When the user is relaxed, a more challenging scenario is presented, and when they feel tense or anxious, easier exercises are presented, designed to gradually improve their skills.

[0401] Furthermore, the emotion engine is also used in progress evaluation. The server analyzes the user's learning activities and emotional changes, and generates emotion-based feedback. This feedback allows users to better understand their own learning process and maintain motivation as they continue learning.

[0402] Through the embodiments described above, the present invention aims to realize a personalized language learning experience that takes emotions into consideration, thereby maximizing the user's learning effectiveness. This system is expected to not only improve language skills but also support the user's psychological aspects.

[0403] The following describes the processing flow.

[0404] Step 1:

[0405] The user uses a device to input their learning goals, current skill level, and emotional state. The device then sends this information to the server.

[0406] Step 2:

[0407] The server analyzes the received user data using natural language processing technology. Based on the user's needs, it automatically generates a learning plan, taking their emotional state into consideration.

[0408] Step 3:

[0409] The server sends the generated learning plan to the device. The device displays the plan details to the user and presents learning content tailored to their emotions.

[0410] Step 4:

[0411] The user activates the voice interaction function through the device and begins speaking. The device records the voice data and sends it to the server.

[0412] Step 5:

[0413] The server uses speech recognition technology to convert the audio data into text and analyzes its content. Furthermore, it uses an emotion engine to evaluate the user's emotions and generate feedback.

[0414] Step 6:

[0415] The server generates customized feedback using speech synthesis technology and sends it to the terminal. The terminal provides the user with real-time feedback in either voice or text.

[0416] Step 7:

[0417] When a user requests visual learning materials, the device sends a request to the server. The server uses image generation technology to generate learning materials that respond to the user's emotions.

[0418] Step 8:

[0419] The server sends the generated visual learning materials to the device. The device displays the materials to the user, supporting emotionally sensitive learning.

[0420] Step 9:

[0421] When a user requests a video simulation, the device sends the scenario to the server. The server generates a video using video generation technology and incorporates the user's emotions into it.

[0422] Step 10:

[0423] The server sends the generated video to the device. The device plays the video for the user, assisting in the practice of practical skills. The practice is provided at a pace that suits the user's mood.

[0424] Step 11:

[0425] The device tracks the user's learning activities and emotional changes, and sends the data to the server. The server performs progress and emotional assessments and manages the user's learning status.

[0426] Step 12:

[0427] The server generates personalized feedback based on training data and sentiment evaluations. The terminal presents the feedback to the user and suggests a learning direction that takes sentiment into account.

[0428] (Example 2)

[0429] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0430] Current language learning systems suffer from insufficient personalization that takes into account each user's individual learning progress and emotional state, making it difficult to maximize learning effectiveness. Furthermore, they sometimes fail to provide adequate feedback to maintain user motivation. In addition, it is difficult to integrate and utilize diverse forms of learning materials, preventing the provision of a learning experience tailored to each individual user.

[0431] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0432] In this invention, the server includes means for analyzing the user's learning goals and skill level, means for automatically generating a learning plan based on the analysis results, and means for analyzing the user's emotional state and reflecting it in the learning content. This makes it possible to respond to the user's individual needs and provide a personalized learning experience based on their emotional state. Furthermore, this allows the user to maintain their motivation while learning effectively.

[0433] "User learning objectives" refer to the specific language learning goals that learners wish to achieve.

[0434] "Skill level" is an indicator that shows the degree of language proficiency a user currently possesses.

[0435] "Means of analysis" refers to the process by which a system understands the input information and gains appropriate insights.

[0436] "Automatic generation methods" refer to the function of a system that generates content and plans without human intervention, based on pre-set rules and algorithms.

[0437] "Interactive voice communication" is a feature that allows users to communicate in real time using natural language.

[0438] "Visual learning materials" are educational media provided to learners to acquire information through visual means.

[0439] "Virtual experience" is a method of providing users with realistic experiences through computer-generated content.

[0440] "Learning progress" is an indicator that measures the degree of progress made towards the goals set by the user.

[0441] "Emotional state" refers to a learner's psychological and emotional condition and is a factor that influences their learning activities.

[0442] "Feedback" refers to information provided by a system in response to user input and activities, such as opinions and evaluations, that helps improve the learning process.

[0443] This invention is a multimodal language learning system that integrates an emotion engine and aims to optimize the individual learning experience of each user. The system mainly consists of three elements: a server, a terminal, and the user.

[0444] First, the user uses a device to input information about their learning goals and skill level. The device securely transmits this information to a server via the internet. The device can operate using a browser application or a dedicated application.

[0445] Next, the server analyzes the received data using natural language processing (NLP) techniques. This analysis utilizes Python NLP libraries (such as SpaCy or NLTK). Based on the analysis results, a personalized learning plan tailored to the user's learning needs is automatically generated by an AI model. This AI model is designed to take into account the user's past data and emotional state.

[0446] Furthermore, when using the voice interaction function, the user inputs voice using the device's microphone. This voice is sent from the device to the server. The server uses a speech recognition API (for example, Google Cloud Speech-to-Text) to analyze the utterance and evaluates the user's emotions using an emotion engine. This emotion evaluation is reflected in the feedback generated by speech synthesis technology and presented to the user in real time.

[0447] Furthermore, the server automatically generates visual learning materials and video content using image and video generation technologies. This allows for the creation of learning materials tailored to the user's chosen learning goals and emotional state, enriching the learning experience.

[0448] For example, if a user enters "I want to improve my French conversation skills" into the device, the system will consider the user's skill level and emotional state, and then provide appropriate conversation practice and learning materials to help them understand the emotions of French. Another example of a prompt sentence for the generating AI model is, "Please suggest ways for the user to efficiently learn new vocabulary."

[0449] Based on the above, the system of the present invention aims to make user learning a comprehensive educational experience that includes emotional support, rather than merely the acquisition of knowledge.

[0450] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0451] Step 1:

[0452] The user inputs learning goals and skill levels into the device. The user text-inputs the language to be learned and their goals through the device's interface. This input information is treated as basic data necessary for customizing the learning content. The device processes this input data, formats it, and then sends it to the server.

[0453] Step 2:

[0454] The device sends input data to the server. The device uses a secure communication protocol (e.g., HTTPS) to send formatted data to the server. This ensures user privacy. The data includes learning objectives, skill level, and timestamps.

[0455] Step 3:

[0456] The server receives data from the user and analyzes it using natural language processing (NLP) techniques. Based on the received data, the server uses Python's NLP library to identify the user's needs. The input for the analysis is the user's learning goals and skill level, and the output includes insights necessary for designing a personalized learning plan.

[0457] Step 4:

[0458] The server automatically generates a learning plan using a generated AI model. In this step, the server inputs the analysis results into the generated AI model to precisely determine the content and stages of learning. The input also includes the user's learning history and emotional state, and the output is a learning plan tailored to the user.

[0459] Step 5:

[0460] The device receives the learning plan from the server and presents it to the user. The learning plan is displayed on the screen in a user-friendly format. Upon receiving the plan, the device decrypts its contents and provides it to the user as appropriately formatted information.

[0461] Step 6:

[0462] The user uses the voice interaction function to input speech into the device. The user speaks into the device's microphone, and the audio is converted into a digital format and sent to the server. This data is treated as a voice input prompt and is analyzed in the next step.

[0463] Step 7:

[0464] The server analyzes audio data using speech recognition technology and evaluates it using an emotion engine. The server uses a speech recognition API to convert user speech into text. Then, the emotion engine evaluates the user's emotional state. The input is audio data, and the output is the analyzed text and the emotion evaluation result.

[0465] Step 8:

[0466] The server generates feedback and delivers it to the user via speech synthesis. The server uses speech synthesis technology to generate feedback messages tailored to the user's emotional state. The final output is in audio format, which is provided to the user in real time through the device.

[0467] Step 9:

[0468] The user receives feedback and decides on their next learning action. Based on the feedback provided, the user chooses the next step. This process allows the user to learn efficiently.

[0469] (Application Example 2)

[0470] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0471] Modern language learning demands flexible learning approaches tailored to each learner's ability level and emotional state. However, traditional systems fail to adequately address individual needs, posing challenges in maintaining motivation and efficient learning. Furthermore, standardized feedback makes it difficult to maximize learning effectiveness, and insufficient psychological support for users is also a problem.

[0472] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0473] In this invention, the server includes means for analyzing the user's learning goals and ability level; means for automatically generating a learning plan based on the analysis results; means for analyzing the user's pronunciation and language use in real time; means for automatically generating and presenting visual learning materials to the user using image generation technology; means for generating videos and providing simulations based on specified situations; means for analyzing the user's learning progress and providing individual feedback; and means for analyzing the user's emotional state and providing voice encouragement and learning adjustments according to that situation. This makes it possible to provide a personalized learning experience tailored to each user and improve learning efficiency and motivation.

[0474] A "user" is an individual learner who utilizes a language learning system.

[0475] A "learning objective" is the specific language skill or knowledge level that the user wants to achieve.

[0476] "Proficiency level" is an indicator that shows the degree of language knowledge and skills a user currently possesses.

[0477] "Analysis" is the process of thoroughly examining information and data to reveal its structure and characteristics.

[0478] A "learning plan" refers to a chronologically organized set of steps and strategies aimed at helping a user achieve their goals.

[0479] "Real-time analysis" means processing phenomena and data as they occur and reflecting the results immediately.

[0480] "Interactive voice communication" is a process in which the user and the system exchange information bidirectionally through voice.

[0481] "Visual learning materials" are educational content created to provide information to users through visual means.

[0482] "Image generation technology" refers to the technology of creating new images within a computer using algorithms and software.

[0483] "Generating video based on context" means automatically creating appropriate video content according to specific conditions or context.

[0484] "Simulation" is a method of imitating real-world phenomena and predicting or analyzing their states and changes.

[0485] "Analyzing a user's learning progress" means evaluating how close a learner is to achieving their goals.

[0486] "Providing individualized feedback" means offering optimal advice and suggestions for improvement based on the user's situation and progress.

[0487] "Analyzing emotional states" is the process of understanding a user's psychological state and emotions, and comprehending their characteristics.

[0488] "Voice encouragement" is the act of sending messages through voice to support a user's motivation and mental state.

[0489] "Adjusting the learning plan" is the process of reviewing the learning plan and making adjustments in the optimal direction according to the user's progress and circumstances.

[0490] This invention is based on a system that analyzes emotional states and learning progress in real time to personalize the user's learning experience and provides a learning plan based on that analysis.

[0491] The server uses natural language processing technology and sentiment analysis engines to analyze the learning goals and ability levels provided by the user. Based on the results of these analyses, an algorithm is used to select the most suitable content for generating the learning plan. In this process, the user's past learning history and sentiment data are utilized to establish a personalized plan.

[0492] On the device side, speech recognition technology is used to collect the user's speech and instantly transmit it to the server. The server analyzes the received audio data and evaluates the emotional state. For example, if it is detected that the user is feeling anxious, the server uses speech synthesis technology to generate encouraging feedback and presents it to the user through the device.

[0493] Furthermore, the server combines image and video generation technologies to create visual learning materials and simulation videos tailored to the user's interests and situation. This makes the learning content easier to understand intuitively.

[0494] For example, if a user is struggling with a particular topic during their learning process, the server can create a simple scenario based on that topic and present practice problems in a way that alleviates the user's anxiety.

[0495] An example of a prompt based on a generative AI model is: "After the user expresses their feelings, show how to support their motivation and adjust their learning. Include specific encouraging messages in case the user becomes frustrated."

[0496] Overall, this system aims to enhance learning effectiveness by providing individual users with a learning pace and method tailored to their needs.

[0497] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0498] Step 1:

[0499] The device receives input from the user regarding learning goals and ability levels. This information is sent to a server to build a database of personalized learning plans. The input information serves as foundational data for analyzing the user's specific learning needs.

[0500] Step 2:

[0501] The server uses natural language processing techniques to analyze the user's learning goals and ability level based on the received data. This analysis prepares the data necessary to generate a learning plan tailored to the user. The analyzed data is then passed to the learning planning algorithm, which leads to the design of an individualized plan.

[0502] Step 3:

[0503] When a user speaks into the device, voice data is collected. The device sends this voice data to a server, which uses speech recognition technology to analyze the content of the speech. As a result, the user's emotional state based on the speech is evaluated. In this step, the input voice is processed as digital data, and the corresponding text and emotional state are output.

[0504] Step 4:

[0505] The server generates appropriate feedback using speech synthesis technology based on the user's emotional state. If the emotion is determined to be dissatisfaction or anxiety, an encouraging message is created. The generated voice feedback is delivered to the user through the terminal. In this step, voice data corresponding to the analysis results is output.

[0506] Step 5:

[0507] The server utilizes image and video generation technologies to create visual learning materials and simulation videos tailored to the user's interests and emotions. These materials are designed to enhance the user's learning experience. The generated visual content is displayed to the user via their device. The generated materials serve as supplementary content for the learning plan.

[0508] Step 6:

[0509] The server analyzes the user's learning progress and provides personalized feedback based on the analysis results. This allows users to understand their own learning progress and make necessary improvements and adjustments. The feedback based on the analysis results contributes to maintaining the user's learning motivation.

[0510] This entire process provides users with an optimal learning environment tailored to their needs, enabling efficient language acquisition.

[0511] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0512] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0513] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0514] [Third Embodiment]

[0515] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0516] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0517] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0518] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0519] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0520] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0521] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0522] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0523] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0524] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0525] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0526] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0527] The multimodal language learning system of the present invention provides users with an individualized learning experience through the cooperation of the server, terminal, and user elements. This system operates in the following manner, with each element working in coordination.

[0528] First, the user uses their device to input their learning objectives and current skill level. The device sends this information to a server, which uses natural language processing technology to analyze the user's needs and automatically generate a personalized learning plan. This plan is tailored to the user's requirements and can be specialized in specific areas, such as business English or travel English.

[0529] Next, users can improve their language skills using the voice interaction function. The device records the user's voice and sends it to the server. The server analyzes the user's speech using speech recognition technology and provides real-time feedback on pronunciation and grammar using speech synthesis technology. For example, if it is necessary to distinguish between the pronunciation of "r" and "l," the server will point out the difference and provide an example of the correct pronunciation.

[0530] Furthermore, in the generation of visual learning materials, illustrations and scenario images are automatically generated by the server using image generation technology. The terminal then presents these to the user. This makes it easier for the user to visually understand the meaning of new words. For example, in a lesson themed on "airport," an image of boarding procedures is generated and provided.

[0531] The video simulation is conducted based on a specific scenario, and the server uses video generation technology to generate relevant videos. Users can observe these videos through their devices and hone their practical skills. For example, when practicing conversation in a restaurant, videos are provided that include ordering methods and customer service interactions.

[0532] Finally, the progress evaluation and feedback function allows the server to analyze the user's learning data and provide personalized evaluations. This enables users to understand their strengths and areas for improvement, allowing them to learn more efficiently.

[0533] Based on the above configuration, the present invention provides flexible and effective support for language learning that meets the user's needs. This system is expected to solve the challenges of maintaining motivation and evaluating progress in language learning, thereby improving learning efficiency.

[0534] The following describes the processing flow.

[0535] Step 1:

[0536] The user uses a device to input their learning objectives and current skill level. The device then sends this information to the server.

[0537] Step 2:

[0538] The server analyzes the received user information using natural language processing technology to understand the user's needs. Based on those needs, the server generates a personalized learning plan.

[0539] Step 3:

[0540] The server sends the generated learning plan to the device, and the device displays the plan details to the user. The user then begins learning based on this plan.

[0541] Step 4:

[0542] The user initiates a voice interaction using the device's microphone. The device records the user's voice and sends the audio data to the server.

[0543] Step 5:

[0544] The server uses speech recognition technology to analyze the audio data and evaluate the user's pronunciation and grammar. The server then generates feedback using speech synthesis technology and sends it to the terminal.

[0545] Step 6:

[0546] The device provides real-time feedback to the user in voice or text. The user then uses this feedback to improve their pronunciation and grammar.

[0547] Step 7:

[0548] When a user requests visual learning materials, the device sends the request to the server. The server uses image generation technology to generate relevant illustrations and scenario images.

[0549] Step 8:

[0550] The server sends the generated visual learning materials to the terminal, which then displays them to the user. The user uses the visual learning materials to gain a deeper understanding of vocabulary and grammar.

[0551] Step 9:

[0552] When a user requests a video simulation, the device sends scenario information to the server. The server uses video generation technology to generate a video based on the specified scenario.

[0553] Step 10:

[0554] The server sends the generated video to the terminal, and the terminal plays the video for the user. The user practices practical skills through simulation videos that mimic realistic situations.

[0555] Step 11:

[0556] The device tracks the user's learning activities and periodically sends progress data to the server. The server analyzes the data and evaluates the user's learning progress.

[0557] Step 12:

[0558] The server generates personalized feedback based on learning assessments and sends it to the device. The device presents the feedback to the user, who then identifies areas for improvement and uses them to further their learning.

[0559] (Example 1)

[0560] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0561] A challenge with conventional language learning systems was the insufficient generation of personalized learning plans tailored to the user's learning goals and skill level. Furthermore, the lack of real-time feedback on pronunciation and grammar, coupled with the manual generation of visual learning materials and simulation videos, resulted in an inconsistent and inefficient learning experience for the learner.

[0562] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0563] In this invention, the server includes means for analyzing user information and automatically generating a learning plan using a generative AI model; means for analyzing the user's pronunciation and language use in real time using speech recognition technology and speech synthesis technology and providing feedback; and means for automatically generating visual learning materials and simulation videos using image generation technology and video generation technology. This enables the user to receive a personalized learning experience and improves learning efficiency through real-time voice feedback and automatically generated visual learning materials and videos.

[0564] "User information" refers to data that learners input via a device to define their own learning goals and skill levels.

[0565] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze user information and automatically generate personalized learning plans.

[0566] A "learning plan" is a plan of specific learning activities and content that is automatically generated according to the user's learning goals and skill level.

[0567] "Speech recognition technology" is a technology that analyzes voice data input by a user and identifies and recognizes the linguistic elements within it.

[0568] "Speech synthesis technology" is a technology that generates speech data and provides real-time feedback.

[0569] "Visual teaching materials" are visual educational resources presented to learners using image generation technology.

[0570] "Video generation technology" is a technology that generates video content based on a specified scenario and provides learners with a simulation.

[0571] "Feedback" refers to evaluations and improvement suggestions provided for a user's learning activities, often specifically pointing out aspects such as pronunciation and progress.

[0572] The language learning system of the present invention provides personalized learning through the coordinated operation of the user, terminal, and server. In this system, the user first inputs their learning objectives and skill level using a terminal. This input process is performed via a user interface and can be done using common devices such as tablets and smartphones.

[0573] The terminal transmits user input information to the server via the internet. The server operates on a cloud platform with high computing power and analyzes user information using natural language processing technology. The server uses a generative AI model to generate a personalized learning plan tailored to the user's learning needs. This plan includes daily learning content and progress goals.

[0574] Furthermore, users can practice pronunciation through voice input. The device records the user's speech and sends the data to a server. The server analyzes the user's pronunciation using speech recognition technology and provides immediate feedback using speech synthesis technology. This allows users to receive specific advice on the accuracy of their pronunciation and grammatical errors.

[0575] To aid in visual learning, the server uses image generation technology to create illustrations and scene diagrams, which are then presented to the user via the terminal. This feature supports the visual understanding of new words and concepts. In particular, video generation technology is used for scenario-based video simulations, allowing users to acquire practical skills while watching them on their terminals.

[0576] The server also analyzes the user's learning progress and provides personalized feedback using machine learning algorithms. This feedback includes clear areas for improvement and specific learning advice.

[0577] For example, if a user enters "I want to practice English conversation for business meetings" into the terminal, the server will propose a corresponding learning plan and provide practical learning through voice dialogue and video simulations. An example of a prompt sentence is "Please teach me a conversation about ordering at a restaurant." Through this system, users can learn a language effectively and efficiently.

[0578] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0579] Step 1:

[0580] The user uses a device to input their learning objectives and current skill level. This input data includes the target language, learning level, and specific needs (e.g., travel conversation). The device then formats this information and prepares it for transmission to the server.

[0581] Step 2:

[0582] The terminal transmits user input data to the server via the internet. During this process, the data is encrypted to ensure security. The server registers the received data in a database for analysis.

[0583] Step 3:

[0584] The server uses natural language processing technology to analyze user information. Based on the analysis, a generative AI model creates a personalized learning plan tailored to the user. This plan includes recommended lessons, materials, and practice methods. The generated plan is temporarily stored on the server and prepared for transmission to the user's device.

[0585] Step 4:

[0586] The user uses the voice input function on their device to speak phrases or words they want to practice. The device records the voice data from the microphone and converts it into digital data for transmission to the server.

[0587] Step 5:

[0588] The server uses speech recognition technology to analyze the user's voice data. It converts the voice data into text and detects pronunciation and grammatical errors. Based on this analysis, it uses speech synthesis technology to generate feedback data that includes correct pronunciation and suggested corrections.

[0589] Step 6:

[0590] The device displays feedback data received from the server to the user. The feedback is provided in audio or text format and includes specific areas for improvement and advice. The user then uses this information to practice pronunciation.

[0591] Step 7:

[0592] The server uses image generation technology to generate visual learning materials related to the learning plan. These materials are designed to help with understanding new words and scenarios. The generated image data is sent to the terminal.

[0593] Step 8:

[0594] The server uses video generation technology to create a simulated video based on a specified scenario. This video is designed to simulate a real-life conversation and is provided to the user's device so that they can watch it repeatedly for learning.

[0595] Step 9:

[0596] The server continuously records the user's learning progress and analyzes it using machine learning algorithms. Based on this analysis, it generates data to provide personalized feedback and advice on goal achievement, and sends it to the user's device.

[0597] <|ipynb_marker|> Code

[0598] There is no code provided to execute or demonstrate.

[0599] (Application Example 1)

[0600] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0601] Traditional systems have limitations in terms of personalization and interactivity when it comes to effective language learning tailored to individual user needs. Furthermore, the lack of effective means to provide visual learning materials and simulation videos restricts the user's learning experience. This makes it difficult to maintain learning efficiency and motivation.

[0602] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0603] In this invention, the server includes means for analyzing the user's learning goals and ability level, means for automatically generating a training plan based on the analysis results, and means for providing interactive voice conversation using means for analyzing the user's pronunciation and vocabulary use in real time. This enables the automatic generation of personalized training plans and an improved learning experience through advanced interactive functions.

[0604] A "user" is a person who uses the system to learn a language.

[0605] "Learning objectives" refer to the specific language abilities and skills that the user wants to achieve.

[0606] "Proficiency level" is an indicator that represents the user's current language skill level.

[0607] "Means of analysis" refers to technologies that process user input information to understand its intent and content.

[0608] A "training plan" is a learning process designed based on the user's learning goals and skill level.

[0609] "Automatic generation methods" refer to technologies that automatically create optimal training plans from user information.

[0610] "Pronunciation" refers to the accuracy of the phonetic aspects of words.

[0611] "Vocabulary usage" refers to the selection and use of words and expressions by the user.

[0612] "Real-time analysis" refers to technology that processes and analyzes user voice instantly.

[0613] "Means of providing interactive voice conversations" refers to a system that enables interactive communication with users through voice.

[0614] "Visual learning materials" are teaching materials that use images and visuals to support learning.

[0615] "Image generation technology" is a technology that uses algorithms to create visual content.

[0616] "Scene" is a term that refers to a specific situation or scenario.

[0617] "Means of generating and providing videos" refers to technologies that create and present scene-based video content to users.

[0618] "Learning progress" indicates the degree to which the user's language ability is improving.

[0619] "Feedback" refers to information that provides evaluations of user performance and suggestions for improvement.

[0620] A "robot" is an electronic device that operates based on a program and can interact with a user.

[0621] The system for implementing this invention consists of a server, a terminal, and a user. First, the user operates the terminal to input their learning goals and current ability level. Based on this, the terminal sends data to the server. The server receives this information and analyzes it using natural language processing technology. Based on the results of this analysis, the system automatically generates an optimal training plan for the user.

[0622] Next, the user engages in an interactive voice conversation through the robot. The robot incorporates speech recognition and speech synthesis technologies to analyze the user's pronunciation and vocabulary usage in real time. For example, if areas for improvement in pronunciation are detected, feedback is provided immediately.

[0623] Furthermore, the server utilizes image generation technology to create visual learning materials tailored to the user's learning situation and presents them to the user via the terminal. Simulation videos are also generated in a similar manner, making it easier for users to visualize the actual situation.

[0624] The user's learning progress is periodically evaluated by the server, and detailed feedback is provided. This process is implemented using various hardware and software. For example, Google Cloud Speech-to-Text is used for speech processing, and OpenAI's GPT model is used for natural language processing. Stable Diffusion can be used for image generation, and the Pexels API can be used for video generation.

[0625] As a concrete example, consider a scenario where a user practices conversation in a restaurant. The robot acts as the waiter, taking orders and providing real-time feedback on pronunciation. Furthermore, the learning effect can be enhanced by presenting images and simulation videos related to the order.

[0626] An example of a prompt for a generative AI model is: "A user places an order at a restaurant. As a waiter, check the pronunciation and grammar, point out areas for improvement, and provide correct examples. Generate and present an image based on the situation."

[0627] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0628] Step 1:

[0629] The user inputs their learning goals and current proficiency level via a terminal. The input data is then sent to the server by the terminal. In this step, the input is the user's learning goals and proficiency level, and the output is the data sent to the server. The terminal's operation involves receiving user input and sending data.

[0630] Step 2:

[0631] The server uses natural language processing techniques to analyze the data it receives. The input is user data sent from the terminal, and the output is information about the analyzed learning needs. The server processes this data to automatically generate an optimal learning plan for the user.

[0632] Step 3:

[0633] The server automatically generates a learning plan and sends it to the terminal. The input is the learning plan generated by the server, and the output is the terminal that received it. The server's operation is to format and send the plan data.

[0634] Step 4:

[0635] The user initiates an interactive voice conversation with the robot using a terminal. The input is the user's voice, which is analyzed in real time by the robot. The output is either voice or text, including feedback on pronunciation and grammar. The terminal and robot's actions are voice recognition and feedback provision.

[0636] Step 5:

[0637] The server uses image generation technology to generate visual learning materials related to the user's learning content and sends them to the terminal. The input is scene information based on the learning plan, and the output is the generated image. The server's operation consists of generating and sending image data.

[0638] Step 6:

[0639] The server generates video content based on a specified scenario and provides the simulation to the terminal. The input is scenario information from the learning plan, and the output is the generated simulation video. The server's operation consists of executing the video generation algorithm and sending data.

[0640] Step 7:

[0641] The server analyzes the user's learning progress and provides personalized feedback to the terminal. The input is the user's learning history data, and the output is progress evaluation feedback information. The server's operation consists of data analysis and feedback generation.

[0642] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0643] This invention provides a multimodal language learning system that combines an emotion engine, thereby enabling further personalization of the user's learning experience. The system operates as follows, with the server, terminal, and user each playing a specific role.

[0644] First, the user inputs their learning goals and skill level through their device, and the device sends this information to the server. The server uses natural language processing technology to analyze the user's needs and automatically generates a personalized learning plan. In this process, the user's learning history and emotional state are also taken into consideration to provide a more appropriate plan.

[0645] When using the voice interaction function, the user speaks into the device's microphone, and the voice data is sent to the server. The server analyzes the spoken content based on speech recognition technology and evaluates the user's emotional state using an emotion engine. This evaluation result is reflected in the feedback generated using speech synthesis technology, providing advice tailored to the user's state in real time. For example, if the server detects that the user is feeling dissatisfied or stressed, it can offer encouraging messages or simple tasks.

[0646] Furthermore, the emotion engine is also used when generating visual learning materials and video simulations. The server generates content tailored to the user's interests and emotions using image and video generation technologies and presents it through the device. When the user is relaxed, a more challenging scenario is presented, and when they feel tense or anxious, easier exercises are presented, designed to gradually improve their skills.

[0647] Furthermore, the emotion engine is also used in progress evaluation. The server analyzes the user's learning activities and emotional changes, and generates emotion-based feedback. This feedback allows users to better understand their own learning process and maintain motivation as they continue learning.

[0648] Through the embodiments described above, the present invention aims to realize a personalized language learning experience that takes emotions into consideration, thereby maximizing the user's learning effectiveness. This system is expected to not only improve language skills but also support the user's psychological aspects.

[0649] The following describes the processing flow.

[0650] Step 1:

[0651] The user uses a device to input their learning goals, current skill level, and emotional state. The device then sends this information to the server.

[0652] Step 2:

[0653] The server analyzes the received user data using natural language processing technology. Based on the user's needs, it automatically generates a learning plan, taking their emotional state into consideration.

[0654] Step 3:

[0655] The server sends the generated learning plan to the device. The device displays the plan details to the user and presents learning content tailored to their emotions.

[0656] Step 4:

[0657] The user activates the voice interaction function through the device and begins speaking. The device records the voice data and sends it to the server.

[0658] Step 5:

[0659] The server uses speech recognition technology to convert the audio data into text and analyzes its content. Furthermore, it uses an emotion engine to evaluate the user's emotions and generate feedback.

[0660] Step 6:

[0661] The server generates customized feedback using speech synthesis technology and sends it to the terminal. The terminal provides the user with real-time feedback in either voice or text.

[0662] Step 7:

[0663] When a user requests visual learning materials, the device sends a request to the server. The server uses image generation technology to generate learning materials that respond to the user's emotions.

[0664] Step 8:

[0665] The server sends the generated visual learning materials to the device. The device displays the materials to the user, supporting emotionally sensitive learning.

[0666] Step 9:

[0667] When a user requests a video simulation, the device sends the scenario to the server. The server generates a video using video generation technology and incorporates the user's emotions into it.

[0668] Step 10:

[0669] The server sends the generated video to the device. The device plays the video for the user, assisting in the practice of practical skills. The practice is provided at a pace that suits the user's mood.

[0670] Step 11:

[0671] The device tracks the user's learning activities and emotional changes, and sends the data to the server. The server performs progress and emotional assessments and manages the user's learning status.

[0672] Step 12:

[0673] The server generates personalized feedback based on training data and sentiment evaluations. The terminal presents the feedback to the user and suggests a learning direction that takes sentiment into account.

[0674] (Example 2)

[0675] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0676] Current language learning systems suffer from insufficient personalization that takes into account each user's individual learning progress and emotional state, making it difficult to maximize learning effectiveness. Furthermore, they sometimes fail to provide adequate feedback to maintain user motivation. In addition, it is difficult to integrate and utilize diverse forms of learning materials, preventing the provision of a learning experience tailored to each individual user.

[0677] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0678] In this invention, the server includes means for analyzing the user's learning goals and skill level, means for automatically generating a learning plan based on the analysis results, and means for analyzing the user's emotional state and reflecting it in the learning content. This makes it possible to respond to the user's individual needs and provide a personalized learning experience based on their emotional state. Furthermore, this allows the user to maintain their motivation while learning effectively.

[0679] "User learning objectives" refer to the specific language learning goals that learners wish to achieve.

[0680] "Skill level" is an indicator that shows the degree of language proficiency a user currently possesses.

[0681] "Means of analysis" refers to the process by which a system understands the input information and gains appropriate insights.

[0682] "Automatic generation methods" refer to the function of a system that generates content and plans without human intervention, based on pre-set rules and algorithms.

[0683] "Interactive voice communication" is a feature that allows users to communicate in real time using natural language.

[0684] "Visual learning materials" are educational media provided to learners to acquire information through visual means.

[0685] "Virtual experience" is a method of providing users with realistic experiences through computer-generated content.

[0686] "Learning progress" is an indicator that measures the degree of progress made towards the goals set by the user.

[0687] "Emotional state" refers to a learner's psychological and emotional condition and is a factor that influences their learning activities.

[0688] "Feedback" refers to information provided by a system in response to user input and activities, such as opinions and evaluations, that helps improve the learning process.

[0689] This invention is a multimodal language learning system that integrates an emotion engine and aims to optimize the individual learning experience of each user. The system mainly consists of three elements: a server, a terminal, and the user.

[0690] First, the user uses a device to input information about their learning goals and skill level. The device securely transmits this information to a server via the internet. The device can operate using a browser application or a dedicated application.

[0691] Next, the server analyzes the received data using natural language processing (NLP) techniques. This analysis utilizes Python NLP libraries (such as SpaCy or NLTK). Based on the analysis results, a personalized learning plan tailored to the user's learning needs is automatically generated by an AI model. This AI model is designed to take into account the user's past data and emotional state.

[0692] Furthermore, when using the voice interaction function, the user inputs voice using the device's microphone. This voice is sent from the device to the server. The server uses a speech recognition API (for example, Google Cloud Speech-to-Text) to analyze the utterance and evaluates the user's emotions using an emotion engine. This emotion evaluation is reflected in the feedback generated by speech synthesis technology and presented to the user in real time.

[0693] Furthermore, the server automatically generates visual learning materials and video content using image and video generation technologies. This allows for the creation of learning materials tailored to the user's chosen learning goals and emotional state, enriching the learning experience.

[0694] For example, if a user enters "I want to improve my French conversation skills" into the device, the system will consider the user's skill level and emotional state, and then provide appropriate conversation practice and learning materials to help them understand the emotions of French. Another example of a prompt sentence for the generating AI model is, "Please suggest ways for the user to efficiently learn new vocabulary."

[0695] Based on the above, the system of the present invention aims to make user learning a comprehensive educational experience that includes emotional support, rather than merely the acquisition of knowledge.

[0696] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0697] Step 1:

[0698] The user inputs learning goals and skill levels into the device. The user text-inputs the language to be learned and their goals through the device's interface. This input information is treated as basic data necessary for customizing the learning content. The device processes this input data, formats it, and then sends it to the server.

[0699] Step 2:

[0700] The device sends input data to the server. The device uses a secure communication protocol (e.g., HTTPS) to send formatted data to the server. This ensures user privacy. The data includes learning objectives, skill level, and timestamps.

[0701] Step 3:

[0702] The server receives data from the user and analyzes it using natural language processing (NLP) techniques. Based on the received data, the server uses Python's NLP library to identify the user's needs. The input for the analysis is the user's learning goals and skill level, and the output includes insights necessary for designing a personalized learning plan.

[0703] Step 4:

[0704] The server automatically generates a learning plan using a generated AI model. In this step, the server inputs the analysis results into the generated AI model to precisely determine the content and stages of learning. The input also includes the user's learning history and emotional state, and the output is a learning plan tailored to the user.

[0705] Step 5:

[0706] The device receives the learning plan from the server and presents it to the user. The learning plan is displayed on the screen in a user-friendly format. Upon receiving the plan, the device decrypts its contents and provides it to the user as appropriately formatted information.

[0707] Step 6:

[0708] The user uses the voice interaction function to input speech into the device. The user speaks into the device's microphone, and the audio is converted into a digital format and sent to the server. This data is treated as a voice input prompt and is analyzed in the next step.

[0709] Step 7:

[0710] The server analyzes audio data using speech recognition technology and evaluates it using an emotion engine. The server uses a speech recognition API to convert user speech into text. Then, the emotion engine evaluates the user's emotional state. The input is audio data, and the output is the analyzed text and the emotion evaluation result.

[0711] Step 8:

[0712] The server generates feedback and delivers it to the user via speech synthesis. The server uses speech synthesis technology to generate feedback messages tailored to the user's emotional state. The final output is in audio format, which is provided to the user in real time through the device.

[0713] Step 9:

[0714] The user receives feedback and decides on their next learning action. Based on the feedback provided, the user chooses the next step. This process allows the user to learn efficiently.

[0715] (Application Example 2)

[0716] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0717] Modern language learning demands flexible learning approaches tailored to each learner's ability level and emotional state. However, traditional systems fail to adequately address individual needs, posing challenges in maintaining motivation and efficient learning. Furthermore, standardized feedback makes it difficult to maximize learning effectiveness, and insufficient psychological support for users is also a problem.

[0718] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0719] In this invention, the server includes means for analyzing the user's learning goals and ability level; means for automatically generating a learning plan based on the analysis results; means for analyzing the user's pronunciation and language use in real time; means for automatically generating and presenting visual learning materials to the user using image generation technology; means for generating videos and providing simulations based on specified situations; means for analyzing the user's learning progress and providing individual feedback; and means for analyzing the user's emotional state and providing voice encouragement and learning adjustments according to that situation. This makes it possible to provide a personalized learning experience tailored to each user and improve learning efficiency and motivation.

[0720] A "user" is an individual learner who utilizes a language learning system.

[0721] A "learning objective" is the specific language skill or knowledge level that the user wants to achieve.

[0722] "Proficiency level" is an indicator that shows the degree of language knowledge and skills a user currently possesses.

[0723] "Analysis" is the process of thoroughly examining information and data to reveal its structure and characteristics.

[0724] A "learning plan" refers to a chronologically organized set of steps and strategies aimed at helping a user achieve their goals.

[0725] "Real-time analysis" means processing phenomena and data as they occur and reflecting the results immediately.

[0726] "Interactive voice communication" is a process in which the user and the system exchange information bidirectionally through voice.

[0727] "Visual learning materials" are educational content created to provide information to users through visual means.

[0728] "Image generation technology" refers to the technology of creating new images within a computer using algorithms and software.

[0729] "Generating video based on context" means automatically creating appropriate video content according to specific conditions or context.

[0730] "Simulation" is a method of imitating real-world phenomena and predicting or analyzing their states and changes.

[0731] "Analyzing a user's learning progress" means evaluating how close a learner is to achieving their goals.

[0732] "Providing individualized feedback" means offering optimal advice and suggestions for improvement based on the user's situation and progress.

[0733] "Analyzing emotional states" is the process of understanding a user's psychological state and emotions, and comprehending their characteristics.

[0734] "Voice encouragement" is the act of sending messages through voice to support a user's motivation and mental state.

[0735] "Adjusting the learning plan" is the process of reviewing the learning plan and making adjustments in the optimal direction according to the user's progress and circumstances.

[0736] This invention is based on a system that analyzes emotional states and learning progress in real time to personalize the user's learning experience and provides a learning plan based on that analysis.

[0737] The server uses natural language processing technology and sentiment analysis engines to analyze the learning goals and ability levels provided by the user. Based on the results of these analyses, an algorithm is used to select the most suitable content for generating the learning plan. In this process, the user's past learning history and sentiment data are utilized to establish a personalized plan.

[0738] On the device side, speech recognition technology is used to collect the user's speech and instantly transmit it to the server. The server analyzes the received audio data and evaluates the emotional state. For example, if it is detected that the user is feeling anxious, the server uses speech synthesis technology to generate encouraging feedback and presents it to the user through the device.

[0739] Furthermore, the server combines image and video generation technologies to create visual learning materials and simulation videos tailored to the user's interests and situation. This makes the learning content easier to understand intuitively.

[0740] For example, if a user is struggling with a particular topic during their learning process, the server can create a simple scenario based on that topic and present practice problems in a way that alleviates the user's anxiety.

[0741] An example of a prompt based on a generative AI model is: "After the user expresses their feelings, show how to support their motivation and adjust their learning. Include specific encouraging messages in case the user becomes frustrated."

[0742] Overall, this system aims to enhance learning effectiveness by providing individual users with a learning pace and method tailored to their needs.

[0743] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0744] Step 1:

[0745] The device receives input from the user regarding learning goals and ability levels. This information is sent to a server to build a database of personalized learning plans. The input information serves as foundational data for analyzing the user's specific learning needs.

[0746] Step 2:

[0747] The server uses natural language processing techniques to analyze the user's learning goals and ability level based on the received data. This analysis prepares the data necessary to generate a learning plan tailored to the user. The analyzed data is then passed to the learning planning algorithm, which leads to the design of an individualized plan.

[0748] Step 3:

[0749] When a user speaks into the device, voice data is collected. The device sends this voice data to a server, which uses speech recognition technology to analyze the content of the speech. As a result, the user's emotional state based on the speech is evaluated. In this step, the input voice is processed as digital data, and the corresponding text and emotional state are output.

[0750] Step 4:

[0751] The server generates appropriate feedback using speech synthesis technology based on the user's emotional state. If the emotion is determined to be dissatisfaction or anxiety, an encouraging message is created. The generated voice feedback is delivered to the user through the terminal. In this step, voice data corresponding to the analysis results is output.

[0752] Step 5:

[0753] The server utilizes image and video generation technologies to create visual learning materials and simulation videos tailored to the user's interests and emotions. These materials are designed to enhance the user's learning experience. The generated visual content is displayed to the user via their device. The generated materials serve as supplementary content for the learning plan.

[0754] Step 6:

[0755] The server analyzes the user's learning progress and provides personalized feedback based on the analysis results. This allows users to understand their own learning progress and make necessary improvements and adjustments. The feedback based on the analysis results contributes to maintaining the user's learning motivation.

[0756] This entire process provides users with an optimal learning environment tailored to their needs, enabling efficient language acquisition.

[0757] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0758] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0759] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0760] [Fourth Embodiment]

[0761] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0762] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0763] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0764] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0765] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0766] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0767] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0768] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0769] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0770] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0771] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0772] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0773] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0774] The multimodal language learning system of the present invention provides users with an individualized learning experience through the cooperation of the server, terminal, and user elements. This system operates in the following manner, with each element working in coordination.

[0775] First, the user uses their device to input their learning objectives and current skill level. The device sends this information to a server, which uses natural language processing technology to analyze the user's needs and automatically generate a personalized learning plan. This plan is tailored to the user's requirements and can be specialized in specific areas, such as business English or travel English.

[0776] Next, users can improve their language skills using the voice interaction function. The device records the user's voice and sends it to the server. The server analyzes the user's speech using speech recognition technology and provides real-time feedback on pronunciation and grammar using speech synthesis technology. For example, if it is necessary to distinguish between the pronunciation of "r" and "l," the server will point out the difference and provide an example of the correct pronunciation.

[0777] Furthermore, in the generation of visual learning materials, illustrations and scenario images are automatically generated by the server using image generation technology. The terminal then presents these to the user. This makes it easier for the user to visually understand the meaning of new words. For example, in a lesson themed on "airport," an image of boarding procedures is generated and provided.

[0778] The video simulation is conducted based on a specific scenario, and the server uses video generation technology to generate relevant videos. Users can observe these videos through their devices and hone their practical skills. For example, when practicing conversation in a restaurant, videos are provided that include ordering methods and customer service interactions.

[0779] Finally, the progress evaluation and feedback function allows the server to analyze the user's learning data and provide personalized evaluations. This enables users to understand their strengths and areas for improvement, allowing them to learn more efficiently.

[0780] Based on the above configuration, the present invention provides flexible and effective support for language learning that meets the user's needs. This system is expected to solve the challenges of maintaining motivation and evaluating progress in language learning, thereby improving learning efficiency.

[0781] The following describes the processing flow.

[0782] Step 1:

[0783] The user uses a device to input their learning objectives and current skill level. The device then sends this information to the server.

[0784] Step 2:

[0785] The server analyzes the received user information using natural language processing technology to understand the user's needs. Based on those needs, the server generates a personalized learning plan.

[0786] Step 3:

[0787] The server sends the generated learning plan to the device, and the device displays the plan details to the user. The user then begins learning based on this plan.

[0788] Step 4:

[0789] The user initiates a voice interaction using the device's microphone. The device records the user's voice and sends the audio data to the server.

[0790] Step 5:

[0791] The server uses speech recognition technology to analyze the audio data and evaluate the user's pronunciation and grammar. The server then generates feedback using speech synthesis technology and sends it to the terminal.

[0792] Step 6:

[0793] The device provides real-time feedback to the user in voice or text. The user then uses this feedback to improve their pronunciation and grammar.

[0794] Step 7:

[0795] When a user requests visual learning materials, the device sends the request to the server. The server uses image generation technology to generate relevant illustrations and scenario images.

[0796] Step 8:

[0797] The server sends the generated visual learning materials to the terminal, which then displays them to the user. The user uses the visual learning materials to gain a deeper understanding of vocabulary and grammar.

[0798] Step 9:

[0799] When a user requests a video simulation, the device sends scenario information to the server. The server uses video generation technology to generate a video based on the specified scenario.

[0800] Step 10:

[0801] The server sends the generated video to the terminal, and the terminal plays the video for the user. The user practices practical skills through simulation videos that mimic realistic situations.

[0802] Step 11:

[0803] The device tracks the user's learning activities and periodically sends progress data to the server. The server analyzes the data and evaluates the user's learning progress.

[0804] Step 12:

[0805] The server generates personalized feedback based on learning assessments and sends it to the device. The device presents the feedback to the user, who then identifies areas for improvement and uses them to further their learning.

[0806] (Example 1)

[0807] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0808] A challenge with conventional language learning systems was the insufficient generation of personalized learning plans tailored to the user's learning goals and skill level. Furthermore, the lack of real-time feedback on pronunciation and grammar, coupled with the manual generation of visual learning materials and simulation videos, resulted in an inconsistent and inefficient learning experience for the learner.

[0809] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0810] In this invention, the server includes means for analyzing user information and automatically generating a learning plan using a generative AI model; means for analyzing the user's pronunciation and language use in real time using speech recognition technology and speech synthesis technology and providing feedback; and means for automatically generating visual learning materials and simulation videos using image generation technology and video generation technology. This enables the user to receive a personalized learning experience and improves learning efficiency through real-time voice feedback and automatically generated visual learning materials and videos.

[0811] "User information" refers to data that learners input via a device to define their own learning goals and skill levels.

[0812] A "generative AI model" is an artificial intelligence model that uses natural language processing technology to analyze user information and automatically generate personalized learning plans.

[0813] A "learning plan" is a plan of specific learning activities and content that is automatically generated according to the user's learning goals and skill level.

[0814] "Speech recognition technology" is a technology that analyzes voice data input by a user and identifies and recognizes the linguistic elements within it.

[0815] "Speech synthesis technology" is a technology that generates speech data and provides real-time feedback.

[0816] "Visual teaching materials" are visual educational resources presented to learners using image generation technology.

[0817] "Video generation technology" is a technology that generates video content based on a specified scenario and provides learners with a simulation.

[0818] "Feedback" refers to evaluations and improvement suggestions provided for a user's learning activities, often specifically pointing out aspects such as pronunciation and progress.

[0819] The language learning system of the present invention provides personalized learning through the coordinated operation of the user, terminal, and server. In this system, the user first inputs their learning objectives and skill level using a terminal. This input process is performed via a user interface and can be done using common devices such as tablets and smartphones.

[0820] The terminal transmits user input information to the server via the internet. The server operates on a cloud platform with high computing power and analyzes user information using natural language processing technology. The server uses a generative AI model to generate a personalized learning plan tailored to the user's learning needs. This plan includes daily learning content and progress goals.

[0821] Furthermore, users can practice pronunciation through voice input. The device records the user's speech and sends the data to a server. The server analyzes the user's pronunciation using speech recognition technology and provides immediate feedback using speech synthesis technology. This allows users to receive specific advice on the accuracy of their pronunciation and grammatical errors.

[0822] To aid in visual learning, the server uses image generation technology to create illustrations and scene diagrams, which are then presented to the user via the terminal. This feature supports the visual understanding of new words and concepts. In particular, video generation technology is used for scenario-based video simulations, allowing users to acquire practical skills while watching them on their terminals.

[0823] The server also analyzes the user's learning progress and provides personalized feedback using machine learning algorithms. This feedback includes clear areas for improvement and specific learning advice.

[0824] For example, if a user enters "I want to practice English conversation for business meetings" into the terminal, the server will propose a corresponding learning plan and provide practical learning through voice dialogue and video simulations. An example of a prompt sentence is "Please teach me a conversation about ordering at a restaurant." Through this system, users can learn a language effectively and efficiently.

[0825] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0826] Step 1:

[0827] The user uses a device to input their learning objectives and current skill level. This input data includes the target language, learning level, and specific needs (e.g., travel conversation). The device then formats this information and prepares it for transmission to the server.

[0828] Step 2:

[0829] The terminal transmits user input data to the server via the internet. During this process, the data is encrypted to ensure security. The server registers the received data in a database for analysis.

[0830] Step 3:

[0831] The server uses natural language processing technology to analyze user information. Based on the analysis, a generative AI model creates a personalized learning plan tailored to the user. This plan includes recommended lessons, materials, and practice methods. The generated plan is temporarily stored on the server and prepared for transmission to the user's device.

[0832] Step 4:

[0833] The user uses the voice input function on their device to speak phrases or words they want to practice. The device records the voice data from the microphone and converts it into digital data for transmission to the server.

[0834] Step 5:

[0835] The server uses speech recognition technology to analyze the user's voice data. It converts the voice data into text and detects pronunciation and grammatical errors. Based on this analysis, it uses speech synthesis technology to generate feedback data that includes correct pronunciation and suggested corrections.

[0836] Step 6:

[0837] The device displays feedback data received from the server to the user. The feedback is provided in audio or text format and includes specific areas for improvement and advice. The user then uses this information to practice pronunciation.

[0838] Step 7:

[0839] The server uses image generation technology to generate visual learning materials related to the learning plan. These materials are designed to help with understanding new words and scenarios. The generated image data is sent to the terminal.

[0840] Step 8:

[0841] The server uses video generation technology to create a simulated video based on a specified scenario. This video is designed to simulate a real-life conversation and is provided to the user's device so that they can watch it repeatedly for learning.

[0842] Step 9:

[0843] The server continuously records the user's learning progress and analyzes it using machine learning algorithms. Based on this analysis, it generates data to provide personalized feedback and advice on goal achievement, and sends it to the user's device.

[0844] <|ipynb_marker|> Code

[0845] There is no code provided to execute or demonstrate.

[0846] (Application Example 1)

[0847] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0848] Traditional systems have limitations in terms of personalization and interactivity when it comes to effective language learning tailored to individual user needs. Furthermore, the lack of effective means to provide visual learning materials and simulation videos restricts the user's learning experience. This makes it difficult to maintain learning efficiency and motivation.

[0849] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0850] In this invention, the server includes means for analyzing the user's learning goals and ability level, means for automatically generating a training plan based on the analysis results, and means for providing interactive voice conversation using means for analyzing the user's pronunciation and vocabulary use in real time. This enables the automatic generation of personalized training plans and an improved learning experience through advanced interactive functions.

[0851] A "user" is a person who uses the system to learn a language.

[0852] "Learning objectives" refer to the specific language abilities and skills that the user wants to achieve.

[0853] "Proficiency level" is an indicator that represents the user's current language skill level.

[0854] "Means of analysis" refers to technologies that process user input information to understand its intent and content.

[0855] A "training plan" is a learning process designed based on the user's learning goals and skill level.

[0856] "Automatic generation methods" refer to technologies that automatically create optimal training plans from user information.

[0857] "Pronunciation" refers to the accuracy of the phonetic aspects of words.

[0858] "Vocabulary usage" refers to the selection and use of words and expressions by the user.

[0859] "Real-time analysis" refers to technology that processes and analyzes user voice instantly.

[0860] "Means of providing interactive voice conversations" refers to a system that enables interactive communication with users through voice.

[0861] "Visual learning materials" are teaching materials that use images and visuals to support learning.

[0862] "Image generation technology" is a technology that uses algorithms to create visual content.

[0863] "Scene" is a term that refers to a specific situation or scenario.

[0864] "Means of generating and providing videos" refers to technologies that create and present scene-based video content to users.

[0865] "Learning progress" indicates the degree to which the user's language ability is improving.

[0866] "Feedback" refers to information that provides evaluations of user performance and suggestions for improvement.

[0867] A "robot" is an electronic device that operates based on a program and can interact with a user.

[0868] The system for implementing this invention consists of a server, a terminal, and a user. First, the user operates the terminal to input their learning goals and current ability level. Based on this, the terminal sends data to the server. The server receives this information and analyzes it using natural language processing technology. Based on the results of this analysis, the system automatically generates an optimal training plan for the user.

[0869] Next, the user engages in an interactive voice conversation through the robot. The robot incorporates speech recognition and speech synthesis technologies to analyze the user's pronunciation and vocabulary usage in real time. For example, if areas for improvement in pronunciation are detected, feedback is provided immediately.

[0870] Furthermore, the server utilizes image generation technology to create visual learning materials tailored to the user's learning situation and presents them to the user via the terminal. Simulation videos are also generated in a similar manner, making it easier for users to visualize the actual situation.

[0871] The user's learning progress is periodically evaluated by the server, and detailed feedback is provided. This process is implemented using various hardware and software. For example, Google Cloud Speech-to-Text is used for speech processing, and OpenAI's GPT model is used for natural language processing. Stable Diffusion can be used for image generation, and the Pexels API can be used for video generation.

[0872] As a concrete example, consider a scenario where a user practices conversation in a restaurant. The robot acts as the waiter, taking orders and providing real-time feedback on pronunciation. Furthermore, the learning effect can be enhanced by presenting images and simulation videos related to the order.

[0873] An example of a prompt for a generative AI model is: "A user places an order at a restaurant. As a waiter, check the pronunciation and grammar, point out areas for improvement, and provide correct examples. Generate and present an image based on the situation."

[0874] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0875] Step 1:

[0876] The user inputs their learning goals and current proficiency level via a terminal. The input data is then sent to the server by the terminal. In this step, the input is the user's learning goals and proficiency level, and the output is the data sent to the server. The terminal's operation involves receiving user input and sending data.

[0877] Step 2:

[0878] The server uses natural language processing techniques to analyze the data it receives. The input is user data sent from the terminal, and the output is information about the analyzed learning needs. The server processes this data to automatically generate an optimal learning plan for the user.

[0879] Step 3:

[0880] The server automatically generates a learning plan and sends it to the terminal. The input is the learning plan generated by the server, and the output is the terminal that received it. The server's operation is to format and send the plan data.

[0881] Step 4:

[0882] The user initiates an interactive voice conversation with the robot using a terminal. The input is the user's voice, which is analyzed in real time by the robot. The output is either voice or text, including feedback on pronunciation and grammar. The terminal and robot's actions are voice recognition and feedback provision.

[0883] Step 5:

[0884] The server uses image generation technology to generate visual learning materials related to the user's learning content and sends them to the terminal. The input is scene information based on the learning plan, and the output is the generated image. The server's operation consists of generating and sending image data.

[0885] Step 6:

[0886] The server generates video content based on a specified scenario and provides the simulation to the terminal. The input is scenario information from the learning plan, and the output is the generated simulation video. The server's operation consists of executing the video generation algorithm and sending data.

[0887] Step 7:

[0888] The server analyzes the user's learning progress and provides personalized feedback to the terminal. The input is the user's learning history data, and the output is progress evaluation feedback information. The server's operation consists of data analysis and feedback generation.

[0889] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0890] This invention provides a multimodal language learning system that combines an emotion engine, thereby enabling further personalization of the user's learning experience. The system operates as follows, with the server, terminal, and user each playing a specific role.

[0891] First, the user inputs their learning goals and skill level through their device, and the device sends this information to the server. The server uses natural language processing technology to analyze the user's needs and automatically generates a personalized learning plan. In this process, the user's learning history and emotional state are also taken into consideration to provide a more appropriate plan.

[0892] When using the voice interaction function, the user speaks into the device's microphone, and the voice data is sent to the server. The server analyzes the spoken content based on speech recognition technology and evaluates the user's emotional state using an emotion engine. This evaluation result is reflected in the feedback generated using speech synthesis technology, providing advice tailored to the user's state in real time. For example, if the server detects that the user is feeling dissatisfied or stressed, it can offer encouraging messages or simple tasks.

[0893] Furthermore, the emotion engine is also used when generating visual learning materials and video simulations. The server generates content tailored to the user's interests and emotions using image and video generation technologies and presents it through the device. When the user is relaxed, a more challenging scenario is presented, and when they feel tense or anxious, easier exercises are presented, designed to gradually improve their skills.

[0894] Furthermore, the emotion engine is also used in progress evaluation. The server analyzes the user's learning activities and emotional changes, and generates emotion-based feedback. This feedback allows users to better understand their own learning process and maintain motivation as they continue learning.

[0895] Through the embodiments described above, the present invention aims to realize a personalized language learning experience that takes emotions into consideration, thereby maximizing the user's learning effectiveness. This system is expected to not only improve language skills but also support the user's psychological aspects.

[0896] The following describes the processing flow.

[0897] Step 1:

[0898] The user uses a device to input their learning goals, current skill level, and emotional state. The device then sends this information to the server.

[0899] Step 2:

[0900] The server analyzes the received user data using natural language processing technology. Based on the user's needs, it automatically generates a learning plan, taking their emotional state into consideration.

[0901] Step 3:

[0902] The server sends the generated learning plan to the device. The device displays the plan details to the user and presents learning content tailored to their emotions.

[0903] Step 4:

[0904] The user activates the voice interaction function through the device and begins speaking. The device records the voice data and sends it to the server.

[0905] Step 5:

[0906] The server uses speech recognition technology to convert the audio data into text and analyzes its content. Furthermore, it uses an emotion engine to evaluate the user's emotions and generate feedback.

[0907] Step 6:

[0908] The server generates customized feedback using speech synthesis technology and sends it to the terminal. The terminal provides the user with real-time feedback in either voice or text.

[0909] Step 7:

[0910] When a user requests visual learning materials, the device sends a request to the server. The server uses image generation technology to generate learning materials that respond to the user's emotions.

[0911] Step 8:

[0912] The server sends the generated visual learning materials to the device. The device displays the materials to the user, supporting emotionally sensitive learning.

[0913] Step 9:

[0914] When a user requests a video simulation, the device sends the scenario to the server. The server generates a video using video generation technology and incorporates the user's emotions into it.

[0915] Step 10:

[0916] The server sends the generated video to the device. The device plays the video for the user, assisting in the practice of practical skills. The practice is provided at a pace that suits the user's mood.

[0917] Step 11:

[0918] The device tracks the user's learning activities and emotional changes, and sends the data to the server. The server performs progress and emotional assessments and manages the user's learning status.

[0919] Step 12:

[0920] The server generates personalized feedback based on training data and sentiment evaluations. The terminal presents the feedback to the user and suggests a learning direction that takes sentiment into account.

[0921] (Example 2)

[0922] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0923] Current language learning systems suffer from insufficient personalization that takes into account each user's individual learning progress and emotional state, making it difficult to maximize learning effectiveness. Furthermore, they sometimes fail to provide adequate feedback to maintain user motivation. In addition, it is difficult to integrate and utilize diverse forms of learning materials, preventing the provision of a learning experience tailored to each individual user.

[0924] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0925] In this invention, the server includes means for analyzing the user's learning goals and skill level, means for automatically generating a learning plan based on the analysis results, and means for analyzing the user's emotional state and reflecting it in the learning content. This makes it possible to respond to the user's individual needs and provide a personalized learning experience based on their emotional state. Furthermore, this allows the user to maintain their motivation while learning effectively.

[0926] "User learning objectives" refer to the specific language learning goals that learners wish to achieve.

[0927] "Skill level" is an indicator that shows the degree of language proficiency a user currently possesses.

[0928] "Means of analysis" refers to the process by which a system understands the input information and gains appropriate insights.

[0929] "Automatic generation methods" refer to the function of a system that generates content and plans without human intervention, based on pre-set rules and algorithms.

[0930] "Interactive voice communication" is a feature that allows users to communicate in real time using natural language.

[0931] "Visual learning materials" are educational media provided to learners to acquire information through visual means.

[0932] "Virtual experience" is a method of providing users with realistic experiences through computer-generated content.

[0933] "Learning progress" is an indicator that measures the degree of progress made towards the goals set by the user.

[0934] "Emotional state" refers to a learner's psychological and emotional condition and is a factor that influences their learning activities.

[0935] "Feedback" refers to information provided by a system in response to user input and activities, such as opinions and evaluations, that helps improve the learning process.

[0936] This invention is a multimodal language learning system that integrates an emotion engine and aims to optimize the individual learning experience of each user. The system mainly consists of three elements: a server, a terminal, and the user.

[0937] First, the user uses a device to input information about their learning goals and skill level. The device securely transmits this information to a server via the internet. The device can operate using a browser application or a dedicated application.

[0938] Next, the server analyzes the received data using natural language processing (NLP) techniques. This analysis utilizes Python NLP libraries (such as SpaCy or NLTK). Based on the analysis results, a personalized learning plan tailored to the user's learning needs is automatically generated by an AI model. This AI model is designed to take into account the user's past data and emotional state.

[0939] Furthermore, when using the voice interaction function, the user inputs voice using the device's microphone. This voice is sent from the device to the server. The server uses a speech recognition API (for example, Google Cloud Speech-to-Text) to analyze the utterance and evaluates the user's emotions using an emotion engine. This emotion evaluation is reflected in the feedback generated by speech synthesis technology and presented to the user in real time.

[0940] Furthermore, the server automatically generates visual learning materials and video content using image and video generation technologies. This allows for the creation of learning materials tailored to the user's chosen learning goals and emotional state, enriching the learning experience.

[0941] For example, if a user enters "I want to improve my French conversation skills" into the device, the system will consider the user's skill level and emotional state, and then provide appropriate conversation practice and learning materials to help them understand the emotions of French. Another example of a prompt sentence for the generating AI model is, "Please suggest ways for the user to efficiently learn new vocabulary."

[0942] Based on the above, the system of the present invention aims to make user learning a comprehensive educational experience that includes emotional support, rather than merely the acquisition of knowledge.

[0943] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0944] Step 1:

[0945] The user inputs learning goals and skill levels into the device. The user text-inputs the language to be learned and their goals through the device's interface. This input information is treated as basic data necessary for customizing the learning content. The device processes this input data, formats it, and then sends it to the server.

[0946] Step 2:

[0947] The device sends input data to the server. The device uses a secure communication protocol (e.g., HTTPS) to send formatted data to the server. This ensures user privacy. The data includes learning objectives, skill level, and timestamps.

[0948] Step 3:

[0949] The server receives data from the user and analyzes it using natural language processing (NLP) techniques. Based on the received data, the server uses Python's NLP library to identify the user's needs. The input for the analysis is the user's learning goals and skill level, and the output includes insights necessary for designing a personalized learning plan.

[0950] Step 4:

[0951] The server automatically generates a learning plan using a generated AI model. In this step, the server inputs the analysis results into the generated AI model to precisely determine the content and stages of learning. The input also includes the user's learning history and emotional state, and the output is a learning plan tailored to the user.

[0952] Step 5:

[0953] The device receives the learning plan from the server and presents it to the user. The learning plan is displayed on the screen in a user-friendly format. Upon receiving the plan, the device decrypts its contents and provides it to the user as appropriately formatted information.

[0954] Step 6:

[0955] The user uses the voice interaction function to input speech into the device. The user speaks into the device's microphone, and the audio is converted into a digital format and sent to the server. This data is treated as a voice input prompt and is analyzed in the next step.

[0956] Step 7:

[0957] The server analyzes audio data using speech recognition technology and evaluates it using an emotion engine. The server uses a speech recognition API to convert user speech into text. Then, the emotion engine evaluates the user's emotional state. The input is audio data, and the output is the analyzed text and the emotion evaluation result.

[0958] Step 8:

[0959] The server generates feedback and delivers it to the user via speech synthesis. The server uses speech synthesis technology to generate feedback messages tailored to the user's emotional state. The final output is in audio format, which is provided to the user in real time through the device.

[0960] Step 9:

[0961] The user receives feedback and decides on their next learning action. Based on the feedback provided, the user chooses the next step. This process allows the user to learn efficiently.

[0962] (Application Example 2)

[0963] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0964] Modern language learning demands flexible learning approaches tailored to each learner's ability level and emotional state. However, traditional systems fail to adequately address individual needs, posing challenges in maintaining motivation and efficient learning. Furthermore, standardized feedback makes it difficult to maximize learning effectiveness, and insufficient psychological support for users is also a problem.

[0965] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0966] In this invention, the server includes means for analyzing the user's learning goals and ability level; means for automatically generating a learning plan based on the analysis results; means for analyzing the user's pronunciation and language use in real time; means for automatically generating and presenting visual learning materials to the user using image generation technology; means for generating videos and providing simulations based on specified situations; means for analyzing the user's learning progress and providing individual feedback; and means for analyzing the user's emotional state and providing voice encouragement and learning adjustments according to that situation. This makes it possible to provide a personalized learning experience tailored to each user and improve learning efficiency and motivation.

[0967] A "user" is an individual learner who utilizes a language learning system.

[0968] A "learning objective" is the specific language skill or knowledge level that the user wants to achieve.

[0969] "Proficiency level" is an indicator that shows the degree of language knowledge and skills a user currently possesses.

[0970] "Analysis" is the process of thoroughly examining information and data to reveal its structure and characteristics.

[0971] A "learning plan" refers to a chronologically organized set of steps and strategies aimed at helping a user achieve their goals.

[0972] "Real-time analysis" means processing phenomena and data as they occur and reflecting the results immediately.

[0973] "Interactive voice communication" is a process in which the user and the system exchange information bidirectionally through voice.

[0974] "Visual learning materials" are educational content created to provide information to users through visual means.

[0975] "Image generation technology" refers to the technology of creating new images within a computer using algorithms and software.

[0976] "Generating video based on context" means automatically creating appropriate video content according to specific conditions or context.

[0977] "Simulation" is a method of imitating real-world phenomena and predicting or analyzing their states and changes.

[0978] "Analyzing a user's learning progress" means evaluating how close a learner is to achieving their goals.

[0979] "Providing individualized feedback" means offering optimal advice and suggestions for improvement based on the user's situation and progress.

[0980] "Analyzing emotional states" is the process of understanding a user's psychological state and emotions, and comprehending their characteristics.

[0981] "Voice encouragement" is the act of sending messages through voice to support a user's motivation and mental state.

[0982] "Adjusting the learning plan" is the process of reviewing the learning plan and making adjustments in the optimal direction according to the user's progress and circumstances.

[0983] This invention is based on a system that analyzes emotional states and learning progress in real time to personalize the user's learning experience and provides a learning plan based on that analysis.

[0984] The server uses natural language processing technology and sentiment analysis engines to analyze the learning goals and ability levels provided by the user. Based on the results of these analyses, an algorithm is used to select the most suitable content for generating the learning plan. In this process, the user's past learning history and sentiment data are utilized to establish a personalized plan.

[0985] On the device side, speech recognition technology is used to collect the user's speech and instantly transmit it to the server. The server analyzes the received audio data and evaluates the emotional state. For example, if it is detected that the user is feeling anxious, the server uses speech synthesis technology to generate encouraging feedback and presents it to the user through the device.

[0986] Furthermore, the server combines image and video generation technologies to create visual learning materials and simulation videos tailored to the user's interests and situation. This makes the learning content easier to understand intuitively.

[0987] For example, if a user is struggling with a particular topic during their learning process, the server can create a simple scenario based on that topic and present practice problems in a way that alleviates the user's anxiety.

[0988] An example of a prompt based on a generative AI model is: "After the user expresses their feelings, show how to support their motivation and adjust their learning. Include specific encouraging messages in case the user becomes frustrated."

[0989] Overall, this system aims to enhance learning effectiveness by providing individual users with a learning pace and method tailored to their needs.

[0990] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0991] Step 1:

[0992] The device receives input from the user regarding learning goals and ability levels. This information is sent to a server to build a database of personalized learning plans. The input information serves as foundational data for analyzing the user's specific learning needs.

[0993] Step 2:

[0994] The server uses natural language processing techniques to analyze the user's learning goals and ability level based on the received data. This analysis prepares the data necessary to generate a learning plan tailored to the user. The analyzed data is then passed to the learning planning algorithm, which leads to the design of an individualized plan.

[0995] Step 3:

[0996] When a user speaks into the device, voice data is collected. The device sends this voice data to a server, which uses speech recognition technology to analyze the content of the speech. As a result, the user's emotional state based on the speech is evaluated. In this step, the input voice is processed as digital data, and the corresponding text and emotional state are output.

[0997] Step 4:

[0998] The server generates appropriate feedback using speech synthesis technology based on the user's emotional state. If the emotion is determined to be dissatisfaction or anxiety, an encouraging message is created. The generated voice feedback is delivered to the user through the terminal. In this step, voice data corresponding to the analysis results is output.

[0999] Step 5:

[1000] The server utilizes image and video generation technologies to create visual learning materials and simulation videos tailored to the user's interests and emotions. These materials are designed to enhance the user's learning experience. The generated visual content is displayed to the user via their device. The generated materials serve as supplementary content for the learning plan.

[1001] Step 6:

[1002] The server analyzes the user's learning progress and provides personalized feedback based on the analysis results. This allows users to understand their own learning progress and make necessary improvements and adjustments. The feedback based on the analysis results contributes to maintaining the user's learning motivation.

[1003] This entire process provides users with an optimal learning environment tailored to their needs, enabling efficient language acquisition.

[1004] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1005] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1006] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1007] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1008] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1009] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1010] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1011] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1012] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1013] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1014] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1015] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1016] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1017] 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.

[1018] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1019] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1020] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1021] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1022] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1023] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1024] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1025] The following is further disclosed regarding the embodiments described above.

[1026] (Claim 1)

[1027] A means for analyzing the user's learning goals and skill level,

[1028] A means for automatically generating a learning plan based on the analysis results,

[1029] A means for providing interactive voice dialogue using means for analyzing the user's pronunciation and language use in real time,

[1030] A means of automatically generating visual teaching materials using image generation technology and presenting them to the user,

[1031] A means for generating a video and providing a simulation based on a specified scenario,

[1032] A means of analyzing the user's learning progress and providing individualized feedback,

[1033] A system that includes this.

[1034] (Claim 2)

[1035] The system according to claim 1, which utilizes natural language processing technology in generating the aforementioned learning plan.

[1036] (Claim 3)

[1037] The system according to claim 1, wherein speech recognition and speech synthesis technologies are used in the real-time voice dialogue.

[1038] "Example 1"

[1039] (Claim 1)

[1040] A means for users to input learning goals and skill levels using a device,

[1041] Means for transmitting the input information to the server,

[1042] A server analyzes user information using natural language processing technology and automatically generates a learning plan using a generative AI model,

[1043] A means for analyzing the user's pronunciation and language use in real time using speech recognition and speech synthesis technologies, and providing feedback.

[1044] A means of automatically generating visual teaching materials using image generation technology and presenting them to the user,

[1045] A means for generating a video using video generation technology based on a specified scenario and providing a simulation,

[1046] A means of analyzing the user's learning progress and providing individualized feedback using machine learning algorithms,

[1047] A system that includes this.

[1048] (Claim 2)

[1049] The system according to claim 1, which utilizes natural language processing technology and a generative AI model in generating the learning plan.

[1050] (Claim 3)

[1051] The system according to claim 1, wherein speech recognition and speech synthesis technologies are used in the real-time voice dialogue.

[1052] "Application Example 1"

[1053] (Claim 1)

[1054] A means for analyzing the user's learning goals and ability level,

[1055] A means for automatically generating a training plan based on the analysis results,

[1056] A means for providing interactive voice conversation using means for analyzing the user's pronunciation and vocabulary use in real time,

[1057] A means of automatically generating visual teaching materials using image generation technology and displaying them to the user,

[1058] A means for generating videos based on specified scenes and providing training,

[1059] A means of analyzing the user's learning progress and providing individualized feedback,

[1060] A means of using a robot to conduct voice dialogue and present visual teaching materials,

[1061] A system that includes this.

[1062] (Claim 2)

[1063] The system according to claim 1, which utilizes natural language processing technology in generating the aforementioned training plan.

[1064] (Claim 3)

[1065] The system according to claim 1, which utilizes speech recognition and speech synthesis technologies in the aforementioned real-time voice conversation.

[1066] "Example 2 of combining an emotion engine"

[1067] (Claim 1)

[1068] A means for analyzing the user's learning goals and skill level,

[1069] A means for automatically generating a learning plan based on the analysis results,

[1070] A means for providing interactive voice dialogue using means for analyzing the user's pronunciation and language use in real time,

[1071] A means of automatically generating and presenting visual teaching materials to the user using generation technology,

[1072] A means for generating a video based on a specified scene and providing a virtual experience,

[1073] A means of analyzing the user's learning progress and providing feedback that takes into account their emotional state,

[1074] A means of analyzing the user's emotional state and reflecting it in the learning content,

[1075] A means of enhancing learning by using multiple forms of learning materials,

[1076] A system that includes this.

[1077] (Claim 2)

[1078] The system according to claim 1, which utilizes natural language processing technology in generating the aforementioned learning plan.

[1079] (Claim 3)

[1080] The system according to claim 1, which uses speech recognition and speech synthesis technologies and utilizes an emotion engine in the aforementioned real-time voice dialogue.

[1081] "Application example 2 when combining with an emotional engine"

[1082] (Claim 1)

[1083] A means for analyzing the user's learning goals and ability level,

[1084] A means for automatically generating a learning plan based on the analysis results,

[1085] A means of providing interactive voice communication using a means of analyzing the user's pronunciation and language use in real time,

[1086] A means of automatically generating and presenting visual teaching materials to users using image generation technology,

[1087] A means for generating images and providing simulations based on specified circumstances,

[1088] A means of analyzing the user's learning progress and providing individual feedback,

[1089] A means of analyzing the user's emotional state and providing voice encouragement and learning adjustments according to that situation,

[1090] A system that includes this.

[1091] (Claim 2)

[1092] The system according to claim 1, which utilizes natural language processing technology in generating the learning plan.

[1093] (Claim 3)

[1094] The system according to claim 1, which uses speech recognition and speech synthesis technologies in the aforementioned interactive voice communication and provides feedback based on emotional state. [Explanation of Symbols]

[1095] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for analyzing the user's learning goals and skill level, A means for automatically generating a learning plan based on the analysis results, A means for providing interactive voice dialogue using means for analyzing the user's pronunciation and language use in real time, A means of automatically generating visual teaching materials using image generation technology and presenting them to the user, A means for generating a video and providing a simulation based on a specified scenario, A means of analyzing the user's learning progress and providing individualized feedback, A system that includes this.

2. The system according to claim 1, which utilizes natural language processing technology in generating the learning plan.

3. The system according to claim 1, wherein speech recognition and speech synthesis technologies are used in the real-time voice dialogue.

Images