system

Abstract

We provide the system. [Solution] A means for analyzing speech information acquired by speech recognition means and converting the speech information into text information, A means for detecting pronunciation errors and generating feedback by comparing the converted character information with the previously acquired character information for teaching materials, A means for automatically generating visual material related to a predetermined term by an image generation means, A means for generating virtual simulation images using a video generation means, The aforementioned video is provided to learners as a means of promoting practical experience, A means of providing an interactive language learning experience by integrating speech recognition, image generation, and video generation technologies. A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] As problems faced by individual learners in language learning, the learning content may not be personalized uniformly, it may be difficult to maintain the motivation for learning, or there may be a lack of methods to efficiently improve communication skills. For this reason, the learning outcomes are likely to be limited, and there is a problem that it is difficult for learners to continuously engage.

Means for Solving the Problems

[0005] This invention provides a multimodal language learning system combining speech recognition, image generation, and video generation means. The speech recognition means converts acquired speech data into text, compares it with learning material text to detect pronunciation errors, and generates feedback. Furthermore, the system provides a practical experience by automatically generating visual materials related to words using the image generation means and generating virtual learning simulation videos using the video generation means. In addition, it improves learning outcomes by analyzing the learner's progress and dynamically updating individual learning plans.

[0006] "Speech recognition means" refers to a technology that analyzes language data from speech input in real time and converts it into corresponding text.

[0007] "Text data" refers to a collection of sentences and phrases expressed in natural language, and is character information recorded in digital format.

[0008] "Feedback" is information that points out areas for improvement and errors based on an assessment of the learner's performance, and directs them to the next step.

[0009] "Image generation means" refers to a technology that generates relevant visual materials using algorithms based on specific text or concepts.

[0010] "Video generation methods" refer to technologies that use algorithms to create animations and video clips based on specific scenarios or scenes.

[0011] A "virtual simulation video" is a video created to provide practical learning opportunities for users by simulating scenarios based on real-world situations and allowing them to experience them firsthand.

[0012] A "learner" refers to an individual who participates in an educational program with the aim of improving a specific language or skill.

[0013] Personalized feedback is a form of information that provides optimized feedback based on the individual learner's progress and characteristics.

[0014] "Natural language processing means" refers to technologies that use computer methods to process language data for the purpose of analyzing and understanding data that includes natural language. [Brief explanation of the drawing]

[0015] [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]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one 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.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] This invention is a multimodal learning system that integrates speech recognition, image generation, and video generation technologies to improve the language learning experience of learners. Specific embodiments for carrying out the invention are described below.

[0037] First, the user selects the language and topic they want to learn through an application installed on their device. This initiates a personalized learning path tailored to the learner's interests and goals.

[0038] Next, the server pulls appropriate learning materials from the database based on the selected topic and sends them to the terminal. These might include business English email templates or example sentences for everyday conversation. The terminal then displays them in a user-friendly format.

[0039] When a user practices speaking, the device uses its microphone to record the user's voice and sends it to the server in real time. The server uses speech recognition technology to convert this voice into text and compares the acquired text data with the original learning material to identify errors in pronunciation and intonation. This allows the user to receive clear feedback on where their pronunciation needs to be corrected. For example, if the user mispronounces "business" as "buisness," the correct pronunciation can be shown visually and audibly. This feedback information is provided to the user through the device.

[0040] Furthermore, to visually support learning, the server uses image generation AI to automatically generate visual materials related to new words and phrases. For example, if the word "dog" is included in the learning materials, it generates various images of dogs and presents them to the user through the device, thereby reinforcing the association between visuals and language.

[0041] Furthermore, the server uses video generation AI to create simulation videos that allow users to virtually experience educational and practical scenarios. For example, these videos might simulate meetings in English or customer service situations. The terminal displays these videos, helping users to gain an immersive learning experience.

[0042] Ultimately, the server periodically collects and analyzes learner progress data, dynamically updating individual learning plans using natural language processing technology. Based on this analysis, it identifies the user's learning tendencies and areas for improvement, and suggests the next steps in their learning. The device provides this personalized feedback to the user, supporting them in efficiently developing their skills.

[0043] In this way, the system provides learners with an interactive and multifaceted learning experience, promoting effective language acquisition tailored to individual needs.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The user launches the application on their device and selects the language and topic they want to learn. The user's selection is sent to the server.

[0047] Step 2:

[0048] The server searches the database for relevant text learning materials based on the user's selection and sends the corresponding data to the terminal. For example, it might provide examples of business English conversations.

[0049] Step 3:

[0050] The device displays acquired text learning materials to the user and provides an interface to encourage reading practice. The user reads the displayed text aloud into the microphone.

[0051] Step 4:

[0052] The device records the user's voice and sends the audio data to the server. The audio data is processed in real time.

[0053] Step 5:

[0054] The server uses speech recognition technology to convert the audio data into text. It then compares the converted text to the original text material to detect pronunciation errors. For example, if "business" is pronounced as "buisness," the server will point out the error.

[0055] Step 6:

[0056] The server generates pronunciation feedback based on the detected errors. This feedback includes areas for improvement and examples of correct pronunciation. The feedback information is sent to the terminal.

[0057] Step 7:

[0058] The device displays feedback to the user and presents solutions for improvement visually and audibly. Based on the feedback, the user continues practicing pronunciation.

[0059] Step 8:

[0060] The server uses image generation technology to generate visual material related to new words and phrases contained in the text. For example, it generates images of dog breeds for the word "dog".

[0061] Step 9:

[0062] The device provides the user with generated images to assist in visual language comprehension. The user enhances the association between visuals and text.

[0063] Step 10:

[0064] The server uses video generation technology to generate simulation videos according to the specified learning scenario. For example, it can create a video of a meeting scene.

[0065] Step 11:

[0066] The device plays the generated video for the user, providing a practical experience. By watching the video, the user learns how to apply the language.

[0067] Step 12:

[0068] The server collects user progress data and analyzes learning history using natural language processing techniques. It then updates individual learning plans and determines the next steps.

[0069] Step 13:

[0070] The device presents the user with updated learning plans and feedback, and indicates the next learning objectives. The user continues learning based on the information provided.

[0071] (Example 1)

[0072] 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."

[0073] In recent years, there has been a growing demand for diverse methods of language learning, but traditional teaching methods present challenges in effectively enabling learners to acquire practical language skills. Furthermore, there is a lack of adequate feedback tailored to individual learning paces and insufficient visualization of progress, resulting in a lack of means to maintain learner motivation.

[0074] 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.

[0075] In this invention, the server includes a device that analyzes speech information acquired by a speech recognition device and converts the speech information into document information; a device that detects pronunciation errors and generates a response by comparing the converted document information with previously acquired educational document information; and a device that automatically generates visual materials related to predetermined vocabulary using a visual information generation device. This enables learners to improve their pronunciation and effectively promotes language learning through visual stimuli.

[0076] A "speech recognition device" is a device that analyzes acquired speech information and converts it into document information.

[0077] "Document information" refers to text data that has been converted from audio information by a speech recognition device.

[0078] "Educational document information" refers to text data acquired in advance for use as learning reference.

[0079] A "visual information generation device" is a device equipped with the function of automatically generating visual materials related to a given vocabulary.

[0080] "Response" refers to feedback information generated based on the detection of pronunciation errors.

[0081] "Virtual experience video" refers to video data generated by a video generation device to facilitate simulations and practical experiences.

[0082] An "individualized learning plan" is a plan for determining the next learning stage, which is dynamically updated based on the analysis of the learner's progress.

[0083] A "natural language processing device" is a device that analyzes information, including learning history, and provides personalized responses to users.

[0084] This invention is a system for providing learners with an interactive language learning experience. The system integrates multimodal technology, utilizing speech recognition, image generation, and video generation to aid learning. Specifically, it uses a speech recognition device, a visual information generation device, and a video generation device to analyze user input and provide appropriate feedback and learning materials.

[0085] First, the user selects the language and topic they wish to learn using the corresponding input device. Based on this selection, the system retrieves appropriate educational document information from its database. For example, information tailored to different topics such as everyday conversation or business English is provided.

[0086] Next, the terminal uses a display device to show the text selected by the user. When the user practices pronunciation using the voice input function, the terminal captures the voice and sends the voice information to the server. The server analyzes this voice information using a speech recognition device, converts it into document information, and compares it with educational document information. This allows the user to receive accurate pronunciation feedback.

[0087] Furthermore, the server uses a visual information generation device to generate visual materials related to new vocabulary. These visual materials are displayed as images on the terminal's screen, providing the user with visual learning. For example, for the word "dog," various images of dogs are generated and presented. In addition, virtual experience videos generated using a video generation device are sent to the terminal, providing videos that simulate situations such as "ordering at a restaurant."

[0088] Ultimately, the server utilizes a natural language processing unit to analyze the user's progress and adjust the individual learning plan. By dynamically determining and providing the next steps based on progress information and the user's learning history, a more personalized learning experience is achieved.

[0089] An example of a prompt is, "Generate a simulated video of ordering at a restaurant." This system allows users to effectively improve their language skills.

[0090] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0091] Step 1:

[0092] The user launches the application on their terminal and selects the language and topic they wish to learn. As input, the user communicates their desired selections to the system via the interface. This selection guides the database search and is sent as a request to the server. As output, data related to the user's desired topic is requested from the server.

[0093] Step 2:

[0094] The server searches the database for relevant educational document information based on the user's selection. The input is a request from the user, and the server extracts text data related to the topic. The server then sends this data to the terminal, providing the user with educational materials as output.

[0095] Step 3:

[0096] The terminal displays text data received from the server. The input consists of educational document information from the server, preparing the user to begin visual learning. The output is text information displayed on the terminal in a user-friendly format.

[0097] Step 4:

[0098] The user uses the device's microphone function to practice pronunciation of selected learning materials via voice input. The input is an audio signal, which the device records as digital audio information. The recorded audio information is sent to the server as output.

[0099] Step 5:

[0100] The server uses a speech recognition device to analyze speech information and convert it into document information. The input is the user's speech information, which is converted into text using speech recognition technology. The resulting document information is then compared with educational document information.

[0101] Step 6:

[0102] The server identifies pronunciation errors and generates feedback by comparing the converted document information with the educational document information. The input consists of the converted document information and the educational document information, and the identified errors are sent to the terminal as feedback information. The output is feedback that includes specific correction suggestions.

[0103] Step 7:

[0104] The terminal presents the user with feedback information from the server, both visually and audibly. The input is feedback data received from the server, clearly indicating to the user which parts of the pronunciation need correction. The output includes visual highlighting and audio guidance for correct pronunciation.

[0105] Step 8:

[0106] The server uses a generative AI model to generate visual materials related to new vocabulary. The input is vocabulary contained in educational document information, and the visual information generation device outputs this as image data. The output image is sent to the terminal.

[0107] Step 9:

[0108] The terminal presents image data from the server to the user, aiming to associate vocabulary with visual information. The input is image data sent from the server, and visual presentation is used to facilitate the user's language learning. The output is the associated image displayed on the terminal's screen.

[0109] Step 10:

[0110] The server uses a video generation device to generate virtual experience videos related to the selected topic. The input consists of educational document information and the user's learning topic, and the generated video simulates the user's experience. The output is video data including detailed simulations.

[0111] Step 11:

[0112] The device plays video data from the server, providing the user with an immersive learning experience. The input is video data transmitted from the server, and videos are played to allow the user to gain practical experience. The output is a video displayed on the screen, intended to deepen the user's understanding through viewing.

[0113] Step 12:

[0114] The server utilizes a natural language processing unit to analyze the user's learning history and progress, and adjusts the individual learning plan accordingly. The input is the user's learning history and progress, and the dynamically updated plan guides the next learning step. As output, the adjusted learning plan is sent to the terminal and presented to the user.

[0115] (Application Example 1)

[0116] 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."

[0117] In recent years, there has been a growing demand for interactive and efficient language learning experiences. However, current systems often lack sufficient individualized support and real-time feedback for learners. Furthermore, there is a lack of technology that can provide learners with opportunities to acquire a language naturally at home. Against this backdrop, there are technical challenges in realizing flexible and intuitive learning support.

[0118] 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.

[0119] In this invention, the server includes means for analyzing audio information acquired by speech recognition means and converting the audio information into text information; means for detecting pronunciation errors and generating feedback by comparing the converted text information with previously acquired text information for teaching materials; and means for automatically generating visual materials related to predetermined terms using image generation means. This enables learners to effectively acquire a language at home and facilitates interactive and personalized language learning.

[0120] "Speech recognition means" refers to technology that analyzes speech information and converts it into text information.

[0121] "Textual information" refers to information represented by digital strings converted through speech recognition.

[0122] "Educational material text information" refers to text data that has been prepared in advance for use in learning.

[0123] "Feedback" is information that informs the user of pronunciation errors based on comparison results.

[0124] "Image generation means" refers to a technology that automatically creates visual materials related to a given term.

[0125] "Terminology" refers to words and phrases used in language learning.

[0126] "Visual material" refers to images presented to learners as visual information.

[0127] "Video generation method" refers to technology that automatically creates simulated videos.

[0128] "Interactive" refers to a dynamic relationship in which the user and the system exchange information with each other.

[0129] "Language learning experience" refers to all activities related to language acquisition, encompassing the process by which learners acquire a language.

[0130] "Progress information" refers to records of learners' learning status and achievements.

[0131] An "individualized learning plan" is a learning process that is customized according to the learner's needs.

[0132] A "language learning partner" is a robot or device that assists learners in acquiring a language.

[0133] "Natural language processing technology" refers to methods that enable computers to understand and process human language.

[0134] "Real-time feedback" refers to corrections and advice provided immediately during the learning process.

[0135] This invention is a system to support language learning, allowing users to gain a learning experience at home. The system integrates speech recognition, image generation, and video generation technologies.

[0136] First, users can select what they want to learn. They choose a language and topic of interest through their device and begin learning.

[0137] Next, the server provides the terminal with relevant learning materials based on the user's selection. Based on these materials, the user can practice speaking. The terminal's microphone captures the user's pronunciation and sends it to the server. The server uses a speech recognition program (e.g., Google® Cloud Speech-to-Text) to convert this speech into text and compares it with the text information of the learning materials.

[0138] If a learner makes a pronunciation error, the server identifies the error and generates real-time feedback. This feedback visually or audibly demonstrates the correct pronunciation. In this way, users can immediately correct their pronunciation in their daily learning.

[0139] Furthermore, the server uses image generation AI (e.g., OpenAI® DALL-E) to create visual materials related to learning. This makes it easier for learners to associate terms with images. In addition, video generation AI (e.g., DeepAI) generates virtual simulation videos, allowing users to visually experience practical scenarios.

[0140] Robots and smart devices function as home learning partners, enhancing learning effectiveness by providing users with conversation practice and interactive quizzes. Specifically, a scenario is envisioned where a user practices English phrases about animals for 10 minutes each day.

[0141] This system analyzes progress information and uses natural language processing technology to generate personalized feedback based on the learner's history. For example, the server might process an instruction such as, "Convert the word the user pronounces into text, compare it to the correct pronunciation, and provide visual or auditory feedback on how to correct the pronunciation if there are errors." This allows learners to improve their language skills efficiently at their own pace.

[0142] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0143] Step 1:

[0144] The user selects a learning language and topic using a terminal. The selected information is sent from the terminal to the server. The input is the user's selection information, and the output is the transmission of the selection information to the server.

[0145] Step 2:

[0146] The server extracts the relevant text information for educational materials from the database based on the received topic information and sends it to the terminal. The input is topic information, and the output is text information for educational materials.

[0147] Step 3:

[0148] The user performs audio practice based on the learning materials through the device, and the audio is captured by the device's microphone and sent to the server. The input is the user's pronunciation, and the output is the transmission of audio data to the server.

[0149] Step 4:

[0150] The server uses Google Cloud Speech-to-Text to convert audio data into text data. Furthermore, it compares this text to the original text information and detects errors. The input is the transmitted audio data, and the output is the converted text data and error identification.

[0151] Step 5:

[0152] The server generates feedback for the user based on the error and sends it to the terminal in a visual or auditory way. The input is the error information, and the output is the generation and transmission of feedback to the terminal.

[0153] Step 6:

[0154] The server uses OpenAI DALL-E to generate visual materials related to new terminology and sends them to the terminal. The input is term information, and the output is visual materials. The terminal displays these visual materials to the user.

[0155] Step 7:

[0156] The server uses Deep AI to generate a virtual simulation video and sends it to the terminal. The input is the simulation scenario information, and the output is the generated video. The terminal then plays this simulation video for the user.

[0157] Step 8:

[0158] The server analyzes the learning history and progress information, generates personalized feedback using natural language processing technology, and determines the next learning step. The input is the learning history data, and the output is an updated learning plan.

[0159] 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.

[0160] This invention is a multimodal learning system that integrates speech recognition, image generation, and video generation technologies with an emotion engine that recognizes user emotions. Specific embodiments for carrying out the invention are described below.

[0161] First, the user launches the application on their device and selects the language and topic they want to learn. Based on this selection, an individual learning scenario is initiated.

[0162] The server retrieves appropriate text learning materials from the database based on the user's selection and sends them to the terminal. The terminal is configured to display these materials to the user.

[0163] During voice practice, the device captures the user's voice via its microphone and sends this data to the server in real time. The server uses speech recognition technology to convert the voice into text and compares it with the learning material text to identify pronunciation errors. Feedback is generated and presented to the user through the device. For example, it might guide the user on the correct pronunciation of "business."

[0164] The server also uses image generation technology to create visual materials related to new words and phrases and presents them to the user, thereby assisting with visual learning.

[0165] Furthermore, video generation technology is used to generate virtual simulation videos based on learning scenarios, which are then provided to the user via their device. This allows users to learn how to apply language through practical experience.

[0166] In particular, this system incorporates an emotion engine, which analyzes the user's facial expressions, voice tone, and other factors on the terminal and sends the results to the server.

[0167] The server identifies the user's emotional state based on data obtained by the emotion engine and adjusts the learning experience accordingly. This adjustment includes adjusting feedback and difficulty levels. For example, if the user is feeling frustrated, the system will emphasize positive feedback to boost their motivation.

[0168] Finally, the server analyzes the user's progress data, including emotional data, and dynamically updates the individual learning plan. The updated plan is presented to the user via the device, and new learning goals are set. In this way, the entire system provides a personalized learning experience that responds to the user's emotions and progress.

[0169] The following describes the processing flow.

[0170] Step 1:

[0171] The user launches the application on their device and selects the language and topic they want to learn. This selection is then sent to the server.

[0172] Step 2:

[0173] The server retrieves appropriate text learning materials from the database based on the user's selection and sends them to the terminal. The terminal then displays these text learning materials to the user.

[0174] Step 3:

[0175] The user reads the displayed text aloud. The device records the user's voice and prepares to send the audio data to the server.

[0176] Step 4:

[0177] The server uses speech recognition technology to convert audio data into text. The converted text is compared to the textbook material to identify pronunciation errors.

[0178] Step 5:

[0179] The server generates feedback based on pronunciation errors. This feedback includes instructions for improving pronunciation accuracy. The feedback information is sent to the terminal.

[0180] Step 6:

[0181] The device displays feedback to the user visually and audibly. The user receives the feedback and continues practicing pronunciation.

[0182] Step 7:

[0183] The server identifies new words and phrases from the selected text and uses image generation technology to create related visual materials.

[0184] Step 8:

[0185] The device displays the generated visual materials to the user. These visual materials enhance the user's understanding.

[0186] Step 9:

[0187] The server uses video generation technology to create virtual simulation videos based on scenarios related to the learning topic.

[0188] Step 10:

[0189] The device provides users with generated videos, facilitating a practical learning experience.

[0190] Step 11:

[0191] The device uses its camera and microphone to transmit the user's facial expressions and voice to an emotion engine, which then analyzes the user's emotional state in real time.

[0192] Step 12:

[0193] The server analyzes emotional data obtained by the emotion engine and adjusts the user's learning experience. Specifically, it dynamically changes the tone of feedback and the difficulty level of learning materials according to the user's emotional state.

[0194] Step 13:

[0195] The server analyzes the user's progress and sentiment data and updates their individual learning plan.

[0196] Step 14:

[0197] The device presents the user with an updated learning plan and additional feedback, and provides new learning objectives. Based on this information, the user progresses to the next learning stage.

[0198] (Example 2)

[0199] 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".

[0200] In modern education systems, there is a need for individualized learning support tailored to each learner's level of understanding and emotional state, but traditional methods struggle to provide such individualized support. Furthermore, there is a demand to enhance learning effectiveness by integrating elements such as audio, visuals, and emotion analysis, but there is a lack of technology to efficiently combine these elements.

[0201] 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.

[0202] In this invention, the server includes means for analyzing speech information acquired by speech recognition means and converting the speech information into text information; means for detecting pronunciation errors and generating evaluation information by comparing the converted text information with previously acquired educational material text information; means for automatically generating visual materials related to predetermined terms using visual information generation means; means for generating virtual simulation videos using video generation means; and means for identifying the learner's emotional state using emotion analysis means and adjusting the learning experience based on the state. This provides an individually personalized learning experience and enables a flexible learning environment that responds to the learner's emotions and progress.

[0203] "Speech recognition means" refers to a technology or function that analyzes speech information and converts that information into text information.

[0204] "Text information" refers to string data converted from audio or other sources.

[0205] "Educational material text information" refers to string data prepared as teaching materials to be provided to learners.

[0206] "Evaluation information" refers to feedback and analysis results generated based on speech recognition and analysis of learning progress.

[0207] "Visual information generation means" refers to a technology or function that automatically creates visual materials related to terms or concepts.

[0208] "Motion image generation means" refers to a technology or function for creating virtual simulations or digital videos.

[0209] "Emotional analysis means" refers to a technology or function that identifies an emotional state by analyzing a learner's facial expressions and tone of voice.

[0210] "Learning experience" refers to the process by which learners acquire knowledge and skills through an educational program.

[0211] A "personalized learning experience" is the provision of education that is customized based on the individual needs, progress, and emotional state of each learner.

[0212] This invention is a multimodal education system that provides learners with a personalized learning experience. Its main components are a server, terminals, and users working together. The specific form of this system is described below.

[0213] First, the user launches a dedicated application on their device and begins by selecting a language to learn and a topic. This selection information is then sent from the device to the server. The device uses a standard PC or smart device for this process.

[0214] The server retrieves appropriate educational materials from its database based on information from the user and sends them to the device. These materials include text, visuals, and videos. The server uses a speech recognition engine (e.g., a common cloud-based speech service) to analyze the user's pronunciation. Specifically, it converts the audio information into text and compares it to pre-recorded text materials to detect pronunciation errors. Afterward, it generates evaluation information and returns it to the device as feedback.

[0215] To enhance visual learning, the server utilizes generative AI models (e.g., general-purpose image generation algorithms) to generate visual materials related to terms and concepts. It also leverages video generation technology to create and provide users with videos for virtual simulations, enabling practical experience.

[0216] Furthermore, the device uses sensors and simple emotion analysis software to detect the user's emotional state. This data is sent to a server, where the emotion analysis tool individually tailors the user's learning experience.

[0217] For example, if a user enters the prompt "Provide visual learning materials to help me learn everyday Japanese phrases in a fun way" into the system, the server will generate corresponding text materials and visual resources and deliver them to the user's terminal.

[0218] In this way, the system combines voice, visual, and emotion analysis technologies to provide users with a unique and personalized learning experience. This helps learners achieve their goals efficiently and effectively.

[0219] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0220] Step 1:

[0221] The user launches the application on their device and selects the language and topic they want to learn. The input is the language and topic information selected by the user. Based on this, the device sends this information to the server. The output is the selection information received by the server.

[0222] Step 2:

[0223] The server uses the received language and topic information to search the database for relevant educational materials. The input is user selection information, and the output is extracted as appropriate text information, visual materials, and video data. This data is then sent to the user's terminal.

[0224] Step 3:

[0225] The terminal displays educational materials sent from the server to the user. It receives educational material data from the server as input. As output, text information is displayed on the screen for the user, and visual materials and videos are played.

[0226] Step 4:

[0227] The user begins voice practice. The device's microphone captures the user's pronunciation. The input is the user's spoken audio information. The device sends this to the server, and the audio data is sent to the speech recognition process as output.

[0228] Step 5:

[0229] The server uses speech recognition to convert input speech data into text information. The input is speech data sent from the terminal. This data is analyzed and converted into text information. The output is the converted text information.

[0230] Step 6:

[0231] The server uses a generative AI model to generate visual materials related to new terminology. The input is converted text information, which is used to create the visual materials. The output is the generated visual information, which is then sent to the terminal.

[0232] Step 7:

[0233] The device uses sensors and emotion analysis software to detect the user's emotional state. Input includes the user's facial expressions and voice tone data. This data is analyzed, and information regarding the emotional state is sent to the server as output.

[0234] Step 8:

[0235] The server analyzes emotional state information and learning progress to generate optimal feedback for the user. Emotional state information and learning data are used as input. Based on this information, it generates feedback that adjusts the learning experience. The adjusted feedback is sent to the terminal as output.

[0236] (Application Example 2)

[0237] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0238] Conventional language learning systems offer limited feedback on learners' pronunciation practice and comprehension, and lack individualized support based on learners' emotions. This results in insufficient motivation and efficient learning support. Therefore, a system that provides a more practical and effective learning experience is needed.

[0239] 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.

[0240] In this invention, the server includes means for analyzing speech information acquired by a speech recognition device and converting the speech information into text information; means for detecting pronunciation errors and generating feedback by comparing the converted text information with previously acquired learning text data; means for automatically generating visual data related to predetermined terms using a visual material generation device; means for generating virtual simulation images using a video generation device; and means for analyzing the learner's emotional state using an emotion analysis device and adjusting the learning content. This enables learners to receive more personalized, emotion-responsive feedback and a learning experience.

[0241] A "speech recognition device" is a technology that analyzes received speech information and converts it into text information.

[0242] "Textual information" refers to digitized text data obtained by analyzing and converting audio information.

[0243] "Learning text data" refers to pre-prepared textual information for learning, used to aid in understanding pronunciation and grammar.

[0244] A "visual material generation device" is a technology that automatically generates visual data related to specific terms or phrases.

[0245] A "video generation device" is a technology that generates video data in order to realize a virtual simulation.

[0246] An "emotion analysis device" is a technology that analyzes a learner's emotional state from information such as facial expressions and voice.

[0247] "Feedback" refers to information provided to learners, such as suggestions, evaluations, and areas for improvement regarding pronunciation and comprehension.

[0248] A "personalized learning experience" refers to an educational experience that is tailored and delivered according to the individual characteristics and emotional state of the learner.

[0249] This invention provides an educational tool that integrates speech recognition and sentiment analysis technologies as a system to support learners' language learning. Learners can select a target language and topic using a terminal and begin learning on the system.

[0250] The server uses a speech recognition device to convert speech information acquired from the microphone into text. This information is compared with pre-prepared training text data to detect pronunciation errors. Based on the detected errors, feedback is generated and presented to the learner. In addition, a visual material generation device automatically generates visual materials that match the specified terms and displays them to the learner through the terminal's display.

[0251] Furthermore, the server uses a video generation device to generate virtual simulation images, providing a practical experience. This process utilizes a generative AI model to depict specific scenes and situations that learners should be taught.

[0252] In addition, an emotion analysis device uses data from the device's camera and microphone to analyze the learner's emotional state. Based on this emotional state, the server adjusts the learning content and provides feedback and learning tasks that match the learner's emotions. This personalized learning experience is expected to enable learners to learn more effectively.

[0253] As a concrete example, the server sends a prompt message to the AI ​​model saying, "Please suggest images and videos that can be generated to learn English words and actions related to animals," and the results are displayed on the terminal. In this way, an effective learning environment is realized through the cooperation of the server, terminal, and user.

[0254] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0255] Step 1:

[0256] The user selects the target language and topic on their device. This input information is sent to the server, and a learning scenario is constructed as output. The server retrieves the corresponding learning text data from the database and prepares it for display on the device.

[0257] Step 2:

[0258] The user provides voice input through the device. The device uses a microphone to acquire voice information and sends it to the server. The server uses a speech recognition device to convert the voice information into text. This converted text information forms the basis for the next step.

[0259] Step 3:

[0260] The server compares the text information with pre-prepared training text data. During the comparison process, it detects differences from the correct pronunciation and generates feedback. This feedback is then presented to the user via the terminal.

[0261] Step 4:

[0262] The server uses a visual material generation device to generate visual materials related to specified terms. Appropriate images and illustrations are created to facilitate learning for the user, and these are displayed to the user via the terminal.

[0263] Step 5:

[0264] The server uses a video generation device to generate virtual simulation videos. In this generation process, a generation AI model is used to create prompt messages and visualize specific scenes and situations. The videos are then presented to the user via a terminal.

[0265] Step 6:

[0266] The device captures the user's facial expressions and voice tone using its camera and microphone, and sends this data to a server. The server analyzes the user's emotional state through an emotion analysis device and provides feedback and adjusts learning tasks accordingly.

[0267] Step 7:

[0268] The server dynamically updates individual learning programs based on collected progress information and sentiment data. The updated learning plan is presented to the user via the terminal, and the next learning step is suggested.

[0269] 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.

[0270] Data generation model 58 is a type of 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.

[0271] 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.

[0272] [Second Embodiment]

[0273] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0274] 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.

[0275] 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).

[0276] 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.

[0277] 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.

[0278] 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).

[0279] 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.

[0280] 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.

[0281] The specific processing program 56 is an example of the "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by operating as the specific processing unit 290 according to the specific processing program 56 executed by the processor 28 on the RAM 30.

[0282] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the specific processing unit 290.

[0283] In the smart glasses 214, the receiving and output processing is performed by the processor 46. The storage 50 stores a receiving and output program 60. The processor 46 reads the receiving and output program 60 from the storage 50 and executes the read receiving and output program 60 on the RAM 48. The receiving and output processing is realized by operating as the control unit 46A according to the receiving and output program 60 executed by the processor 46 on the RAM 48.

[0284] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0285] This invention is a multimodal learning system that integrates speech recognition, image generation, and video generation technologies to improve the language learning experience of learners. The following shows specific embodiments for implementing the invention.

[0286] First, the user selects the language and topic to be learned through the application installed on the terminal. Thereby, an individual learning route according to the learner's interests and goals is started.

[0287] Next, the server pulls appropriate learning materials from the database based on the selected topic and sends them to the terminal. These might include business English email templates or example sentences for everyday conversation. The terminal then displays them in a user-friendly format.

[0288] When a user practices speaking, the device uses its microphone to record the user's voice and sends it to the server in real time. The server uses speech recognition technology to convert this voice into text and compares the acquired text data with the original learning material to identify errors in pronunciation and intonation. This allows the user to receive clear feedback on where their pronunciation needs to be corrected. For example, if the user mispronounces "business" as "buisness," the correct pronunciation can be shown visually and audibly. This feedback information is provided to the user through the device.

[0289] Furthermore, to visually support learning, the server uses image generation AI to automatically generate visual materials related to new words and phrases. For example, if the word "dog" is included in the learning materials, it generates various images of dogs and presents them to the user through the device, thereby reinforcing the association between visuals and language.

[0290] Furthermore, the server uses video generation AI to create simulation videos that allow users to virtually experience educational and practical scenarios. For example, these videos might simulate meetings in English or customer service situations. The terminal displays these videos, helping users to gain an immersive learning experience.

[0291] Ultimately, the server periodically collects and analyzes learner progress data, dynamically updating individual learning plans using natural language processing technology. Based on this analysis, it identifies the user's learning tendencies and areas for improvement, and suggests the next steps in their learning. The device provides this personalized feedback to the user, supporting them in efficiently developing their skills.

[0292] In this way, the system provides learners with an interactive and multifaceted learning experience, promoting effective language acquisition tailored to individual needs.

[0293] The following describes the processing flow.

[0294] Step 1:

[0295] The user launches the application on their device and selects the language and topic they want to learn. The user's selection is sent to the server.

[0296] Step 2:

[0297] The server searches the database for relevant text learning materials based on the user's selection and sends the corresponding data to the terminal. For example, it might provide examples of business English conversations.

[0298] Step 3:

[0299] The device displays acquired text learning materials to the user and provides an interface to encourage reading practice. The user reads the displayed text aloud into the microphone.

[0300] Step 4:

[0301] The device records the user's voice and sends the audio data to the server. The audio data is processed in real time.

[0302] Step 5:

[0303] The server uses speech recognition technology to convert the audio data into text. It then compares the converted text to the original text material to detect pronunciation errors. For example, if "business" is pronounced as "buisness," the server will point out the error.

[0304] Step 6:

[0305] The server generates pronunciation feedback based on the detected errors. This feedback includes areas for pronunciation improvement and examples of correct pronunciation. The feedback information is sent to the terminal.

[0306] Step 7:

[0307] The terminal displays the feedback to the user and presents improvement measures visually and auditorily. The user continues pronunciation practice based on the feedback.

[0308] Step 8:

[0309] The server uses image generation technology to generate visual materials related to new words and phrases included in the text. For example, it generates images of dog breeds for the word "dog".

[0310] Step 9:

[0311] The terminal provides the generated image to the user to assist in visual language understanding. The user strengthens the association between vision and text.

[0312] Step 10:

[0313] The server uses video generation technology to generate a simulation video according to the specified learning scenario. For example, it creates a video of a meeting scene.

[0314] Step 11:

[0315] The terminal plays the generated video for the user to provide a practical experience. The user learns how to apply the language by watching the video.

[0316] Step 12:

[0317] The server collects the user's progress data and analyzes the learning history using natural language processing technology. It updates the individual learning plan and determines the next step.

[0318] Step 13:

[0319] The device presents the user with updated learning plans and feedback, and indicates the next learning objectives. The user continues learning based on the information provided.

[0320] (Example 1)

[0321] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0322] In recent years, there has been a growing demand for diverse methods of language learning, but traditional teaching methods present challenges in effectively enabling learners to acquire practical language skills. Furthermore, there is a lack of adequate feedback tailored to individual learning paces and insufficient visualization of progress, resulting in a lack of means to maintain learner motivation.

[0323] 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.

[0324] In this invention, the server includes a device that analyzes speech information acquired by a speech recognition device and converts the speech information into document information; a device that detects pronunciation errors and generates a response by comparing the converted document information with previously acquired educational document information; and a device that automatically generates visual materials related to predetermined vocabulary using a visual information generation device. This enables learners to improve their pronunciation and effectively promotes language learning through visual stimuli.

[0325] A "speech recognition device" is a device that analyzes acquired speech information and converts it into document information.

[0326] "Document information" refers to text data that has been converted from audio information by a speech recognition device.

[0327] "Educational document information" refers to text data acquired in advance for use as learning reference.

[0328] A "visual information generation device" is a device equipped with the function of automatically generating visual materials related to a given vocabulary.

[0329] "Response" refers to feedback information generated based on the detection of pronunciation errors.

[0330] "Virtual experience video" refers to video data generated by a video generation device to facilitate simulations and practical experiences.

[0331] An "individualized learning plan" is a plan for determining the next learning stage, which is dynamically updated based on the analysis of the learner's progress.

[0332] A "natural language processing device" is a device that analyzes information, including learning history, and provides personalized responses to users.

[0333] This invention is a system for providing learners with an interactive language learning experience. The system integrates multimodal technology, utilizing speech recognition, image generation, and video generation to aid learning. Specifically, it uses a speech recognition device, a visual information generation device, and a video generation device to analyze user input and provide appropriate feedback and learning materials.

[0334] First, the user selects the language and topic they wish to learn using the corresponding input device. Based on this selection, the system retrieves appropriate educational document information from its database. For example, information tailored to different topics such as everyday conversation or business English is provided.

[0335] Next, the terminal uses a display device to show the text selected by the user. When the user practices pronunciation using the voice input function, the terminal captures the voice and sends the voice information to the server. The server analyzes this voice information using a speech recognition device, converts it into document information, and compares it with educational document information. This allows the user to receive accurate pronunciation feedback.

[0336] Furthermore, the server uses a visual information generation device to generate visual materials related to new vocabulary. These visual materials are displayed as images on the terminal's screen, providing the user with visual learning. For example, for the word "dog," various images of dogs are generated and presented. In addition, virtual experience videos generated using a video generation device are sent to the terminal, providing videos that simulate situations such as "ordering at a restaurant."

[0337] Ultimately, the server utilizes a natural language processing unit to analyze the user's progress and adjust the individual learning plan. By dynamically determining and providing the next steps based on progress information and the user's learning history, a more personalized learning experience is achieved.

[0338] An example of a prompt is, "Generate a simulated video of ordering at a restaurant." This system allows users to effectively improve their language skills.

[0339] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0340] Step 1:

[0341] The user launches the application on their terminal and selects the language and topic they wish to learn. As input, the user communicates their desired selections to the system via the interface. This selection guides the database search and is sent as a request to the server. As output, data related to the user's desired topic is requested from the server.

[0342] Step 2:

[0343] The server searches the database for relevant educational document information based on the user's selection. The input is a request from the user, and the server extracts text data related to the topic. The server then sends this data to the terminal, providing the user with educational materials as output.

[0344] Step 3:

[0345] The terminal displays text data received from the server. The input consists of educational document information from the server, preparing the user to begin visual learning. The output is text information displayed on the terminal in a user-friendly format.

[0346] Step 4:

[0347] The user uses the device's microphone function to practice pronunciation of selected learning materials via voice input. The input is an audio signal, which the device records as digital audio information. The recorded audio information is sent to the server as output.

[0348] Step 5:

[0349] The server uses a speech recognition device to analyze speech information and convert it into document information. The input is the user's speech information, which is converted into text using speech recognition technology. The resulting document information is then compared with educational document information.

[0350] Step 6:

[0351] The server identifies pronunciation errors and generates feedback by comparing the converted document information with the educational document information. The input consists of the converted document information and the educational document information, and the identified errors are sent to the terminal as feedback information. The output is feedback that includes specific correction suggestions.

[0352] Step 7:

[0353] The terminal presents the user with feedback information from the server, both visually and audibly. The input is feedback data received from the server, clearly indicating to the user which parts of the pronunciation need correction. The output includes visual highlighting and audio guidance for correct pronunciation.

[0354] Step 8:

[0355] The server uses a generative AI model to generate visual materials related to new vocabulary. The input is vocabulary contained in educational document information, and the visual information generation device outputs this as image data. The output image is sent to the terminal.

[0356] Step 9:

[0357] The terminal presents image data from the server to the user, aiming to associate vocabulary with visual information. The input is image data sent from the server, and visual presentation is used to facilitate the user's language learning. The output is the associated image displayed on the terminal's screen.

[0358] Step 10:

[0359] The server uses a video generation device to generate virtual experience videos related to the selected topic. The input consists of educational document information and the user's learning topic, and the generated video simulates the user's experience. The output is video data including detailed simulations.

[0360] Step 11:

[0361] The device plays video data from the server, providing the user with an immersive learning experience. The input is video data transmitted from the server, and videos are played to allow the user to gain practical experience. The output is a video displayed on the screen, intended to deepen the user's understanding through viewing.

[0362] Step 12:

[0363] The server utilizes a natural language processing unit to analyze the user's learning history and progress, and adjusts the individual learning plan accordingly. The input is the user's learning history and progress, and the dynamically updated plan guides the next learning step. As output, the adjusted learning plan is sent to the terminal and presented to the user.

[0364] (Application Example 1)

[0365] 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."

[0366] In recent years, there has been a growing demand for interactive and efficient language learning experiences. However, current systems often lack sufficient individualized support and real-time feedback for learners. Furthermore, there is a lack of technology that can provide learners with opportunities to acquire a language naturally at home. Against this backdrop, there are technical challenges in realizing flexible and intuitive learning support.

[0367] 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.

[0368] In this invention, the server includes means for analyzing audio information acquired by speech recognition means and converting the audio information into text information; means for detecting pronunciation errors and generating feedback by comparing the converted text information with previously acquired text information for teaching materials; and means for automatically generating visual materials related to predetermined terms using image generation means. This enables learners to effectively acquire a language at home and facilitates interactive and personalized language learning.

[0369] "Speech recognition means" refers to technology that analyzes speech information and converts it into text information.

[0370] "Textual information" refers to information represented by digital strings converted through speech recognition.

[0371] "Educational material text information" refers to text data that has been prepared in advance for use in learning.

[0372] "Feedback" is information that informs the user of pronunciation errors based on comparison results.

[0373] "Image generation means" refers to a technology that automatically creates visual materials related to a given term.

[0374] "Terminology" refers to words and phrases used in language learning.

[0375] "Visual material" refers to images presented to learners as visual information.

[0376] "Video generation method" refers to technology that automatically creates simulated videos.

[0377] "Interactive" refers to a dynamic relationship in which the user and the system exchange information with each other.

[0378] "Language learning experience" refers to all activities related to language acquisition, encompassing the process by which learners acquire a language.

[0379] "Progress information" refers to records of learners' learning status and achievements.

[0380] An "individualized learning plan" is a learning process that is customized according to the learner's needs.

[0381] A "language learning partner" is a robot or device that assists learners in acquiring a language.

[0382] "Natural language processing technology" refers to methods that enable computers to understand and process human language.

[0383] "Real-time feedback" refers to corrections and advice provided immediately during the learning process.

[0384] This invention is a system to support language learning, allowing users to gain a learning experience at home. The system integrates speech recognition, image generation, and video generation technologies.

[0385] First, users can select what they want to learn. They choose a language and topic of interest through their device and begin learning.

[0386] Next, the server provides the terminal with relevant learning materials based on the user's selection. Based on these materials, the user can practice speaking. The terminal's microphone captures the user's pronunciation and sends it to the server. The server uses a speech recognition program (e.g., Google Cloud Speech-to-Text) to convert this speech into text and compares it with the text information of the learning materials.

[0387] If a learner makes a pronunciation error, the server identifies the error and generates real-time feedback. This feedback visually or audibly demonstrates the correct pronunciation. In this way, users can immediately correct their pronunciation in their daily learning.

[0388] Furthermore, the server uses image generation AI (e.g., OpenAI DALL-E) to create visual materials relevant to learning. This makes it easier for learners to associate terms with images. In addition, video generation AI (e.g., DeepAI) generates virtual simulation videos, allowing users to visually experience practical scenarios.

[0389] Robots and smart devices function as home learning partners, enhancing learning effectiveness by providing users with conversation practice and interactive quizzes. Specifically, a scenario is envisioned where a user practices English phrases about animals for 10 minutes each day.

[0390] This system analyzes progress information and uses natural language processing technology to generate personalized feedback based on the learner's history. For example, the server might process an instruction such as, "Convert the word the user pronounces into text, compare it to the correct pronunciation, and provide visual or auditory feedback on how to correct the pronunciation if there are errors." This allows learners to improve their language skills efficiently at their own pace.

[0391] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0392] Step 1:

[0393] The user selects a learning language and topic using a terminal. The selected information is sent from the terminal to the server. The input is the user's selection information, and the output is the transmission of the selection information to the server.

[0394] Step 2:

[0395] The server extracts the relevant text information for educational materials from the database based on the received topic information and sends it to the terminal. The input is topic information, and the output is text information for educational materials.

[0396] Step 3:

[0397] The user performs audio practice based on the learning materials through the device, and the audio is captured by the device's microphone and sent to the server. The input is the user's pronunciation, and the output is the transmission of audio data to the server.

[0398] Step 4:

[0399] The server uses Google Cloud Speech-to-Text to convert audio data into text data. Furthermore, it compares this text to the original text information and detects errors. The input is the transmitted audio data, and the output is the converted text data and error identification.

[0400] Step 5:

[0401] The server generates feedback for the user based on the error and sends it to the terminal in a visual or auditory way. The input is the error information, and the output is the generation and transmission of feedback to the terminal.

[0402] Step 6:

[0403] The server uses OpenAI DALL-E to generate visual materials related to new terminology and sends them to the terminal. The input is term information, and the output is visual materials. The terminal displays these visual materials to the user.

[0404] Step 7:

[0405] The server uses Deep AI to generate a virtual simulation video and sends it to the terminal. The input is the simulation scenario information, and the output is the generated video. The terminal then plays this simulation video for the user.

[0406] Step 8:

[0407] The server analyzes the learning history and progress information, generates personalized feedback using natural language processing technology, and determines the next learning step. The input is the learning history data, and the output is an updated learning plan.

[0408] 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.

[0409] This invention is a multimodal learning system that integrates speech recognition, image generation, and video generation technologies with an emotion engine that recognizes user emotions. Specific embodiments for carrying out the invention are described below.

[0410] First, the user launches the application on their device and selects the language and topic they want to learn. Based on this selection, an individual learning scenario is initiated.

[0411] The server retrieves appropriate text learning materials from the database based on the user's selection and sends them to the terminal. The terminal is configured to display these materials to the user.

[0412] During voice practice, the device captures the user's voice via its microphone and sends this data to the server in real time. The server uses speech recognition technology to convert the voice into text and compares it with the learning material text to identify pronunciation errors. Feedback is generated and presented to the user through the device. For example, it might guide the user on the correct pronunciation of "business."

[0413] The server also uses image generation technology to create visual materials related to new words and phrases and presents them to the user, thereby assisting with visual learning.

[0414] Furthermore, video generation technology is used to generate virtual simulation videos based on learning scenarios, which are then provided to the user via their device. This allows users to learn how to apply language through practical experience.

[0415] In particular, this system incorporates an emotion engine, which analyzes the user's facial expressions, voice tone, and other factors on the terminal and sends the results to the server.

[0416] The server identifies the user's emotional state based on data obtained by the emotion engine and adjusts the learning experience accordingly. This adjustment includes adjusting feedback and difficulty levels. For example, if the user is feeling frustrated, the system will emphasize positive feedback to boost their motivation.

[0417] Finally, the server analyzes the user's progress data, including emotional data, and dynamically updates the individual learning plan. The updated plan is presented to the user via the device, and new learning goals are set. In this way, the entire system provides a personalized learning experience that responds to the user's emotions and progress.

[0418] The following describes the processing flow.

[0419] Step 1:

[0420] The user launches the application on their device and selects the language and topic they want to learn. This selection is then sent to the server.

[0421] Step 2:

[0422] The server retrieves appropriate text learning materials from the database based on the user's selection and sends them to the terminal. The terminal then displays these text learning materials to the user.

[0423] Step 3:

[0424] The user reads the displayed text aloud. The device records the user's voice and prepares to send the audio data to the server.

[0425] Step 4:

[0426] The server uses speech recognition technology to convert audio data into text. The converted text is compared to the textbook material to identify pronunciation errors.

[0427] Step 5:

[0428] The server generates feedback based on pronunciation errors. This feedback includes instructions for improving pronunciation accuracy. The feedback information is sent to the terminal.

[0429] Step 6:

[0430] The device displays feedback to the user visually and audibly. The user receives the feedback and continues practicing pronunciation.

[0431] Step 7:

[0432] The server identifies new words and phrases from the selected text and uses image generation technology to create related visual materials.

[0433] Step 8:

[0434] The device displays the generated visual materials to the user. These visual materials enhance the user's understanding.

[0435] Step 9:

[0436] The server uses video generation technology to create virtual simulation videos based on scenarios related to the learning topic.

[0437] Step 10:

[0438] The device provides users with generated videos, facilitating a practical learning experience.

[0439] Step 11:

[0440] The device uses its camera and microphone to transmit the user's facial expressions and voice to an emotion engine, which then analyzes the user's emotional state in real time.

[0441] Step 12:

[0442] The server analyzes emotional data obtained by the emotion engine and adjusts the user's learning experience. Specifically, it dynamically changes the tone of feedback and the difficulty level of learning materials according to the user's emotional state.

[0443] Step 13:

[0444] The server analyzes the user's progress and sentiment data and updates their individual learning plan.

[0445] Step 14:

[0446] The device presents the user with an updated learning plan and additional feedback, and provides new learning objectives. Based on this information, the user progresses to the next learning stage.

[0447] (Example 2)

[0448] 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".

[0449] In modern education systems, there is a need for individualized learning support tailored to each learner's level of understanding and emotional state, but traditional methods struggle to provide such individualized support. Furthermore, there is a demand to enhance learning effectiveness by integrating elements such as audio, visuals, and emotion analysis, but there is a lack of technology to efficiently combine these elements.

[0450] 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.

[0451] In this invention, the server includes means for analyzing speech information acquired by speech recognition means and converting the speech information into text information; means for detecting pronunciation errors and generating evaluation information by comparing the converted text information with previously acquired educational material text information; means for automatically generating visual materials related to predetermined terms using visual information generation means; means for generating virtual simulation videos using video generation means; and means for identifying the learner's emotional state using emotion analysis means and adjusting the learning experience based on the state. This provides an individually personalized learning experience and enables a flexible learning environment that responds to the learner's emotions and progress.

[0452] "Speech recognition means" refers to a technology or function that analyzes speech information and converts that information into text information.

[0453] "Text information" refers to string data converted from audio or other sources.

[0454] "Educational material text information" refers to string data prepared as teaching materials to be provided to learners.

[0455] "Evaluation information" refers to feedback and analysis results generated based on speech recognition and analysis of learning progress.

[0456] "Visual information generation means" refers to a technology or function that automatically creates visual materials related to terms or concepts.

[0457] "Motion image generation means" refers to a technology or function for creating virtual simulations or digital videos.

[0458] "Emotional analysis means" refers to a technology or function that identifies an emotional state by analyzing a learner's facial expressions and tone of voice.

[0459] "Learning experience" refers to the process by which learners acquire knowledge and skills through an educational program.

[0460] A "personalized learning experience" is the provision of education that is customized based on the individual needs, progress, and emotional state of each learner.

[0461] This invention is a multimodal education system that provides learners with a personalized learning experience. Its main components are a server, terminals, and users working together. The specific form of this system is described below.

[0462] First, the user launches a dedicated application on their device and begins by selecting a language to learn and a topic. This selection information is then sent from the device to the server. The device uses a standard PC or smart device for this process.

[0463] The server retrieves appropriate educational materials from its database based on information from the user and sends them to the device. These materials include text, visuals, and videos. The server uses a speech recognition engine (e.g., a common cloud-based speech service) to analyze the user's pronunciation. Specifically, it converts the audio information into text and compares it to pre-recorded text materials to detect pronunciation errors. Afterward, it generates evaluation information and returns it to the device as feedback.

[0464] To enhance visual learning, the server utilizes generative AI models (e.g., general-purpose image generation algorithms) to generate visual materials related to terms and concepts. It also leverages video generation technology to create and provide users with videos for virtual simulations, enabling practical experience.

[0465] Furthermore, the device uses sensors and simple emotion analysis software to detect the user's emotional state. This data is sent to a server, where the emotion analysis tool individually tailors the user's learning experience.

[0466] For example, if a user enters the prompt "Provide visual learning materials to help me learn everyday Japanese phrases in a fun way" into the system, the server will generate corresponding text materials and visual resources and deliver them to the user's terminal.

[0467] In this way, the system combines voice, visual, and emotion analysis technologies to provide users with a unique and personalized learning experience. This helps learners achieve their goals efficiently and effectively.

[0468] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0469] Step 1:

[0470] The user launches the application on their device and selects the language and topic they want to learn. The input is the language and topic information selected by the user. Based on this, the device sends this information to the server. The output is the selection information received by the server.

[0471] Step 2:

[0472] The server uses the received language and topic information to search the database for relevant educational materials. The input is user selection information, and the output is extracted as appropriate text information, visual materials, and video data. This data is then sent to the user's terminal.

[0473] Step 3:

[0474] The terminal displays educational materials sent from the server to the user. It receives educational material data from the server as input. As output, text information is displayed on the screen for the user, and visual materials and videos are played.

[0475] Step 4:

[0476] The user begins voice practice. The device's microphone captures the user's pronunciation. The input is the user's spoken audio information. The device sends this to the server, and the audio data is sent to the speech recognition process as output.

[0477] Step 5:

[0478] The server uses speech recognition to convert input speech data into text information. The input is speech data sent from the terminal. This data is analyzed and converted into text information. The output is the converted text information.

[0479] Step 6:

[0480] The server uses a generative AI model to generate visual materials related to new terminology. The input is converted text information, which is used to create the visual materials. The output is the generated visual information, which is then sent to the terminal.

[0481] Step 7:

[0482] The device uses sensors and emotion analysis software to detect the user's emotional state. Input includes the user's facial expressions and voice tone data. This data is analyzed, and information regarding the emotional state is sent to the server as output.

[0483] Step 8:

[0484] The server analyzes emotional state information and learning progress to generate optimal feedback for the user. Emotional state information and learning data are used as input. Based on this information, it generates feedback that adjusts the learning experience. The adjusted feedback is sent to the terminal as output.

[0485] (Application Example 2)

[0486] 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."

[0487] Conventional language learning systems offer limited feedback on learners' pronunciation practice and comprehension, and lack individualized support based on learners' emotions. This results in insufficient motivation and efficient learning support. Therefore, a system that provides a more practical and effective learning experience is needed.

[0488] 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.

[0489] In this invention, the server includes means for analyzing speech information acquired by a speech recognition device and converting the speech information into text information; means for detecting pronunciation errors and generating feedback by comparing the converted text information with previously acquired learning text data; means for automatically generating visual data related to predetermined terms using a visual material generation device; means for generating virtual simulation images using a video generation device; and means for analyzing the learner's emotional state using an emotion analysis device and adjusting the learning content. This enables learners to receive more personalized, emotion-responsive feedback and a learning experience.

[0490] A "speech recognition device" is a technology that analyzes received speech information and converts it into text information.

[0491] "Textual information" refers to digitized text data obtained by analyzing and converting audio information.

[0492] "Learning text data" refers to pre-prepared textual information for learning, used to aid in understanding pronunciation and grammar.

[0493] A "visual material generation device" is a technology that automatically generates visual data related to specific terms or phrases.

[0494] A "video generation device" is a technology that generates video data in order to realize a virtual simulation.

[0495] An "emotion analysis device" is a technology that analyzes a learner's emotional state from information such as facial expressions and voice.

[0496] "Feedback" refers to information provided to learners, such as suggestions, evaluations, and areas for improvement regarding pronunciation and comprehension.

[0497] A "personalized learning experience" refers to an educational experience that is tailored and delivered according to the individual characteristics and emotional state of the learner.

[0498] This invention provides an educational tool that integrates speech recognition and sentiment analysis technologies as a system to support learners' language learning. Learners can select a target language and topic using a terminal and begin learning on the system.

[0499] The server uses a speech recognition device to convert speech information acquired from the microphone into text. This information is compared with pre-prepared training text data to detect pronunciation errors. Based on the detected errors, feedback is generated and presented to the learner. In addition, a visual material generation device automatically generates visual materials that match the specified terms and displays them to the learner through the terminal's display.

[0500] Furthermore, the server uses a video generation device to generate virtual simulation images, providing a practical experience. This process utilizes a generative AI model to depict specific scenes and situations that learners should be taught.

[0501] In addition, an emotion analysis device uses data from the device's camera and microphone to analyze the learner's emotional state. Based on this emotional state, the server adjusts the learning content and provides feedback and learning tasks that match the learner's emotions. This personalized learning experience is expected to enable learners to learn more effectively.

[0502] As a concrete example, the server sends a prompt message to the AI ​​model saying, "Please suggest images and videos that can be generated to learn English words and actions related to animals," and the results are displayed on the terminal. In this way, an effective learning environment is realized through the cooperation of the server, terminal, and user.

[0503] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0504] Step 1:

[0505] The user selects the target language and topic on their device. This input information is sent to the server, and a learning scenario is constructed as output. The server retrieves the corresponding learning text data from the database and prepares it for display on the device.

[0506] Step 2:

[0507] The user provides voice input through the device. The device uses a microphone to acquire voice information and sends it to the server. The server uses a speech recognition device to convert the voice information into text. This converted text information forms the basis for the next step.

[0508] Step 3:

[0509] The server compares the text information with pre-prepared training text data. During the comparison process, it detects differences from the correct pronunciation and generates feedback. This feedback is then presented to the user via the terminal.

[0510] Step 4:

[0511] The server uses a visual material generation device to generate visual materials related to specified terms. Appropriate images and illustrations are created to facilitate learning for the user, and these are displayed to the user via the terminal.

[0512] Step 5:

[0513] The server uses a video generation device to generate virtual simulation videos. In this generation process, a generation AI model is used to create prompt messages and visualize specific scenes and situations. The videos are then presented to the user via a terminal.

[0514] Step 6:

[0515] The device captures the user's facial expressions and voice tone using its camera and microphone, and sends this data to a server. The server analyzes the user's emotional state through an emotion analysis device and provides feedback and adjusts learning tasks accordingly.

[0516] Step 7:

[0517] The server dynamically updates individual learning programs based on collected progress information and sentiment data. The updated learning plan is presented to the user via the terminal, and the next learning step is suggested.

[0518] 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.

[0519] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0520] 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.

[0521] [Third Embodiment]

[0522] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0523] 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.

[0524] 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).

[0525] 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.

[0526] 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.

[0527] 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).

[0528] 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.

[0529] 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.

[0530] 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.

[0531] 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.

[0532] 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.

[0533] 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".

[0534] This invention is a multimodal learning system that integrates speech recognition, image generation, and video generation technologies to improve the language learning experience of learners. Specific embodiments for carrying out the invention are described below.

[0535] First, the user selects the language and topic they want to learn through an application installed on their device. This initiates a personalized learning path tailored to the learner's interests and goals.

[0536] Next, the server pulls appropriate learning materials from the database based on the selected topic and sends them to the terminal. These might include business English email templates or example sentences for everyday conversation. The terminal then displays them in a user-friendly format.

[0537] When a user practices speaking, the device uses its microphone to record the user's voice and sends it to the server in real time. The server uses speech recognition technology to convert this voice into text and compares the acquired text data with the original learning material to identify errors in pronunciation and intonation. This allows the user to receive clear feedback on where their pronunciation needs to be corrected. For example, if the user mispronounces "business" as "buisness," the correct pronunciation can be shown visually and audibly. This feedback information is provided to the user through the device.

[0538] Furthermore, to visually support learning, the server uses image generation AI to automatically generate visual materials related to new words and phrases. For example, if the word "dog" is included in the learning materials, it generates various images of dogs and presents them to the user through the device, thereby reinforcing the association between visuals and language.

[0539] Furthermore, the server uses video generation AI to create simulation videos that allow users to virtually experience educational and practical scenarios. For example, these videos might simulate meetings in English or customer service situations. The terminal displays these videos, helping users to gain an immersive learning experience.

[0540] Ultimately, the server periodically collects and analyzes learner progress data, dynamically updating individual learning plans using natural language processing technology. Based on this analysis, it identifies the user's learning tendencies and areas for improvement, and suggests the next steps in their learning. The device provides this personalized feedback to the user, supporting them in efficiently developing their skills.

[0541] In this way, the system provides learners with an interactive and multifaceted learning experience, promoting effective language acquisition tailored to individual needs.

[0542] The following describes the processing flow.

[0543] Step 1:

[0544] The user launches the application on their device and selects the language and topic they want to learn. The user's selection is sent to the server.

[0545] Step 2:

[0546] The server searches the database for relevant text learning materials based on the user's selection and sends the corresponding data to the terminal. For example, it might provide examples of business English conversations.

[0547] Step 3:

[0548] The device displays acquired text learning materials to the user and provides an interface to encourage reading practice. The user reads the displayed text aloud into the microphone.

[0549] Step 4:

[0550] The device records the user's voice and sends the audio data to the server. The audio data is processed in real time.

[0551] Step 5:

[0552] The server uses speech recognition technology to convert the audio data into text. It then compares the converted text to the original text material to detect pronunciation errors. For example, if "business" is pronounced as "buisness," the server will point out the error.

[0553] Step 6:

[0554] The server generates pronunciation feedback based on the detected errors. This feedback includes areas for improvement and examples of correct pronunciation. The feedback information is sent to the terminal.

[0555] Step 7:

[0556] The device displays feedback to the user and presents solutions for improvement visually and audibly. Based on the feedback, the user continues practicing pronunciation.

[0557] Step 8:

[0558] The server uses image generation technology to generate visual material related to new words and phrases contained in the text. For example, it generates images of dog breeds for the word "dog".

[0559] Step 9:

[0560] The device provides the user with generated images to assist in visual language comprehension. The user enhances the association between visuals and text.

[0561] Step 10:

[0562] The server uses video generation technology to generate simulation videos according to the specified learning scenario. For example, it can create a video of a meeting scene.

[0563] Step 11:

[0564] The device plays the generated video for the user, providing a practical experience. By watching the video, the user learns how to apply the language.

[0565] Step 12:

[0566] The server collects user progress data and analyzes learning history using natural language processing techniques. It then updates individual learning plans and determines the next steps.

[0567] Step 13:

[0568] The device presents the user with updated learning plans and feedback, and indicates the next learning objectives. The user continues learning based on the information provided.

[0569] (Example 1)

[0570] 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."

[0571] In recent years, there has been a growing demand for diverse methods of language learning, but traditional teaching methods present challenges in effectively enabling learners to acquire practical language skills. Furthermore, there is a lack of adequate feedback tailored to individual learning paces and insufficient visualization of progress, resulting in a lack of means to maintain learner motivation.

[0572] 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.

[0573] In this invention, the server includes a device that analyzes speech information acquired by a speech recognition device and converts the speech information into document information; a device that detects pronunciation errors and generates a response by comparing the converted document information with previously acquired educational document information; and a device that automatically generates visual materials related to predetermined vocabulary using a visual information generation device. This enables learners to improve their pronunciation and effectively promotes language learning through visual stimuli.

[0574] A "speech recognition device" is a device that analyzes acquired speech information and converts it into document information.

[0575] "Document information" refers to text data that has been converted from audio information by a speech recognition device.

[0576] "Educational document information" refers to text data acquired in advance for use as learning reference.

[0577] A "visual information generation device" is a device equipped with the function of automatically generating visual materials related to a given vocabulary.

[0578] "Response" refers to feedback information generated based on the detection of pronunciation errors.

[0579] "Virtual experience video" refers to video data generated by a video generation device to facilitate simulations and practical experiences.

[0580] An "individualized learning plan" is a plan for determining the next learning stage, which is dynamically updated based on the analysis of the learner's progress.

[0581] A "natural language processing device" is a device that analyzes information, including learning history, and provides personalized responses to users.

[0582] This invention is a system for providing learners with an interactive language learning experience. The system integrates multimodal technology, utilizing speech recognition, image generation, and video generation to aid learning. Specifically, it uses a speech recognition device, a visual information generation device, and a video generation device to analyze user input and provide appropriate feedback and learning materials.

[0583] First, the user selects the language and topic they wish to learn using the corresponding input device. Based on this selection, the system retrieves appropriate educational document information from its database. For example, information tailored to different topics such as everyday conversation or business English is provided.

[0584] Next, the terminal uses a display device to show the text selected by the user. When the user practices pronunciation using the voice input function, the terminal captures the voice and sends the voice information to the server. The server analyzes this voice information using a speech recognition device, converts it into document information, and compares it with educational document information. This allows the user to receive accurate pronunciation feedback.

[0585] Furthermore, the server uses a visual information generation device to generate visual materials related to new vocabulary. These visual materials are displayed as images on the terminal's screen, providing the user with visual learning. For example, for the word "dog," various images of dogs are generated and presented. In addition, virtual experience videos generated using a video generation device are sent to the terminal, providing videos that simulate situations such as "ordering at a restaurant."

[0586] Ultimately, the server utilizes a natural language processing unit to analyze the user's progress and adjust the individual learning plan. By dynamically determining and providing the next steps based on progress information and the user's learning history, a more personalized learning experience is achieved.

[0587] An example of a prompt is, "Generate a simulated video of ordering at a restaurant." This system allows users to effectively improve their language skills.

[0588] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0589] Step 1:

[0590] The user launches the application on their terminal and selects the language and topic they wish to learn. As input, the user communicates their desired selections to the system via the interface. This selection guides the database search and is sent as a request to the server. As output, data related to the user's desired topic is requested from the server.

[0591] Step 2:

[0592] The server searches the database for relevant educational document information based on the user's selection. The input is a request from the user, and the server extracts text data related to the topic. The server then sends this data to the terminal, providing the user with educational materials as output.

[0593] Step 3:

[0594] The terminal displays text data received from the server. The input consists of educational document information from the server, preparing the user to begin visual learning. The output is text information displayed on the terminal in a user-friendly format.

[0595] Step 4:

[0596] The user uses the device's microphone function to practice pronunciation of selected learning materials via voice input. The input is an audio signal, which the device records as digital audio information. The recorded audio information is sent to the server as output.

[0597] Step 5:

[0598] The server uses a speech recognition device to analyze speech information and convert it into document information. The input is the user's speech information, which is converted into text using speech recognition technology. The resulting document information is then compared with educational document information.

[0599] Step 6:

[0600] The server identifies pronunciation errors and generates feedback by comparing the converted document information with the educational document information. The input consists of the converted document information and the educational document information, and the identified errors are sent to the terminal as feedback information. The output is feedback that includes specific correction suggestions.

[0601] Step 7:

[0602] The terminal presents the user with feedback information from the server, both visually and audibly. The input is feedback data received from the server, clearly indicating to the user which parts of the pronunciation need correction. The output includes visual highlighting and audio guidance for correct pronunciation.

[0603] Step 8:

[0604] The server uses a generative AI model to generate visual materials related to new vocabulary. The input is vocabulary contained in educational document information, and the visual information generation device outputs this as image data. The output image is sent to the terminal.

[0605] Step 9:

[0606] The terminal presents image data from the server to the user, aiming to associate vocabulary with visual information. The input is image data sent from the server, and visual presentation is used to facilitate the user's language learning. The output is the associated image displayed on the terminal's screen.

[0607] Step 10:

[0608] The server uses a video generation device to generate virtual experience videos related to the selected topic. The input consists of educational document information and the user's learning topic, and the generated video simulates the user's experience. The output is video data including detailed simulations.

[0609] Step 11:

[0610] The device plays video data from the server, providing the user with an immersive learning experience. The input is video data transmitted from the server, and videos are played to allow the user to gain practical experience. The output is a video displayed on the screen, intended to deepen the user's understanding through viewing.

[0611] Step 12:

[0612] The server utilizes a natural language processing unit to analyze the user's learning history and progress, and adjusts the individual learning plan accordingly. The input is the user's learning history and progress, and the dynamically updated plan guides the next learning step. As output, the adjusted learning plan is sent to the terminal and presented to the user.

[0613] (Application Example 1)

[0614] 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."

[0615] In recent years, there has been a growing demand for interactive and efficient language learning experiences. However, current systems often lack sufficient individualized support and real-time feedback for learners. Furthermore, there is a lack of technology that can provide learners with opportunities to acquire a language naturally at home. Against this backdrop, there are technical challenges in realizing flexible and intuitive learning support.

[0616] 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.

[0617] In this invention, the server includes means for analyzing audio information acquired by speech recognition means and converting the audio information into text information; means for detecting pronunciation errors and generating feedback by comparing the converted text information with previously acquired text information for teaching materials; and means for automatically generating visual materials related to predetermined terms using image generation means. This enables learners to effectively acquire a language at home and facilitates interactive and personalized language learning.

[0618] "Speech recognition means" refers to technology that analyzes speech information and converts it into text information.

[0619] "Textual information" refers to information represented by digital strings converted through speech recognition.

[0620] "Educational material text information" refers to text data that has been prepared in advance for use in learning.

[0621] "Feedback" is information that informs the user of pronunciation errors based on comparison results.

[0622] "Image generation means" refers to a technology that automatically creates visual materials related to a given term.

[0623] "Terminology" refers to words and phrases used in language learning.

[0624] "Visual material" refers to images presented to learners as visual information.

[0625] "Video generation method" refers to technology that automatically creates simulated videos.

[0626] "Interactive" refers to a dynamic relationship in which the user and the system exchange information with each other.

[0627] "Language learning experience" refers to all activities related to language acquisition, encompassing the process by which learners acquire a language.

[0628] "Progress information" refers to records of learners' learning status and achievements.

[0629] An "individualized learning plan" is a learning process that is customized according to the learner's needs.

[0630] A "language learning partner" is a robot or device that assists learners in acquiring a language.

[0631] "Natural language processing technology" refers to methods that enable computers to understand and process human language.

[0632] "Real-time feedback" refers to corrections and advice provided immediately during the learning process.

[0633] This invention is a system to support language learning, allowing users to gain a learning experience at home. The system integrates speech recognition, image generation, and video generation technologies.

[0634] First, users can select what they want to learn. They choose a language and topic of interest through their device and begin learning.

[0635] Next, the server provides the terminal with relevant learning materials based on the user's selection. Based on these materials, the user can practice speaking. The terminal's microphone captures the user's pronunciation and sends it to the server. The server uses a speech recognition program (e.g., Google Cloud Speech-to-Text) to convert this speech into text and compares it with the text information of the learning materials.

[0636] If a learner makes a pronunciation error, the server identifies the error and generates real-time feedback. This feedback visually or audibly demonstrates the correct pronunciation. In this way, users can immediately correct their pronunciation in their daily learning.

[0637] Furthermore, the server uses image generation AI (e.g., OpenAI DALL-E) to create visual materials relevant to learning. This makes it easier for learners to associate terms with images. In addition, video generation AI (e.g., DeepAI) generates virtual simulation videos, allowing users to visually experience practical scenarios.

[0638] Robots and smart devices function as home learning partners, enhancing learning effectiveness by providing users with conversation practice and interactive quizzes. Specifically, a scenario is envisioned where a user practices English phrases about animals for 10 minutes each day.

[0639] This system analyzes progress information and uses natural language processing technology to generate personalized feedback based on the learner's history. For example, the server might process an instruction such as, "Convert the word the user pronounces into text, compare it to the correct pronunciation, and provide visual or auditory feedback on how to correct the pronunciation if there are errors." This allows learners to improve their language skills efficiently at their own pace.

[0640] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0641] Step 1:

[0642] The user selects a learning language and topic using a terminal. The selected information is sent from the terminal to the server. The input is the user's selection information, and the output is the transmission of the selection information to the server.

[0643] Step 2:

[0644] The server extracts the relevant text information for educational materials from the database based on the received topic information and sends it to the terminal. The input is topic information, and the output is text information for educational materials.

[0645] Step 3:

[0646] The user performs audio practice based on the learning materials through the device, and the audio is captured by the device's microphone and sent to the server. The input is the user's pronunciation, and the output is the transmission of audio data to the server.

[0647] Step 4:

[0648] The server uses Google Cloud Speech-to-Text to convert audio data into text data. Furthermore, it compares this text to the original text information and detects errors. The input is the transmitted audio data, and the output is the converted text data and error identification.

[0649] Step 5:

[0650] The server generates feedback for the user based on the error and sends it to the terminal in a visual or auditory way. The input is the error information, and the output is the generation and transmission of feedback to the terminal.

[0651] Step 6:

[0652] The server uses OpenAI DALL-E to generate visual materials related to new terminology and sends them to the terminal. The input is term information, and the output is visual materials. The terminal displays these visual materials to the user.

[0653] Step 7:

[0654] The server uses Deep AI to generate a virtual simulation video and sends it to the terminal. The input is the simulation scenario information, and the output is the generated video. The terminal then plays this simulation video for the user.

[0655] Step 8:

[0656] The server analyzes the learning history and progress information, generates personalized feedback using natural language processing technology, and determines the next learning step. The input is the learning history data, and the output is an updated learning plan.

[0657] 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.

[0658] This invention is a multimodal learning system that integrates speech recognition, image generation, and video generation technologies with an emotion engine that recognizes user emotions. Specific embodiments for carrying out the invention are described below.

[0659] First, the user launches the application on their device and selects the language and topic they want to learn. Based on this selection, an individual learning scenario is initiated.

[0660] The server retrieves appropriate text learning materials from the database based on the user's selection and sends them to the terminal. The terminal is configured to display these materials to the user.

[0661] During voice practice, the device captures the user's voice via its microphone and sends this data to the server in real time. The server uses speech recognition technology to convert the voice into text and compares it with the learning material text to identify pronunciation errors. Feedback is generated and presented to the user through the device. For example, it might guide the user on the correct pronunciation of "business."

[0662] The server also uses image generation technology to create visual materials related to new words and phrases and presents them to the user, thereby assisting with visual learning.

[0663] Furthermore, video generation technology is used to generate virtual simulation videos based on learning scenarios, which are then provided to the user via their device. This allows users to learn how to apply language through practical experience.

[0664] In particular, this system incorporates an emotion engine, which analyzes the user's facial expressions, voice tone, and other factors on the terminal and sends the results to the server.

[0665] The server identifies the user's emotional state based on data obtained by the emotion engine and adjusts the learning experience accordingly. This adjustment includes adjusting feedback and difficulty levels. For example, if the user is feeling frustrated, the system will emphasize positive feedback to boost their motivation.

[0666] Finally, the server analyzes the user's progress data, including emotional data, and dynamically updates the individual learning plan. The updated plan is presented to the user via the device, and new learning goals are set. In this way, the entire system provides a personalized learning experience that responds to the user's emotions and progress.

[0667] The following describes the processing flow.

[0668] Step 1:

[0669] The user launches the application on their device and selects the language and topic they want to learn. This selection is then sent to the server.

[0670] Step 2:

[0671] The server retrieves appropriate text learning materials from the database based on the user's selection and sends them to the terminal. The terminal then displays these text learning materials to the user.

[0672] Step 3:

[0673] The user reads the displayed text aloud. The device records the user's voice and prepares to send the audio data to the server.

[0674] Step 4:

[0675] The server uses speech recognition technology to convert audio data into text. The converted text is compared to the textbook material to identify pronunciation errors.

[0676] Step 5:

[0677] The server generates feedback based on pronunciation errors. This feedback includes instructions for improving pronunciation accuracy. The feedback information is sent to the terminal.

[0678] Step 6:

[0679] The device displays feedback to the user visually and audibly. The user receives the feedback and continues practicing pronunciation.

[0680] Step 7:

[0681] The server identifies new words and phrases from the selected text and uses image generation technology to create related visual materials.

[0682] Step 8:

[0683] The device displays the generated visual materials to the user. These visual materials enhance the user's understanding.

[0684] Step 9:

[0685] The server uses video generation technology to create virtual simulation videos based on scenarios related to the learning topic.

[0686] Step 10:

[0687] The device provides users with generated videos, facilitating a practical learning experience.

[0688] Step 11:

[0689] The device uses its camera and microphone to transmit the user's facial expressions and voice to an emotion engine, which then analyzes the user's emotional state in real time.

[0690] Step 12:

[0691] The server analyzes emotional data obtained by the emotion engine and adjusts the user's learning experience. Specifically, it dynamically changes the tone of feedback and the difficulty level of learning materials according to the user's emotional state.

[0692] Step 13:

[0693] The server analyzes the user's progress and sentiment data and updates their individual learning plan.

[0694] Step 14:

[0695] The device presents the user with an updated learning plan and additional feedback, and provides new learning objectives. Based on this information, the user progresses to the next learning stage.

[0696] (Example 2)

[0697] 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."

[0698] In modern education systems, there is a need for individualized learning support tailored to each learner's level of understanding and emotional state, but traditional methods struggle to provide such individualized support. Furthermore, there is a demand to enhance learning effectiveness by integrating elements such as audio, visuals, and emotion analysis, but there is a lack of technology to efficiently combine these elements.

[0699] 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.

[0700] In this invention, the server includes means for analyzing speech information acquired by speech recognition means and converting the speech information into text information; means for detecting pronunciation errors and generating evaluation information by comparing the converted text information with previously acquired educational material text information; means for automatically generating visual materials related to predetermined terms using visual information generation means; means for generating virtual simulation videos using video generation means; and means for identifying the learner's emotional state using emotion analysis means and adjusting the learning experience based on the state. This provides an individually personalized learning experience and enables a flexible learning environment that responds to the learner's emotions and progress.

[0701] "Speech recognition means" refers to a technology or function that analyzes speech information and converts that information into text information.

[0702] "Text information" refers to string data converted from audio or other sources.

[0703] "Educational material text information" refers to string data prepared as teaching materials to be provided to learners.

[0704] "Evaluation information" refers to feedback and analysis results generated based on speech recognition and analysis of learning progress.

[0705] "Visual information generation means" refers to a technology or function that automatically creates visual materials related to terms or concepts.

[0706] "Motion image generation means" refers to a technology or function for creating virtual simulations or digital videos.

[0707] "Emotional analysis means" refers to a technology or function that identifies an emotional state by analyzing a learner's facial expressions and tone of voice.

[0708] "Learning experience" refers to the process by which learners acquire knowledge and skills through an educational program.

[0709] A "personalized learning experience" is the provision of education that is customized based on the individual needs, progress, and emotional state of each learner.

[0710] This invention is a multimodal education system that provides learners with a personalized learning experience. Its main components are a server, terminals, and users working together. The specific form of this system is described below.

[0711] First, the user launches a dedicated application on their device and begins by selecting a language to learn and a topic. This selection information is then sent from the device to the server. The device uses a standard PC or smart device for this process.

[0712] The server retrieves appropriate educational materials from its database based on information from the user and sends them to the device. These materials include text, visuals, and videos. The server uses a speech recognition engine (e.g., a common cloud-based speech service) to analyze the user's pronunciation. Specifically, it converts the audio information into text and compares it to pre-recorded text materials to detect pronunciation errors. Afterward, it generates evaluation information and returns it to the device as feedback.

[0713] To enhance visual learning, the server utilizes generative AI models (e.g., general-purpose image generation algorithms) to generate visual materials related to terms and concepts. It also leverages video generation technology to create and provide users with videos for virtual simulations, enabling practical experience.

[0714] Furthermore, the device uses sensors and simple emotion analysis software to detect the user's emotional state. This data is sent to a server, where the emotion analysis tool individually tailors the user's learning experience.

[0715] For example, if a user enters the prompt "Provide visual learning materials to help me learn everyday Japanese phrases in a fun way" into the system, the server will generate corresponding text materials and visual resources and deliver them to the user's terminal.

[0716] In this way, the system combines voice, visual, and emotion analysis technologies to provide users with a unique and personalized learning experience. This helps learners achieve their goals efficiently and effectively.

[0717] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0718] Step 1:

[0719] The user launches the application on their device and selects the language and topic they want to learn. The input is the language and topic information selected by the user. Based on this, the device sends this information to the server. The output is the selection information received by the server.

[0720] Step 2:

[0721] The server uses the received language and topic information to search the database for relevant educational materials. The input is user selection information, and the output is extracted as appropriate text information, visual materials, and video data. This data is then sent to the user's terminal.

[0722] Step 3:

[0723] The terminal displays educational materials sent from the server to the user. It receives educational material data from the server as input. As output, text information is displayed on the screen for the user, and visual materials and videos are played.

[0724] Step 4:

[0725] The user begins voice practice. The device's microphone captures the user's pronunciation. The input is the user's spoken audio information. The device sends this to the server, and the audio data is sent to the speech recognition process as output.

[0726] Step 5:

[0727] The server uses speech recognition to convert input speech data into text information. The input is speech data sent from the terminal. This data is analyzed and converted into text information. The output is the converted text information.

[0728] Step 6:

[0729] The server uses a generative AI model to generate visual materials related to new terminology. The input is converted text information, which is used to create the visual materials. The output is the generated visual information, which is then sent to the terminal.

[0730] Step 7:

[0731] The device uses sensors and emotion analysis software to detect the user's emotional state. Input includes the user's facial expressions and voice tone data. This data is analyzed, and information regarding the emotional state is sent to the server as output.

[0732] Step 8:

[0733] The server analyzes emotional state information and learning progress to generate optimal feedback for the user. Emotional state information and learning data are used as input. Based on this information, it generates feedback that adjusts the learning experience. The adjusted feedback is sent to the terminal as output.

[0734] (Application Example 2)

[0735] 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."

[0736] Conventional language learning systems offer limited feedback on learners' pronunciation practice and comprehension, and lack individualized support based on learners' emotions. This results in insufficient motivation and efficient learning support. Therefore, a system that provides a more practical and effective learning experience is needed.

[0737] 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.

[0738] In this invention, the server includes means for analyzing speech information acquired by a speech recognition device and converting the speech information into text information; means for detecting pronunciation errors and generating feedback by comparing the converted text information with previously acquired learning text data; means for automatically generating visual data related to predetermined terms using a visual material generation device; means for generating virtual simulation images using a video generation device; and means for analyzing the learner's emotional state using an emotion analysis device and adjusting the learning content. This enables learners to receive more personalized, emotion-responsive feedback and a learning experience.

[0739] A "speech recognition device" is a technology that analyzes received speech information and converts it into text information.

[0740] "Textual information" refers to digitized text data obtained by analyzing and converting audio information.

[0741] "Learning text data" refers to pre-prepared textual information for learning, used to aid in understanding pronunciation and grammar.

[0742] A "visual material generation device" is a technology that automatically generates visual data related to specific terms or phrases.

[0743] A "video generation device" is a technology that generates video data in order to realize a virtual simulation.

[0744] An "emotion analysis device" is a technology that analyzes a learner's emotional state from information such as facial expressions and voice.

[0745] "Feedback" refers to information provided to learners, such as suggestions, evaluations, and areas for improvement regarding pronunciation and comprehension.

[0746] A "personalized learning experience" refers to an educational experience that is tailored and delivered according to the individual characteristics and emotional state of the learner.

[0747] This invention provides an educational tool that integrates speech recognition and sentiment analysis technologies as a system to support learners' language learning. Learners can select a target language and topic using a terminal and begin learning on the system.

[0748] The server uses a speech recognition device to convert speech information acquired from the microphone into text. This information is compared with pre-prepared training text data to detect pronunciation errors. Based on the detected errors, feedback is generated and presented to the learner. In addition, a visual material generation device automatically generates visual materials that match the specified terms and displays them to the learner through the terminal's display.

[0749] Furthermore, the server uses a video generation device to generate virtual simulation images, providing a practical experience. This process utilizes a generative AI model to depict specific scenes and situations that learners should be taught.

[0750] In addition, an emotion analysis device uses data from the device's camera and microphone to analyze the learner's emotional state. Based on this emotional state, the server adjusts the learning content and provides feedback and learning tasks that match the learner's emotions. This personalized learning experience is expected to enable learners to learn more effectively.

[0751] As a concrete example, the server sends a prompt message to the AI ​​model saying, "Please suggest images and videos that can be generated to learn English words and actions related to animals," and the results are displayed on the terminal. In this way, an effective learning environment is realized through the cooperation of the server, terminal, and user.

[0752] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0753] Step 1:

[0754] The user selects the target language and topic on their device. This input information is sent to the server, and a learning scenario is constructed as output. The server retrieves the corresponding learning text data from the database and prepares it for display on the device.

[0755] Step 2:

[0756] The user provides voice input through the device. The device uses a microphone to acquire voice information and sends it to the server. The server uses a speech recognition device to convert the voice information into text. This converted text information forms the basis for the next step.

[0757] Step 3:

[0758] The server compares the text information with pre-prepared training text data. During the comparison process, it detects differences from the correct pronunciation and generates feedback. This feedback is then presented to the user via the terminal.

[0759] Step 4:

[0760] The server uses a visual material generation device to generate visual materials related to specified terms. Appropriate images and illustrations are created to facilitate learning for the user, and these are displayed to the user via the terminal.

[0761] Step 5:

[0762] The server uses a video generation device to generate virtual simulation videos. In this generation process, a generation AI model is used to create prompt messages and visualize specific scenes and situations. The videos are then presented to the user via a terminal.

[0763] Step 6:

[0764] The device captures the user's facial expressions and voice tone using its camera and microphone, and sends this data to a server. The server analyzes the user's emotional state through an emotion analysis device and provides feedback and adjusts learning tasks accordingly.

[0765] Step 7:

[0766] The server dynamically updates individual learning programs based on collected progress information and sentiment data. The updated learning plan is presented to the user via the terminal, and the next learning step is suggested.

[0767] 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.

[0768] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0769] 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.

[0770] [Fourth Embodiment]

[0771] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0772] 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.

[0773] 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).

[0774] 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.

[0775] 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.

[0776] 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).

[0777] 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.

[0778] 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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".

[0784] This invention is a multimodal learning system that integrates speech recognition, image generation, and video generation technologies to improve the language learning experience of learners. Specific embodiments for carrying out the invention are described below.

[0785] First, the user selects the language and topic they want to learn through an application installed on their device. This initiates a personalized learning path tailored to the learner's interests and goals.

[0786] Next, the server pulls appropriate learning materials from the database based on the selected topic and sends them to the terminal. These might include business English email templates or example sentences for everyday conversation. The terminal then displays them in a user-friendly format.

[0787] When a user practices speaking, the device uses its microphone to record the user's voice and sends it to the server in real time. The server uses speech recognition technology to convert this voice into text and compares the acquired text data with the original learning material to identify errors in pronunciation and intonation. This allows the user to receive clear feedback on where their pronunciation needs to be corrected. For example, if the user mispronounces "business" as "buisness," the correct pronunciation can be shown visually and audibly. This feedback information is provided to the user through the device.

[0788] Furthermore, to visually support learning, the server uses image generation AI to automatically generate visual materials related to new words and phrases. For example, if the word "dog" is included in the learning materials, it generates various images of dogs and presents them to the user through the device, thereby reinforcing the association between visuals and language.

[0789] Furthermore, the server uses video generation AI to create simulation videos that allow users to virtually experience educational and practical scenarios. For example, these videos might simulate meetings in English or customer service situations. The terminal displays these videos, helping users to gain an immersive learning experience.

[0790] Ultimately, the server periodically collects and analyzes learner progress data, dynamically updating individual learning plans using natural language processing technology. Based on this analysis, it identifies the user's learning tendencies and areas for improvement, and suggests the next steps in their learning. The device provides this personalized feedback to the user, supporting them in efficiently developing their skills.

[0791] In this way, the system provides learners with an interactive and multifaceted learning experience, promoting effective language acquisition tailored to individual needs.

[0792] The following describes the processing flow.

[0793] Step 1:

[0794] The user launches the application on their device and selects the language and topic they want to learn. The user's selection is sent to the server.

[0795] Step 2:

[0796] The server searches the database for relevant text learning materials based on the user's selection and sends the corresponding data to the terminal. For example, it might provide examples of business English conversations.

[0797] Step 3:

[0798] The device displays acquired text learning materials to the user and provides an interface to encourage reading practice. The user reads the displayed text aloud into the microphone.

[0799] Step 4:

[0800] The device records the user's voice and sends the audio data to the server. The audio data is processed in real time.

[0801] Step 5:

[0802] The server uses speech recognition technology to convert the audio data into text. It then compares the converted text to the original text material to detect pronunciation errors. For example, if "business" is pronounced as "buisness," the server will point out the error.

[0803] Step 6:

[0804] The server generates pronunciation feedback based on the detected errors. This feedback includes areas for improvement and examples of correct pronunciation. The feedback information is sent to the terminal.

[0805] Step 7:

[0806] The device displays feedback to the user and presents solutions for improvement visually and audibly. Based on the feedback, the user continues practicing pronunciation.

[0807] Step 8:

[0808] The server uses image generation technology to generate visual material related to new words and phrases contained in the text. For example, it generates images of dog breeds for the word "dog".

[0809] Step 9:

[0810] The device provides the user with generated images to assist in visual language comprehension. The user enhances the association between visuals and text.

[0811] Step 10:

[0812] The server uses video generation technology to generate simulation videos according to the specified learning scenario. For example, it can create a video of a meeting scene.

[0813] Step 11:

[0814] The device plays the generated video for the user, providing a practical experience. By watching the video, the user learns how to apply the language.

[0815] Step 12:

[0816] The server collects user progress data and analyzes learning history using natural language processing techniques. It then updates individual learning plans and determines the next steps.

[0817] Step 13:

[0818] The device presents the user with updated learning plans and feedback, and indicates the next learning objectives. The user continues learning based on the information provided.

[0819] (Example 1)

[0820] 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".

[0821] In recent years, there has been a growing demand for diverse methods of language learning, but traditional teaching methods present challenges in effectively enabling learners to acquire practical language skills. Furthermore, there is a lack of adequate feedback tailored to individual learning paces and insufficient visualization of progress, resulting in a lack of means to maintain learner motivation.

[0822] 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.

[0823] In this invention, the server includes a device that analyzes speech information acquired by a speech recognition device and converts the speech information into document information; a device that detects pronunciation errors and generates a response by comparing the converted document information with previously acquired educational document information; and a device that automatically generates visual materials related to predetermined vocabulary using a visual information generation device. This enables learners to improve their pronunciation and effectively promotes language learning through visual stimuli.

[0824] A "speech recognition device" is a device that analyzes acquired speech information and converts it into document information.

[0825] "Document information" refers to text data that has been converted from audio information by a speech recognition device.

[0826] "Educational document information" refers to text data acquired in advance for use as learning reference.

[0827] A "visual information generation device" is a device equipped with the function of automatically generating visual materials related to a given vocabulary.

[0828] "Response" refers to feedback information generated based on the detection of pronunciation errors.

[0829] "Virtual experience video" refers to video data generated by a video generation device to facilitate simulations and practical experiences.

[0830] An "individualized learning plan" is a plan for determining the next learning stage, which is dynamically updated based on the analysis of the learner's progress.

[0831] A "natural language processing device" is a device that analyzes information, including learning history, and provides personalized responses to users.

[0832] This invention is a system for providing learners with an interactive language learning experience. The system integrates multimodal technology, utilizing speech recognition, image generation, and video generation to aid learning. Specifically, it uses a speech recognition device, a visual information generation device, and a video generation device to analyze user input and provide appropriate feedback and learning materials.

[0833] First, the user selects the language and topic they wish to learn using the corresponding input device. Based on this selection, the system retrieves appropriate educational document information from its database. For example, information tailored to different topics such as everyday conversation or business English is provided.

[0834] Next, the terminal uses a display device to show the text selected by the user. When the user practices pronunciation using the voice input function, the terminal captures the voice and sends the voice information to the server. The server analyzes this voice information using a speech recognition device, converts it into document information, and compares it with educational document information. This allows the user to receive accurate pronunciation feedback.

[0835] Furthermore, the server uses a visual information generation device to generate visual materials related to new vocabulary. These visual materials are displayed as images on the terminal's screen, providing the user with visual learning. For example, for the word "dog," various images of dogs are generated and presented. In addition, virtual experience videos generated using a video generation device are sent to the terminal, providing videos that simulate situations such as "ordering at a restaurant."

[0836] Ultimately, the server utilizes a natural language processing unit to analyze the user's progress and adjust the individual learning plan. By dynamically determining and providing the next steps based on progress information and the user's learning history, a more personalized learning experience is achieved.

[0837] An example of a prompt is, "Generate a simulated video of ordering at a restaurant." This system allows users to effectively improve their language skills.

[0838] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0839] Step 1:

[0840] The user launches the application on their terminal and selects the language and topic they wish to learn. As input, the user communicates their desired selections to the system via the interface. This selection guides the database search and is sent as a request to the server. As output, data related to the user's desired topic is requested from the server.

[0841] Step 2:

[0842] The server searches the database for relevant educational document information based on the user's selection. The input is a request from the user, and the server extracts text data related to the topic. The server then sends this data to the terminal, providing the user with educational materials as output.

[0843] Step 3:

[0844] The terminal displays text data received from the server. The input consists of educational document information from the server, preparing the user to begin visual learning. The output is text information displayed on the terminal in a user-friendly format.

[0845] Step 4:

[0846] The user uses the device's microphone function to practice pronunciation of selected learning materials via voice input. The input is an audio signal, which the device records as digital audio information. The recorded audio information is sent to the server as output.

[0847] Step 5:

[0848] The server uses a speech recognition device to analyze speech information and convert it into document information. The input is the user's speech information, which is converted into text using speech recognition technology. The resulting document information is then compared with educational document information.

[0849] Step 6:

[0850] The server identifies pronunciation errors and generates feedback by comparing the converted document information with the educational document information. The input consists of the converted document information and the educational document information, and the identified errors are sent to the terminal as feedback information. The output is feedback that includes specific correction suggestions.

[0851] Step 7:

[0852] The terminal presents the user with feedback information from the server, both visually and audibly. The input is feedback data received from the server, clearly indicating to the user which parts of the pronunciation need correction. The output includes visual highlighting and audio guidance for correct pronunciation.

[0853] Step 8:

[0854] The server uses a generative AI model to generate visual materials related to new vocabulary. The input is vocabulary contained in educational document information, and the visual information generation device outputs this as image data. The output image is sent to the terminal.

[0855] Step 9:

[0856] The terminal presents image data from the server to the user, aiming to associate vocabulary with visual information. The input is image data sent from the server, and visual presentation is used to facilitate the user's language learning. The output is the associated image displayed on the terminal's screen.

[0857] Step 10:

[0858] The server uses a video generation device to generate virtual experience videos related to the selected topic. The input consists of educational document information and the user's learning topic, and the generated video simulates the user's experience. The output is video data including detailed simulations.

[0859] Step 11:

[0860] The device plays video data from the server, providing the user with an immersive learning experience. The input is video data transmitted from the server, and videos are played to allow the user to gain practical experience. The output is a video displayed on the screen, intended to deepen the user's understanding through viewing.

[0861] Step 12:

[0862] The server utilizes a natural language processing unit to analyze the user's learning history and progress, and adjusts the individual learning plan accordingly. The input is the user's learning history and progress, and the dynamically updated plan guides the next learning step. As output, the adjusted learning plan is sent to the terminal and presented to the user.

[0863] (Application Example 1)

[0864] 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".

[0865] In recent years, there has been a growing demand for interactive and efficient language learning experiences. However, current systems often lack sufficient individualized support and real-time feedback for learners. Furthermore, there is a lack of technology that can provide learners with opportunities to acquire a language naturally at home. Against this backdrop, there are technical challenges in realizing flexible and intuitive learning support.

[0866] 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.

[0867] In this invention, the server includes means for analyzing audio information acquired by speech recognition means and converting the audio information into text information; means for detecting pronunciation errors and generating feedback by comparing the converted text information with previously acquired text information for teaching materials; and means for automatically generating visual materials related to predetermined terms using image generation means. This enables learners to effectively acquire a language at home and facilitates interactive and personalized language learning.

[0868] "Speech recognition means" refers to technology that analyzes speech information and converts it into text information.

[0869] "Textual information" refers to information represented by digital strings converted through speech recognition.

[0870] "Educational material text information" refers to text data that has been prepared in advance for use in learning.

[0871] "Feedback" is information that informs the user of pronunciation errors based on comparison results.

[0872] "Image generation means" refers to a technology that automatically creates visual materials related to a given term.

[0873] "Terminology" refers to words and phrases used in language learning.

[0874] "Visual material" refers to images presented to learners as visual information.

[0875] "Video generation method" refers to technology that automatically creates simulated videos.

[0876] "Interactive" refers to a dynamic relationship in which the user and the system exchange information with each other.

[0877] "Language learning experience" refers to all activities related to language acquisition, encompassing the process by which learners acquire a language.

[0878] "Progress information" refers to records of learners' learning status and achievements.

[0879] An "individualized learning plan" is a learning process that is customized according to the learner's needs.

[0880] A "language learning partner" is a robot or device that assists learners in acquiring a language.

[0881] "Natural language processing technology" refers to methods that enable computers to understand and process human language.

[0882] "Real-time feedback" refers to corrections and advice provided immediately during the learning process.

[0883] This invention is a system to support language learning, allowing users to gain a learning experience at home. The system integrates speech recognition, image generation, and video generation technologies.

[0884] First, users can select what they want to learn. They choose a language and topic of interest through their device and begin learning.

[0885] Next, the server provides the terminal with relevant learning materials based on the user's selection. Based on these materials, the user can practice speaking. The terminal's microphone captures the user's pronunciation and sends it to the server. The server uses a speech recognition program (e.g., Google Cloud Speech-to-Text) to convert this speech into text and compares it with the text information of the learning materials.

[0886] If a learner makes a pronunciation error, the server identifies the error and generates real-time feedback. This feedback visually or audibly demonstrates the correct pronunciation. In this way, users can immediately correct their pronunciation in their daily learning.

[0887] Furthermore, the server uses image generation AI (e.g., OpenAI DALL-E) to create visual materials relevant to learning. This makes it easier for learners to associate terms with images. In addition, video generation AI (e.g., DeepAI) generates virtual simulation videos, allowing users to visually experience practical scenarios.

[0888] Robots and smart devices function as home learning partners, enhancing learning effectiveness by providing users with conversation practice and interactive quizzes. Specifically, a scenario is envisioned where a user practices English phrases about animals for 10 minutes each day.

[0889] This system analyzes progress information and uses natural language processing technology to generate personalized feedback based on the learner's history. For example, the server might process an instruction such as, "Convert the word the user pronounces into text, compare it to the correct pronunciation, and provide visual or auditory feedback on how to correct the pronunciation if there are errors." This allows learners to improve their language skills efficiently at their own pace.

[0890] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0891] Step 1:

[0892] The user selects a learning language and topic using a terminal. The selected information is sent from the terminal to the server. The input is the user's selection information, and the output is the transmission of the selection information to the server.

[0893] Step 2:

[0894] The server extracts the relevant text information for educational materials from the database based on the received topic information and sends it to the terminal. The input is topic information, and the output is text information for educational materials.

[0895] Step 3:

[0896] The user performs audio practice based on the learning materials through the device, and the audio is captured by the device's microphone and sent to the server. The input is the user's pronunciation, and the output is the transmission of audio data to the server.

[0897] Step 4:

[0898] The server uses Google Cloud Speech-to-Text to convert audio data into text data. Furthermore, it compares this text to the original text information and detects errors. The input is the transmitted audio data, and the output is the converted text data and error identification.

[0899] Step 5:

[0900] The server generates feedback for the user based on the error and sends it to the terminal in a visual or auditory way. The input is the error information, and the output is the generation and transmission of feedback to the terminal.

[0901] Step 6:

[0902] The server uses OpenAI DALL-E to generate visual materials related to new terminology and sends them to the terminal. The input is term information, and the output is visual materials. The terminal displays these visual materials to the user.

[0903] Step 7:

[0904] The server uses Deep AI to generate a virtual simulation video and sends it to the terminal. The input is the simulation scenario information, and the output is the generated video. The terminal then plays this simulation video for the user.

[0905] Step 8:

[0906] The server analyzes the learning history and progress information, generates personalized feedback using natural language processing technology, and determines the next learning step. The input is the learning history data, and the output is an updated learning plan.

[0907] 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.

[0908] This invention is a multimodal learning system that integrates speech recognition, image generation, and video generation technologies with an emotion engine that recognizes user emotions. Specific embodiments for carrying out the invention are described below.

[0909] First, the user launches the application on their device and selects the language and topic they want to learn. Based on this selection, an individual learning scenario is initiated.

[0910] The server retrieves appropriate text learning materials from the database based on the user's selection and sends them to the terminal. The terminal is configured to display these materials to the user.

[0911] During voice practice, the device captures the user's voice via its microphone and sends this data to the server in real time. The server uses speech recognition technology to convert the voice into text and compares it with the learning material text to identify pronunciation errors. Feedback is generated and presented to the user through the device. For example, it might guide the user on the correct pronunciation of "business."

[0912] The server also uses image generation technology to create visual materials related to new words and phrases and presents them to the user, thereby assisting with visual learning.

[0913] Furthermore, video generation technology is used to generate virtual simulation videos based on learning scenarios, which are then provided to the user via their device. This allows users to learn how to apply language through practical experience.

[0914] In particular, this system incorporates an emotion engine, which analyzes the user's facial expressions, voice tone, and other factors on the terminal and sends the results to the server.

[0915] The server identifies the user's emotional state based on data obtained by the emotion engine and adjusts the learning experience accordingly. This adjustment includes adjusting feedback and difficulty levels. For example, if the user is feeling frustrated, the system will emphasize positive feedback to boost their motivation.

[0916] Finally, the server analyzes the user's progress data, including emotional data, and dynamically updates the individual learning plan. The updated plan is presented to the user via the device, and new learning goals are set. In this way, the entire system provides a personalized learning experience that responds to the user's emotions and progress.

[0917] The following describes the processing flow.

[0918] Step 1:

[0919] The user launches the application on their device and selects the language and topic they want to learn. This selection is then sent to the server.

[0920] Step 2:

[0921] The server retrieves appropriate text learning materials from the database based on the user's selection and sends them to the terminal. The terminal then displays these text learning materials to the user.

[0922] Step 3:

[0923] The user reads the displayed text aloud. The device records the user's voice and prepares to send the audio data to the server.

[0924] Step 4:

[0925] The server uses speech recognition technology to convert audio data into text. The converted text is compared to the textbook material to identify pronunciation errors.

[0926] Step 5:

[0927] The server generates feedback based on pronunciation errors. This feedback includes instructions for improving pronunciation accuracy. The feedback information is sent to the terminal.

[0928] Step 6:

[0929] The device displays feedback to the user visually and audibly. The user receives the feedback and continues practicing pronunciation.

[0930] Step 7:

[0931] The server identifies new words and phrases from the selected text and uses image generation technology to create related visual materials.

[0932] Step 8:

[0933] The device displays the generated visual materials to the user. These visual materials enhance the user's understanding.

[0934] Step 9:

[0935] The server uses video generation technology to create virtual simulation videos based on scenarios related to the learning topic.

[0936] Step 10:

[0937] The device provides users with generated videos, facilitating a practical learning experience.

[0938] Step 11:

[0939] The device uses its camera and microphone to transmit the user's facial expressions and voice to an emotion engine, which then analyzes the user's emotional state in real time.

[0940] Step 12:

[0941] The server analyzes emotional data obtained by the emotion engine and adjusts the user's learning experience. Specifically, it dynamically changes the tone of feedback and the difficulty level of learning materials according to the user's emotional state.

[0942] Step 13:

[0943] The server analyzes the user's progress and sentiment data and updates their individual learning plan.

[0944] Step 14:

[0945] The device presents the user with an updated learning plan and additional feedback, and provides new learning objectives. Based on this information, the user progresses to the next learning stage.

[0946] (Example 2)

[0947] 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".

[0948] In modern education systems, there is a need for individualized learning support tailored to each learner's level of understanding and emotional state, but traditional methods struggle to provide such individualized support. Furthermore, there is a demand to enhance learning effectiveness by integrating elements such as audio, visuals, and emotion analysis, but there is a lack of technology to efficiently combine these elements.

[0949] 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.

[0950] In this invention, the server includes means for analyzing speech information acquired by speech recognition means and converting the speech information into text information; means for detecting pronunciation errors and generating evaluation information by comparing the converted text information with previously acquired educational material text information; means for automatically generating visual materials related to predetermined terms using visual information generation means; means for generating virtual simulation videos using video generation means; and means for identifying the learner's emotional state using emotion analysis means and adjusting the learning experience based on the state. This provides an individually personalized learning experience and enables a flexible learning environment that responds to the learner's emotions and progress.

[0951] "Speech recognition means" refers to a technology or function that analyzes speech information and converts that information into text information.

[0952] "Text information" refers to string data converted from audio or other sources.

[0953] "Educational material text information" refers to string data prepared as teaching materials to be provided to learners.

[0954] "Evaluation information" refers to feedback and analysis results generated based on speech recognition and analysis of learning progress.

[0955] "Visual information generation means" refers to a technology or function that automatically creates visual materials related to terms or concepts.

[0956] "Motion image generation means" refers to a technology or function for creating virtual simulations or digital videos.

[0957] "Emotional analysis means" refers to a technology or function that identifies an emotional state by analyzing a learner's facial expressions and tone of voice.

[0958] "Learning experience" refers to the process by which learners acquire knowledge and skills through an educational program.

[0959] A "personalized learning experience" is the provision of education that is customized based on the individual needs, progress, and emotional state of each learner.

[0960] This invention is a multimodal education system that provides learners with a personalized learning experience. Its main components are a server, terminals, and users working together. The specific form of this system is described below.

[0961] First, the user launches a dedicated application on their device and begins by selecting a language to learn and a topic. This selection information is then sent from the device to the server. The device uses a standard PC or smart device for this process.

[0962] The server retrieves appropriate educational materials from its database based on information from the user and sends them to the device. These materials include text, visuals, and videos. The server uses a speech recognition engine (e.g., a common cloud-based speech service) to analyze the user's pronunciation. Specifically, it converts the audio information into text and compares it to pre-recorded text materials to detect pronunciation errors. Afterward, it generates evaluation information and returns it to the device as feedback.

[0963] To enhance visual learning, the server utilizes generative AI models (e.g., general-purpose image generation algorithms) to generate visual materials related to terms and concepts. It also leverages video generation technology to create and provide users with videos for virtual simulations, enabling practical experience.

[0964] Furthermore, the device uses sensors and simple emotion analysis software to detect the user's emotional state. This data is sent to a server, where the emotion analysis tool individually tailors the user's learning experience.

[0965] For example, if a user enters the prompt "Provide visual learning materials to help me learn everyday Japanese phrases in a fun way" into the system, the server will generate corresponding text materials and visual resources and deliver them to the user's terminal.

[0966] In this way, the system combines voice, visual, and emotion analysis technologies to provide users with a unique and personalized learning experience. This helps learners achieve their goals efficiently and effectively.

[0967] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0968] Step 1:

[0969] The user launches the application on their device and selects the language and topic they want to learn. The input is the language and topic information selected by the user. Based on this, the device sends this information to the server. The output is the selection information received by the server.

[0970] Step 2:

[0971] The server uses the received language and topic information to search the database for relevant educational materials. The input is user selection information, and the output is extracted as appropriate text information, visual materials, and video data. This data is then sent to the user's terminal.

[0972] Step 3:

[0973] The terminal displays educational materials sent from the server to the user. It receives educational material data from the server as input. As output, text information is displayed on the screen for the user, and visual materials and videos are played.

[0974] Step 4:

[0975] The user begins voice practice. The device's microphone captures the user's pronunciation. The input is the user's spoken audio information. The device sends this to the server, and the audio data is sent to the speech recognition process as output.

[0976] Step 5:

[0977] The server uses speech recognition to convert input speech data into text information. The input is speech data sent from the terminal. This data is analyzed and converted into text information. The output is the converted text information.

[0978] Step 6:

[0979] The server uses a generative AI model to generate visual materials related to new terminology. The input is converted text information, which is used to create the visual materials. The output is the generated visual information, which is then sent to the terminal.

[0980] Step 7:

[0981] The device uses sensors and emotion analysis software to detect the user's emotional state. Input includes the user's facial expressions and voice tone data. This data is analyzed, and information regarding the emotional state is sent to the server as output.

[0982] Step 8:

[0983] The server analyzes emotional state information and learning progress to generate optimal feedback for the user. Emotional state information and learning data are used as input. Based on this information, it generates feedback that adjusts the learning experience. The adjusted feedback is sent to the terminal as output.

[0984] (Application Example 2)

[0985] 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".

[0986] Conventional language learning systems offer limited feedback on learners' pronunciation practice and comprehension, and lack individualized support based on learners' emotions. This results in insufficient motivation and efficient learning support. Therefore, a system that provides a more practical and effective learning experience is needed.

[0987] 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.

[0988] In this invention, the server includes means for analyzing speech information acquired by a speech recognition device and converting the speech information into text information; means for detecting pronunciation errors and generating feedback by comparing the converted text information with previously acquired learning text data; means for automatically generating visual data related to predetermined terms using a visual material generation device; means for generating virtual simulation images using a video generation device; and means for analyzing the learner's emotional state using an emotion analysis device and adjusting the learning content. This enables learners to receive more personalized, emotion-responsive feedback and a learning experience.

[0989] A "speech recognition device" is a technology that analyzes received speech information and converts it into text information.

[0990] "Textual information" refers to digitized text data obtained by analyzing and converting audio information.

[0991] "Learning text data" refers to pre-prepared textual information for learning, used to aid in understanding pronunciation and grammar.

[0992] A "visual material generation device" is a technology that automatically generates visual data related to specific terms or phrases.

[0993] A "video generation device" is a technology that generates video data in order to realize a virtual simulation.

[0994] An "emotion analysis device" is a technology that analyzes a learner's emotional state from information such as facial expressions and voice.

[0995] "Feedback" refers to information provided to learners, such as suggestions, evaluations, and areas for improvement regarding pronunciation and comprehension.

[0996] A "personalized learning experience" refers to an educational experience that is tailored and delivered according to the individual characteristics and emotional state of the learner.

[0997] This invention provides an educational tool that integrates speech recognition and sentiment analysis technologies as a system to support learners' language learning. Learners can select a target language and topic using a terminal and begin learning on the system.

[0998] The server uses a speech recognition device to convert speech information acquired from the microphone into text. This information is compared with pre-prepared training text data to detect pronunciation errors. Based on the detected errors, feedback is generated and presented to the learner. In addition, a visual material generation device automatically generates visual materials that match the specified terms and displays them to the learner through the terminal's display.

[0999] Furthermore, the server uses a video generation device to generate virtual simulation images, providing a practical experience. This process utilizes a generative AI model to depict specific scenes and situations that learners should be taught.

[1000] In addition, an emotion analysis device uses data from the device's camera and microphone to analyze the learner's emotional state. Based on this emotional state, the server adjusts the learning content and provides feedback and learning tasks that match the learner's emotions. This personalized learning experience is expected to enable learners to learn more effectively.

[1001] As a concrete example, the server sends a prompt message to the AI ​​model saying, "Please suggest images and videos that can be generated to learn English words and actions related to animals," and the results are displayed on the terminal. In this way, an effective learning environment is realized through the cooperation of the server, terminal, and user.

[1002] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1003] Step 1:

[1004] The user selects the target language and topic on their device. This input information is sent to the server, and a learning scenario is constructed as output. The server retrieves the corresponding learning text data from the database and prepares it for display on the device.

[1005] Step 2:

[1006] The user provides voice input through the device. The device uses a microphone to acquire voice information and sends it to the server. The server uses a speech recognition device to convert the voice information into text. This converted text information forms the basis for the next step.

[1007] Step 3:

[1008] The server compares the text information with pre-prepared training text data. During the comparison process, it detects differences from the correct pronunciation and generates feedback. This feedback is then presented to the user via the terminal.

[1009] Step 4:

[1010] The server uses a visual material generation device to generate visual materials related to specified terms. Appropriate images and illustrations are created to facilitate learning for the user, and these are displayed to the user via the terminal.

[1011] Step 5:

[1012] The server uses a video generation device to generate virtual simulation videos. In this generation process, a generation AI model is used to create prompt messages and visualize specific scenes and situations. The videos are then presented to the user via a terminal.

[1013] Step 6:

[1014] The device captures the user's facial expressions and voice tone using its camera and microphone, and sends this data to a server. The server analyzes the user's emotional state through an emotion analysis device and provides feedback and adjusts learning tasks accordingly.

[1015] Step 7:

[1016] The server dynamically updates individual learning programs based on collected progress information and sentiment data. The updated learning plan is presented to the user via the terminal, and the next learning step is suggested.

[1017] 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.

[1018] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1019] 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 robot 414.

[1020] 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.

[1021] 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.

[1022] 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.

[1023] 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.

[1024] 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.

[1025] 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."

[1026] 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.

[1027] 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.

[1028] 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.

[1029] 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.

[1030] 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.

[1031] 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.

[1032] 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.

[1033] 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.

[1034] 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.

[1035] 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.

[1036] 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.

[1037] 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.

[1038] The following is further disclosed regarding the embodiments described above.

[1039] (Claim 1)

[1040] A means for analyzing audio data acquired by speech recognition means and converting the audio data into text data,

[1041] A means for detecting pronunciation errors and generating feedback by comparing the converted text data with previously acquired teaching material text data,

[1042] A means for automatically generating visual material related to a given word using an image generation means,

[1043] A means for generating a virtual simulation video using a video generation means,

[1044] The aforementioned videos are provided to learners as a means of promoting practical experience,

[1045] A system that includes this.

[1046] (Claim 2)

[1047] A means of collecting and analyzing learner progress data,

[1048] A means for dynamically updating the individual learning plan based on the above analysis and determining the next learning step,

[1049] The system according to claim 1, further comprising:

[1050] (Claim 3)

[1051] A means of analyzing data including learning history using natural language processing means and providing personalized feedback to the user,

[1052] The system according to claim 1, further comprising:

[1053] "Example 1"

[1054] (Claim 1)

[1055] A device that analyzes voice information acquired by a voice recognition device and converts the voice information into document information,

[1056] A device that detects pronunciation errors and generates a response by comparing the converted document information with previously acquired educational document information,

[1057] A device that automatically generates visual materials related to a given vocabulary using a visual information generation device,

[1058] A device that generates virtual experience videos using a video generation device,

[1059] A device that provides the aforementioned video to learners and promotes practical experience,

[1060] A system that includes this.

[1061] (Claim 2)

[1062] A device for collecting and analyzing learner progress information,

[1063] A device that dynamically updates the individual learning plan based on the above analysis and determines the next learning stage,

[1064] The system according to claim 1, further comprising:

[1065] (Claim 3)

[1066] A device that uses a natural language processing unit to analyze information including learning history and provides personalized responses to users,

[1067] The system according to claim 1, further comprising:

[1068] "Application Example 1"

[1069] (Claim 1)

[1070] A means for analyzing speech information acquired by speech recognition means and converting the speech information into text information,

[1071] A means for detecting pronunciation errors and generating feedback by comparing the converted character information with the previously acquired character information for teaching materials,

[1072] A means for automatically generating visual material related to a predetermined term by an image generation means,

[1073] A means for generating virtual simulation images using a video generation means,

[1074] The aforementioned video is provided to learners as a means of promoting practical experience,

[1075] A means of providing an interactive language learning experience by integrating speech recognition, image generation, and video generation technologies.

[1076] A system that includes this.

[1077] (Claim 2)

[1078] A means of collecting and analyzing learner progress information,

[1079] A means for dynamically updating the individual learning plan based on the above analysis and determining the next learning step,

[1080] The system according to claim 1, further comprising means for functioning as a language learning partner within the home.

[1081] (Claim 3)

[1082] A means of analyzing information, including learning history, using natural language processing technology to provide personalized feedback to users,

[1083] The system according to claim 1, further comprising means for observing pronunciation practice and providing real-time feedback.

[1084] "Example 2 of combining an emotion engine"

[1085] (Claim 1)

[1086] A means for analyzing speech information acquired by a speech recognition means and converting the speech information into text information,

[1087] A means for detecting pronunciation errors and generating evaluation information by comparing the converted text information with previously acquired educational material text information,

[1088] A means for automatically generating visual materials related to a predetermined term using a visual information generation means,

[1089] A means for generating a virtual simulation video by a video generation means,

[1090] A means of providing the aforementioned video images to learners and promoting applied experience,

[1091] A means for identifying the learner's emotional state using emotion analysis means and adjusting the learning experience based on said state,

[1092] A system that includes this.

[1093] (Claim 2)

[1094] A means of collecting and analyzing learners' progress information and emotional state,

[1095] A means for dynamically updating the individual learning plan based on the above analysis and determining the next educational procedure,

[1096] The system according to claim 1, further comprising:

[1097] (Claim 3)

[1098] A means of analyzing information including learning history using natural language processing means and providing personalized evaluation information to the user,

[1099] The system according to claim 1, further comprising:

[1100] "Application example 2 when combining with an emotional engine"

[1101] (Claim 1)

[1102] A means for analyzing voice information acquired by a voice recognition device and converting the voice information into text information,

[1103] A means for detecting pronunciation errors and generating feedback by comparing the converted character information with previously acquired training text data,

[1104] A means for automatically generating visual data related to a predetermined term using a visual material generation device,

[1105] A means for generating virtual simulation images using an image generation device,

[1106] The aforementioned video is provided to learners as a means of promoting practical experience,

[1107] A means of analyzing the learner's emotional state using an emotion analysis device and adjusting the learning content accordingly,

[1108] A system that includes this.

[1109] (Claim 2)

[1110] A means of collecting and analyzing learners' progress and emotional information,

[1111] A means for dynamically updating the individual learning program based on the above analysis and determining the next learning stage,

[1112] The system according to claim 1, including the following:

[1113] (Claim 3)

[1114] A means of providing personalized feedback to users by analyzing data including learning history using natural language processing capabilities,

[1115] The system according to claim 1, including the following: [Explanation of Symbols]

[1116] 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 speech information acquired by speech recognition means and converting the speech information into text information, A means for detecting pronunciation errors and generating feedback by comparing the converted character information with the previously acquired character information for teaching materials, A means for automatically generating visual material related to a predetermined term by an image generation means, A means for generating virtual simulation images using a video generation means, The aforementioned video is provided to learners as a means of promoting practical experience, A means of providing an interactive language learning experience by integrating speech recognition, image generation, and video generation technologies. A system that includes this.

2. A means of collecting and analyzing learner progress information, A means for dynamically updating the individual learning plan based on the above analysis and determining the next learning step, The system according to claim 1, further comprising means for functioning as a language learning partner within the home.

3. A means of analyzing information, including learning history, using natural language processing technology to provide personalized feedback to users, The system according to claim 1, further comprising means for observing pronunciation practice and providing real-time feedback.

Images