system

Abstract

We provide the system. [Solution] An input means for collecting audio data, A conversion method for converting audio data into text data, An analytical method for extracting keywords from text data, A generation means for generating or retrieving relevant visual information based on extracted keywords, A transmission means that transmits the generated visual information to a user device through an output means, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a 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] Children with learning disabilities, especially those with dyslexia, have a problem that it is difficult to immediately understand the content of a lesson in a conventional teaching method. This problem refers to the fact that they cannot adapt to the standard lesson progress received by general children, resulting in differences in the progress and understanding of learning. Such a situation may damage the confidence and learning motivation of children, so appropriate support is necessary.

Means for Solving the Problems

[0005] This invention proposes a system that collects audio information within a classroom, converts it into text data, and extracts keywords related to the lesson content. Furthermore, based on these extracted keywords, it generates or searches for relevant visual information and provides it visually and audibly to the user's device, enabling students to efficiently understand the lesson content. This invention also provides audio information to students using speech synthesis technology and has a function that allows for flexible adjustment of information presentation in response to user feedback. As a result, students with learning disabilities can learn at their own pace and increase their confidence and motivation.

[0006] "Audio data" refers to information electronically acquired from speech and sounds made by teachers and students in a classroom.

[0007] "Input means" refers to hardware or software components for collecting audio data.

[0008] "Conversion means" refers to a function or process within a system for converting audio data into text information.

[0009] "Analysis tools" refer to functions that process text data to identify important keywords related to the lesson.

[0010] "Generation method" refers to the process of creating or acquiring relevant visual information based on analyzed keywords.

[0011] "Visual information" refers to information that visually represents learning content, including text, images, diagrams, or videos.

[0012] "Output means" refers to a function that transmits data to a user device in order to display the generated visual information.

[0013] "Transmission method" refers to the process of sending educational material data packages to the user's device via a network.

[0014] "Voice synthesis" is a technology used to provide text data to users as voice information.

[0015] "Feedback" is an opinion or reaction regarding the provided information and its format based on input from the user.

[0016] "Adjustment means" is a process of changing the content and presentation method of the displayed information based on feedback.

Brief Explanation of Drawings

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12]It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0021] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] This invention provides an assistive system to help children with learning disabilities to smoothly understand school lessons. This system has various functions for processing audio emitted in the classroom in real time and providing visual learning materials.

[0039] This system is configured as follows: First, the server collects audio data through microphones placed in the classroom. This audio data is converted into text data using a speech recognition engine on the server. This converted text is then processed by the server using natural language processing to extract important keywords and concepts related to the lesson content.

[0040] The server then generates visual information or searches for related information based on the extracted keywords. This includes diagrams, illustrations, and animations. This generated visual content is then formatted in a user-friendly way and transmitted to the terminal via the network.

[0041] Meanwhile, the terminal receives data transmitted from the server and displays visual information on the screen. The terminal also uses speech synthesis technology to reproduce text data, allowing users to perceive information aurally. Through this process, children can understand the lesson content using both sight and hearing, instead of reading text.

[0042] Users can provide feedback through their devices if they have questions about the lesson content or need further explanation. This feedback information is then sent back to the server and adjusted to optimize the way the information is presented for the user.

[0043] For example, if "adding fractions" is being explained in class, the server extracts keywords such as "fraction" and "addition," and generates diagrams and animations related to them. These visual materials are then sent to the terminal, which displays them on the screen. Simultaneously, it provides voice guidance using speech synthesis, such as, "The key to adding fractions is to find a common denominator even if the denominators are different."

[0044] In this way, children with learning disabilities can review lesson content and progress through their learning in a way that is easy for them to understand.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The server collects teacher and student speech in real time as audio data through microphones installed in the classroom.

[0048] Step 2:

[0049] The server converts the collected audio data into text data using speech recognition software. Noise filtering is also performed during this process to prevent misrecognition.

[0050] Step 3:

[0051] The server uses natural language processing techniques to extract keywords and key concepts from the converted text data. For example, it identifies core lesson terms such as "fractions" and "addition."

[0052] Step 4:

[0053] Based on the extracted keywords, the server generates or retrieves relevant visual information from its internal database or via the internet. This information includes diagrams, graphs, animations, and more.

[0054] Step 5:

[0055] The server combines the generated or acquired visual information to create a data package that clearly explains the learning content, and prepares it for transmission to the terminal.

[0056] Step 6:

[0057] The terminal interprets the data package received from the server and displays visual content on the screen. Simultaneously, it converts text data into speech using a speech synthesis engine and plays it through the speaker.

[0058] Step 7:

[0059] Users understand the lesson content through visual information and audio guides displayed on their devices. If they have questions or need further explanation, they can send feedback through the user interface.

[0060] Step 8:

[0061] The device receives feedback from the user and sends it to the server. The server analyzes this feedback and incorporates appropriate adjustments into the next content delivery.

[0062] (Example 1)

[0063] 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."

[0064] Children with learning disabilities face challenges in effectively understanding information visually and aurally within traditional classroom settings. Furthermore, there are difficulties in providing effective learning materials tailored to each child's level of understanding and learning style in real time.

[0065] 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.

[0066] In this invention, the server includes an input means for collecting sound, a conversion means for converting sound into text, and an analysis means for extracting important words from the text. This makes it possible to extract important information in real time from sounds emitted in the classroom and provide visual and auditory teaching materials tailored to individual children.

[0067] "Input means" refers to devices or functions that acquire sound from the environment and capture it as data.

[0068] "Conversion method" refers to the process or technology used to convert audio data into text data.

[0069] "Analysis method" refers to a method for identifying and extracting important words and phrases from text data.

[0070] "Generation means" refers to techniques for creating or acquiring relevant visual information based on extracted words.

[0071] "Transmission means" refers to a method or technique for transmitting generated visual information to an output device.

[0072] "Audio output means" refers to technologies or devices that reproduce text data as audio data.

[0073] "Adjustment means" refers to a function that optimizes and adjusts the information displayed based on user feedback.

[0074] An "output device" is a device or interface for displaying visual information and providing audio information.

[0075] This invention functions as an auxiliary system to help children with learning disabilities effectively understand lesson content. Specific embodiments of this system are described below.

[0076] The server collects sound in real time using high-sensitivity microphones installed in the classroom. This process employs advanced sound collection techniques to reduce ambient noise and accurately capture what the teacher is saying. The collected audio data is converted into text data by speech recognition software on the server (e.g., Google® Cloud Speech-to-Text). Natural language processing software (e.g., SpaCy or NLTK) analyzes this text data and extracts important keywords.

[0077] Next, the server utilizes a generative AI model (e.g., DALL-E) to generate visual information based on the extracted keywords. It also searches for educational materials on the internet and retrieves relevant content if necessary. This visual information is organized for user understanding and adjusted to avoid overly complex display.

[0078] The generated visual information and audio guides using speech synthesis technology (e.g., Amazon Polly) are transmitted to the device via the network. The device receives this information, displays the visual information on its screen, and plays the audio guide, helping students understand the lesson content through both sight and hearing. Users can also send feedback to the server via the device. Based on this feedback, the server adjusts the way information is presented and the content itself, providing an environment optimized for each individual student.

[0079] As a concrete example, when "adding fractions" is being explained in class, the server extracts keywords such as "fraction" and "addition." In this case, the AI ​​model is given a command such as "Generate visual materials to explain adding fractions" as an example of a prompt, and it creates related illustrations and animations. This allows students to gain a deeper understanding of the lesson content through visual materials, along with audio guidance such as "The key to adding fractions is to find a common denominator even if the denominators are different."

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server collects sound from microphones installed in the classroom. This input is real-time audio data, and the server uses acoustic signal processing technology to remove noise and clarify the teacher's voice. As a result, clean audio data is output.

[0083] Step 2:

[0084] The server inputs the collected audio data into a speech recognition engine, which converts it into text data. This speech recognition engine (for example, Google Cloud Speech-to-Text) analyzes the audio waveform and transcribes it into text. The output is time-tagged text data. This data provides the lesson content as text information.

[0085] Step 3:

[0086] The server processes the text data through a natural language processing engine to extract important keywords. The natural language processing engine (e.g., SpaCy) analyzes the context and identifies particularly significant words and phrases. The input is the text data from step 2, and the output is a list of extracted keywords.

[0087] Step 4:

[0088] The server inputs the extracted keywords as prompts into a generative AI model to generate visual information. The generative AI model (e.g., DALL-E) generates relevant illustrations and animations based on the input prompts. In this step, the keywords are transformed into creative visual learning materials and output as visual resources.

[0089] Step 5:

[0090] The server sends the generated visual information to the terminal. This communication takes place over the network, and the terminal prepares the received data. The input is the generated visual information, and the output is the visual content prepared for display on the terminal.

[0091] Step 6:

[0092] The device displays received visual information on its screen and uses a speech synthesis engine to play text data as audio. The speech synthesis engine (e.g., Amazon Polly) generates audio guides and plays them in sync with the visual information. This provides the user with lesson content both visually and aurally. The input is visual and text information from the server, and the output is the displayed screen and the played audio.

[0093] Step 7:

[0094] Users send feedback on lesson content to the server via their devices. The server analyzes this feedback and incorporates it into the next displayed content and audio guides, providing a learning experience tailored to the user. The input is user feedback, and the output is the adjusted information presentation.

[0095] (Application Example 1)

[0096] 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."

[0097] A challenge exists in that children with learning disabilities often have difficulty fully understanding school lessons. In particular, traditional methods are insufficient for promoting comprehension during lessons, and there is a need for real-time support. Efficiently converting audio data into text and providing information visually and aurally is necessary to deepen students' understanding and promote their participation in lessons.

[0098] 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.

[0099] In this invention, the server includes input means for collecting audio data, conversion means for converting audio data into text data, analysis means for extracting keywords from the text data, generation means for generating or retrieving relevant visual information based on the extracted keywords, distribution means for displaying visual information on a user device and providing audio guidance, and adjustment means for adjusting the displayed information based on user feedback. This enables children to understand the content of lessons more effectively in real time through sight and hearing.

[0100] "Audio data" refers to information that represents an acoustic signal in digital format.

[0101] "Input means" refers to a device or function for collecting audio data from an external source.

[0102] "Conversion means" refers to a device or function for converting audio data into text data.

[0103] "Text data" refers to information expressed as character data, representing the content of audio in written form.

[0104] "Analysis means" refers to a device or function for extracting keywords or important concepts from text data.

[0105] "Generation means" refers to a device or function for generating or retrieving relevant visual information based on extracted keywords.

[0106] "Visual information" refers to information in a format that can be viewed with the eyes, such as diagrams, illustrations, and animations.

[0107] "Distribution means" refers to a device or function for transmitting generated visual information to a user device and providing display and audio guidance.

[0108] "Feedback" refers to information and opinions provided by users, which are used to improve and adjust the system.

[0109] "Adjustment means" refers to a device or function for optimizing display information based on user feedback.

[0110] A "user device" is a device used to receive and display visual and auditory information, and includes smartphones and head-mounted displays.

[0111] The system for implementing this invention operates primarily through the cooperation of a server and a user terminal. The server collects audio from the classroom in real time and converts it into text data using a speech recognition engine. Specifically, a microphone is used to collect audio data, and a speech recognition engine such as the Google Cloud Speech-to-Text API is used for the conversion process.

[0112] The converted text data is then processed using a natural language processing engine on the server, such as the Google Cloud Natural Language API, to extract important keywords and themes. This step allows for the selection of information relevant to the subject and content in real time.

[0113] Next, the server uses the Adobe Creative Cloud API and other tools to generate or retrieve relevant visual information based on the extracted keywords. This visual information includes illustrations and animations, which are presented in a format that is easier for students to understand.

[0114] The generated visual information and audio guides are transmitted from the server to the user's terminal via the network. The user's terminal displays this information on its screen and simultaneously plays the audio guide using speech synthesis technology, such as Amazon Polly. This allows learners to understand the information through both sight and hearing.

[0115] As a concrete example, consider a situation where students are learning the concept of "differentiation" in a mathematics class. The server extracts keywords such as "differentiation" and "derivative function" and generates visualized learning materials. The terminal then displays these materials, and an audio guide plays stating, "The derivative function shows the instantaneous rate of change of a function."

[0116] An example of a prompt would be: "Convert the audio from the live lesson to text and visualize the educational content. Extract key concepts and keywords, generate animations based on them, and deliver them to the user in an easy-to-understand manner."

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

[0118] Step 1:

[0119] The server collects audio data through microphones placed throughout the classroom. The input is the real-time audio signal from the classroom, and the output is digital audio data. This data is then converted to a format usable in the next step.

[0120] Step 2:

[0121] The server converts the collected audio data into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). In this step, speech recognition technology is used to output the content of the audio in text format. The input is digital audio data, and the output is text data.

[0122] Step 3:

[0123] The server processes text data using a natural language processing engine (e.g., Google Cloud Natural Language API) to extract important keywords and concepts. The input is text data, and the output is a keyword list. This process involves text analysis and selection of key items.

[0124] Step 4:

[0125] The server generates or searches for relevant visual information based on extracted keywords (e.g., using the Adobe Creative Cloud API). The input is a list of keywords, and the output is visual information (diagrams, illustrations, animations, etc.). Here, a generative AI model is used to construct the content.

[0126] Step 5:

[0127] The server transmits the generated visual information and audio guide data to the user's terminal via the network. The input is the visual information and audio guide data, and the output is the transmitted data. Efficient data communication takes place during this process.

[0128] Step 6:

[0129] The device displays received visual information on its screen and plays audio guides using speech synthesis technology (e.g., Amazon Polly). The input is the transmitted data, and the output is the displayed visual information and the played audio. This allows the user to understand the lesson content through both sight and sound.

[0130] Step 7:

[0131] Users send questions and feedback about the lesson content to the server via their terminal. The input is the user's feedback information, and the output is feedback data transferred to the server. This information is used to improve and adjust the system.

[0132] 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.

[0133] This invention provides an auxiliary system for helping children with learning disabilities understand lesson content, equipped with a function to recognize the user's emotions and further enhance learning effectiveness. This system integrates and executes a series of processes, from collecting audio data to emotion recognition.

[0134] First, the server uses microphones in the classroom to record the teacher's voice in real time and converts this audio data into text. Once the text data is generated, natural language processing is used to extract important keywords from the lesson. Based on the extracted keywords, the server generates or searches for relevant visual materials and creates content that aids learning.

[0135] Furthermore, the server transmits the generated visual materials and audio data to the user's device. The device receives this content, displays it on its screen, and plays the explanations aloud using speech synthesis technology. This allows the user to understand the lesson content using both their sight and hearing.

[0136] In addition, this system is equipped with an emotion engine that recognizes the user's emotions in real time. Cameras and sensors installed on the terminal collect the user's facial expressions and gaze data, which the emotion engine then analyzes. Based on the analysis results, it estimates the user's level of interest and understanding, and adjusts the presentation speed and difficulty level of the learning materials accordingly.

[0137] For example, if the emotion engine detects a user's decreased concentration while learning fraction addition, the system will select and display simpler examples to adjust the learning pace. Furthermore, if the emotion engine detects that the user is struggling to understand, the device will provide additional visual and audio guidance to support comprehension.

[0138] Thus, the system of the present invention provides an environment in which children can learn effectively at their own pace by combining integrated auditory and visual support with emotion recognition.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The server collects audio data in real time from microphones installed in the classroom. Measures have been taken to ensure that all teacher speech is captured without omission.

[0142] Step 2:

[0143] The server converts the collected audio data into text data using a speech recognition engine. This conversion includes noise reduction to generate accurate text.

[0144] Step 3:

[0145] The server analyzes the generated text data using natural language processing techniques to extract keywords and key concepts. It identifies important points of the lesson content and uses them to design teaching materials.

[0146] Step 4:

[0147] The server searches for or generates relevant visual information based on the extracted keywords. It retrieves relevant images, animations, videos, etc., from a database or utilizes online resources.

[0148] Step 5:

[0149] The server creates a data package for sending properly organized visual information to the user terminal and then transmits the data. Optimization is in place for efficient data transfer.

[0150] Step 6:

[0151] The terminal interprets data packages received from the server and displays visual learning materials on its screen. It also uses speech synthesis to play back related text data as audio.

[0152] Step 7:

[0153] The camera and sensors built into the device collect the user's facial expressions and gaze data and transmit it to the emotion engine. This allows for real-time monitoring of the user's emotional state.

[0154] Step 8:

[0155] The emotion engine analyzes collected data to determine the user's emotions, interests, and level of engagement. This allows it to predict which content will be most effective for the user.

[0156] Step 9:

[0157] The server dynamically adjusts the presentation speed and difficulty level of the learning materials based on the analysis results of the emotion engine. For example, if there are signs that the user is not understanding the material, it selects materials that are easier to access.

[0158] Step 10:

[0159] Users understand the lesson content through adjusted visual and auditory information. If necessary, users can interact with their devices to provide feedback. This feedback will be used to adjust the content in the next lesson.

[0160] (Example 2)

[0161] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0162] In conventional educational support systems, the processes of voice-to-text conversion and material generation are independent of each other, making it difficult to understand learners' emotional states in real time and adjust learning content accordingly. In particular, there is a lack of effective learning support for children with learning disabilities, and there is an urgent need to create an environment where children can learn at their own pace.

[0163] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0164] In this invention, the server includes an input means for collecting audio information, a conversion means for converting the audio information into text information, and an analysis means for extracting important words from the text information. This enables the generation of user-optimized visual materials and the adjustment of learning content based on emotion through real-time text conversion of audio data and extraction of important words.

[0165] "Auditory information" refers to information transmitted through sound, and specifically includes data used in an educational context, particularly the speech of teachers.

[0166] "Input means" refers to devices and methods for acquiring audio information and incorporating it into a system, and mainly includes devices that utilize microphones.

[0167] "Conversion means" refers to a process or device that converts audio information into text information, and includes functions that utilize speech recognition technology.

[0168] "Text information" refers to data in which audio information is represented as a string of characters, and includes information that can be verified in a visual format.

[0169] "Analysis methods" refer to processes that identify important words and phrases from text information and extract keywords related to educational content.

[0170] "Key terms" refer to words or phrases within the text that deserve particular attention and include central concepts for understanding the educational content.

[0171] "Generative means" refers to methods or devices for producing or identifying visual supplementary materials and related content based on extracted key keywords.

[0172] "Visual materials" refer to images and video data generated or acquired to present information visually, and are used as educational aids.

[0173] "Transmission means" refers to communication methods and devices for transmitting generated visual material to a user's terminal and providing it in a viewable state.

[0174] "Emotion recognition means" refers to a process or technology for identifying an emotional state by analyzing a user's facial expressions and gaze data.

[0175] "Emotional state" refers to a user's psychological response, interest, and level of understanding, and is used to evaluate the user's attitude towards educational content.

[0176] "Adjustment means" refers to methods and devices for optimizing the content and presentation speed of learning materials based on the user's emotional state.

[0177] This invention is a learning support system that integrates and executes a series of processes, from collecting voice information to recognizing the user's emotions. A specific embodiment of this system is described below.

[0178] First, in a specific classroom environment, the server uses microphones installed in the classroom to collect the teacher's voice in real time. This voice information is then converted into text using speech recognition software. Specifically, a general service providing speech recognition technology can be used.

[0179] Next, the text information is analyzed on the server using natural language processing techniques to extract important words and phrases. Natural language processing libraries are used for the analysis, and keywords relevant to the lesson content are automatically extracted. This step is crucial for visualizing the key points of what the user is learning.

[0180] Based on the extracted key keywords, the server generates or searches for relevant visual materials. The generation of visual materials can utilize online-accessible educational databases. This allows users to gain a deeper understanding by utilizing visual learning materials.

[0181] Subsequently, the generated visual and audio materials are sent from the server to the user's terminal. The terminal displays the received content on its screen and plays the explanation aloud using a speech synthesis engine. This allows the user to effectively utilize both sight and hearing to advance their learning.

[0182] Furthermore, to recognize the user's emotions in real time, this system collects facial expression and gaze data through cameras and sensors installed on the device. For emotion recognition, it uses a common facial recognition API to provide data for estimating the user's interest and level of understanding.

[0183] For example, when a user is learning "fraction addition," the server uses emotion recognition data to evaluate the user's level of concentration. If the server determines that the user's understanding is insufficient, it automatically presents learning materials with adjusted difficulty levels.

[0184] An example of a prompt message might be, "Explain how the system should respond if the user is learning fraction addition and their concentration wanes."

[0185] Thus, the present invention is a system that integrates audio and visual information and further recognizes the user's emotional state to provide effective educational support tailored to the learning pace of each individual child.

[0186] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0187] Step 1:

[0188] The server uses microphones installed in the classroom to collect teacher voice information in real time. The collected voice information is converted into text information through speech recognition software. Specifically, it receives voice waveform data as input, uses acoustic and language models to recognize phonemes and predict words, and outputs it as text information.

[0189] Step 2:

[0190] The server applies natural language processing techniques to text information to extract important terms. This process involves morphological analysis to extract keywords based on part-of-speech information such as nouns and verbs. From the input text information, it identifies important terms corresponding to specific educational content and outputs a keyword list.

[0191] Step 3:

[0192] The server generates or searches for relevant visual materials based on the extracted key keywords. Specifically, it searches for relevant images and videos from the database, or generates new visual materials using existing templates. The input is a keyword list, and the server outputs visual material files based on this list.

[0193] Step 4:

[0194] The server sends the generated visual and audio information to the user's terminal. The data is transferred using a secure communication protocol. Visual material files and synthesized speech data are taken as input and sent to the user's terminal as output.

[0195] Step 5:

[0196] The terminal displays the received visual material on its screen and plays an audio explanation using a speech synthesis engine. This process uses the visual material file and audio data received from the server as input, and simultaneously displays the image on the screen and outputs it to the speaker.

[0197] Step 6:

[0198] The device uses cameras and sensors to collect data on the user's facial expressions and gaze. This data is transmitted in real time to an emotion recognition engine. It receives the user's physical data (facial expressions, gaze) as input and outputs it directly as data for analysis.

[0199] Step 7:

[0200] The server uses an emotion recognition engine to analyze collected user facial expressions and gaze data to identify the user's emotional state. It then uses feature extraction and discrimination models from the input data to evaluate the user's interest and understanding, and outputs the results.

[0201] Step 8:

[0202] The server adjusts the content and presentation speed of learning materials based on the results of the emotional state analysis. Specifically, it supports user comprehension by appropriately changing the difficulty level of the materials. It receives the emotional analysis results as input and outputs the adjusted learning materials.

[0203] (Application Example 2)

[0204] 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".

[0205] Conventional learning support systems have a problem in that they do not adequately provide adaptive learning support tailored to the user's level of understanding and emotional state, resulting in limited effectiveness, particularly for children with learning disabilities or for training new employees in the workplace. This project aims to solve this problem and provide effective learning and educational support.

[0206] 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.

[0207] In this invention, the server includes input means for collecting audio data, conversion means for converting audio data into text data, analysis means for extracting keywords from the text data, sensor means for collecting user facial expression and gaze data, and emotion recognition means for analyzing the user's emotions and adjusting the presented information based on the results. This enables adaptive learning support and educational support that responds to the user's emotional state.

[0208] "Audio data" refers to sound information recorded as sound waves, and includes digital or analog data such as speech and ambient sounds.

[0209] "Input means" refers to a device or system for collecting audio data, specifically a receiving device such as a microphone or sensor.

[0210] "Conversion means" refers to a technology or device for converting audio data into text data, and includes speech recognition software, etc.

[0211] "Analysis tools" refer to systems or programs that have the function of extracting important information from text data, and utilize natural language processing technology, etc.

[0212] "Generation means" refers to an apparatus or system that performs a process of generating or retrieving relevant visual information based on extracted keywords.

[0213] "Transmission means" refers to a communication device or method for transmitting generated visual information to a user device.

[0214] "Sensor means" refers to a device or system for collecting user facial expression and gaze data, and includes cameras and other sensory sensors.

[0215] "Emotion recognition means" refers to technologies or systems for evaluating a user's emotions, such as estimating their level of interest and understanding through facial expression analysis or gaze data analysis.

[0216] This invention is a complex system used for learning support and educational assistance, and consists of the following main elements: The server first collects audio data using an input means. This audio data is converted into text data by a conversion means. From the converted text data, important keywords are extracted using an analysis means. Next, related visual information is generated or retrieved based on these keywords by a generation means.

[0217] The generated visual information is transmitted to the user device via a means of communication. The user device is typically a terminal equipped with a display, which displays this information. Furthermore, the terminal can use speech synthesis technology to provide information to the user through the audio it plays. Through this process, the user gains a learning experience that utilizes both visual and auditory senses.

[0218] The user device incorporates sensors to collect the user's facial expressions and gaze data. This data is analyzed by emotion recognition to estimate the user's emotional state (e.g., interest and comprehension). Based on this estimation, the system adjusts the visual information and explanations it presents to improve the user's learning efficiency.

[0219] As a concrete example, in the context of training new employees in a factory, this system monitors the level of stress and confusion of users through emotion recognition mechanisms as they learn how to operate new machinery, and dynamically adapts the training content accordingly. For instance, if it is determined that the user is not understanding the material, detailed step-by-step guidance is provided via audio and visuals to aid their comprehension.

[0220] An example of a prompt is, "Use an emotion recognition system to monitor worker stress levels during new machine operation training and dynamically adjust the training content."

[0221] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0222] Step 1:

[0223] The server collects audio data from environments such as classrooms and work sites using input devices. At this stage, a microphone is used to acquire audio in real time and transmit it to the server as digital data. Audio data is the input, and data collection is the output.

[0224] Step 2:

[0225] The server converts the collected audio data into text data using a conversion mechanism. Specifically, it analyzes the audio waveform using speech recognition software and converts it into corresponding text. Audio data is the input, and text data is the output.

[0226] Step 3:

[0227] The server uses analytical tools to extract important keywords from text data. It utilizes natural language processing techniques to identify key words and phrases within the text. This forms the basis for generating related visual information. Text data is the input, and a list of keywords is the output.

[0228] Step 4:

[0229] The server generates or retrieves relevant visual information based on keywords extracted by the generation method. This may involve generating visual information from scratch or retrieving relevant images and videos from a database. Keywords are the input, and visual information is the output.

[0230] Step 5:

[0231] The server transmits the generated visual information to the user device via a means of communication. Internet communication is typically used for this purpose. The visual information is the input, and its delivery to the user device is the output.

[0232] Step 6:

[0233] The terminal displays the transmitted visual information on its screen and, if necessary, uses speech synthesis technology to play relevant explanations aloud to the user. Here, the speech synthesis engine generates speech from text and outputs it through the speaker. Visual information and text are the inputs, and the display and audio output are the outputs.

[0234] Step 7:

[0235] The device uses sensors to collect user facial expressions and gaze data. This information is sent to emotion recognition systems in real time. Cameras and other sensors function as input devices, and the collected data is the output.

[0236] Step 8:

[0237] The device uses emotion recognition to analyze the user's emotional state (interest, understanding, etc.) from collected data. It uses machine learning algorithms to recognize patterns and estimate the user's state. Facial expressions and eye gaze data are inputs, and the emotional state evaluation is the output.

[0238] Step 9:

[0239] The server dynamically adjusts the content and pace of the presented information based on the results of emotion recognition. If necessary, it adds supplementary visual information or audio guidance. The emotional state assessment is the input, and the adjusted presented information is the output.

[0240] 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.

[0241] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0242] 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.

[0243] [Second Embodiment]

[0244] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0245] 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.

[0246] 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).

[0247] 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.

[0248] 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.

[0249] 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).

[0250] 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.

[0251] 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.

[0252] 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.

[0253] 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.

[0254] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0255] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0256] This invention provides an assistive system to help children with learning disabilities to smoothly understand school lessons. This system has various functions for processing audio emitted in the classroom in real time and providing visual learning materials.

[0257] This system is configured as follows: First, the server collects audio data through microphones placed in the classroom. This audio data is converted into text data using a speech recognition engine on the server. This converted text is then processed by the server using natural language processing to extract important keywords and concepts related to the lesson content.

[0258] The server then generates visual information or searches for related information based on the extracted keywords. This includes diagrams, illustrations, and animations. This generated visual content is then formatted in a user-friendly way and transmitted to the terminal via the network.

[0259] Meanwhile, the terminal receives data transmitted from the server and displays visual information on the screen. The terminal also uses speech synthesis technology to reproduce text data, allowing users to perceive information aurally. Through this process, children can understand the lesson content using both sight and hearing, instead of reading text.

[0260] Users can provide feedback through their devices if they have questions about the lesson content or need further explanation. This feedback information is then sent back to the server and adjusted to optimize the way the information is presented for the user.

[0261] For example, if "adding fractions" is being explained in class, the server extracts keywords such as "fraction" and "addition," and generates diagrams and animations related to them. These visual materials are then sent to the terminal, which displays them on the screen. Simultaneously, it provides voice guidance using speech synthesis, such as, "The key to adding fractions is to find a common denominator even if the denominators are different."

[0262] In this way, children with learning disabilities can review lesson content and progress through their learning in a way that is easy for them to understand.

[0263] The following describes the processing flow.

[0264] Step 1:

[0265] The server collects teacher and student speech in real time as audio data through microphones installed in the classroom.

[0266] Step 2:

[0267] The server converts the collected audio data into text data using speech recognition software. Noise filtering is also performed during this process to prevent misrecognition.

[0268] Step 3:

[0269] The server uses natural language processing techniques to extract keywords and key concepts from the converted text data. For example, it identifies core lesson terms such as "fractions" and "addition."

[0270] Step 4:

[0271] Based on the extracted keywords, the server generates or retrieves relevant visual information from its internal database or via the internet. This information includes diagrams, graphs, animations, and more.

[0272] Step 5:

[0273] The server combines the generated or acquired visual information to create a data package that clearly explains the learning content, and prepares it for transmission to the terminal.

[0274] Step 6:

[0275] The terminal interprets the data package received from the server and displays visual content on the screen. Simultaneously, it converts text data into speech using a speech synthesis engine and plays it through the speaker.

[0276] Step 7:

[0277] Users understand the lesson content through visual information and audio guides displayed on their devices. If they have questions or need further explanation, they can send feedback through the user interface.

[0278] Step 8:

[0279] The terminal receives feedback from the user and sends it to the server. The server analyzes this feedback and reflects appropriate adjustments during the next content provision.

[0280] (Example 1)

[0281] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0282] There is a problem that it is difficult for children with learning disabilities to effectively understand information visually and auditorily in the conventional class format. There is also a problem that it is difficult to provide effective teaching materials in real time according to the understanding level and learning style of each child.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0284] In this invention, the server includes an input means for collecting sound, a conversion means for converting sound into characters, and an analysis means for extracting important words from the characters. Thereby, it becomes possible to extract important information in real time from the voices emitted in the classroom and provide visual and auditory teaching materials suitable for individual children.

[0285] The "input means" is a device or function for acquiring sound from the environment and taking it in as data.

[0286] The "conversion means" is a process or technology for converting sound data into character data.

[0287] The "analysis means" is a method for identifying and extracting important words or phrases from character data.

[0288] The "generation means" is a technology for creating or acquiring related visual information based on the extracted words.

[0289] "Transmission means" refers to a method or technique for transmitting generated visual information to an output device.

[0290] "Audio output means" refers to technologies or devices that reproduce text data as audio data.

[0291] "Adjustment means" refers to a function that optimizes and adjusts the information displayed based on user feedback.

[0292] An "output device" is a device or interface for displaying visual information and providing audio information.

[0293] This invention functions as an auxiliary system to help children with learning disabilities effectively understand lesson content. Specific embodiments of this system are described below.

[0294] The server collects sound in real time using high-sensitivity microphones installed in the classroom. This process employs advanced sound collection techniques to reduce ambient noise and accurately capture what the teacher is saying. The collected audio data is converted into text data by speech recognition software on the server (e.g., Google Cloud Speech-to-Text). Natural language processing software (e.g., SpaCy or NLTK) analyzes this text data and extracts important keywords.

[0295] Next, the server utilizes a generative AI model (e.g., DALL-E) to generate visual information based on the extracted keywords. It also searches for educational materials on the internet and retrieves relevant content if necessary. This visual information is organized for user understanding and adjusted to avoid overly complex display.

[0296] The generated visual information and audio guides using speech synthesis technology (e.g., Amazon Polly) are transmitted to the device via the network. The device receives this information, displays the visual information on its screen, and plays the audio guide, helping students understand the lesson content through both sight and hearing. Users can also send feedback to the server via the device. Based on this feedback, the server adjusts the way information is presented and the content itself, providing an environment optimized for each individual student.

[0297] As a concrete example, when "adding fractions" is being explained in class, the server extracts keywords such as "fraction" and "addition." In this case, the AI ​​model is given a command such as "Generate visual materials to explain adding fractions" as an example of a prompt, and it creates related illustrations and animations. This allows students to gain a deeper understanding of the lesson content through visual materials, along with audio guidance such as "The key to adding fractions is to find a common denominator even if the denominators are different."

[0298] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0299] Step 1:

[0300] The server collects sound from microphones installed in the classroom. This input is real-time audio data, and the server uses acoustic signal processing technology to remove noise and clarify the teacher's voice. As a result, clean audio data is output.

[0301] Step 2:

[0302] The server inputs the collected audio data into a speech recognition engine, which converts it into text data. This speech recognition engine (for example, Google Cloud Speech-to-Text) analyzes the audio waveform and transcribes it into text. The output is time-tagged text data. This data provides the lesson content as text information.

[0303] Step 3:

[0304] The server extracts important keywords by passing the text data through a natural language processing engine. The natural language processing engine (e.g., SpaCy) analyzes the context and identifies particularly significant words and phrases. The input is the text data from Step 2, and the output is a list of the extracted keywords.

[0305] Step 4:

[0306] The server inputs the extracted keywords as prompts into a generative AI model to generate visual information. The generative AI model (e.g., DALL-E) generates relevant illustrations and animations based on the input prompts. In this step, the keywords are converted into creative visual teaching materials and output as visual materials.

[0307] Step 5:

[0308] The server transmits the generated visual information to the terminal. This communication is carried out via a network, and the terminal prepares the received data. The input is the generated visual information, and the output is the visual content prepared for display on the terminal.

[0309] Step 6:

[0310] The terminal displays the received visual information on the display and uses a text-to-speech engine to reproduce the text data as audio. The text-to-speech engine (e.g., Amazon Polly) generates an audio guide and plays it in synchronization with the visual information. Thereby, the teaching content is provided to the user visually and auditorily. The input is the visual and text information from the server, and the output is the displayed screen and the reproduced audio.

[0311] Step 7:

[0312] Users send feedback on lesson content to the server via their devices. The server analyzes this feedback and incorporates it into the next displayed content and audio guides, providing a learning experience tailored to the user. The input is user feedback, and the output is the adjusted information presentation.

[0313] (Application Example 1)

[0314] 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."

[0315] A challenge exists in that children with learning disabilities often have difficulty fully understanding school lessons. In particular, traditional methods are insufficient for promoting comprehension during lessons, and there is a need for real-time support. Efficiently converting audio data into text and providing information visually and aurally is necessary to deepen students' understanding and promote their participation in lessons.

[0316] 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.

[0317] In this invention, the server includes input means for collecting audio data, conversion means for converting audio data into text data, analysis means for extracting keywords from the text data, generation means for generating or retrieving relevant visual information based on the extracted keywords, distribution means for displaying visual information on a user device and providing audio guidance, and adjustment means for adjusting the displayed information based on user feedback. This enables children to understand the content of lessons more effectively in real time through sight and hearing.

[0318] "Audio data" refers to information that represents an acoustic signal in digital format.

[0319] "Input means" refers to a device or function for collecting audio data from an external source.

[0320] "Conversion means" refers to a device or function for converting audio data into text data.

[0321] "Text data" refers to information expressed as character data, representing the content of audio in written form.

[0322] "Analysis means" refers to a device or function for extracting keywords or important concepts from text data.

[0323] "Generation means" refers to a device or function for generating or retrieving relevant visual information based on extracted keywords.

[0324] "Visual information" refers to information in a format that can be viewed with the eyes, such as diagrams, illustrations, and animations.

[0325] "Distribution means" refers to a device or function for transmitting generated visual information to a user device and providing display and audio guidance.

[0326] "Feedback" refers to information and opinions provided by users, which are used to improve and adjust the system.

[0327] "Adjustment means" refers to a device or function for optimizing display information based on user feedback.

[0328] A "user device" is a device used to receive and display visual and auditory information, and includes smartphones and head-mounted displays.

[0329] The system for implementing this invention operates primarily through the cooperation of a server and a user terminal. The server collects audio from the classroom in real time and converts it into text data using a speech recognition engine. Specifically, a microphone is used to collect audio data, and a speech recognition engine such as the Google Cloud Speech-to-Text API is used for the conversion process.

[0330] The converted text data is then processed using a natural language processing engine on the server, such as the Google Cloud Natural Language API, to extract important keywords and themes. This step allows for the selection of information relevant to the subject and content in real time.

[0331] Next, the server uses the Adobe Creative Cloud API and other tools to generate or retrieve relevant visual information based on the extracted keywords. This visual information includes illustrations and animations, which are presented in a format that is easier for students to understand.

[0332] The generated visual information and audio guides are transmitted from the server to the user's terminal via the network. The user's terminal displays this information on its screen and simultaneously plays the audio guide using speech synthesis technology, such as Amazon Polly. This allows learners to understand the information through both sight and hearing.

[0333] As a concrete example, consider a case where students are learning the concept of "differentiation" in a mathematics class. The server extracts keywords such as "differentiation" and "derivative function" and generates visualized learning materials. The terminal then displays these materials, and an audio guide plays stating, "The derivative function shows the instantaneous rate of change of a function."

[0334] An example of a prompt would be: "Convert the audio from the live lesson to text and visualize the educational content. Extract key concepts and keywords, generate animations based on them, and deliver them to the user in an easy-to-understand manner."

[0335] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0336] Step 1:

[0337] The server collects audio data through microphones placed throughout the classroom. The input is the real-time audio signal from the classroom, and the output is digital audio data. This data is then converted to a format usable in the next step.

[0338] Step 2:

[0339] The server converts the collected audio data into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). In this step, speech recognition technology is used to output the content of the audio in text format. The input is digital audio data, and the output is text data.

[0340] Step 3:

[0341] The server processes text data using a natural language processing engine (e.g., Google Cloud Natural Language API) to extract important keywords and concepts. The input is text data, and the output is a keyword list. This process involves text analysis and selection of key items.

[0342] Step 4:

[0343] The server generates or searches for relevant visual information based on extracted keywords (e.g., using the Adobe Creative Cloud API). The input is a list of keywords, and the output is visual information (diagrams, illustrations, animations, etc.). Here, a generative AI model is used to construct the content.

[0344] Step 5:

[0345] The server transmits the generated visual information and audio guide data to the user's terminal via the network. The input is the visual information and audio guide data, and the output is the transmitted data. Efficient data communication takes place during this process.

[0346] Step 6:

[0347] The device displays received visual information on its screen and plays audio guides using speech synthesis technology (e.g., Amazon Polly). The input is the transmitted data, and the output is the displayed visual information and the played audio. This allows the user to understand the lesson content through both sight and sound.

[0348] Step 7:

[0349] Users send questions and feedback about the lesson content to the server via their terminal. The input is the user's feedback information, and the output is feedback data transferred to the server. This information is used to improve and adjust the system.

[0350] 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.

[0351] This invention provides an auxiliary system for helping children with learning disabilities understand lesson content, equipped with a function to recognize the user's emotions and further enhance learning effectiveness. This system integrates and executes a series of processes, from collecting audio data to emotion recognition.

[0352] First, the server uses microphones in the classroom to record the teacher's voice in real time and converts this audio data into text. Once the text data is generated, natural language processing is used to extract important keywords from the lesson. Based on the extracted keywords, the server generates or searches for relevant visual materials and creates content that aids learning.

[0353] Furthermore, the server sends the generated visual materials and audio data to the user's device. The device receives this content, displays it on its screen, and plays the explanations aloud using speech synthesis technology. This allows the user to understand the lesson content using both their sight and hearing.

[0354] In addition, this system is equipped with an emotion engine that recognizes the user's emotions in real time. Cameras and sensors installed on the terminal collect the user's facial expressions and gaze data, which the emotion engine then analyzes. Based on the analysis results, it estimates the user's level of interest and understanding, and adjusts the presentation speed and difficulty level of the learning materials accordingly.

[0355] For example, if the emotion engine detects a user's decreased concentration while learning fraction addition, the system will select and display simpler examples to adjust the learning pace. Furthermore, if the emotion engine detects that the user is struggling to understand, the device will provide additional visual and audio guidance to support comprehension.

[0356] Thus, the system of the present invention provides an environment in which children can learn effectively at their own pace by combining integrated auditory and visual support with emotion recognition.

[0357] The following describes the processing flow.

[0358] Step 1:

[0359] The server collects audio data in real time from microphones installed in the classroom. Measures have been taken to ensure that all teacher speech is captured without omission.

[0360] Step 2:

[0361] The server converts the collected audio data into text data using a speech recognition engine. This conversion includes noise reduction to generate accurate text.

[0362] Step 3:

[0363] The server analyzes the generated text data using natural language processing techniques to extract keywords and key concepts. It identifies important points of the lesson content and uses them to design teaching materials.

[0364] Step 4:

[0365] The server searches for or generates relevant visual information based on the extracted keywords. It retrieves relevant images, animations, videos, etc., from a database or utilizes online resources.

[0366] Step 5:

[0367] The server creates a data package for sending properly organized visual information to the user terminal and then transmits the data. Optimization is in place for efficient data transfer.

[0368] Step 6:

[0369] The terminal interprets data packages received from the server and displays visual learning materials on its screen. It also uses speech synthesis to play back related text data as audio.

[0370] Step 7:

[0371] Cameras and sensors built into the device collect the user's facial expressions and gaze data and transmit it to the emotion engine. The user's emotional state is monitored in real time.

[0372] Step 8:

[0373] The emotion engine analyzes collected data to determine the user's emotions, interests, and level of engagement. This allows it to predict which content will be most effective for the user.

[0374] Step 9:

[0375] The server dynamically adjusts the presentation speed and difficulty level of the learning materials based on the analysis results of the emotion engine. For example, if there are signs that the user is not understanding the material, it selects materials that are easier to access.

[0376] Step 10:

[0377] Users understand the lesson content through adjusted visual and auditory information. If necessary, users can interact with their devices to provide feedback. This feedback will be used to adjust the content in the next lesson.

[0378] (Example 2)

[0379] 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".

[0380] In conventional educational support systems, the processes of voice-to-text conversion and material generation are independent of each other, making it difficult to understand learners' emotional states in real time and adjust learning content accordingly. In particular, there is a lack of effective learning support for children with learning disabilities, and there is an urgent need to create an environment where children can learn at their own pace.

[0381] 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.

[0382] In this invention, the server includes an input means for collecting audio information, a conversion means for converting the audio information into text information, and an analysis means for extracting important words from the text information. This enables the generation of user-optimized visual materials and the adjustment of learning content based on emotion through real-time text conversion of audio data and extraction of important words.

[0383] "Auditory information" refers to information transmitted through sound, and specifically includes data used in an educational context, particularly the speech of teachers.

[0384] "Input means" refers to devices and methods for acquiring audio information and incorporating it into a system, and mainly includes devices that utilize microphones.

[0385] "Conversion means" refers to a process or device that converts audio information into text information, and includes functions that utilize speech recognition technology.

[0386] "Text information" refers to data in which audio information is represented as a string of characters, and includes information that can be verified in a visual format.

[0387] "Analysis methods" refer to processes that identify important words and phrases from text information and extract keywords related to educational content.

[0388] "Key terms" refer to words or phrases within the text that deserve particular attention and include central concepts for understanding the educational content.

[0389] "Generative means" refers to methods or devices for producing or identifying visual supplementary materials and related content based on extracted key keywords.

[0390] "Visual materials" refer to images and video data generated or acquired to present information visually, and are used as educational aids.

[0391] "Transmission means" refers to communication methods and devices for transmitting generated visual material to a user's terminal and providing it in a viewable state.

[0392] "Emotion recognition means" refers to a process or technology for identifying an emotional state by analyzing a user's facial expressions and gaze data.

[0393] "Emotional state" refers to a user's psychological response, interest, and level of understanding, and is used to evaluate the user's attitude towards educational content.

[0394] "Adjustment means" refers to methods and devices for optimizing the content and presentation speed of learning materials based on the user's emotional state.

[0395] This invention is a learning support system that integrates and executes a series of processes, from collecting voice information to recognizing the user's emotions. A specific embodiment of this system is described below.

[0396] First, in a specific classroom environment, the server uses microphones installed in the classroom to collect the teacher's voice in real time. This voice information is then converted into text using speech recognition software. Specifically, a general service providing speech recognition technology can be used.

[0397] Next, the text information is analyzed on the server using natural language processing techniques to extract important words and phrases. Natural language processing libraries are used for the analysis, and keywords relevant to the lesson content are automatically extracted. This step is crucial for visualizing the key points of what the user is learning.

[0398] Based on the extracted key keywords, the server generates or searches for relevant visual materials. The generation of visual materials can utilize online-accessible educational databases. This allows users to gain a deeper understanding by utilizing visual learning materials.

[0399] Subsequently, the generated visual and audio materials are sent from the server to the user's terminal. The terminal displays the received content on its screen and plays the explanation aloud using a speech synthesis engine. This allows the user to effectively utilize both sight and hearing to advance their learning.

[0400] Furthermore, this system collects user facial expressions and gaze data through cameras and sensors installed on the device in order to recognize the user's emotions in real time. For emotion recognition, it uses a general facial recognition API and provides data to estimate the user's interest and level of understanding.

[0401] For example, when a user is learning "fraction addition," the server uses emotion recognition data to evaluate the user's level of concentration. If the server determines that the user's understanding is insufficient, it automatically presents learning materials with adjusted difficulty levels.

[0402] An example of a prompt message might be, "Explain how the system should respond if the user is learning fraction addition and their concentration wanes."

[0403] Thus, the present invention is a system that integrates audio and visual information and further recognizes the user's emotional state to provide effective educational support tailored to the learning pace of each individual child.

[0404] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0405] Step 1:

[0406] The server uses microphones installed in the classroom to collect teacher voice information in real time. The collected voice information is converted into text information through speech recognition software. Specifically, it receives voice waveform data as input, uses acoustic and language models to recognize phonemes and predict words, and outputs it as text information.

[0407] Step 2:

[0408] The server applies natural language processing techniques to text information to extract important terms. This process involves morphological analysis to extract keywords based on part-of-speech information such as nouns and verbs. From the input text information, it identifies important terms corresponding to specific educational content and outputs a keyword list.

[0409] Step 3:

[0410] The server generates or searches for relevant visual materials based on the extracted key keywords. Specifically, it searches for relevant images and videos from the database, or generates new visual materials using existing templates. The input is a keyword list, and the server outputs visual material files based on this list.

[0411] Step 4:

[0412] The server sends the generated visual and audio information to the user's terminal. The data is transferred using a secure communication protocol. Visual material files and synthesized speech data are taken as input and sent to the user's terminal as output.

[0413] Step 5:

[0414] The terminal displays the received visual material on its screen and plays an audio explanation using a speech synthesis engine. This process uses the visual material file and audio data received from the server as input, and simultaneously displays the image on the screen and outputs it to the speaker.

[0415] Step 6:

[0416] The device uses cameras and sensors to collect data on the user's facial expressions and gaze. This data is transmitted in real time to an emotion recognition engine. It receives the user's physical data (facial expressions, gaze) as input and outputs it directly as data for analysis.

[0417] Step 7:

[0418] The server uses an emotion recognition engine to analyze collected user facial expressions and gaze data to identify the user's emotional state. It then uses feature extraction and discrimination models from the input data to evaluate the user's interest and understanding, and outputs the results.

[0419] Step 8:

[0420] The server adjusts the content and presentation speed of learning materials based on the results of the emotional state analysis. Specifically, it supports user comprehension by appropriately changing the difficulty level of the materials. It receives the emotional analysis results as input and outputs the adjusted learning materials.

[0421] (Application Example 2)

[0422] 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."

[0423] Conventional learning support systems have a problem in that they do not adequately provide adaptive learning support tailored to the user's level of understanding and emotional state, resulting in limited effectiveness, particularly for children with learning disabilities or for training new employees in the workplace. This project aims to solve this problem and provide effective learning and educational support.

[0424] 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.

[0425] In this invention, the server includes input means for collecting audio data, conversion means for converting audio data into text data, analysis means for extracting keywords from the text data, sensor means for collecting user facial expression and gaze data, and emotion recognition means for analyzing the user's emotions and adjusting the presented information based on the results. This enables adaptive learning support and educational support that responds to the user's emotional state.

[0426] "Audio data" refers to sound information recorded as sound waves, and includes digital or analog data such as speech and ambient sounds.

[0427] "Input means" refers to a device or system for collecting audio data, specifically a receiving device such as a microphone or sensor.

[0428] "Conversion means" refers to a technology or device for converting audio data into text data, and includes speech recognition software, etc.

[0429] "Analysis tools" refer to systems or programs that have the function of extracting important information from text data, and utilize natural language processing technology, etc.

[0430] "Generation means" refers to an apparatus or system that performs a process of generating or retrieving relevant visual information based on extracted keywords.

[0431] "Transmission means" refers to a communication device or method for transmitting generated visual information to a user device.

[0432] "Sensor means" refers to a device or system for collecting user facial expression and gaze data, and includes cameras and other sensory sensors.

[0433] "Emotion recognition means" refers to technologies or systems for evaluating a user's emotions, such as estimating their level of interest and understanding through facial expression analysis or gaze data analysis.

[0434] This invention is a complex system used for learning support and educational assistance, and consists of the following main elements: The server first collects audio data using an input means. This audio data is converted into text data by a conversion means. From the converted text data, important keywords are extracted using an analysis means. Next, related visual information is generated or retrieved based on these keywords by a generation means.

[0435] The generated visual information is transmitted to the user device via a means of communication. The user device is typically a terminal equipped with a display, which displays this information. Furthermore, the terminal can use speech synthesis technology to provide information to the user through the audio it plays. Through this process, the user gains a learning experience that utilizes both visual and auditory senses.

[0436] The user device incorporates sensors to collect the user's facial expressions and gaze data. This data is analyzed by emotion recognition to estimate the user's emotional state (e.g., interest and comprehension). Based on this estimation, the system adjusts the visual information and explanations it presents to improve the user's learning efficiency.

[0437] As a concrete example, in the context of training new employees in a factory, this system monitors the level of stress and confusion of users through emotion recognition mechanisms as they learn how to operate new machinery, and dynamically adapts the training content accordingly. For instance, if it is determined that the user is not understanding the material, detailed step-by-step guidance is provided via audio and visuals to aid their comprehension.

[0438] An example of a prompt is, "Use an emotion recognition system to monitor worker stress levels during new machine operation training and dynamically adjust the training content."

[0439] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0440] Step 1:

[0441] The server collects audio data from environments such as classrooms and work sites using input devices. At this stage, a microphone is used to acquire audio in real time and transmit it to the server as digital data. Audio data is the input, and data collection is the output.

[0442] Step 2:

[0443] The server converts the collected audio data into text data using a conversion mechanism. Specifically, it analyzes the audio waveform using speech recognition software and converts it into corresponding text. Audio data is the input, and text data is the output.

[0444] Step 3:

[0445] The server uses analytical tools to extract important keywords from text data. It utilizes natural language processing techniques to identify key words and phrases within the text. This forms the basis for generating related visual information. Text data is the input, and a list of keywords is the output.

[0446] Step 4:

[0447] The server generates or retrieves relevant visual information based on keywords extracted by the generation method. This may involve generating visual information from scratch or retrieving relevant images and videos from a database. Keywords are the input, and visual information is the output.

[0448] Step 5:

[0449] The server transmits the generated visual information to the user device via a means of communication. Internet communication is typically used for this purpose. The visual information is the input, and its delivery to the user device is the output.

[0450] Step 6:

[0451] The terminal displays the transmitted visual information on its screen and, if necessary, uses speech synthesis technology to play relevant explanations aloud to the user. Here, the speech synthesis engine generates speech from text and outputs it through the speaker. Visual information and text are the inputs, and the display and audio output are the outputs.

[0452] Step 7:

[0453] The device uses sensors to collect user facial expressions and gaze data. This information is sent to emotion recognition systems in real time. Cameras and other sensors function as input devices, and the collected data is the output.

[0454] Step 8:

[0455] The device uses emotion recognition to analyze the user's emotional state (interest, understanding, etc.) from collected data. It uses machine learning algorithms to recognize patterns and estimate the user's state. Facial expressions and eye gaze data are inputs, and the emotional state evaluation is the output.

[0456] Step 9:

[0457] The server dynamically adjusts the content and pace of the presented information based on the results of emotion recognition. If necessary, it adds supplementary visual information or audio guidance. The emotional state assessment is the input, and the adjusted presented information is the output.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] [Third Embodiment]

[0462] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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).

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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".

[0474] This invention provides an assistive system to help children with learning disabilities to smoothly understand school lessons. This system has various functions for processing audio emitted in the classroom in real time and providing visual learning materials.

[0475] This system is configured as follows: First, the server collects audio data through microphones placed in the classroom. This audio data is converted into text data using a speech recognition engine on the server. This converted text is then processed by the server using natural language processing to extract important keywords and concepts related to the lesson content.

[0476] The server then generates visual information or searches for related information based on the extracted keywords. This includes diagrams, illustrations, and animations. This generated visual content is then formatted in a user-friendly way and transmitted to the terminal via the network.

[0477] Meanwhile, the terminal receives data transmitted from the server and displays visual information on the screen. The terminal also uses speech synthesis technology to reproduce text data, allowing users to perceive information aurally. Through this process, children can understand the lesson content using both sight and hearing, instead of reading text.

[0478] Users can provide feedback through their devices if they have questions about the lesson content or need further explanation. This feedback information is then sent back to the server and adjusted to optimize the way the information is presented for the user.

[0479] For example, if "adding fractions" is being explained in class, the server extracts keywords such as "fraction" and "addition," and generates diagrams and animations related to them. These visual materials are then sent to the terminal, which displays them on the screen. Simultaneously, it provides voice guidance using speech synthesis, such as, "The key to adding fractions is to find a common denominator even if the denominators are different."

[0480] In this way, children with learning disabilities can review lesson content and progress through their learning in a way that is easy for them to understand.

[0481] The following describes the processing flow.

[0482] Step 1:

[0483] The server collects teacher and student speech in real time as audio data through microphones installed in the classroom.

[0484] Step 2:

[0485] The server converts the collected audio data into text data using speech recognition software. Noise filtering is also performed during this process to prevent misrecognition.

[0486] Step 3:

[0487] The server uses natural language processing techniques to extract keywords and key concepts from the converted text data. For example, it identifies core lesson terms such as "fractions" and "addition."

[0488] Step 4:

[0489] Based on the extracted keywords, the server generates or retrieves relevant visual information from its internal database or via the internet. This information includes diagrams, graphs, animations, and more.

[0490] Step 5:

[0491] The server combines the generated or acquired visual information to create a data package that clearly explains the learning content, and prepares it for transmission to the terminal.

[0492] Step 6:

[0493] The terminal interprets the data package received from the server and displays visual content on the screen. Simultaneously, it converts text data into speech using a speech synthesis engine and plays it through the speaker.

[0494] Step 7:

[0495] Users understand the lesson content through visual information and audio guides displayed on their devices. If they have questions or need further explanation, they can send feedback through the user interface.

[0496] Step 8:

[0497] The device receives feedback from the user and sends it to the server. The server analyzes this feedback and incorporates appropriate adjustments into the next content delivery.

[0498] (Example 1)

[0499] 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."

[0500] Children with learning disabilities face challenges in effectively understanding information visually and aurally within traditional classroom settings. Furthermore, there are difficulties in providing effective learning materials tailored to each child's level of understanding and learning style in real time.

[0501] 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.

[0502] In this invention, the server includes an input means for collecting sound, a conversion means for converting sound into text, and an analysis means for extracting important words from the text. This makes it possible to extract important information in real time from sounds emitted in the classroom and provide visual and auditory teaching materials tailored to individual children.

[0503] "Input means" refers to devices or functions that acquire sound from the environment and capture it as data.

[0504] "Conversion method" refers to the process or technology used to convert audio data into text data.

[0505] "Analysis method" refers to a method for identifying and extracting important words and phrases from text data.

[0506] "Generation means" refers to techniques for creating or acquiring relevant visual information based on extracted words.

[0507] "Transmission means" refers to a method or technique for transmitting generated visual information to an output device.

[0508] "Audio output means" refers to technologies or devices that reproduce text data as audio data.

[0509] "Adjustment means" refers to a function that optimizes and adjusts the information displayed based on user feedback.

[0510] An "output device" is a device or interface for displaying visual information and providing audio information.

[0511] This invention functions as an auxiliary system to help children with learning disabilities effectively understand lesson content. Specific embodiments of this system are described below.

[0512] The server collects sound in real time using high-sensitivity microphones installed in the classroom. This process employs advanced sound collection techniques to reduce ambient noise and accurately capture what the teacher is saying. The collected audio data is converted into text data by speech recognition software on the server (e.g., Google Cloud Speech-to-Text). Natural language processing software (e.g., SpaCy or NLTK) analyzes this text data and extracts important keywords.

[0513] Next, the server utilizes a generative AI model (e.g., DALL-E) to generate visual information based on the extracted keywords. It also searches for educational materials on the internet and retrieves relevant content if necessary. This visual information is organized for user understanding and adjusted to avoid overly complex display.

[0514] The generated visual information and audio guides using speech synthesis technology (e.g., Amazon Polly) are transmitted to the device via the network. The device receives this information, displays the visual information on its screen, and plays the audio guide, helping students understand the lesson content through both sight and hearing. Users can also send feedback to the server via the device. Based on this feedback, the server adjusts the way information is presented and the content itself, providing an environment optimized for each individual student.

[0515] As a concrete example, when "adding fractions" is being explained in class, the server extracts keywords such as "fraction" and "addition." In this case, the AI ​​model is given a command such as "Generate visual materials to explain adding fractions" as an example of a prompt, and it creates related illustrations and animations. This allows students to gain a deeper understanding of the lesson content through visual materials, along with audio guidance such as "The key to adding fractions is to find a common denominator even if the denominators are different."

[0516] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0517] Step 1:

[0518] The server collects sound from microphones installed in the classroom. This input is real-time audio data, and the server uses acoustic signal processing technology to remove noise and clarify the teacher's voice. As a result, clean audio data is output.

[0519] Step 2:

[0520] The server inputs the collected audio data into a speech recognition engine, which converts it into text data. This speech recognition engine (for example, Google Cloud Speech-to-Text) analyzes the audio waveform and transcribes it into text. The output is time-tagged text data. This data provides the lesson content as text information.

[0521] Step 3:

[0522] The server processes the text data through a natural language processing engine to extract important keywords. The natural language processing engine (e.g., SpaCy) analyzes the context and identifies particularly significant words and phrases. The input is the text data from step 2, and the output is a list of extracted keywords.

[0523] Step 4:

[0524] The server inputs the extracted keywords as prompts into a generative AI model to generate visual information. The generative AI model (e.g., DALL-E) generates relevant illustrations and animations based on the input prompts. In this step, the keywords are transformed into creative visual learning materials and output as visual resources.

[0525] Step 5:

[0526] The server sends the generated visual information to the terminal. This communication takes place over the network, and the terminal prepares the received data. The input is the generated visual information, and the output is the visual content prepared for display on the terminal.

[0527] Step 6:

[0528] The device displays received visual information on its screen and uses a speech synthesis engine to play text data as audio. The speech synthesis engine (e.g., Amazon Polly) generates audio guides and plays them in sync with the visual information. This provides the user with lesson content both visually and aurally. The input is visual and text information from the server, and the output is the displayed screen and the played audio.

[0529] Step 7:

[0530] Users send feedback on lesson content to the server via their devices. The server analyzes this feedback and incorporates it into the next displayed content and audio guides, providing a learning experience tailored to the user. The input is user feedback, and the output is the adjusted information presentation.

[0531] (Application Example 1)

[0532] 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."

[0533] A challenge exists in that children with learning disabilities often have difficulty fully understanding school lessons. In particular, traditional methods are insufficient for promoting comprehension during lessons, and there is a need for real-time support. Efficiently converting audio data into text and providing information visually and aurally is necessary to deepen students' understanding and promote their participation in lessons.

[0534] 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.

[0535] In this invention, the server includes input means for collecting audio data, conversion means for converting audio data into text data, analysis means for extracting keywords from the text data, generation means for generating or retrieving relevant visual information based on the extracted keywords, distribution means for displaying visual information on a user device and providing audio guidance, and adjustment means for adjusting the displayed information based on user feedback. This enables children to understand the content of lessons more effectively in real time through sight and hearing.

[0536] "Audio data" refers to information that represents an acoustic signal in digital format.

[0537] "Input means" refers to a device or function for collecting audio data from an external source.

[0538] "Conversion means" refers to a device or function for converting audio data into text data.

[0539] "Text data" refers to information expressed as character data, representing the content of audio in written form.

[0540] "Analysis means" refers to a device or function for extracting keywords or important concepts from text data.

[0541] "Generation means" refers to a device or function for generating or retrieving relevant visual information based on extracted keywords.

[0542] "Visual information" refers to information in a format that can be viewed with the eyes, such as diagrams, illustrations, and animations.

[0543] "Distribution means" refers to a device or function for transmitting generated visual information to a user device and providing display and audio guidance.

[0544] "Feedback" refers to information and opinions provided by users, which are used to improve and adjust the system.

[0545] "Adjustment means" refers to a device or function for optimizing display information based on user feedback.

[0546] A "user device" is a device used to receive and display visual and auditory information, and includes smartphones and head-mounted displays.

[0547] The system for implementing this invention operates primarily through the cooperation of a server and a user terminal. The server collects audio from the classroom in real time and converts it into text data using a speech recognition engine. Specifically, a microphone is used to collect audio data, and a speech recognition engine such as the Google Cloud Speech-to-Text API is used for the conversion process.

[0548] The converted text data is then processed using a natural language processing engine on the server, such as the Google Cloud Natural Language API, to extract important keywords and themes. This step allows for the selection of information relevant to the subject and content in real time.

[0549] Next, the server uses the Adobe Creative Cloud API and other tools to generate or retrieve relevant visual information based on the extracted keywords. This visual information includes illustrations and animations, which are presented in a format that is easier for students to understand.

[0550] The generated visual information and audio guides are transmitted from the server to the user's terminal via the network. The user's terminal displays this information on its screen and simultaneously plays the audio guide using speech synthesis technology, such as Amazon Polly. This allows learners to understand the information through both sight and hearing.

[0551] As a concrete example, consider a situation where students are learning the concept of "differentiation" in a mathematics class. The server extracts keywords such as "differentiation" and "derivative function" and generates visualized learning materials. The terminal then displays these materials, and an audio guide plays stating, "The derivative function shows the instantaneous rate of change of a function."

[0552] An example of a prompt would be: "Convert the audio from the live lesson to text and visualize the educational content. Extract key concepts and keywords, generate animations based on them, and deliver them to the user in an easy-to-understand manner."

[0553] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0554] Step 1:

[0555] The server collects audio data through microphones placed throughout the classroom. The input is the real-time audio signal from the classroom, and the output is digital audio data. This data is then converted to a format usable in the next step.

[0556] Step 2:

[0557] The server converts the collected audio data into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). In this step, speech recognition technology is used to output the content of the audio in text format. The input is digital audio data, and the output is text data.

[0558] Step 3:

[0559] The server processes text data using a natural language processing engine (e.g., Google Cloud Natural Language API) to extract important keywords and concepts. The input is text data, and the output is a keyword list. This process involves text analysis and selection of key items.

[0560] Step 4:

[0561] The server generates or searches for relevant visual information based on extracted keywords (e.g., using the Adobe Creative Cloud API). The input is a list of keywords, and the output is visual information (diagrams, illustrations, animations, etc.). Here, a generative AI model is used to construct the content.

[0562] Step 5:

[0563] The server transmits the generated visual information and audio guide data to the user's terminal via the network. The input is the visual information and audio guide data, and the output is the transmitted data. Efficient data communication takes place during this process.

[0564] Step 6:

[0565] The device displays received visual information on its screen and plays audio guides using speech synthesis technology (e.g., Amazon Polly). The input is the transmitted data, and the output is the displayed visual information and the played audio. This allows the user to understand the lesson content through both sight and sound.

[0566] Step 7:

[0567] Users send questions and feedback about the lesson content to the server via their terminal. The input is the user's feedback information, and the output is feedback data transferred to the server. This information is used to improve and adjust the system.

[0568] 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.

[0569] This invention provides an auxiliary system for helping children with learning disabilities understand lesson content, equipped with a function to recognize the user's emotions and further enhance learning effectiveness. This system integrates and executes a series of processes, from collecting audio data to emotion recognition.

[0570] First, the server uses microphones in the classroom to record the teacher's voice in real time and converts this audio data into text. Once the text data is generated, natural language processing is used to extract important keywords from the lesson. Based on the extracted keywords, the server generates or searches for relevant visual materials and creates content that aids learning.

[0571] Furthermore, the server transmits the generated visual materials and audio data to the user's device. The device receives this content, displays it on its screen, and plays the explanations aloud using speech synthesis technology. This allows the user to understand the lesson content using both their sight and hearing.

[0572] In addition, this system is equipped with an emotion engine that recognizes the user's emotions in real time. Cameras and sensors installed on the terminal collect the user's facial expressions and gaze data, which the emotion engine then analyzes. Based on the analysis results, it estimates the user's level of interest and understanding, and adjusts the presentation speed and difficulty level of the learning materials accordingly.

[0573] For example, if the emotion engine detects a user's decreased concentration while learning fraction addition, the system will select and display simpler examples to adjust the learning pace. Furthermore, if the emotion engine detects that the user is struggling to understand, the device will provide additional visual and audio guidance to support comprehension.

[0574] Thus, the system of the present invention provides an environment in which children can learn effectively at their own pace by combining integrated auditory and visual support with emotion recognition.

[0575] The following describes the processing flow.

[0576] Step 1:

[0577] The server collects audio data in real time from microphones installed in the classroom. Measures have been taken to ensure that all teacher speech is captured without omission.

[0578] Step 2:

[0579] The server converts the collected audio data into text data using a speech recognition engine. This conversion includes noise reduction to generate accurate text.

[0580] Step 3:

[0581] The server analyzes the generated text data using natural language processing techniques to extract keywords and key concepts. It identifies important points of the lesson content and uses them to design teaching materials.

[0582] Step 4:

[0583] The server searches for or generates relevant visual information based on the extracted keywords. It retrieves relevant images, animations, videos, etc., from a database or utilizes online resources.

[0584] Step 5:

[0585] The server creates a data package for sending properly organized visual information to the user terminal and then transmits the data. Optimization is in place for efficient data transfer.

[0586] Step 6:

[0587] The terminal interprets data packages received from the server and displays visual learning materials on its screen. It also uses speech synthesis to play back related text data as audio.

[0588] Step 7:

[0589] The camera and sensors built into the device collect the user's facial expressions and gaze data and transmit it to the emotion engine. This allows for real-time monitoring of the user's emotional state.

[0590] Step 8:

[0591] The emotion engine analyzes collected data to determine the user's emotions, interests, and level of engagement. This allows it to predict which content will be most effective for the user.

[0592] Step 9:

[0593] The server dynamically adjusts the presentation speed and difficulty level of the learning materials based on the analysis results of the emotion engine. For example, if there are signs that the user is not understanding the material, it selects materials that are easier to access.

[0594] Step 10:

[0595] Users understand the lesson content through adjusted visual and auditory information. If necessary, users can interact with their devices to provide feedback. This feedback will be used to adjust the content in the next lesson.

[0596] (Example 2)

[0597] 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."

[0598] In conventional educational support systems, the processes of voice-to-text conversion and material generation are independent of each other, making it difficult to understand learners' emotional states in real time and adjust learning content accordingly. In particular, there is a lack of effective learning support for children with learning disabilities, and there is an urgent need to create an environment where children can learn at their own pace.

[0599] 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.

[0600] In this invention, the server includes an input means for collecting audio information, a conversion means for converting the audio information into text information, and an analysis means for extracting important words from the text information. This enables the generation of user-optimized visual materials and the adjustment of learning content based on emotion through real-time text conversion of audio data and extraction of important words.

[0601] "Auditory information" refers to information transmitted through sound, and specifically includes data used in an educational context, particularly the speech of teachers.

[0602] "Input means" refers to devices and methods for acquiring audio information and incorporating it into a system, and mainly includes devices that utilize microphones.

[0603] "Conversion means" refers to a process or device that converts audio information into text information, and includes functions that utilize speech recognition technology.

[0604] "Text information" refers to data in which audio information is represented as a string of characters, and includes information that can be verified in a visual format.

[0605] "Analysis methods" refer to processes that identify important words and phrases from text information and extract keywords related to educational content.

[0606] "Key terms" refer to words or phrases within the text that deserve particular attention and include central concepts for understanding the educational content.

[0607] "Generative means" refers to methods or devices for producing or identifying visual supplementary materials and related content based on extracted key keywords.

[0608] "Visual materials" refer to images and video data generated or acquired to present information visually, and are used as educational aids.

[0609] "Transmission means" refers to communication methods and devices for transmitting generated visual material to a user's terminal and providing it in a viewable state.

[0610] "Emotion recognition means" refers to a process or technology for identifying an emotional state by analyzing a user's facial expressions and gaze data.

[0611] "Emotional state" refers to a user's psychological response, interest, and level of understanding, and is used to evaluate the user's attitude towards educational content.

[0612] "Adjustment means" refers to methods and devices for optimizing the content and presentation speed of learning materials based on the user's emotional state.

[0613] This invention is a learning support system that integrates and executes a series of processes, from collecting voice information to recognizing the user's emotions. A specific embodiment of this system is described below.

[0614] First, in a specific classroom environment, the server uses microphones installed in the classroom to collect the teacher's voice in real time. This voice information is then converted into text using speech recognition software. Specifically, a general service providing speech recognition technology can be used.

[0615] Next, the text information is analyzed on the server using natural language processing techniques to extract important words and phrases. Natural language processing libraries are used for the analysis, and keywords relevant to the lesson content are automatically extracted. This step is crucial for visualizing the key points of what the user is learning.

[0616] Based on the extracted key keywords, the server generates or searches for relevant visual materials. The generation of visual materials can utilize online-accessible educational databases. This allows users to gain a deeper understanding by utilizing visual learning materials.

[0617] Subsequently, the generated visual and audio materials are sent from the server to the user's terminal. The terminal displays the received content on its screen and plays the explanation aloud using a speech synthesis engine. This allows the user to effectively utilize both sight and hearing to advance their learning.

[0618] Furthermore, to recognize the user's emotions in real time, this system collects facial expression and gaze data through cameras and sensors installed on the device. For emotion recognition, it uses a common facial recognition API to provide data for estimating the user's interest and level of understanding.

[0619] For example, when a user is learning "fraction addition," the server uses emotion recognition data to evaluate the user's level of concentration. If the server determines that the user's understanding is insufficient, it automatically presents learning materials with adjusted difficulty levels.

[0620] An example of a prompt message might be: "Explain how the system should respond if the user is learning fraction addition and their concentration wanes."

[0621] Thus, the present invention is a system that integrates audio and visual information and further recognizes the user's emotional state to provide effective educational support tailored to the learning pace of each individual child.

[0622] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0623] Step 1:

[0624] The server uses microphones installed in the classroom to collect teacher voice information in real time. The collected voice information is converted into text information through speech recognition software. Specifically, it receives voice waveform data as input, uses acoustic and language models to recognize phonemes and predict words, and outputs it as text information.

[0625] Step 2:

[0626] The server applies natural language processing techniques to text information to extract important terms. This process involves morphological analysis to extract keywords based on part-of-speech information such as nouns and verbs. From the input text information, it identifies important terms corresponding to specific educational content and outputs a keyword list.

[0627] Step 3:

[0628] The server generates or searches for relevant visual materials based on the extracted key keywords. Specifically, it searches for relevant images and videos from the database, or generates new visual materials using existing templates. The input is a keyword list, and the server outputs visual material files based on this list.

[0629] Step 4:

[0630] The server sends the generated visual and audio information to the user's terminal. The data is transferred using a secure communication protocol. Visual material files and synthesized speech data are taken as input and sent to the user's terminal as output.

[0631] Step 5:

[0632] The terminal displays the received visual material on its screen and plays an audio explanation using a speech synthesis engine. This process uses the visual material file and audio data received from the server as input, and simultaneously displays the image on the screen and outputs it to the speaker.

[0633] Step 6:

[0634] The device uses cameras and sensors to collect data on the user's facial expressions and gaze. This data is transmitted in real time to an emotion recognition engine. It receives the user's physical data (facial expressions, gaze) as input and outputs it directly as data for analysis.

[0635] Step 7:

[0636] The server uses an emotion recognition engine to analyze collected user facial expressions and gaze data to identify the user's emotional state. It then uses feature extraction and discrimination models from the input data to evaluate the user's interest and understanding, and outputs the results.

[0637] Step 8:

[0638] The server adjusts the content and presentation speed of learning materials based on the results of the emotional state analysis. Specifically, it supports user comprehension by appropriately changing the difficulty level of the materials. It receives the emotional analysis results as input and outputs the adjusted learning materials.

[0639] (Application Example 2)

[0640] 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."

[0641] Conventional learning support systems have a problem in that they do not adequately provide adaptive learning support tailored to the user's level of understanding and emotional state, resulting in limited effectiveness, particularly for children with learning disabilities or for training new employees in the workplace. This project aims to solve this problem and provide effective learning and educational support.

[0642] 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.

[0643] In this invention, the server includes input means for collecting audio data, conversion means for converting audio data into text data, analysis means for extracting keywords from the text data, sensor means for collecting user facial expression and gaze data, and emotion recognition means for analyzing the user's emotions and adjusting the presented information based on the results. This enables adaptive learning support and educational support that responds to the user's emotional state.

[0644] "Audio data" refers to sound information recorded as sound waves, and includes digital or analog data such as speech and ambient sounds.

[0645] "Input means" refers to a device or system for collecting audio data, specifically a receiving device such as a microphone or sensor.

[0646] "Conversion means" refers to a technology or device for converting audio data into text data, and includes speech recognition software, etc.

[0647] "Analysis tools" refer to systems or programs that have the function of extracting important information from text data, and utilize natural language processing technology, etc.

[0648] "Generation means" refers to an apparatus or system that performs a process of generating or retrieving relevant visual information based on extracted keywords.

[0649] "Transmission means" refers to a communication device or method for transmitting generated visual information to a user device.

[0650] "Sensor means" refers to a device or system for collecting user facial expression and gaze data, and includes cameras and other sensory sensors.

[0651] "Emotion recognition means" refers to technologies or systems for evaluating a user's emotions, such as estimating their level of interest and understanding through facial expression analysis or gaze data analysis.

[0652] This invention is a complex system used for learning support and educational assistance, and consists of the following main elements: The server first collects audio data using an input means. This audio data is converted into text data by a conversion means. From the converted text data, important keywords are extracted using an analysis means. Next, related visual information is generated or retrieved based on these keywords by a generation means.

[0653] The generated visual information is transmitted to the user device via a means of communication. The user device is typically a terminal equipped with a display, which displays this information. Furthermore, the terminal can use speech synthesis technology to provide information to the user through the audio it plays. Through this process, the user gains a learning experience that utilizes both visual and auditory senses.

[0654] The user device incorporates sensors to collect the user's facial expressions and gaze data. This data is analyzed by emotion recognition to estimate the user's emotional state (e.g., interest and comprehension). Based on this estimation, the system adjusts the visual information and explanations it presents to improve the user's learning efficiency.

[0655] As a concrete example, in the context of training new employees in a factory, this system monitors the level of stress and confusion of users through emotion recognition mechanisms as they learn how to operate new machinery, and dynamically adapts the training content accordingly. For instance, if it is determined that the user is not understanding the material, detailed step-by-step guidance is provided via audio and visuals to aid their comprehension.

[0656] An example of a prompt is, "Use an emotion recognition system to monitor worker stress levels during new machine operation training and dynamically adjust the training content."

[0657] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0658] Step 1:

[0659] The server collects audio data from environments such as classrooms and work sites using input devices. At this stage, a microphone is used to acquire audio in real time and transmit it to the server as digital data. The audio data is the input, and the data collection is the output.

[0660] Step 2:

[0661] The server converts the collected audio data into text data using a conversion mechanism. Specifically, it analyzes the audio waveform using speech recognition software and converts it into corresponding text. Audio data is the input, and text data is the output.

[0662] Step 3:

[0663] The server uses analytical tools to extract important keywords from text data. It utilizes natural language processing techniques to identify key words and phrases within the text. This forms the basis for generating related visual information. Text data is the input, and a list of keywords is the output.

[0664] Step 4:

[0665] The server generates or retrieves relevant visual information based on keywords extracted by the generation method. This may involve generating visual information from scratch or retrieving relevant images and videos from a database. Keywords are the input, and visual information is the output.

[0666] Step 5:

[0667] The server transmits the generated visual information to the user device via a means of communication. Internet communication is typically used for this purpose. The visual information is the input, and its delivery to the user device is the output.

[0668] Step 6:

[0669] The terminal displays the transmitted visual information on its screen and, if necessary, uses speech synthesis technology to play relevant explanations aloud to the user. Here, the speech synthesis engine generates speech from text and outputs it through the speaker. Visual information and text are the inputs, and the display and audio output are the outputs.

[0670] Step 7:

[0671] The device uses sensors to collect user facial expressions and gaze data. This information is sent to emotion recognition systems in real time. Cameras and other sensors function as input devices, and the collected data is the output.

[0672] Step 8:

[0673] The device uses emotion recognition to analyze the user's emotional state (interest, understanding, etc.) from collected data. It uses machine learning algorithms to recognize patterns and estimate the user's state. Facial expressions and eye gaze data are inputs, and the emotional state evaluation is the output.

[0674] Step 9:

[0675] The server dynamically adjusts the content and pace of the presented information based on the results of emotion recognition. If necessary, it adds supplementary visual information or audio guidance. The emotional state assessment is the input, and the adjusted presented information is the output.

[0676] 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.

[0677] 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.

[0678] 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.

[0679] [Fourth Embodiment]

[0680] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0681] 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.

[0682] 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).

[0683] 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.

[0684] 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.

[0685] 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).

[0686] 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.

[0687] 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.

[0688] 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.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] 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".

[0693] This invention provides an assistive system to help children with learning disabilities to smoothly understand school lessons. This system has various functions for processing audio emitted in the classroom in real time and providing visual learning materials.

[0694] This system is configured as follows: First, the server collects audio data through microphones placed in the classroom. This audio data is converted into text data using a speech recognition engine on the server. This converted text is then processed by the server using natural language processing to extract important keywords and concepts related to the lesson content.

[0695] The server then generates visual information or searches for related information based on the extracted keywords. This includes diagrams, illustrations, and animations. This generated visual content is then formatted in a user-friendly way and transmitted to the terminal via the network.

[0696] Meanwhile, the terminal receives data transmitted from the server and displays visual information on the screen. The terminal also uses speech synthesis technology to reproduce text data, allowing users to perceive information aurally. Through this process, children can understand the lesson content using both sight and hearing, instead of reading text.

[0697] Users can provide feedback through their devices if they have questions about the lesson content or need further explanation. This feedback information is then sent back to the server and adjusted to optimize the way the information is presented for the user.

[0698] For example, if "adding fractions" is being explained in class, the server extracts keywords such as "fraction" and "addition," and generates diagrams and animations related to them. These visual materials are then sent to the terminal, which displays them on the screen. Simultaneously, it provides voice guidance using speech synthesis, such as, "The key to adding fractions is to find a common denominator even if the denominators are different."

[0699] In this way, children with learning disabilities can review lesson content and progress through their learning in a way that is easy for them to understand.

[0700] The following describes the processing flow.

[0701] Step 1:

[0702] The server collects teacher and student speech in real time as audio data through microphones installed in the classroom.

[0703] Step 2:

[0704] The server converts the collected audio data into text data using speech recognition software. Noise filtering is also performed during this process to prevent misrecognition.

[0705] Step 3:

[0706] The server uses natural language processing techniques to extract keywords and key concepts from the converted text data. For example, it identifies core lesson terms such as "fractions" and "addition."

[0707] Step 4:

[0708] Based on the extracted keywords, the server generates or retrieves relevant visual information from its internal database or via the internet. This information includes diagrams, graphs, animations, and more.

[0709] Step 5:

[0710] The server combines the generated or acquired visual information to create a data package that clearly explains the learning content, and prepares it for transmission to the terminal.

[0711] Step 6:

[0712] The terminal interprets the data package received from the server and displays visual content on the screen. Simultaneously, it converts text data into speech using a speech synthesis engine and plays it through the speaker.

[0713] Step 7:

[0714] Users understand the lesson content through visual information and audio guides displayed on their devices. If they have questions or need further explanation, they can send feedback through the user interface.

[0715] Step 8:

[0716] The device receives feedback from the user and sends it to the server. The server analyzes this feedback and incorporates appropriate adjustments into the next content delivery.

[0717] (Example 1)

[0718] 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".

[0719] Children with learning disabilities face challenges in effectively understanding information visually and aurally within traditional classroom settings. Furthermore, there are difficulties in providing effective learning materials tailored to each child's level of understanding and learning style in real time.

[0720] 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.

[0721] In this invention, the server includes an input means for collecting sound, a conversion means for converting sound into text, and an analysis means for extracting important words from the text. This makes it possible to extract important information in real time from sounds emitted in the classroom and provide visual and auditory teaching materials tailored to individual children.

[0722] "Input means" refers to devices or functions that acquire sound from the environment and capture it as data.

[0723] "Conversion method" refers to the process or technology used to convert audio data into text data.

[0724] "Analysis method" refers to a method for identifying and extracting important words and phrases from text data.

[0725] "Generation means" refers to techniques for creating or acquiring relevant visual information based on extracted words.

[0726] "Transmission means" refers to a method or technique for transmitting generated visual information to an output device.

[0727] "Audio output means" refers to technologies or devices that reproduce text data as audio data.

[0728] "Adjustment means" refers to a function that optimizes and adjusts the information displayed based on user feedback.

[0729] An "output device" is a device or interface for displaying visual information and providing audio information.

[0730] This invention functions as an auxiliary system to help children with learning disabilities effectively understand lesson content. Specific embodiments of this system are described below.

[0731] The server collects sound in real time using high-sensitivity microphones installed in the classroom. This process employs advanced sound collection techniques to reduce ambient noise and accurately capture what the teacher is saying. The collected audio data is converted into text data by speech recognition software on the server (e.g., Google Cloud Speech-to-Text). Natural language processing software (e.g., SpaCy or NLTK) analyzes this text data and extracts important keywords.

[0732] Next, the server utilizes a generative AI model (e.g., DALL-E) to generate visual information based on the extracted keywords. It also searches for educational materials on the internet and retrieves relevant content if necessary. This visual information is organized for user understanding and adjusted to avoid overly complex display.

[0733] The generated visual information and audio guides using speech synthesis technology (e.g., Amazon Polly) are transmitted to the device via the network. The device receives this information, displays the visual information on its screen, and plays the audio guide, helping students understand the lesson content through both sight and hearing. Users can also send feedback to the server via the device. Based on this feedback, the server adjusts the way information is presented and the content itself, providing an environment optimized for each individual student.

[0734] As a concrete example, when "adding fractions" is being explained in class, the server extracts keywords such as "fraction" and "addition." In this case, the AI ​​model is given a command such as "Generate visual materials to explain adding fractions" as an example of a prompt, and it creates related illustrations and animations. This allows students to gain a deeper understanding of the lesson content through visual materials, along with audio guidance such as "The key to adding fractions is to find a common denominator even if the denominators are different."

[0735] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0736] Step 1:

[0737] The server collects sound from microphones installed in the classroom. This input is real-time audio data, and the server uses acoustic signal processing technology to remove noise and clarify the teacher's voice. As a result, clean audio data is output.

[0738] Step 2:

[0739] The server inputs the collected audio data into a speech recognition engine, which converts it into text data. This speech recognition engine (for example, Google Cloud Speech-to-Text) analyzes the audio waveform and transcribes it into text. The output is time-tagged text data. This data provides the lesson content as text information.

[0740] Step 3:

[0741] The server processes the text data through a natural language processing engine to extract important keywords. The natural language processing engine (e.g., SpaCy) analyzes the context and identifies particularly significant words and phrases. The input is the text data from step 2, and the output is a list of extracted keywords.

[0742] Step 4:

[0743] The server inputs the extracted keywords as prompts into a generative AI model to generate visual information. The generative AI model (e.g., DALL-E) generates relevant illustrations and animations based on the input prompts. In this step, the keywords are transformed into creative visual learning materials and output as visual resources.

[0744] Step 5:

[0745] The server sends the generated visual information to the terminal. This communication takes place over the network, and the terminal prepares the received data. The input is the generated visual information, and the output is the visual content prepared for display on the terminal.

[0746] Step 6:

[0747] The device displays received visual information on its screen and uses a speech synthesis engine to play text data as audio. The speech synthesis engine (e.g., Amazon Polly) generates audio guides and plays them in sync with the visual information. This provides the user with lesson content both visually and aurally. The input is visual and text information from the server, and the output is the displayed screen and the played audio.

[0748] Step 7:

[0749] Users send feedback on lesson content to the server via their devices. The server analyzes this feedback and incorporates it into the next displayed content and audio guides, providing a learning experience tailored to the user. The input is user feedback, and the output is the adjusted information presentation.

[0750] (Application Example 1)

[0751] 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".

[0752] A challenge exists in that children with learning disabilities often have difficulty fully understanding school lessons. In particular, traditional methods are insufficient for promoting comprehension during lessons, and there is a need for real-time support. Efficiently converting audio data into text and providing information visually and aurally is necessary to deepen students' understanding and promote their participation in lessons.

[0753] 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.

[0754] In this invention, the server includes input means for collecting audio data, conversion means for converting audio data into text data, analysis means for extracting keywords from the text data, generation means for generating or retrieving relevant visual information based on the extracted keywords, distribution means for displaying visual information on a user device and providing audio guidance, and adjustment means for adjusting the displayed information based on user feedback. This enables children to understand the content of lessons more effectively in real time through sight and hearing.

[0755] "Audio data" refers to information that represents an acoustic signal in digital format.

[0756] "Input means" refers to a device or function for collecting audio data from an external source.

[0757] "Conversion means" refers to a device or function for converting audio data into text data.

[0758] "Text data" refers to information expressed as character data, representing the content of audio in written form.

[0759] "Analysis means" refers to a device or function for extracting keywords or important concepts from text data.

[0760] "Generation means" refers to a device or function for generating or retrieving relevant visual information based on extracted keywords.

[0761] "Visual information" refers to information in a format that can be viewed with the eyes, such as diagrams, illustrations, and animations.

[0762] "Distribution means" refers to a device or function for transmitting generated visual information to a user device and providing display and audio guidance.

[0763] "Feedback" refers to information and opinions provided by users, which are used to improve and adjust the system.

[0764] "Adjustment means" refers to a device or function for optimizing display information based on user feedback.

[0765] A "user device" is a device used to receive and display visual and auditory information, and includes smartphones and head-mounted displays.

[0766] The system for implementing this invention operates primarily through the cooperation of a server and a user terminal. The server collects audio from the classroom in real time and converts it into text data using a speech recognition engine. Specifically, a microphone is used to collect audio data, and a speech recognition engine such as the Google Cloud Speech-to-Text API is used for the conversion process.

[0767] The converted text data is then processed using a natural language processing engine on the server, such as the Google Cloud Natural Language API, to extract important keywords and themes. This step allows for the selection of information relevant to the subject and content in real time.

[0768] Next, the server uses the Adobe Creative Cloud API and other tools to generate or retrieve relevant visual information based on the extracted keywords. This visual information includes illustrations and animations, which are presented in a format that is easier for students to understand.

[0769] The generated visual information and audio guides are transmitted from the server to the user's terminal via the network. The user's terminal displays this information on its screen and simultaneously plays the audio guide using speech synthesis technology, such as Amazon Polly. This allows learners to understand the information through both sight and hearing.

[0770] As a concrete example, consider a situation where students are learning the concept of "differentiation" in a mathematics class. The server extracts keywords such as "differentiation" and "derivative function" and generates visualized learning materials. The terminal then displays these materials, and an audio guide plays stating, "The derivative function shows the instantaneous rate of change of a function."

[0771] An example of a prompt would be: "Convert the audio from the live lesson to text and visualize the educational content. Extract key concepts and keywords, generate animations based on them, and deliver them to the user in an easy-to-understand manner."

[0772] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0773] Step 1:

[0774] The server collects audio data through microphones placed throughout the classroom. The input is the real-time audio signal from the classroom, and the output is digital audio data. This data is then converted to a format usable in the next step.

[0775] Step 2:

[0776] The server converts the collected audio data into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). In this step, speech recognition technology is used to output the content of the audio in text format. The input is digital audio data, and the output is text data.

[0777] Step 3:

[0778] The server processes text data using a natural language processing engine (e.g., Google Cloud Natural Language API) to extract important keywords and concepts. The input is text data, and the output is a keyword list. This process involves text analysis and selection of key items.

[0779] Step 4:

[0780] The server generates or searches for relevant visual information based on extracted keywords (e.g., using the Adobe Creative Cloud API). The input is a list of keywords, and the output is visual information (diagrams, illustrations, animations, etc.). Here, a generative AI model is used to construct the content.

[0781] Step 5:

[0782] The server transmits the generated visual information and audio guide data to the user's terminal via the network. The input is the visual information and audio guide data, and the output is the transmitted data. Efficient data communication takes place during this process.

[0783] Step 6:

[0784] The device displays received visual information on its screen and plays audio guides using speech synthesis technology (e.g., Amazon Polly). The input is the transmitted data, and the output is the displayed visual information and the played audio. This allows the user to understand the lesson content through both sight and sound.

[0785] Step 7:

[0786] Users send questions and feedback about the lesson content to the server via their terminal. The input is the user's feedback information, and the output is feedback data transferred to the server. This information is used to improve and adjust the system.

[0787] 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.

[0788] This invention provides an auxiliary system for helping children with learning disabilities understand lesson content, equipped with a function to recognize the user's emotions and further enhance learning effectiveness. This system integrates and executes a series of processes, from collecting audio data to emotion recognition.

[0789] First, the server uses microphones in the classroom to record the teacher's voice in real time and converts this audio data into text. Once the text data is generated, natural language processing is used to extract important keywords from the lesson. Based on the extracted keywords, the server generates or searches for relevant visual materials and creates content that aids learning.

[0790] Furthermore, the server transmits the generated visual materials and audio data to the user's device. The device receives this content, displays it on its screen, and plays the explanations aloud using speech synthesis technology. This allows the user to understand the lesson content using both their sight and hearing.

[0791] In addition, this system is equipped with an emotion engine that recognizes the user's emotions in real time. Cameras and sensors installed on the terminal collect the user's facial expressions and gaze data, which the emotion engine then analyzes. Based on the analysis results, it estimates the user's level of interest and understanding, and adjusts the presentation speed and difficulty level of the learning materials accordingly.

[0792] For example, if the emotion engine detects a user's decreased concentration while learning fraction addition, the system will select and display simpler examples to adjust the learning pace. Furthermore, if the emotion engine detects that the user is struggling to understand, the device will provide additional visual and audio guidance to support comprehension.

[0793] Thus, the system of the present invention provides an environment in which children can learn effectively at their own pace by combining integrated auditory and visual support with emotion recognition.

[0794] The following describes the processing flow.

[0795] Step 1:

[0796] The server collects audio data in real time from microphones installed in the classroom. Measures have been taken to ensure that all teacher speech is captured without omission.

[0797] Step 2:

[0798] The server converts the collected audio data into text data using a speech recognition engine. This conversion includes noise reduction to generate accurate text.

[0799] Step 3:

[0800] The server analyzes the generated text data using natural language processing techniques to extract keywords and key concepts. It identifies important points of the lesson content and uses them to design teaching materials.

[0801] Step 4:

[0802] The server searches for or generates relevant visual information based on the extracted keywords. It retrieves relevant images, animations, videos, etc., from a database or utilizes online resources.

[0803] Step 5:

[0804] The server creates a data package for sending properly organized visual information to the user terminal and then transmits the data. Optimization is in place for efficient data transfer.

[0805] Step 6:

[0806] The terminal interprets data packages received from the server and displays visual learning materials on its screen. It also uses speech synthesis to play back related text data as audio.

[0807] Step 7:

[0808] The camera and sensors built into the device collect the user's facial expressions and gaze data and transmit it to the emotion engine. This allows for real-time monitoring of the user's emotional state.

[0809] Step 8:

[0810] The emotion engine analyzes collected data to determine the user's emotions, interests, and level of engagement. This allows it to predict which content will be most effective for the user.

[0811] Step 9:

[0812] The server dynamically adjusts the presentation speed and difficulty level of the learning materials based on the analysis results of the emotion engine. For example, if there are signs that the user is not understanding the material, it selects materials that are easier to access.

[0813] Step 10:

[0814] Users understand the lesson content through adjusted visual and auditory information. If necessary, users can interact with their devices to provide feedback. This feedback will be used to adjust the content in the next lesson.

[0815] (Example 2)

[0816] 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".

[0817] In conventional educational support systems, the processes of voice-to-text conversion and material generation are independent of each other, making it difficult to understand learners' emotional states in real time and adjust learning content accordingly. In particular, there is a lack of effective learning support for children with learning disabilities, and there is an urgent need to create an environment where children can learn at their own pace.

[0818] 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.

[0819] In this invention, the server includes an input means for collecting audio information, a conversion means for converting the audio information into text information, and an analysis means for extracting important words from the text information. This enables the generation of user-optimized visual materials and the adjustment of learning content based on emotion through real-time text conversion of audio data and extraction of important words.

[0820] "Auditory information" refers to information transmitted through sound, and specifically includes data used in an educational context, particularly the speech of teachers.

[0821] "Input means" refers to devices and methods for acquiring audio information and incorporating it into a system, and mainly includes devices that utilize microphones.

[0822] "Conversion means" refers to a process or device that converts audio information into text information, and includes functions that utilize speech recognition technology.

[0823] "Text information" refers to data in which audio information is represented as a string of characters, and includes information that can be verified in a visual format.

[0824] "Analysis methods" refer to processes that identify important words and phrases from text information and extract keywords related to educational content.

[0825] "Key terms" refer to words or phrases within the text that deserve particular attention and include central concepts for understanding the educational content.

[0826] "Generative means" refers to methods or devices for producing or identifying visual supplementary materials and related content based on extracted key keywords.

[0827] "Visual materials" refer to images and video data generated or acquired to present information visually, and are used as educational aids.

[0828] "Transmission means" refers to communication methods and devices for transmitting generated visual material to a user's terminal and providing it in a viewable state.

[0829] "Emotion recognition means" refers to a process or technology for identifying an emotional state by analyzing a user's facial expressions and gaze data.

[0830] "Emotional state" refers to a user's psychological response, interest, and level of understanding, and is used to evaluate the user's attitude towards educational content.

[0831] "Adjustment means" refers to methods and devices for optimizing the content and presentation speed of learning materials based on the user's emotional state.

[0832] This invention is a learning support system that integrates and executes a series of processes, from collecting voice information to recognizing the user's emotions. A specific embodiment of this system is described below.

[0833] First, in a specific classroom environment, the server uses microphones installed in the classroom to collect the teacher's voice in real time. This voice information is then converted into text using speech recognition software. Specifically, a general service providing speech recognition technology can be used.

[0834] Next, the text information is analyzed on the server using natural language processing techniques to extract important words and phrases. Natural language processing libraries are used for the analysis, and keywords relevant to the lesson content are automatically extracted. This step is crucial for visualizing the key points of what the user is learning.

[0835] Based on the extracted key keywords, the server generates or searches for relevant visual materials. The generation of visual materials can utilize online-accessible educational databases. This allows users to gain a deeper understanding by utilizing visual learning materials.

[0836] Subsequently, the generated visual and audio materials are sent from the server to the user's terminal. The terminal displays the received content on its screen and plays the explanation aloud using a speech synthesis engine. This allows the user to effectively utilize both sight and hearing to advance their learning.

[0837] Furthermore, to recognize the user's emotions in real time, this system collects facial expression and gaze data through cameras and sensors installed on the device. For emotion recognition, it uses a common facial recognition API to provide data for estimating the user's interest and level of understanding.

[0838] For example, when a user is learning "fraction addition," the server uses emotion recognition data to evaluate the user's level of concentration. If the server determines that the user's understanding is insufficient, it automatically presents learning materials with adjusted difficulty levels.

[0839] An example of a prompt message might be: "Explain how the system should respond if the user is learning fraction addition and their concentration wanes."

[0840] Thus, the present invention is a system that integrates audio and visual information and further recognizes the user's emotional state to provide effective educational support tailored to the learning pace of each individual child.

[0841] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0842] Step 1:

[0843] The server uses microphones installed in the classroom to collect teacher voice information in real time. The collected voice information is converted into text information through speech recognition software. Specifically, it receives voice waveform data as input, uses acoustic and language models to recognize phonemes and predict words, and outputs it as text information.

[0844] Step 2:

[0845] The server applies natural language processing techniques to text information to extract important terms. This process involves morphological analysis to extract keywords based on part-of-speech information such as nouns and verbs. From the input text information, it identifies important terms corresponding to specific educational content and outputs a keyword list.

[0846] Step 3:

[0847] The server generates or searches for relevant visual materials based on the extracted key keywords. Specifically, it searches for relevant images and videos from the database, or generates new visual materials using existing templates. The input is a keyword list, and the server outputs visual material files based on this list.

[0848] Step 4:

[0849] The server sends the generated visual and audio information to the user's terminal. The data is transferred using a secure communication protocol. Visual material files and synthesized speech data are taken as input and sent to the user's terminal as output.

[0850] Step 5:

[0851] The terminal displays the received visual material on its screen and plays an audio explanation using a speech synthesis engine. This process uses the visual material file and audio data received from the server as input, and simultaneously displays the image on the screen and outputs it to the speaker.

[0852] Step 6:

[0853] The device uses cameras and sensors to collect data on the user's facial expressions and gaze. This data is transmitted in real time to an emotion recognition engine. It receives the user's physical data (facial expressions, gaze) as input and outputs it directly as data for analysis.

[0854] Step 7:

[0855] The server uses an emotion recognition engine to analyze collected user facial expressions and gaze data to identify the user's emotional state. It then uses feature extraction and discrimination models from the input data to evaluate the user's interest and understanding, and outputs the results.

[0856] Step 8:

[0857] The server adjusts the content and presentation speed of learning materials based on the results of the emotional state analysis. Specifically, it supports user comprehension by appropriately changing the difficulty level of the materials. It receives the emotional analysis results as input and outputs the adjusted learning materials.

[0858] (Application Example 2)

[0859] 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".

[0860] Conventional learning support systems have a problem in that they do not adequately provide adaptive learning support tailored to the user's level of understanding and emotional state, resulting in limited effectiveness, particularly for children with learning disabilities or for training new employees in the workplace. This project aims to solve this problem and provide effective learning and educational support.

[0861] 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.

[0862] In this invention, the server includes input means for collecting audio data, conversion means for converting audio data into text data, analysis means for extracting keywords from the text data, sensor means for collecting user facial expression and gaze data, and emotion recognition means for analyzing the user's emotions and adjusting the presented information based on the results. This enables adaptive learning support and educational support that responds to the user's emotional state.

[0863] "Audio data" refers to sound information recorded as sound waves, and includes digital or analog data such as speech and ambient sounds.

[0864] "Input means" refers to a device or system for collecting audio data, specifically a receiving device such as a microphone or sensor.

[0865] "Conversion means" refers to a technology or device for converting audio data into text data, and includes speech recognition software, etc.

[0866] "Analysis tools" refer to systems or programs that have the function of extracting important information from text data, and utilize natural language processing technology, etc.

[0867] "Generation means" refers to an apparatus or system that performs a process of generating or retrieving relevant visual information based on extracted keywords.

[0868] "Transmission means" refers to a communication device or method for transmitting generated visual information to a user device.

[0869] "Sensor means" refers to a device or system for collecting user facial expression and gaze data, and includes cameras and other sensory sensors.

[0870] "Emotion recognition means" refers to technologies or systems for evaluating a user's emotions, such as estimating their level of interest and understanding through facial expression analysis or gaze data analysis.

[0871] This invention is a complex system used for learning support and educational assistance, and consists of the following main elements: The server first collects audio data using an input means. This audio data is converted into text data by a conversion means. From the converted text data, important keywords are extracted using an analysis means. Next, related visual information is generated or retrieved based on these keywords by a generation means.

[0872] The generated visual information is transmitted to the user device via a means of communication. The user device is typically a terminal equipped with a display, which displays this information. Furthermore, the terminal can use speech synthesis technology to provide information to the user through the audio it plays. Through this process, the user gains a learning experience that utilizes both visual and auditory senses.

[0873] The user device incorporates sensors to collect the user's facial expressions and gaze data. This data is analyzed by emotion recognition to estimate the user's emotional state (e.g., interest and comprehension). Based on this estimation, the system adjusts the visual information and explanations it presents to improve the user's learning efficiency.

[0874] As a concrete example, in the context of training new employees in a factory, this system monitors the level of stress and confusion of users through emotion recognition mechanisms as they learn how to operate new machinery, and dynamically adapts the training content accordingly. For instance, if it is determined that the user is not understanding the material, detailed step-by-step guidance is provided via audio and visuals to aid their comprehension.

[0875] An example of a prompt is, "Use an emotion recognition system to monitor worker stress levels during new machine operation training and dynamically adjust the training content."

[0876] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0877] Step 1:

[0878] The server collects audio data from environments such as classrooms and work sites using input devices. At this stage, a microphone is used to acquire audio in real time and transmit it to the server as digital data. The audio data is the input, and the data collection is the output.

[0879] Step 2:

[0880] The server converts the collected audio data into text data using a conversion mechanism. Specifically, it analyzes the audio waveform using speech recognition software and converts it into corresponding text. Audio data is the input, and text data is the output.

[0881] Step 3:

[0882] The server uses analytical tools to extract important keywords from text data. It utilizes natural language processing techniques to identify key words and phrases within the text. This forms the basis for generating related visual information. Text data is the input, and a list of keywords is the output.

[0883] Step 4:

[0884] The server generates or retrieves relevant visual information based on keywords extracted by the generation method. This may involve generating visual information from scratch or retrieving relevant images and videos from a database. Keywords are the input, and visual information is the output.

[0885] Step 5:

[0886] The server transmits the generated visual information to the user device via a means of communication. Internet communication is typically used for this purpose. The visual information is the input, and its delivery to the user device is the output.

[0887] Step 6:

[0888] The terminal displays the transmitted visual information on its screen and, if necessary, uses speech synthesis technology to play relevant explanations aloud to the user. Here, the speech synthesis engine generates speech from text and outputs it through the speaker. Visual information and text are the inputs, and the display and audio output are the outputs.

[0889] Step 7:

[0890] The device uses sensors to collect user facial expressions and gaze data. This information is sent to emotion recognition systems in real time. Cameras and other sensors function as input devices, and the collected data is the output.

[0891] Step 8:

[0892] The device uses emotion recognition to analyze the user's emotional state (interest, understanding, etc.) from collected data. It uses machine learning algorithms to recognize patterns and estimate the user's state. Facial expressions and eye gaze data are inputs, and the emotional state evaluation is the output.

[0893] Step 9:

[0894] The server dynamically adjusts the content and pace of the presented information based on the results of emotion recognition. If necessary, it adds supplementary visual information or audio guidance. The emotional state assessment is the input, and the adjusted presented information is the output.

[0895] 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.

[0896] 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.

[0897] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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."

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] 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.

[0913] 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.

[0914] 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.

[0915] 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.

[0916] The following is further disclosed regarding the embodiments described above.

[0917] (Claim 1)

[0918] An input means for collecting audio data,

[0919] A conversion method for converting audio data into text data,

[0920] An analytical method for extracting keywords from text data,

[0921] A generation means for generating or retrieving relevant visual information based on extracted keywords,

[0922] A transmission means that transmits the generated visual information to a user device through an output means,

[0923] A system that includes this.

[0924] (Claim 2)

[0925] The system according to claim 1, further comprising an audio output means for reproducing audio data by speech synthesis.

[0926] (Claim 3)

[0927] The system according to claim 1, further comprising adjustment means for collecting user feedback and adjusting the displayed information.

[0928] "Example 1"

[0929] (Claim 1)

[0930] An input means for collecting sound,

[0931] A means of converting sound into text,

[0932] An analytical method for extracting important words from text,

[0933] A generation means for generating or acquiring relevant visual information based on extracted important words,

[0934] A transmission means for transmitting the generated visual information to an output device via an output device,

[0935] A means of displaying visual information with an output device and providing information audibly,

[0936] A system that includes this.

[0937] (Claim 2)

[0938] The system according to claim 1, further comprising a voice output means for converting text into speech and playing it back using speech synthesis.

[0939] (Claim 3)

[0940] The system according to claim 1, further comprising adjustment means for collecting user feedback and adjusting the displayed information.

[0941] "Application Example 1"

[0942] (Claim 1)

[0943] An input means for collecting audio data,

[0944] A conversion method for converting audio data into text data,

[0945] An analytical method for extracting keywords from text data,

[0946] A generation means for generating or retrieving relevant visual information based on extracted keywords,

[0947] A distribution means that displays visual information on a user device and provides audio guidance,

[0948] An adjustment mechanism that adjusts the displayed information based on user feedback,

[0949] A system that includes this.

[0950] (Claim 2)

[0951] The system according to claim 1, further comprising a voice output means for reproducing voice data using synthesized speech and making the information recognizable by hearing.

[0952] (Claim 3)

[0953] The system according to claim 1, comprising the content of processing live classes and lectures in real time and providing visualized learning materials that are easy for learners to understand.

[0954] "Example 2 of combining an emotion engine"

[0955] (Claim 1)

[0956] An input means for collecting audio information,

[0957] A conversion means for converting audio information into text information,

[0958] An analytical method for extracting important keywords from text information,

[0959] A generation means for generating or searching for relevant visual materials based on extracted key keywords,

[0960] A transmission means that transmits the generated visual material to the user terminal via an output means,

[0961] A means of collecting video information to detect the user's emotional state,

[0962] An emotion recognition means that analyzes collected video information to identify the user's emotions,

[0963] An adjustment mechanism that adjusts the content or progression of learning materials based on identified emotions,

[0964] A system that includes this.

[0965] (Claim 2)

[0966] The system according to claim 1, further comprising an audio output means for reproducing audio information by speech synthesis.

[0967] (Claim 3)

[0968] The system according to claim 1, including a method for adjusting the displayed content based on the user's level of awareness and interest.

[0969] "Application example 2 of combining emotional engines"

[0970] (Claim 1)

[0971] An input means for collecting audio data,

[0972] A conversion method for converting audio data into text data,

[0973] An analytical method for extracting keywords from text data,

[0974] A generation means for generating or retrieving relevant visual information based on extracted keywords,

[0975] A transmission means that transmits the generated visual information to a user device through an output means,

[0976] A sensor means for collecting user facial expressions and gaze data,

[0977] An emotion recognition means that analyzes the user's emotions and adjusts the presented information based on the results,

[0978] A system that includes this.

[0979] (Claim 2)

[0980] The system according to claim 1, further comprising an audio output means for reproducing audio data by speech synthesis.

[0981] (Claim 3)

[0982] The system according to claim 1, further comprising adjustment means for collecting user feedback and adjusting display information, and further comprising control means for dynamically generating or adjusting visual information based on the user's emotional state. [Explanation of symbols]

[0983] 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. An input means for collecting audio data, A conversion method for converting audio data into text data, An analytical method for extracting keywords from text data, A generation means for generating or retrieving relevant visual information based on extracted keywords, A transmission means that transmits the generated visual information to a user device through an output means, A system that includes this.

2. The system according to claim 1, further comprising an audio output means for reproducing audio data by speech synthesis.

3. The system according to claim 1, further comprising adjustment means for collecting user feedback and adjusting the displayed information.

Images