system

Abstract

We provide the system. [Solution] A natural language processing means that receives textbook data and extracts important topics and key phrases from the textbook data, A generative model means for generating emotionally charged speech based on extracted key phrases, A sound effect generation means that selects and synthesizes sound effects that are appropriate to the generated audio, A video generation means that generates video in synchronization with audio and sound effects, A conversational agent means that enables interaction with the user, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Textbooks for visually impaired people have problems that, with frequent revisions of textbooks and updates of information, the work of braille conversion and audio translation is delayed and takes a long time to become available. For this reason, it is difficult for visually impaired people to obtain the latest information quickly, and there is a possibility that educational opportunities will be restricted. Also, when performing audio translation or braille conversion, it is required to provide a more intuitive and easy-to-understand learning experience rather than simply reading out characters.

Means for Solving the Problems

[0005] The present invention provides a system that includes natural language processing means for receiving and analyzing textbook data, and for extracting important topics and key phrases from the textbook data. Then, a generation model means is used to generate emotionally charged speech based on the extracted key phrases, and a sound effect generation means is used to select and synthesize sound effects that are appropriate to the generated speech. Through this process, a video generation means is activated to generate video in synchronization with the speech and sound effects, and finally, an interactive agent means is provided to enable interaction with the user, thereby providing a system that allows visually impaired individuals to enjoy a more interactive and easy-to-understand learning experience.

[0006] "Textbook data" refers to information that digitizes the content of books and teaching materials used in educational institutions.

[0007] "Natural language processing means" refers to technologies or systems that analyze meaning and intent from text data and extract important information.

[0008] "Generative model means" refers to a machine learning model or technique for generating speech or text based on specific input information.

[0009] "Sound effect generation means" refers to a technology or device that has the function of selecting sound effects associated with audio content and combining and synthesizing them.

[0010] "Video generation means" refers to a technology or device that generates visual content in conjunction with audio and sound effects.

[0011] An "interactive agent means" is a system or program that generates responses in response to user input, enabling natural dialogue.

[0012] "Extracting important topics and key phrases" means identifying and selecting particularly noteworthy items or important terms from a document.

[0013] "Emotionally charged voice" refers to voices that have been given emotional intonation and nuances. [Brief explanation of the drawing]

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

Embodiment for Carrying Out the Invention

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

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

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

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

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

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

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

[0022] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] This invention is a system for effectively conveying the content of textbooks to visually impaired individuals, and its configuration and operation are described below.

[0036] This system consists of a server, terminals, and users. The system begins by receiving textbook data in digital format to the server. The server then uses natural language processing to extract important topics and key phrases from the textbook data. This allows for the efficient identification of the essential points of the information.

[0037] Next, the server uses a generative model to automatically generate emotionally charged speech based on the extracted key phrases. In this process, the server reflects the emotions that a human would feel in response to specific contexts and terms, providing content that is easy for the listener to understand. The server also selects and synthesizes sound effects that match the speech, complementing situations and atmospheres that cannot be fully conveyed through speech alone.

[0038] Furthermore, the server creates video synchronized with the generated audio and sound effects and sends it to the terminal. The terminal receives this data and integrates the audio, sound effects, and video to present to the user. The user views the provided content and gains a deeper learning experience.

[0039] In addition, the server provides an interactive agent that enables users to engage in natural conversations through their terminals. When a user asks a question about the textbook content, the agent provides an appropriate answer. This interactive function allows users to deepen their understanding of the lesson content.

[0040] For example, if a history textbook contains a section on "the outbreak of World War II," the server would highlight the phrases representing this significant event and express its background with sound effects. Then, if the user asks "why did this war start?", the agent can provide a detailed explanation of the relevant historical context and events.

[0041] In this way, the system creates an environment that provides visually impaired individuals with textbook content in a way that is quick and easy to understand.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server receives textbook data provided in digital format. This may include text, illustrations, tables, and other elements.

[0045] Step 2:

[0046] The server analyzes the received textbook data using natural language processing techniques. It extracts important topics and key phrases and organizes them as metadata.

[0047] Step 3:

[0048] The server applies a generative model to the extracted key phrases to automatically generate emotionally charged speech. It determines appropriate intonation and emotional expression based on the content of the text.

[0049] Step 4:

[0050] The server selects sound effects related to the generated audio from the sound effects library and synthesizes and incorporates them into the audio data.

[0051] Step 5:

[0052] The server generates video that synchronizes with the audio and sound effects. This video consists of animations and visual content based on the textbook material, supplementing the visual information.

[0053] Step 6:

[0054] The server transfers this integrated data (audio, sound effects, and video) to the terminal.

[0055] Step 7:

[0056] The terminal plays back integrated data received from the server through a user interface, making it interactive for visually impaired users.

[0057] Step 8:

[0058] The terminal receives questions from the user through an interactive agent. When the user asks a question about the content of the textbook, the agent generates a response.

[0059] Step 9:

[0060] The server collects and analyzes user interaction logs and feedback data. This information is used to improve future learning materials.

[0061] (Example 1)

[0062] 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."

[0063] For visually impaired individuals, traditional textbook-based learning methods presented challenges in understanding and processing information. In particular, there was a lack of means to efficiently grasp the key points of learning content and provide an emotionally enriching learning experience. Furthermore, there was a need for a system that could address individual learning needs through interactive dialogue functions.

[0064] 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.

[0065] In this invention, the server includes a natural language processing means for receiving textbook data and extracting important information and concepts from the textbook data; a speech synthesis means for generating emotionally charged speech data based on the extracted information; and an acoustic processing means for selecting and combining sound effects appropriate to the generated speech data. This enables visually impaired individuals to learn intuitively and effectively based on their hearing and senses. Furthermore, an interactive interface can respond to learners' questions and enrich their individual learning experiences.

[0066] "Textbook data" refers to a collection of information obtained from printed or digitized learning materials used for educational purposes.

[0067] "Natural language processing" refers to technologies that analyze the structure and meaning of text data to extract important information and key phrases.

[0068] "Speech synthesis means" refers to a technology that generates speech waveforms based on digital text data and outputs them as machine-generated speech.

[0069] "Audio processing means" refers to a technology or process for adding sound effects to generated audio data and applying auditory effects.

[0070] "Media generation means" refers to a technology that creates video data in synchronization with audio and sound effects to generate visual content.

[0071] An "interactive interface means" is a technology that enables interaction with the user and provides the functionality to exchange information through natural conversation.

[0072] "User" refers to an individual or group that uses this system to access and receive information.

[0073] "Opinions" refer to expressions of thoughts, including feedback and impressions from users.

[0074] The "material creation process" refers to the process of creating, editing, and distributing learning materials based on educational objectives.

[0075] This system is designed to enable visually impaired individuals to effectively understand digital textbook content. It primarily consists of three components: a server, terminals, and users.

[0076] The server first receives textbook data in digital format. This data is provided, for example, via a network, using protocols such as HTTP or FTP. The received data is then processed using natural language processing (NLP) to extract important information and concepts. This process utilizes natural language processing libraries (e.g., spaCy, NLTK) to extract topics and key phrases from the document. This allows for efficient identification of the main points of the information.

[0077] Next, the server generates emotionally charged speech based on the extracted information using speech synthesis technology. This process utilizes speech synthesis APIs (e.g., Google® Text-to-Speech, Amazon Polly) to convert text data into speech data. Furthermore, sound processing technology selects appropriate sound effects from a sound library and integrates them with the speech. Finally, audio editing software (e.g., Audacity) is used to edit the final audio content.

[0078] The generated audio data is synchronized with video data by a media generation device and processed into high-resolution visual content. This video data is created using video editing software (e.g., Adobe Premiere Pro, FFmpeg) and sent to the device. The device has advanced decoding capabilities and integrates this data in real time to present it to the user. The user receives the visual and audio content provided through the device, enabling an intuitive learning experience that does not rely on visual input.

[0079] Furthermore, the user can engage in natural conversations with the system using the interactive interface built into the terminal. The server utilizes a generative AI model to generate responses to user questions based on prompt text. This allows the user to enjoy an interactive learning environment and gain a deeper understanding.

[0080] As a concrete example, if content about the "outbreak of World War II" from a history textbook is input, the generation AI model will receive the following prompt: "Extract important key phrases about the 'outbreak of World War II' from the textbook data, and generate emotionally charged speech based on them."

[0081] This system is expected to enable visually impaired individuals to maximize their potential as learners and expand diverse educational opportunities.

[0082] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0083] Step 1:

[0084] The server receives textbook data in digital format. The input is a data file provided over the network. This data file undergoes preprocessing for text processing and is converted into a consistent digital format. The output is the digitized textbook data.

[0085] Step 2:

[0086] The server extracts important information and concepts from received textbook data using natural language processing techniques. Preprocessed text data is used as input. The server uses natural language processing libraries (e.g., spaCy, NLTK) to analyze the text structure and extract key phrases and topics. This process includes techniques such as sentence segmentation and part-of-speech tagging. The output is a list of the extracted important information.

[0087] Step 3:

[0088] The server generates emotionally charged audio data using a generative AI model based on the extracted information. The input is a list of extracted information. The server utilizes a speech synthesis API (e.g., Google Text-to-Speech, Amazon Polly) to generate speech from text. It adjusts phonemes and intonation to produce emotionally conveying audio data. The output is an emotionally charged audio file.

[0089] Step 4:

[0090] The server selects sound effects appropriate to the generated audio data and combines them using sound processing tools. The input is the generated audio file. The server selects appropriate sound effects from a sound library and integrates the audio and sound effects using audio editing software (e.g., Audacity). The output is an integrated file of the synthesized audio and sound effects.

[0091] Step 5:

[0092] The server generates video data synchronized with audio and sound effects. The input is an integrated audio file. The server uses video editing software (e.g., Adobe Premiere Pro, FFmpeg) to create video that matches the audio. The output is a video file synchronized with the audio.

[0093] Step 6:

[0094] The terminal receives video files transmitted from the server and integrates audio, sound effects, and video in real time for presentation to the user. The input is a video file synchronized with audio. The terminal utilizes a decoding function to achieve smooth playback. The output is viewable media content provided to the user.

[0095] Step 7:

[0096] Users can interact with the system using a terminal. Input is a question or comment from the user. The server utilizes a generative AI model to generate an appropriate response based on the prompt and provides it to the user. Output is the response message to the user's inquiry.

[0097] (Application Example 1)

[0098] 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."

[0099] To improve the current situation where visually impaired individuals and the elderly have difficulty fully understanding and enjoying educational and entertainment content, it is necessary to communicate information more effectively by using emotionally charged voices, sound effects, and visually appealing means.

[0100] 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.

[0101] In this invention, the server includes natural language processing means, speech generation means, sound processing means, visual generation means, interactive agent means, and information provision means for providing educational or entertaining content for the elderly. This makes it possible to provide educational and entertaining content using emotionally responsive voices and sound effects to visually impaired people and the elderly.

[0102] "Natural language processing techniques" are technologies used to extract important information from textbook data and related information.

[0103] "Voice generation means" refers to a technology that generates emotionally charged voices based on extracted information.

[0104] "Sound processing means" refers to a technology that selects and synthesizes sound effects suitable for the generated audio.

[0105] "Visual generation means" refers to technology that generates images synchronized with sound and audio.

[0106] "Interactive agent means" refers to technology implemented to enable interaction with users.

[0107] "Information provision methods" refer to technologies for providing educational or entertainment content to the elderly.

[0108] This invention aims to construct a system that effectively provides educational and entertainment content to visually impaired individuals and the elderly. The server analyzes textbook data using a natural language processing engine and extracts important information. Specifically, it processes data using various Python libraries (e.g., NLTK, spaCy). This enables users to accurately obtain the information they need.

[0109] For speech generation, the Google Cloud Text-to-Speech API is used to generate emotionally charged speech from the extracted information. Pydub is used for sound processing, selecting appropriate sound effects and synthesizing them with the speech. This results in richer auditory information. The generated speech and sound effects are intended for playback on the device, so native players for iOS and Android® are used.

[0110] Furthermore, as a means of visual generation, the server will automatically create appropriate video based on the generated data and send it to the terminal. It is envisioned that FFmpeg, an open-source video editing software, will be used for video creation.

[0111] The interactive agent system utilizes natural language processing capabilities powered by generative AI models to provide appropriate responses to user questions. This allows users to directly ask the system questions about the content and engage in dialogue to deepen their understanding. For example, by providing content such as, "Today is a lovely day for a walk. Why not learn about the history of the Edo period while enjoying some relaxing afternoon music?", it enables learning in a relaxed state within the context of daily life.

[0112] An example of a prompt might be, "Generate audio that conveys emotion and historical context, making it easy for visually impaired individuals to understand." This prepares the system to provide users with engaging and easy-to-understand content.

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The server receives textbook data in digital format. Based on this input data, a natural language processing engine is used to extract important information. Here, Python's natural language processing library is used to perform algorithms that identify topics and key phrases. The result is data that highlights the essential points of the information.

[0116] Step 2:

[0117] The server uses the Google Cloud Text-to-Speech API to generate emotionally charged audio data, taking the key information extracted in Step 1 as input. This audio data is specially adjusted to allow the user to perceive emotions. The output is an audio file that includes emotional expression.

[0118] Step 3:

[0119] The server performs acoustic processing on the audio file. Specifically, it uses Pydub to select sound effects that match the audio data and synthesizes them with the audio. In this process, sound effects are incorporated to give the audio a deeper context. As a result, the output is an audio file in which emotional voice and sound effects are synthesized.

[0120] Step 4:

[0121] The server takes an audio file as input and begins the video generation process. Using FFmpeg, it edits the video to match the audio and sound effects. Here, visual elements are created as video to synchronize with the audio. The output is a video file synchronized with the audio.

[0122] Step 5:

[0123] The device plays video files received from the server. Native media players provided by iOS and Android are used for playback. Here, users can enjoy educational and entertainment content visually and aurally.

[0124] Step 6:

[0125] The user communicates questions and requests regarding the content to the conversational agent. This input is provided as a prompt to the generating AI model, which uses natural language processing techniques to generate an appropriate response. The output is an answer to the user's question.

[0126] Step 7:

[0127] The server analyzes user feedback and uses it to improve the system. This feedback is then reflected in the next curriculum generation process, providing a better user experience. This process involves collecting user response data and identifying areas for improvement through computational processing.

[0128] 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.

[0129] This invention further improves the effectiveness and interactivity of a textbook learning system for visually impaired individuals by incorporating an emotion engine that recognizes user emotions. This system consists of a server, a terminal, and a user, and its specific embodiments are described below.

[0130] The system first receives textbook data in digital format on a server, analyzes the data through natural language processing, and extracts important topics and key phrases. Using this information, a generative model generates emotionally charged speech from the text. Furthermore, the server selects sound effects related to this speech and synthesizes them into the audio data.

[0131] Furthermore, the server uses an emotion engine to recognize the user's emotions through user input and voice analysis. The emotion engine determines emotions from the user's facial expressions, voice tone, and entered text information, and has the function to edit responses in real time based on that data.

[0132] Based on this sentiment data, the server dynamically adjusts how content is presented to the user. For example, if the user is confused, the server can slow down the pace of the audio and repeat important information.

[0133] The conversational agent uses data from the emotion engine to appropriately modify its responses and tone. This allows for flexible responses, such as providing detailed explanations for items the user is interested in, or presenting shortened content if the user is feeling fatigued.

[0134] For example, if a user is struggling with a difficult math problem, the emotion engine can recognize that stress and the agent can appropriately encourage them by saying, "Don't rush. Let's take it one step at a time," thereby providing reassurance and supporting their continued learning.

[0135] Ultimately, the device presents the user with integrated data received from the server, providing a multi-sensory learning experience through audio, sound effects, video, and interactive dialogue. By reflecting data from the emotion engine, the user can receive more optimized learning support.

[0136] The following describes the processing flow.

[0137] Step 1:

[0138] The server receives textbook data provided in digital format. This can include text data, graphics, and multimedia files.

[0139] Step 2:

[0140] The server uses a natural language processing engine to analyze textbook data and extract important topics and key phrases. This helps to understand the main points and learning focus of the materials.

[0141] Step 3:

[0142] The server uses a generative model based on the extracted key phrases to generate emotionally charged speech. This speech reflects the importance and emotion of the content, making it easy for the listener to understand.

[0143] Step 4:

[0144] The server selects appropriate sound effects from a sound effects library for the generated audio and synthesizes them into the speech. This adds depth and realism to the learning content.

[0145] Step 5:

[0146] The server uses an emotion engine to analyze user input and audio feedback from the device to measure and recognize the user's emotional state. This data is collected in real time.

[0147] Step 6:

[0148] The server adjusts how it presents educational content based on the emotional data it receives. For example, if the user is tired, it might slow down the audio speed or simplify the content.

[0149] Step 7:

[0150] Conversational agents utilize emotional data to appropriately adjust their interactions with users (the content and tone of their dialogue). This allows them to provide responses that are attentive to the user's current emotional state.

[0151] Step 8:

[0152] The device plays audio, sound effects, and video data received from the server, providing the user with an integrated learning experience. It continuously monitors the user's reactions and emotions during the learning process.

[0153] Step 9:

[0154] Users can respond via their device as needed or ask questions through an interactive agent. User input is analyzed by an emotion engine and reflected in the generation of subsequent content.

[0155] (Example 2)

[0156] 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".

[0157] In textbook learning for visually impaired individuals, there is a challenge in the lack of sufficient interactive and flexible learning support that responds to users' emotions and levels of comprehension. There is a need for a system that can appropriately address situations where users experience difficulty understanding learning materials or feel stressed.

[0158] 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.

[0159] In this invention, the server includes language processing means for receiving textbook data and extracting important topics and key phrases from the textbook data; sentiment analysis means for analyzing user input and recognizing emotions; and content adjustment means for dynamically adjusting the method of presenting textbook content based on the sentiment analysis results. This enables flexible presentation of learning content according to the user's emotions and level of understanding, and provides an interactive learning experience.

[0160] "Textbook data" refers to a collection of digital information provided for learning purposes, and its content includes text, images, graphs, and other elements.

[0161] "Language processing tools" refers to a set of functions that use natural language processing techniques to extract important topics and key phrases from textbook data.

[0162] "Generative model means" refers to an algorithm and its execution environment for generating emotionally rich speech based on extracted key phrases.

[0163] "Sound generation means" refers to a device or program for selecting appropriate sound effects for generated speech and synthesizing them with the speech.

[0164] "Image generation means" refers to a device or program that has the function of generating visual images in synchronization with audio and sound effects.

[0165] "Emotion analysis methods" refer to technologies that recognize and analyze emotions in real time based on user input and actions.

[0166] "Content adjustment means" refers to a function for dynamically adjusting the presentation method of learning content based on the analysis results obtained by the emotion analysis means.

[0167] "Interactive agent means" refers to artificial intelligence systems designed to enable natural dialogue with users.

[0168] This invention is designed to make textbook learning systems for visually impaired individuals highly interactive and effective. The system primarily consists of a server, terminals, and users.

[0169] The server receives textbook data in digital format. The received data is parsed using natural language processing libraries (e.g., NLTK, spaCy). This involves tokenization, part-of-speech tagging, and dependency structure analysis, extracting important topics and key phrases. This parsed data is then converted into emotionally charged speech via a generative AI model (e.g., GPT-3®). The Google Text-to-Speech API is recommended for speech synthesis.

[0170] Next, the server selects and synthesizes relevant sound effects from a database with the generated audio. Furthermore, it generates video in sync with the audio and sound effects. This creates a multi-sensory learning material.

[0171] The server uses emotion analysis technologies (e.g., Microsoft® Azure® Emotion API, OpenCV) to recognize the user's emotions in real time. Based on this information, the server can dynamically adjust how learning materials are presented, providing a customized learning experience that is easy for the user to learn from. For example, if the user is confused, the server can adjust the speed of the voice guidance and repeat important information.

[0172] The device receives integrated audio, sound effects, and video data from the server and presents it to the user. This allows the user to enjoy a rich learning experience without relying on visual information.

[0173] As a concrete example, when a user is studying a history unit, the server plays relevant events and important dates with immersive audio, adding sound effects that convey the historical context. In addition, sentiment analysis adjusts the content to provide more detailed explanations when the user indicates a desire for deeper understanding.

[0174] An example of a prompt might be, "What part of the following math problem do you find difficult?" This example demonstrates how an interactive agent can provide responses based on the user's interests and level of understanding.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The server receives digital textbook data via the internet. The input is raw data files obtained from the network, which are then analyzed on the server. The output is text data prepared for analysis. The data format is then modified as needed, such as to JSON or XML.

[0178] Step 2:

[0179] The server analyzes incoming data using a natural language processing library. It tokenizes, tags, and analyzes dependency structures on the formalized text input, extracting important topics and key phrases. The output is a dataset containing the analysis results. Efficient algorithms are used in the analysis to ensure high speed and accuracy.

[0180] Step 3:

[0181] The server uses a generative AI model to synthesize emotionally charged speech based on extracted key phrases. The input is the key phrases obtained from the analysis. The generative AI model converts these key phrases into emotionally rich speech data. The output is data in the form of an audio file. Pitch and tempo are adjusted to appropriately express emotions.

[0182] Step 4:

[0183] The server selects sound effects related to the generated audio and synthesizes them. The input consists of the audio file and topic information that serves as the selection criterion for the sound effects. The output is an integrated audio file combining the audio and sound effects. The sound effects are selected from a database that are appropriate to the theme and scene, and are seamlessly integrated with the audio.

[0184] Step 5:

[0185] The server receives user input and performs sentiment analysis. This input consists of user voice and text data. Based on this data, the sentiment analysis engine analyzes the user's facial expressions and tone of voice in real time. The output is metadata indicating the user's emotional state. Machine learning models are used in the analysis to achieve highly accurate sentiment recognition.

[0186] Step 6:

[0187] The server dynamically adjusts how content is presented based on the results of sentiment analysis. Inputs are sentiment analysis metadata and existing content data. Output is a presentation of learning content tailored to the user's emotions. Adjustments include changing the playback speed and repeating content.

[0188] Step 7:

[0189] The device presents integrated data received from the server to the user in a multi-sensory format. Inputs include audio, sound effects, and video information. Output provides an interactive learning experience that combines these elements. The device enhances acoustic instruction to enable comprehension even without visual information, and plays audio content and video in sync.

[0190] (Application Example 2)

[0191] 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".

[0192] In education and care systems for visually impaired individuals, the elderly, and especially those with dementia, there is a need for methods that appropriately recognize the emotional state of users and support the maintenance of learning and cognitive function. Current education systems and care services do not adequately respond to the emotions and learning pace of each individual user, making it difficult to maximize learning efficiency and the effectiveness of care.

[0193] 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.

[0194] In this invention, the server includes data analysis means, information generation means, emotion analysis means, and response adjustment means. This enables the recognition of the user's emotions and the presentation of individually optimized content and adjustment of dialogue.

[0195] "Data analysis means" refers to technology that receives textbook data and has the function of extracting important topics and key phrases.

[0196] "Information generation means" refers to a technology that generates emotionally charged voices based on extracted key phrases.

[0197] A "sound effect generation method" is a technology that has the function of selecting a sound effect that is appropriate for the generated audio and synthesizing it into the audio.

[0198] "Display generation means" refers to a technology that generates video in synchronization with audio and sound effects.

[0199] "Emotional analysis techniques" are technologies that analyze users' emotions and dynamically adjust how content is presented based on those emotions.

[0200] "Response adjustment means" refers to technology that has the function of adjusting the interaction with the user and appropriately changing the content and tone of voice.

[0201] This system recognizes users' emotions in real time and provides individually optimized content presentation and dialogue adjustments to support the education and care of visually impaired individuals, the elderly, and especially those with dementia.

[0202] The server receives textbook data using data analysis tools and extracts important topics and key phrases using natural language processing techniques. Next, information generation tools are used to generate speech that imbues the extracted key phrases with emotion. Appropriate sound effects are then synthesized into this speech using sound effect generation tools, resulting in a richer audio experience.

[0203] Furthermore, the server uses emotion analysis to determine the user's emotional state from their voice tone and input, and adjusts the dialogue content and tone using response adjustment mechanisms. This allows for flexible responses tailored to the user's learning pace and level of understanding, such as slowing down the pace of speech or simplifying the content if the user is confused.

[0204] The device receives integrated data from the server and presents audio, sound effects, and visuals to the user. This allows the user to receive multi-sensory, emotionally optimized learning support.

[0205] As a concrete example, a scenario could be envisioned where, for a user confused by a difficult problem, an emotion analysis tool recognizes their stress, and a response adjustment tool provides a reassuring message such as, "Don't worry, let's adjust to your pace."

[0206] An example of a prompt from a generative AI model is: "Create a scenario for an emotion-recognition-based care app for elderly people with visual impairments. This app will adjust the difficulty of quizzes and provide voice feedback according to the user's emotional state."

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The server receives textbook data and uses data analysis tools to extract important topics and key phrases. The input is book data, and the output is the extracted topics and key phrases. In this process, natural language processing techniques are used to analyze the data and identify information that is considered important in education and care.

[0210] Step 2:

[0211] The server uses information generation means to generate emotionally charged speech based on the extracted key phrases. The input is the key phrases obtained in step 1, and the output is the generated speech data. This process includes specific actions that utilize a generation AI model to generate emotionally rich speech.

[0212] Step 3:

[0213] The server uses a sound effect generation mechanism to select and synthesize sound effects that are appropriate for the generated audio. The input is the audio generated in step 2, and the output is the final audio data with the sound effects synthesized. In this step, sound effects are selected and synthesized to add realism and emphasis to the audio.

[0214] Step 4:

[0215] The server uses emotion analysis tools to determine the user's emotional state from their voice tone and input data. The input is voice and text information obtained from the user, and the output is the analyzed emotion data. This process includes specific actions that perform analysis using an emotion recognition algorithm.

[0216] Step 5:

[0217] The server uses a response adjustment mechanism to adjust the dialogue content and tone based on the analyzed emotion data. The input is the emotion data obtained in step 4, and the output is the adjusted dialogue content. In this step, adjustment processing is performed to enable flexible content delivery in response to the user's emotions.

[0218] Step 6:

[0219] The device receives pre-configured data from the server and presents audio, sound effects, and video to the user. The input is the integrated data sent from the server, and the output is the user's viewing experience. In this final step, the actual presentation action is performed using the integrated data, and the user enjoys the content.

[0220] 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.

[0221] 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.

[0222] 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.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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".

[0236] This invention is a system for effectively conveying the content of textbooks to visually impaired individuals, and its configuration and operation are described below.

[0237] This system consists of a server, terminals, and users. The system begins by receiving textbook data in digital format to the server. The server then uses natural language processing to extract important topics and key phrases from the textbook data. This allows for the efficient identification of the essential points of the information.

[0238] Next, the server uses a generative model to automatically generate emotionally charged speech based on the extracted key phrases. In this process, the server reflects the emotions that a human would feel in response to specific contexts and terms, providing content that is easy for the listener to understand. The server also selects and synthesizes sound effects that match the speech, complementing situations and atmospheres that cannot be fully conveyed through speech alone.

[0239] Furthermore, the server creates video synchronized with the generated audio and sound effects and sends it to the terminal. The terminal receives this data and integrates the audio, sound effects, and video to present to the user. The user views the provided content and gains a deeper learning experience.

[0240] In addition, the server provides an interactive agent that enables users to engage in natural conversations through their terminals. When a user asks a question about the textbook content, the agent provides an appropriate answer. This interactive function allows users to deepen their understanding of the lesson content.

[0241] For example, if a history textbook contains a section on "the outbreak of World War II," the server would highlight the phrases representing this significant event and express its background with sound effects. Then, if the user asks "why did this war start?", the agent can provide a detailed explanation of the relevant historical context and events.

[0242] In this way, the system creates an environment that provides visually impaired individuals with textbook content in a way that is quick and easy to understand.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The server receives textbook data provided in digital format. This may include text, illustrations, tables, and other elements.

[0246] Step 2:

[0247] The server analyzes the received textbook data using natural language processing techniques. It extracts important topics and key phrases and organizes them as metadata.

[0248] Step 3:

[0249] The server applies a generative model to the extracted key phrases to automatically generate emotionally charged speech. It determines appropriate intonation and emotional expression based on the content of the text.

[0250] Step 4:

[0251] The server selects sound effects related to the generated audio from the sound effects library and synthesizes and incorporates them into the audio data.

[0252] Step 5:

[0253] The server generates video that synchronizes with the audio and sound effects. This video consists of animations and visual content based on the textbook material, supplementing the visual information.

[0254] Step 6:

[0255] The server transfers this integrated data (audio, sound effects, and video) to the terminal.

[0256] Step 7:

[0257] The terminal plays back integrated data received from the server through a user interface, making it interactive for visually impaired users.

[0258] Step 8:

[0259] The terminal receives questions from the user through an interactive agent. When the user asks a question about the content of the textbook, the agent generates a response.

[0260] Step 9:

[0261] The server collects and analyzes user interaction logs and feedback data. This information is used to improve future learning materials.

[0262] (Example 1)

[0263] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0264] For visually impaired individuals, traditional textbook-based learning methods presented challenges in understanding and processing information. In particular, there was a lack of means to efficiently grasp the key points of learning content and provide an emotionally enriching learning experience. Furthermore, there was a need for a system that could address individual learning needs through interactive dialogue functions.

[0265] 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.

[0266] In this invention, the server includes a natural language processing means for receiving textbook data and extracting important information and concepts from the textbook data; a speech synthesis means for generating emotionally charged speech data based on the extracted information; and an acoustic processing means for selecting and combining sound effects appropriate to the generated speech data. This enables visually impaired individuals to learn intuitively and effectively based on their hearing and senses. Furthermore, an interactive interface can respond to learners' questions and enrich their individual learning experiences.

[0267] "Textbook data" refers to a collection of information obtained from printed or digitized learning materials used for educational purposes.

[0268] "Natural language processing" refers to technologies that analyze the structure and meaning of text data to extract important information and key phrases.

[0269] "Speech synthesis means" refers to a technology that generates speech waveforms based on digital text data and outputs them as machine-generated speech.

[0270] "Audio processing means" refers to a technology or process for adding sound effects to generated audio data and applying auditory effects.

[0271] "Media generation means" refers to a technology that creates video data in synchronization with audio and sound effects to generate visual content.

[0272] An "interactive interface means" is a technology that enables interaction with the user and provides the functionality to exchange information through natural conversation.

[0273] "User" refers to an individual or group that uses this system to access and receive information.

[0274] "Opinions" refer to expressions of thoughts, including feedback and impressions from users.

[0275] The "material creation process" refers to the process of creating, editing, and distributing learning materials based on educational objectives.

[0276] This system is designed to enable visually impaired individuals to effectively understand digital textbook content. It primarily consists of three components: a server, terminals, and users.

[0277] The server first receives textbook data in digital format. This data is provided, for example, via a network, using protocols such as HTTP or FTP. The received data is then processed using natural language processing (NLP) to extract important information and concepts. This process utilizes natural language processing libraries (e.g., spaCy, NLTK) to extract topics and key phrases from the document. This allows for efficient identification of the main points of the information.

[0278] Next, the server generates emotionally charged speech based on the extracted information using speech synthesis technology. This process utilizes speech synthesis APIs (e.g., Google Text-to-Speech, Amazon Polly) to convert text data into speech data. Furthermore, sound processing technology selects appropriate sound effects from a sound library and integrates them with the speech. Finally, audio editing software (e.g., Audacity) is used to edit the final audio content.

[0279] The generated audio data is synchronized with video data by a media generation device and processed into high-resolution visual content. This video data is created using video editing software (e.g., Adobe Premiere Pro, FFmpeg) and sent to the device. The device has advanced decoding capabilities and integrates this data in real time to present it to the user. The user receives the visual and audio content provided through the device, enabling an intuitive learning experience that does not rely on visual input.

[0280] Furthermore, the user can engage in natural conversations with the system using the interactive interface built into the terminal. The server utilizes a generative AI model to generate responses to user questions based on prompt text. This allows the user to enjoy an interactive learning environment and gain a deeper understanding.

[0281] As a specific example, when content related to "the outbreak of World War II" in a history textbook is input, the following prompt sentence is input into the generative AI model: "Extract important key phrases related to 'the outbreak of World War II' from the textbook data and generate voice with emotions based on them."

[0282] With this system, it is expected that visually impaired people can maximize their potential as learners and a variety of educational opportunities will expand.

[0283] The flow of the specific process in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The server receives textbook data in digital form. The data given as input is a data file provided via the network. This data file undergoes preprocessing for text processing and is converted into a consistent digital form. The output is the digitized textbook data.

[0286] Step 2:

[0287] The server extracts important information and concepts from the received textbook data using natural language analysis means. The preprocessed text data is used as input. The server uses a natural language processing library (e.g., spaCy, NLTK) to analyze the structure of the text and extract key phrases and topics. This process includes techniques such as sentence splitting and part-of-speech tagging. The output is a list of the extracted important information.

[0288] Step 3:

[0289] The server generates emotionally charged audio data using a generative AI model based on the extracted information. The input is a list of extracted information. The server utilizes a speech synthesis API (e.g., Google Text-to-Speech, Amazon Polly) to generate speech from text. It adjusts phonemes and intonation to produce emotionally conveying audio data. The output is an emotionally charged audio file.

[0290] Step 4:

[0291] The server selects sound effects appropriate to the generated audio data and combines them using sound processing tools. The input is the generated audio file. The server selects appropriate sound effects from a sound library and integrates the audio and sound effects using audio editing software (e.g., Audacity). The output is an integrated file of the synthesized audio and sound effects.

[0292] Step 5:

[0293] The server generates video data synchronized with audio and sound effects. The input is an integrated audio file. The server uses video editing software (e.g., Adobe Premiere Pro, FFmpeg) to create video that matches the audio. The output is a video file synchronized with the audio.

[0294] Step 6:

[0295] The terminal receives video files transmitted from the server and integrates audio, sound effects, and video in real time for presentation to the user. The input is a video file synchronized with audio. The terminal utilizes a decoding function to achieve smooth playback. The output is viewable media content provided to the user.

[0296] Step 7:

[0297] Users can interact with the system using a terminal. Input is a question or comment from the user. The server utilizes a generative AI model to generate an appropriate response based on the prompt and provides it to the user. Output is the response message to the user's inquiry.

[0298] (Application Example 1)

[0299] 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."

[0300] To improve the current situation where visually impaired individuals and the elderly have difficulty fully understanding and enjoying educational and entertainment content, it is necessary to communicate information more effectively by using emotionally charged voices, sound effects, and visually appealing means.

[0301] 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.

[0302] In this invention, the server includes natural language processing means, speech generation means, sound processing means, visual generation means, interactive agent means, and information provision means for providing educational or entertaining content for the elderly. This makes it possible to provide educational and entertaining content using emotionally responsive voices and sound effects to visually impaired people and the elderly.

[0303] "Natural language processing techniques" are technologies used to extract important information from textbook data and related information.

[0304] "Voice generation means" refers to a technology that generates emotionally charged voices based on extracted information.

[0305] "Sound processing means" refers to a technology that selects and synthesizes sound effects suitable for the generated audio.

[0306] "Visual generation means" is a technology for generating videos synchronized with voice and sound.

[0307] "Interactive agent means" is a technology installed to enable communication with users.

[0308] "Information providing means" is a technology for providing educational or entertaining content for the elderly.

[0309] In the present invention, a system for effectively providing educational and entertaining content to visually impaired persons and the elderly is constructed. The server analyzes textbook data using a natural language processing engine and extracts important information. Specifically, various Python libraries (e.g., NLTK, spaCy) are utilized to process the data. As a result, it becomes possible to accurately obtain the information necessary for the user.

[0310] Regarding voice generation, the Google Cloud Text-to-Speech API is used to generate voice with emotions incorporated into the extracted information. For audio processing, Pydub is used to select appropriate sound effects and synthesize them with the voice. As a result, the auditory information becomes richer. Since the generated voice and sound effects are premised on playback on the terminal, native players for iOS and Android are used.

[0311] Also, as visual generation means, the server automatically creates appropriate videos based on the data generated and transmits them to the terminal. It is assumed that FFmpeg, an open-source video editing software, is used for video creation.

[0312] The interactive agent system utilizes natural language processing capabilities powered by generative AI models to provide appropriate responses to user questions. This allows users to directly ask the system questions about the content and engage in dialogue to deepen their understanding. For example, by providing content such as, "Today is a lovely day for a walk. Why not learn about the history of the Edo period while enjoying some relaxing afternoon music?", it enables learning in a relaxed state within the context of daily life.

[0313] An example of a prompt might be, "Generate audio that conveys emotion and historical context, making it easy for visually impaired individuals to understand." This prepares the system to provide users with engaging and easy-to-understand content.

[0314] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0315] Step 1:

[0316] The server receives textbook data in digital format. Based on this input data, a natural language processing engine is used to extract important information. Here, Python's natural language processing library is used to perform algorithms that identify topics and key phrases. The result is data that highlights the essential points of the information.

[0317] Step 2:

[0318] The server uses the Google Cloud Text-to-Speech API to generate emotionally charged audio data, taking the key information extracted in Step 1 as input. This audio data is specially adjusted to allow the user to perceive emotions. The output is an audio file that includes emotional expression.

[0319] Step 3:

[0320] The server performs acoustic processing on the audio file. Specifically, it uses Pydub to select sound effects that match the audio data and synthesizes them with the audio. In this process, sound effects are incorporated to give the audio a deeper context. As a result, the output is an audio file in which emotional voice and sound effects are synthesized.

[0321] Step 4:

[0322] The server takes an audio file as input and begins the video generation process. Using FFmpeg, it edits the video to match the audio and sound effects. Here, visual elements are created as video to synchronize with the audio. The output is a video file synchronized with the audio.

[0323] Step 5:

[0324] The device plays video files received from the server. Native media players provided by iOS and Android are used for playback. Here, users can enjoy educational and entertainment content visually and aurally.

[0325] Step 6:

[0326] The user communicates questions and requests regarding the content to the conversational agent. This input is provided as a prompt to the generating AI model, which uses natural language processing techniques to generate an appropriate response. The output is an answer to the user's question.

[0327] Step 7:

[0328] The server analyzes user feedback and uses it to improve the system. This feedback is then reflected in the next curriculum generation process, providing a better user experience. This process involves collecting user response data and identifying areas for improvement through computational processing.

[0329] 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.

[0330] This invention further improves the effectiveness and interactivity of a textbook learning system for visually impaired individuals by incorporating an emotion engine that recognizes user emotions. This system consists of a server, a terminal, and a user, and its specific embodiments are described below.

[0331] The system first receives textbook data in digital format on a server, analyzes the data through natural language processing, and extracts important topics and key phrases. Using this information, a generative model generates emotionally charged speech from the text. Furthermore, the server selects sound effects related to this speech and synthesizes them into the audio data.

[0332] Furthermore, the server uses an emotion engine to recognize the user's emotions through user input and voice analysis. The emotion engine determines emotions from the user's facial expressions, voice tone, and entered text information, and has the function to edit responses in real time based on that data.

[0333] Based on this sentiment data, the server dynamically adjusts how content is presented to the user. For example, if the user is confused, the server can slow down the pace of the audio and repeat important information.

[0334] The conversational agent uses data from the emotion engine to appropriately modify its responses and tone. This allows for flexible responses, such as providing detailed explanations for items the user is interested in, or presenting shortened content if the user is feeling fatigued.

[0335] For example, if a user is struggling with a difficult math problem, the emotion engine can recognize that stress and the agent can appropriately encourage them by saying, "Don't rush. Let's take it one step at a time," thereby providing reassurance and supporting their continued learning.

[0336] Ultimately, the device presents the user with integrated data received from the server, providing a multi-sensory learning experience through audio, sound effects, video, and interactive dialogue. By reflecting data from the emotion engine, the user can receive more optimized learning support.

[0337] The following describes the processing flow.

[0338] Step 1:

[0339] The server receives textbook data provided in digital format. This can include text data, graphics, and multimedia files.

[0340] Step 2:

[0341] The server uses a natural language processing engine to analyze textbook data and extract important topics and key phrases. This helps to understand the main points and learning focus of the materials.

[0342] Step 3:

[0343] The server uses a generative model based on the extracted key phrases to generate emotionally charged speech. This speech reflects the importance and emotion of the content, making it easy for the listener to understand.

[0344] Step 4:

[0345] The server selects appropriate sound effects from a sound effects library for the generated audio and synthesizes them into the speech. This adds depth and realism to the learning content.

[0346] Step 5:

[0347] The server uses an emotion engine to analyze user input and audio feedback from the device to measure and recognize the user's emotional state. This data is collected in real time.

[0348] Step 6:

[0349] The server adjusts how it presents educational content based on the emotional data it receives. For example, if the user is tired, it might slow down the audio speed or simplify the content.

[0350] Step 7:

[0351] Conversational agents utilize emotional data to appropriately adjust their interactions with users (the content and tone of their dialogue). This allows them to provide responses that are attentive to the user's current emotional state.

[0352] Step 8:

[0353] The device plays audio, sound effects, and video data received from the server, providing the user with an integrated learning experience. It continuously monitors the user's reactions and emotions during the learning process.

[0354] Step 9:

[0355] Users can respond via their device as needed or ask questions through an interactive agent. User input is analyzed by an emotion engine and reflected in the generation of subsequent content.

[0356] (Example 2)

[0357] 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".

[0358] In textbook learning for visually impaired individuals, there is a challenge in the lack of sufficient interactive and flexible learning support that responds to users' emotions and levels of comprehension. There is a need for a system that can appropriately address situations where users experience difficulty understanding learning materials or feel stressed.

[0359] 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.

[0360] In this invention, the server includes language processing means for receiving textbook data and extracting important topics and key phrases from the textbook data; sentiment analysis means for analyzing user input and recognizing emotions; and content adjustment means for dynamically adjusting the method of presenting textbook content based on the sentiment analysis results. This enables flexible presentation of learning content according to the user's emotions and level of understanding, and provides an interactive learning experience.

[0361] "Textbook data" refers to a collection of digital information provided for learning purposes, and its content includes text, images, graphs, and other elements.

[0362] "Language processing tools" refers to a set of functions that use natural language processing techniques to extract important topics and key phrases from textbook data.

[0363] "Generative model means" refers to an algorithm and its execution environment for generating emotionally rich speech based on extracted key phrases.

[0364] "Sound generation means" refers to a device or program for selecting appropriate sound effects for generated speech and synthesizing them with the speech.

[0365] "Image generation means" refers to a device or program that has the function of generating visual images in synchronization with audio and sound effects.

[0366] "Emotion analysis methods" refer to technologies that recognize and analyze emotions in real time based on user input and actions.

[0367] "Content adjustment means" refers to a function for dynamically adjusting the presentation method of learning content based on the analysis results obtained by the emotion analysis means.

[0368] "Interactive agent means" refers to artificial intelligence systems designed to enable natural dialogue with users.

[0369] This invention is designed to make textbook learning systems for visually impaired individuals highly interactive and effective. The system primarily consists of a server, terminals, and users.

[0370] The server receives textbook data in digital format. The received data is parsed using natural language processing libraries (e.g., NLTK, spaCy). This involves tokenization, part-of-speech tagging, and dependency structure analysis, extracting important topics and key phrases. This parsed data is then converted into emotionally charged speech via a generative AI model (e.g., GPT-3). The Google Text-to-Speech API is recommended for speech synthesis.

[0371] Next, the server selects and synthesizes relevant sound effects from a database with the generated audio. Furthermore, it generates video in sync with the audio and sound effects. This creates a multi-sensory learning material.

[0372] The server uses emotion analysis technologies (e.g., Microsoft Azure's Emotion API, OpenCV) to recognize the user's emotions in real time. Based on this information, the server can dynamically adjust how learning materials are presented, providing a customized learning experience that is easy for the user to understand. For example, if the user is confused, the server can slow down the speed of the voice guidance and repeat important information.

[0373] The device receives integrated audio, sound effects, and video data from the server and presents it to the user. This allows the user to enjoy a rich learning experience without relying on visual information.

[0374] As a concrete example, when a user is studying a history unit, the server plays relevant events and important dates with immersive audio, adding sound effects that convey the historical context. In addition, sentiment analysis adjusts the content to provide more detailed explanations when the user indicates a desire for deeper understanding.

[0375] An example of a prompt might be, "What part of the following math problem do you find difficult?" This example demonstrates how an interactive agent can provide responses based on the user's interests and level of understanding.

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The server receives digital textbook data via the internet. The input is raw data files obtained from the network, which are then analyzed on the server. The output is text data prepared for analysis. The data format is then modified as needed, such as to JSON or XML.

[0379] Step 2:

[0380] The server analyzes incoming data using a natural language processing library. It tokenizes, tags, and analyzes dependency structures on the formalized text input, extracting important topics and key phrases. The output is a dataset containing the analysis results. Efficient algorithms are used in the analysis to ensure high speed and accuracy.

[0381] Step 3:

[0382] The server uses a generative AI model to synthesize emotionally charged speech based on extracted key phrases. The input is the key phrases obtained from the analysis. The generative AI model converts these key phrases into emotionally rich speech data. The output is data in the form of an audio file. Pitch and tempo are adjusted to appropriately express emotions.

[0383] Step 4:

[0384] The server selects sound effects related to the generated audio and synthesizes them. The input consists of the audio file and topic information that serves as the selection criterion for the sound effects. The output is an integrated audio file combining the audio and sound effects. The sound effects are selected from a database that are appropriate to the theme and scene, and are seamlessly integrated with the audio.

[0385] Step 5:

[0386] The server receives user input and performs sentiment analysis. This input consists of user voice and text data. Based on this data, the sentiment analysis engine analyzes the user's facial expressions and tone of voice in real time. The output is metadata indicating the user's emotional state. Machine learning models are used in the analysis to achieve highly accurate sentiment recognition.

[0387] Step 6:

[0388] The server dynamically adjusts how content is presented based on the results of sentiment analysis. Inputs are sentiment analysis metadata and existing content data. Output is a presentation of learning content tailored to the user's emotions. Adjustments include changing the playback speed and repeating content.

[0389] Step 7:

[0390] The device presents integrated data received from the server to the user in a multi-sensory format. Inputs include audio, sound effects, and video information. Output provides an interactive learning experience that combines these elements. The device enhances acoustic instruction to enable comprehension even without visual information, and plays audio content and video in sync.

[0391] (Application Example 2)

[0392] 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."

[0393] In education and care systems for visually impaired individuals, the elderly, and especially those with dementia, there is a need for methods that appropriately recognize the emotional state of users and support the maintenance of learning and cognitive function. Current education systems and care services do not adequately respond to the emotions and learning pace of each individual user, making it difficult to maximize learning efficiency and the effectiveness of care.

[0394] 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.

[0395] In this invention, the server includes data analysis means, information generation means, emotion analysis means, and response adjustment means. This enables the recognition of the user's emotions and the presentation of individually optimized content and adjustment of dialogue.

[0396] "Data analysis means" refers to technology that receives textbook data and has the function of extracting important topics and key phrases.

[0397] "Information generation means" refers to a technology that generates emotionally charged voices based on extracted key phrases.

[0398] A "sound effect generation method" is a technology that has the function of selecting a sound effect that is appropriate for the generated audio and synthesizing it into the audio.

[0399] "Display generation means" refers to a technology that generates video in synchronization with audio and sound effects.

[0400] "Emotional analysis techniques" are technologies that analyze users' emotions and dynamically adjust how content is presented based on those emotions.

[0401] "Response adjustment means" refers to technology that has the function of adjusting the interaction with the user and appropriately changing the content and tone of voice.

[0402] This system recognizes users' emotions in real time and provides individually optimized content presentation and dialogue adjustments to support the education and care of visually impaired individuals, the elderly, and especially those with dementia.

[0403] The server receives textbook data using data analysis tools and extracts important topics and key phrases using natural language processing techniques. Next, information generation tools are used to generate speech that imbues the extracted key phrases with emotion. Appropriate sound effects are then synthesized into this speech using sound effect generation tools, resulting in a richer audio experience.

[0404] Furthermore, the server uses emotion analysis to determine the user's emotional state from their voice tone and input, and adjusts the dialogue content and tone using response adjustment mechanisms. This allows for flexible responses tailored to the user's learning pace and level of understanding, such as slowing down the pace of speech or simplifying the content if the user is confused.

[0405] The device receives integrated data from the server and presents audio, sound effects, and visuals to the user. This allows the user to receive multi-sensory, emotionally optimized learning support.

[0406] As a concrete example, a scenario could be envisioned where, for a user confused by a difficult problem, an emotion analysis tool recognizes their stress, and a response adjustment tool provides a reassuring message such as, "Don't worry, let's adjust to your pace."

[0407] An example of a prompt from a generative AI model is: "Create a scenario for an emotion-recognition-based care app for elderly people with visual impairments. This app will adjust the difficulty of quizzes and provide voice feedback according to the user's emotional state."

[0408] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0409] Step 1:

[0410] The server receives textbook data and uses data analysis tools to extract important topics and key phrases. The input is book data, and the output is the extracted topics and key phrases. In this process, natural language processing techniques are used to analyze the data and identify information that is considered important in education and care.

[0411] Step 2:

[0412] The server uses information generation means to generate emotionally charged speech based on the extracted key phrases. The input is the key phrases obtained in step 1, and the output is the generated speech data. This process includes specific actions that utilize a generation AI model to generate emotionally rich speech.

[0413] Step 3:

[0414] The server uses a sound effect generation mechanism to select and synthesize sound effects that are appropriate for the generated audio. The input is the audio generated in step 2, and the output is the final audio data with the sound effects synthesized. In this step, sound effects are selected and synthesized to add realism and emphasis to the audio.

[0415] Step 4:

[0416] The server uses emotion analysis tools to determine the user's emotional state from their voice tone and input data. The input is voice and text information obtained from the user, and the output is the analyzed emotion data. This process includes specific actions that perform analysis using an emotion recognition algorithm.

[0417] Step 5:

[0418] The server uses a response adjustment mechanism to adjust the dialogue content and tone based on the analyzed emotion data. The input is the emotion data obtained in step 4, and the output is the adjusted dialogue content. In this step, adjustment processing is performed to enable flexible content delivery in response to the user's emotions.

[0419] Step 6:

[0420] The device receives pre-configured data from the server and presents audio, sound effects, and video to the user. The input is the integrated data sent from the server, and the output is the user's viewing experience. In this final step, the actual presentation action is performed using the integrated data, and the user enjoys the content.

[0421] 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.

[0422] 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.

[0423] 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.

[0424] [Third Embodiment]

[0425] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0426] 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.

[0427] 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).

[0428] 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.

[0429] 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.

[0430] 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).

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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".

[0437] This invention is a system for effectively conveying the content of textbooks to visually impaired individuals, and its configuration and operation are described below.

[0438] This system consists of a server, terminals, and users. The system begins by receiving textbook data in digital format to the server. The server then uses natural language processing to extract important topics and key phrases from the textbook data. This allows for the efficient identification of the essential points of the information.

[0439] Next, the server uses a generative model to automatically generate emotionally charged speech based on the extracted key phrases. In this process, the server reflects the emotions that a human would feel in response to specific contexts and terms, providing content that is easy for the listener to understand. The server also selects and synthesizes sound effects that match the speech, complementing situations and atmospheres that cannot be fully conveyed through speech alone.

[0440] Furthermore, the server creates video synchronized with the generated audio and sound effects and sends it to the terminal. The terminal receives this data and integrates the audio, sound effects, and video to present to the user. The user views the provided content and gains a deeper learning experience.

[0441] In addition, the server provides an interactive agent that enables users to engage in natural conversations through their terminals. When a user asks a question about the textbook content, the agent provides an appropriate answer. This interactive function allows users to deepen their understanding of the lesson content.

[0442] For example, if a history textbook contains a section on "the outbreak of World War II," the server would highlight the phrases representing this significant event and express its background with sound effects. Then, if the user asks "why did this war start?", the agent can provide a detailed explanation of the relevant historical context and events.

[0443] In this way, the system creates an environment that provides visually impaired individuals with textbook content in a way that is quick and easy to understand.

[0444] The following describes the processing flow.

[0445] Step 1:

[0446] The server receives textbook data provided in digital format. This may include text, illustrations, tables, and other elements.

[0447] Step 2:

[0448] The server analyzes the received textbook data using natural language processing techniques. It extracts important topics and key phrases and organizes them as metadata.

[0449] Step 3:

[0450] The server applies a generative model to the extracted key phrases to automatically generate emotionally charged speech. It determines appropriate intonation and emotional expression based on the content of the text.

[0451] Step 4:

[0452] The server selects sound effects related to the generated audio from the sound effects library and synthesizes and incorporates them into the audio data.

[0453] Step 5:

[0454] The server generates video that synchronizes with the audio and sound effects. This video consists of animations and visual content based on the textbook material, supplementing the visual information.

[0455] Step 6:

[0456] The server transfers this integrated data (audio, sound effects, and video) to the terminal.

[0457] Step 7:

[0458] The terminal plays back integrated data received from the server through a user interface, making it interactive for visually impaired users.

[0459] Step 8:

[0460] The terminal receives questions from the user through an interactive agent. When the user asks a question about the content of the textbook, the agent generates a response.

[0461] Step 9:

[0462] The server collects and analyzes user interaction logs and feedback data. This information is used to improve future learning materials.

[0463] (Example 1)

[0464] 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."

[0465] For visually impaired individuals, traditional textbook-based learning methods presented challenges in understanding and processing information. In particular, there was a lack of means to efficiently grasp the key points of learning content and provide an emotionally enriching learning experience. Furthermore, there was a need for a system that could address individual learning needs through interactive dialogue functions.

[0466] 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.

[0467] In this invention, the server includes a natural language processing means for receiving textbook data and extracting important information and concepts from the textbook data; a speech synthesis means for generating emotionally charged speech data based on the extracted information; and an acoustic processing means for selecting and combining sound effects appropriate to the generated speech data. This enables visually impaired individuals to learn intuitively and effectively based on their hearing and senses. Furthermore, an interactive interface can respond to learners' questions and enrich their individual learning experiences.

[0468] "Textbook data" refers to a collection of information obtained from printed or digitized learning materials used for educational purposes.

[0469] "Natural language processing" refers to technologies that analyze the structure and meaning of text data to extract important information and key phrases.

[0470] "Speech synthesis means" refers to a technology that generates speech waveforms based on digital text data and outputs them as machine-generated speech.

[0471] "Audio processing means" refers to a technology or process for adding sound effects to generated audio data and applying auditory effects.

[0472] "Media generation means" refers to a technology that creates video data in synchronization with audio and sound effects to generate visual content.

[0473] An "interactive interface means" is a technology that enables interaction with the user and provides the functionality to exchange information through natural conversation.

[0474] "User" refers to an individual or group that uses this system to access and receive information.

[0475] "Opinions" refer to expressions of thoughts, including feedback and impressions from users.

[0476] The "material creation process" refers to the process of creating, editing, and distributing learning materials based on educational objectives.

[0477] This system is designed to enable visually impaired individuals to effectively understand digital textbook content. It primarily consists of three components: a server, terminals, and users.

[0478] The server first receives textbook data in digital format. This data is provided, for example, via a network, using protocols such as HTTP or FTP. The received data is then processed using natural language processing (NLP) to extract important information and concepts. This process utilizes natural language processing libraries (e.g., spaCy, NLTK) to extract topics and key phrases from the document. This allows for efficient identification of the main points of the information.

[0479] Next, the server generates emotionally charged speech based on the extracted information using speech synthesis technology. This process utilizes speech synthesis APIs (e.g., Google Text-to-Speech, Amazon Polly) to convert text data into speech data. Furthermore, sound processing technology selects appropriate sound effects from a sound library and integrates them with the speech. Finally, audio editing software (e.g., Audacity) is used to edit the final audio content.

[0480] The generated audio data is synchronized with video data by a media generation device and processed into high-resolution visual content. This video data is created using video editing software (e.g., Adobe Premiere Pro, FFmpeg) and sent to the device. The device has advanced decoding capabilities and integrates this data in real time to present it to the user. The user receives the visual and audio content provided through the device, enabling an intuitive learning experience that does not rely on visual input.

[0481] Furthermore, the user can engage in natural conversations with the system using the interactive interface built into the terminal. The server utilizes a generative AI model to generate responses to user questions based on prompt text. This allows the user to enjoy an interactive learning environment and gain a deeper understanding.

[0482] As a concrete example, if content about the "outbreak of World War II" from a history textbook is input, the generation AI model will receive the following prompt: "Extract important key phrases about the 'outbreak of World War II' from the textbook data, and generate emotionally charged speech based on them."

[0483] This system is expected to enable visually impaired individuals to maximize their potential as learners and expand diverse educational opportunities.

[0484] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0485] Step 1:

[0486] The server receives textbook data in digital format. The input is a data file provided over the network. This data file undergoes preprocessing for text processing and is converted into a consistent digital format. The output is the digitized textbook data.

[0487] Step 2:

[0488] The server extracts important information and concepts from received textbook data using natural language processing techniques. Preprocessed text data is used as input. The server uses natural language processing libraries (e.g., spaCy, NLTK) to analyze the text structure and extract key phrases and topics. This process includes techniques such as sentence segmentation and part-of-speech tagging. The output is a list of the extracted important information.

[0489] Step 3:

[0490] The server generates emotionally charged audio data using a generative AI model based on the extracted information. The input is a list of extracted information. The server utilizes a speech synthesis API (e.g., Google Text-to-Speech, Amazon Polly) to generate speech from text. It adjusts phonemes and intonation to produce emotionally conveying audio data. The output is an emotionally charged audio file.

[0491] Step 4:

[0492] The server selects sound effects appropriate to the generated audio data and combines them using sound processing tools. The input is the generated audio file. The server selects appropriate sound effects from a sound library and integrates the audio and sound effects using audio editing software (e.g., Audacity). The output is an integrated file of the synthesized audio and sound effects.

[0493] Step 5:

[0494] The server generates video data synchronized with audio and sound effects. The input is an integrated audio file. The server uses video editing software (e.g., Adobe Premiere Pro, FFmpeg) to create video that matches the audio. The output is a video file synchronized with the audio.

[0495] Step 6:

[0496] The terminal receives video files transmitted from the server and integrates audio, sound effects, and video in real time for presentation to the user. The input is a video file synchronized with audio. The terminal utilizes a decoding function to achieve smooth playback. The output is viewable media content provided to the user.

[0497] Step 7:

[0498] Users can interact with the system using a terminal. Input is a question or comment from the user. The server utilizes a generative AI model to generate an appropriate response based on the prompt and provides it to the user. Output is the response message to the user's inquiry.

[0499] (Application Example 1)

[0500] 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."

[0501] To improve the current situation where visually impaired individuals and the elderly have difficulty fully understanding and enjoying educational and entertainment content, it is necessary to communicate information more effectively by using emotionally charged voices, sound effects, and visually appealing means.

[0502] 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.

[0503] In this invention, the server includes natural language processing means, speech generation means, sound processing means, visual generation means, interactive agent means, and information provision means for providing educational or entertaining content for the elderly. This makes it possible to provide educational and entertaining content using emotionally responsive voices and sound effects to visually impaired people and the elderly.

[0504] "Natural language processing techniques" are technologies used to extract important information from textbook data and related information.

[0505] "Voice generation means" refers to a technology that generates emotionally charged voices based on extracted information.

[0506] "Sound processing means" refers to a technology that selects and synthesizes sound effects suitable for the generated audio.

[0507] "Visual generation means" refers to technology that generates images synchronized with sound and audio.

[0508] "Interactive agent means" refers to technology implemented to enable interaction with users.

[0509] "Information provision methods" refer to technologies for providing educational or entertainment content to the elderly.

[0510] This invention aims to construct a system that effectively provides educational and entertainment content to visually impaired individuals and the elderly. The server analyzes textbook data using a natural language processing engine and extracts important information. Specifically, it processes data using various Python libraries (e.g., NLTK, spaCy). This enables users to accurately obtain the information they need.

[0511] For speech generation, the Google Cloud Text-to-Speech API is used to generate emotionally charged speech from the extracted information. Pydub is used for sound processing, selecting appropriate sound effects and synthesizing them with the speech. This results in a richer auditory experience. The generated speech and sound effects are intended for playback on the device, so native players for iOS and Android are used.

[0512] Furthermore, as a means of visual generation, the server will automatically create appropriate video based on the generated data and send it to the terminal. It is envisioned that FFmpeg, an open-source video editing software, will be used for video creation.

[0513] The interactive agent system utilizes natural language processing capabilities powered by generative AI models to provide appropriate responses to user questions. This allows users to directly ask the system questions about the content and engage in dialogue to deepen their understanding. For example, by providing content such as, "Today is a lovely day for a walk. Why not learn about the history of the Edo period while enjoying some relaxing afternoon music?", it enables learning in a relaxed state within the context of daily life.

[0514] An example of a prompt might be, "Generate audio that conveys emotion and historical context, making it easy for visually impaired individuals to understand." This prepares the system to provide users with engaging and easy-to-understand content.

[0515] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0516] Step 1:

[0517] The server receives textbook data in digital format. Based on this input data, a natural language processing engine is used to extract important information. Here, Python's natural language processing library is used to perform algorithms that identify topics and key phrases. The result is data that highlights the essential points of the information.

[0518] Step 2:

[0519] The server uses the Google Cloud Text-to-Speech API to generate emotionally charged audio data, taking the key information extracted in Step 1 as input. This audio data is specially adjusted to allow the user to perceive emotions. The output is an audio file that includes emotional expression.

[0520] Step 3:

[0521] The server performs acoustic processing on the audio file. Specifically, it uses Pydub to select sound effects that match the audio data and synthesizes them with the audio. In this process, sound effects are incorporated to give the audio a deeper context. As a result, the output is an audio file in which emotional voice and sound effects are synthesized.

[0522] Step 4:

[0523] The server takes an audio file as input and begins the video generation process. Using FFmpeg, it edits the video to match the audio and sound effects. Here, visual elements are created as video to synchronize with the audio. The output is a video file synchronized with the audio.

[0524] Step 5:

[0525] The device plays video files received from the server. Native media players provided by iOS and Android are used for playback. Here, users can enjoy educational and entertainment content visually and aurally.

[0526] Step 6:

[0527] The user communicates questions and requests regarding the content to the conversational agent. This input is provided as a prompt to the generating AI model, which uses natural language processing techniques to generate an appropriate response. The output is an answer to the user's question.

[0528] Step 7:

[0529] The server analyzes user feedback and uses it to improve the system. This feedback is then reflected in the next curriculum generation process, providing a better user experience. This process involves collecting user response data and identifying areas for improvement through computational processing.

[0530] 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.

[0531] This invention further improves the effectiveness and interactivity of a textbook learning system for visually impaired individuals by incorporating an emotion engine that recognizes user emotions. This system consists of a server, a terminal, and a user, and its specific embodiments are described below.

[0532] The system first receives textbook data in digital format on a server, analyzes the data through natural language processing, and extracts important topics and key phrases. Using this information, a generative model generates emotionally charged speech from the text. Furthermore, the server selects sound effects related to this speech and synthesizes them into the audio data.

[0533] Furthermore, the server uses an emotion engine to recognize the user's emotions through user input and voice analysis. The emotion engine determines emotions from the user's facial expressions, voice tone, and entered text information, and has the function to edit responses in real time based on that data.

[0534] Based on this sentiment data, the server dynamically adjusts how content is presented to the user. For example, if the user is confused, the server can slow down the pace of the audio and repeat important information.

[0535] The conversational agent uses data from the emotion engine to appropriately modify its responses and tone. This allows for flexible responses, such as providing detailed explanations for items the user is interested in, or presenting shortened content if the user is feeling fatigued.

[0536] For example, if a user is struggling with a difficult math problem, the emotion engine can recognize that stress and the agent can appropriately encourage them by saying, "Don't rush. Let's take it one step at a time," thereby providing reassurance and supporting their continued learning.

[0537] Ultimately, the device presents the user with integrated data received from the server, providing a multi-sensory learning experience through audio, sound effects, video, and interactive dialogue. By reflecting data from the emotion engine, the user can receive more optimized learning support.

[0538] The following describes the processing flow.

[0539] Step 1:

[0540] The server receives textbook data provided in digital format. This can include text data, graphics, and multimedia files.

[0541] Step 2:

[0542] The server uses a natural language processing engine to analyze textbook data and extract important topics and key phrases. This helps to understand the main points and learning focus of the materials.

[0543] Step 3:

[0544] The server uses a generative model based on the extracted key phrases to generate emotionally charged speech. This speech reflects the importance and emotion of the content, making it easy for the listener to understand.

[0545] Step 4:

[0546] The server selects appropriate sound effects from a sound effects library for the generated audio and synthesizes them into the speech. This adds depth and realism to the learning content.

[0547] Step 5:

[0548] The server uses an emotion engine to analyze user input and audio feedback from the device to measure and recognize the user's emotional state. This data is collected in real time.

[0549] Step 6:

[0550] The server adjusts how it presents educational content based on the emotional data it receives. For example, if the user is tired, it might slow down the audio speed or simplify the content.

[0551] Step 7:

[0552] Conversational agents utilize emotional data to appropriately adjust their interactions with users (the content and tone of their dialogue). This allows them to provide responses that are attentive to the user's current emotional state.

[0553] Step 8:

[0554] The device plays audio, sound effects, and video data received from the server, providing the user with an integrated learning experience. It continuously monitors the user's reactions and emotions during the learning process.

[0555] Step 9:

[0556] Users can respond via their device as needed or ask questions through an interactive agent. User input is analyzed by an emotion engine and reflected in the generation of subsequent content.

[0557] (Example 2)

[0558] 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."

[0559] In textbook learning for visually impaired individuals, there is a challenge in the lack of sufficient interactive and flexible learning support that responds to users' emotions and levels of comprehension. There is a need for a system that can appropriately address situations where users experience difficulty understanding learning materials or feel stressed.

[0560] 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.

[0561] In this invention, the server includes language processing means for receiving textbook data and extracting important topics and key phrases from the textbook data; sentiment analysis means for analyzing user input and recognizing emotions; and content adjustment means for dynamically adjusting the method of presenting textbook content based on the sentiment analysis results. This enables flexible presentation of learning content according to the user's emotions and level of understanding, and provides an interactive learning experience.

[0562] "Textbook data" refers to a collection of digital information provided for learning purposes, and its content includes text, images, graphs, and other elements.

[0563] "Language processing tools" refers to a set of functions that use natural language processing techniques to extract important topics and key phrases from textbook data.

[0564] "Generative model means" refers to an algorithm and its execution environment for generating emotionally rich speech based on extracted key phrases.

[0565] "Sound generation means" refers to a device or program for selecting appropriate sound effects for generated speech and synthesizing them with the speech.

[0566] "Image generation means" refers to a device or program that has the function of generating visual images in synchronization with audio and sound effects.

[0567] "Emotion analysis methods" refer to technologies that recognize and analyze emotions in real time based on user input and actions.

[0568] "Content adjustment means" refers to a function for dynamically adjusting the presentation method of learning content based on the analysis results obtained by the emotion analysis means.

[0569] "Interactive agent means" refers to artificial intelligence systems designed to enable natural dialogue with users.

[0570] This invention is designed to make textbook learning systems for visually impaired individuals highly interactive and effective. The system primarily consists of a server, terminals, and users.

[0571] The server receives textbook data in digital format. The received data is parsed using natural language processing libraries (e.g., NLTK, spaCy). This involves tokenization, part-of-speech tagging, and dependency structure analysis, extracting important topics and key phrases. This parsed data is then converted into emotionally charged speech via a generative AI model (e.g., GPT-3). The Google Text-to-Speech API is recommended for speech synthesis.

[0572] Next, the server selects and synthesizes relevant sound effects from a database with the generated audio. Furthermore, it generates video in sync with the audio and sound effects. This creates a multi-sensory learning material.

[0573] The server uses emotion analysis technologies (e.g., Microsoft Azure's Emotion API, OpenCV) to recognize the user's emotions in real time. Based on this information, the server can dynamically adjust how learning materials are presented, providing a customized learning experience that is easy for the user to understand. For example, if the user is confused, the server can slow down the speed of the voice guidance and repeat important information.

[0574] The device receives integrated audio, sound effects, and video data from the server and presents it to the user. This allows the user to enjoy a rich learning experience without relying on visual information.

[0575] As a concrete example, when a user is studying a history unit, the server plays relevant events and important dates with immersive audio, adding sound effects that convey the historical context. In addition, sentiment analysis adjusts the content to provide more detailed explanations when the user indicates a desire for deeper understanding.

[0576] An example of a prompt might be, "What part of the following math problem do you find difficult?" This example demonstrates how an interactive agent can provide responses based on the user's interests and level of understanding.

[0577] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0578] Step 1:

[0579] The server receives digital textbook data via the internet. The input is raw data files obtained from the network, which are then analyzed on the server. The output is text data prepared for analysis. The data format is then modified as needed, such as to JSON or XML.

[0580] Step 2:

[0581] The server analyzes incoming data using a natural language processing library. It tokenizes, tags, and analyzes dependency structures on the formalized text input, extracting important topics and key phrases. The output is a dataset containing the analysis results. Efficient algorithms are used in the analysis to ensure high speed and accuracy.

[0582] Step 3:

[0583] The server uses a generative AI model to synthesize emotionally charged speech based on extracted key phrases. The input is the key phrases obtained from the analysis. The generative AI model converts these key phrases into emotionally rich speech data. The output is data in the form of an audio file. Pitch and tempo are adjusted to appropriately express emotions.

[0584] Step 4:

[0585] The server selects sound effects related to the generated audio and synthesizes them. The input consists of the audio file and topic information that serves as the selection criterion for the sound effects. The output is an integrated audio file combining the audio and sound effects. The sound effects are selected from a database that are appropriate to the theme and scene, and are seamlessly integrated with the audio.

[0586] Step 5:

[0587] The server receives user input and performs sentiment analysis. This input consists of user voice and text data. Based on this data, the sentiment analysis engine analyzes the user's facial expressions and tone of voice in real time. The output is metadata indicating the user's emotional state. Machine learning models are used in the analysis to achieve highly accurate sentiment recognition.

[0588] Step 6:

[0589] The server dynamically adjusts how content is presented based on the results of sentiment analysis. Inputs are sentiment analysis metadata and existing content data. Output is a presentation of learning content tailored to the user's emotions. Adjustments include changing the playback speed and repeating content.

[0590] Step 7:

[0591] The device presents integrated data received from the server to the user in a multi-sensory format. Inputs include audio, sound effects, and video information. Output provides an interactive learning experience that combines these elements. The device enhances acoustic instruction to enable comprehension even without visual information, and plays audio content and video in sync.

[0592] (Application Example 2)

[0593] 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."

[0594] In education and care systems for visually impaired individuals, the elderly, and especially those with dementia, there is a need for methods that appropriately recognize the emotional state of users and support the maintenance of learning and cognitive function. Current education systems and care services do not adequately respond to the emotions and learning pace of each individual user, making it difficult to maximize learning efficiency and the effectiveness of care.

[0595] 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.

[0596] In this invention, the server includes data analysis means, information generation means, emotion analysis means, and response adjustment means. This enables the recognition of the user's emotions and the presentation of individually optimized content and adjustment of dialogue.

[0597] "Data analysis means" refers to technology that receives textbook data and has the function of extracting important topics and key phrases.

[0598] "Information generation means" refers to a technology that generates emotionally charged voices based on extracted key phrases.

[0599] A "sound effect generation method" is a technology that has the function of selecting a sound effect that is appropriate for the generated audio and synthesizing it into the audio.

[0600] "Display generation means" refers to a technology that generates video in synchronization with audio and sound effects.

[0601] "Emotional analysis techniques" are technologies that analyze users' emotions and dynamically adjust how content is presented based on those emotions.

[0602] "Response adjustment means" refers to technology that has the function of adjusting the interaction with the user and appropriately changing the content and tone of voice.

[0603] This system recognizes users' emotions in real time and provides individually optimized content presentation and dialogue adjustments to support the education and care of visually impaired individuals, the elderly, and especially those with dementia.

[0604] The server receives textbook data using data analysis tools and extracts important topics and key phrases using natural language processing techniques. Next, information generation tools are used to generate speech that imbues the extracted key phrases with emotion. Appropriate sound effects are then synthesized into this speech using sound effect generation tools, resulting in a richer audio experience.

[0605] Furthermore, the server uses emotion analysis to determine the user's emotional state from their voice tone and input, and adjusts the dialogue content and tone using response adjustment mechanisms. This allows for flexible responses tailored to the user's learning pace and level of understanding, such as slowing down the pace of speech or simplifying the content if the user is confused.

[0606] The device receives integrated data from the server and presents audio, sound effects, and visuals to the user. This allows the user to receive multi-sensory, emotionally optimized learning support.

[0607] As a concrete example, a scenario could be envisioned where, for a user confused by a difficult problem, an emotion analysis tool recognizes their stress, and a response adjustment tool provides a reassuring message such as, "Don't worry, let's adjust to your pace."

[0608] An example of a prompt from a generative AI model is: "Create a scenario for an emotion-recognition-based care app for elderly people with visual impairments. This app will adjust the difficulty of quizzes and provide voice feedback according to the user's emotional state."

[0609] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0610] Step 1:

[0611] The server receives textbook data and uses data analysis tools to extract important topics and key phrases. The input is book data, and the output is the extracted topics and key phrases. In this process, natural language processing techniques are used to analyze the data and identify information that is considered important in education and care.

[0612] Step 2:

[0613] The server uses information generation means to generate emotionally charged speech based on the extracted key phrases. The input is the key phrases obtained in step 1, and the output is the generated speech data. This process includes specific actions that utilize a generation AI model to generate emotionally rich speech.

[0614] Step 3:

[0615] The server uses a sound effect generation mechanism to select and synthesize sound effects that are appropriate for the generated audio. The input is the audio generated in step 2, and the output is the final audio data with the sound effects synthesized. In this step, sound effects are selected and synthesized to add realism and emphasis to the audio.

[0616] Step 4:

[0617] The server uses emotion analysis tools to determine the user's emotional state from their voice tone and input data. The input is voice and text information obtained from the user, and the output is the analyzed emotion data. This process includes specific actions that perform analysis using an emotion recognition algorithm.

[0618] Step 5:

[0619] The server uses a response adjustment mechanism to adjust the dialogue content and tone based on the analyzed emotion data. The input is the emotion data obtained in step 4, and the output is the adjusted dialogue content. In this step, adjustment processing is performed to enable flexible content delivery in response to the user's emotions.

[0620] Step 6:

[0621] The device receives pre-configured data from the server and presents audio, sound effects, and video to the user. The input is the integrated data sent from the server, and the output is the user's viewing experience. In this final step, the actual presentation action is performed using the integrated data, and the user enjoys the content.

[0622] 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.

[0623] 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.

[0624] 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.

[0625] [Fourth Embodiment]

[0626] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0627] 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.

[0628] 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).

[0629] 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.

[0630] 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.

[0631] 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).

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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.

[0638] 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".

[0639] This invention is a system for effectively conveying the content of textbooks to visually impaired individuals, and its configuration and operation are described below.

[0640] This system consists of a server, terminals, and users. The system begins by receiving textbook data in digital format to the server. The server then uses natural language processing to extract important topics and key phrases from the textbook data. This allows for the efficient identification of the essential points of the information.

[0641] Next, the server uses a generative model to automatically generate emotionally charged speech based on the extracted key phrases. In this process, the server reflects the emotions that a human would feel in response to specific contexts and terms, providing content that is easy for the listener to understand. The server also selects and synthesizes sound effects that match the speech, complementing situations and atmospheres that cannot be fully conveyed through speech alone.

[0642] Furthermore, the server creates video synchronized with the generated audio and sound effects and sends it to the terminal. The terminal receives this data and integrates the audio, sound effects, and video to present to the user. The user views the provided content and gains a deeper learning experience.

[0643] In addition, the server provides an interactive agent that enables users to engage in natural conversations through their terminals. When a user asks a question about the textbook content, the agent provides an appropriate answer. This interactive function allows users to deepen their understanding of the lesson content.

[0644] For example, if a history textbook contains a section on "the outbreak of World War II," the server would highlight the phrases representing this significant event and express its background with sound effects. Then, if the user asks "why did this war start?", the agent can provide a detailed explanation of the relevant historical context and events.

[0645] In this way, the system creates an environment that provides visually impaired individuals with textbook content in a way that is quick and easy to understand.

[0646] The following describes the processing flow.

[0647] Step 1:

[0648] The server receives textbook data provided in digital format. This may include text, illustrations, tables, and other elements.

[0649] Step 2:

[0650] The server analyzes the received textbook data using natural language processing techniques. It extracts important topics and key phrases and organizes them as metadata.

[0651] Step 3:

[0652] The server applies a generative model to the extracted key phrases to automatically generate emotionally charged speech. It determines appropriate intonation and emotional expression based on the content of the text.

[0653] Step 4:

[0654] The server selects sound effects related to the generated audio from the sound effects library and synthesizes and incorporates them into the audio data.

[0655] Step 5:

[0656] The server generates video that synchronizes with the audio and sound effects. This video consists of animations and visual content based on the textbook material, supplementing the visual information.

[0657] Step 6:

[0658] The server transfers this integrated data (audio, sound effects, and video) to the terminal.

[0659] Step 7:

[0660] The terminal plays back integrated data received from the server through a user interface, making it interactive for visually impaired users.

[0661] Step 8:

[0662] The terminal receives questions from the user through an interactive agent. When the user asks a question about the content of the textbook, the agent generates a response.

[0663] Step 9:

[0664] The server collects and analyzes user interaction logs and feedback data. This information is used to improve future learning materials.

[0665] (Example 1)

[0666] 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".

[0667] For visually impaired individuals, traditional textbook-based learning methods presented challenges in understanding and processing information. In particular, there was a lack of means to efficiently grasp the key points of learning content and provide an emotionally enriching learning experience. Furthermore, there was a need for a system that could address individual learning needs through interactive dialogue functions.

[0668] 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.

[0669] In this invention, the server includes a natural language processing means for receiving textbook data and extracting important information and concepts from the textbook data; a speech synthesis means for generating emotionally charged speech data based on the extracted information; and an acoustic processing means for selecting and combining sound effects appropriate to the generated speech data. This enables visually impaired individuals to learn intuitively and effectively based on their hearing and senses. Furthermore, an interactive interface can respond to learners' questions and enrich their individual learning experiences.

[0670] "Textbook data" refers to a collection of information obtained from printed or digitized learning materials used for educational purposes.

[0671] "Natural language processing" refers to technologies that analyze the structure and meaning of text data to extract important information and key phrases.

[0672] "Speech synthesis means" refers to a technology that generates speech waveforms based on digital text data and outputs them as machine-generated speech.

[0673] "Audio processing means" refers to a technology or process for adding sound effects to generated audio data and applying auditory effects.

[0674] "Media generation means" refers to a technology that creates video data in synchronization with audio and sound effects to generate visual content.

[0675] An "interactive interface means" is a technology that enables interaction with the user and provides the functionality to exchange information through natural conversation.

[0676] "User" refers to an individual or group that uses this system to access and receive information.

[0677] "Opinions" refer to expressions of thoughts, including feedback and impressions from users.

[0678] The "material creation process" refers to the process of creating, editing, and distributing learning materials based on educational objectives.

[0679] This system is designed to enable visually impaired individuals to effectively understand digital textbook content. It primarily consists of three components: a server, terminals, and users.

[0680] The server first receives textbook data in digital format. This data is provided, for example, via a network, using protocols such as HTTP or FTP. The received data is then processed using natural language processing (NLP) to extract important information and concepts. This process utilizes natural language processing libraries (e.g., spaCy, NLTK) to extract topics and key phrases from the document. This allows for efficient identification of the main points of the information.

[0681] Next, the server generates emotionally charged speech based on the extracted information using speech synthesis technology. This process utilizes speech synthesis APIs (e.g., Google Text-to-Speech, Amazon Polly) to convert text data into speech data. Furthermore, sound processing technology selects appropriate sound effects from a sound library and integrates them with the speech. Finally, audio editing software (e.g., Audacity) is used to edit the final audio content.

[0682] The generated audio data is synchronized with video data by a media generation device and processed into high-resolution visual content. This video data is created using video editing software (e.g., Adobe Premiere Pro, FFmpeg) and sent to the device. The device has advanced decoding capabilities and integrates this data in real time to present it to the user. The user receives the visual and audio content provided through the device, enabling an intuitive learning experience that does not rely on visual input.

[0683] Furthermore, the user can engage in natural conversations with the system using the interactive interface built into the terminal. The server utilizes a generative AI model to generate responses to user questions based on prompt text. This allows the user to enjoy an interactive learning environment and gain a deeper understanding.

[0684] As a concrete example, if content about the "outbreak of World War II" from a history textbook is input, the generation AI model will receive the following prompt: "Extract important key phrases about the 'outbreak of World War II' from the textbook data, and generate emotionally charged speech based on them."

[0685] This system is expected to enable visually impaired individuals to maximize their potential as learners and expand diverse educational opportunities.

[0686] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0687] Step 1:

[0688] The server receives textbook data in digital format. The input is a data file provided over the network. This data file undergoes preprocessing for text processing and is converted into a consistent digital format. The output is the digitized textbook data.

[0689] Step 2:

[0690] The server extracts important information and concepts from received textbook data using natural language processing techniques. Preprocessed text data is used as input. The server uses natural language processing libraries (e.g., spaCy, NLTK) to analyze the text structure and extract key phrases and topics. This process includes techniques such as sentence segmentation and part-of-speech tagging. The output is a list of the extracted important information.

[0691] Step 3:

[0692] The server generates emotionally charged audio data using a generative AI model based on the extracted information. The input is a list of extracted information. The server utilizes a speech synthesis API (e.g., Google Text-to-Speech, Amazon Polly) to generate speech from text. It adjusts phonemes and intonation to produce emotionally conveying audio data. The output is an emotionally charged audio file.

[0693] Step 4:

[0694] The server selects sound effects appropriate to the generated audio data and combines them using sound processing tools. The input is the generated audio file. The server selects appropriate sound effects from a sound library and integrates the audio and sound effects using audio editing software (e.g., Audacity). The output is an integrated file of the synthesized audio and sound effects.

[0695] Step 5:

[0696] The server generates video data synchronized with audio and sound effects. The input is an integrated audio file. The server uses video editing software (e.g., Adobe Premiere Pro, FFmpeg) to create video that matches the audio. The output is a video file synchronized with the audio.

[0697] Step 6:

[0698] The terminal receives video files transmitted from the server and integrates audio, sound effects, and video in real time for presentation to the user. The input is a video file synchronized with audio. The terminal utilizes a decoding function to achieve smooth playback. The output is viewable media content provided to the user.

[0699] Step 7:

[0700] Users can interact with the system using a terminal. Input is a question or comment from the user. The server utilizes a generative AI model to generate an appropriate response based on the prompt and provides it to the user. Output is the response message to the user's inquiry.

[0701] (Application Example 1)

[0702] 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".

[0703] To improve the current situation where visually impaired individuals and the elderly have difficulty fully understanding and enjoying educational and entertainment content, it is necessary to communicate information more effectively by using emotionally charged voices, sound effects, and visually appealing means.

[0704] 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.

[0705] In this invention, the server includes natural language processing means, speech generation means, sound processing means, visual generation means, interactive agent means, and information provision means for providing educational or entertaining content for the elderly. This makes it possible to provide educational and entertaining content using emotionally responsive voices and sound effects to visually impaired people and the elderly.

[0706] "Natural language processing techniques" are technologies used to extract important information from textbook data and related information.

[0707] "Voice generation means" refers to a technology that generates emotionally charged voices based on extracted information.

[0708] "Sound processing means" refers to a technology that selects and synthesizes sound effects suitable for the generated audio.

[0709] "Visual generation means" refers to technology that generates images synchronized with sound and audio.

[0710] "Interactive agent means" refers to technology implemented to enable interaction with users.

[0711] "Information provision methods" refer to technologies for providing educational or entertainment content to the elderly.

[0712] This invention aims to construct a system that effectively provides educational and entertainment content to visually impaired individuals and the elderly. The server analyzes textbook data using a natural language processing engine and extracts important information. Specifically, it processes data using various Python libraries (e.g., NLTK, spaCy). This enables users to accurately obtain the information they need.

[0713] For speech generation, the Google Cloud Text-to-Speech API is used to generate emotionally charged speech from the extracted information. Pydub is used for sound processing, selecting appropriate sound effects and synthesizing them with the speech. This results in a richer auditory experience. The generated speech and sound effects are intended for playback on the device, so native players for iOS and Android are used.

[0714] Furthermore, as a means of visual generation, the server will automatically create appropriate video based on the generated data and send it to the terminal. It is envisioned that FFmpeg, an open-source video editing software, will be used for video creation.

[0715] The interactive agent system utilizes natural language processing capabilities powered by generative AI models to provide appropriate responses to user questions. This allows users to directly ask the system questions about the content and engage in dialogue to deepen their understanding. For example, by providing content such as, "Today is a lovely day for a walk. Why not learn about the history of the Edo period while enjoying some relaxing afternoon music?", it enables learning in a relaxed state within the context of daily life.

[0716] An example of a prompt might be, "Generate audio that conveys emotion and historical context, making it easy for visually impaired individuals to understand." This prepares the system to provide users with engaging and easy-to-understand content.

[0717] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0718] Step 1:

[0719] The server receives textbook data in digital format. Based on this input data, a natural language processing engine is used to extract important information. Here, Python's natural language processing library is used to perform algorithms that identify topics and key phrases. The result is data that highlights the essential points of the information.

[0720] Step 2:

[0721] The server uses the Google Cloud Text-to-Speech API to generate emotionally charged audio data, taking the key information extracted in Step 1 as input. This audio data is specially adjusted to allow the user to perceive emotions. The output is an audio file that includes emotional expression.

[0722] Step 3:

[0723] The server performs acoustic processing on the audio file. Specifically, it uses Pydub to select sound effects that match the audio data and synthesizes them with the audio. In this process, sound effects are incorporated to give the audio a deeper context. As a result, the output is an audio file in which emotional voice and sound effects are synthesized.

[0724] Step 4:

[0725] The server takes an audio file as input and begins the video generation process. Using FFmpeg, it edits the video to match the audio and sound effects. Here, visual elements are created as video to synchronize with the audio. The output is a video file synchronized with the audio.

[0726] Step 5:

[0727] The device plays video files received from the server. Native media players provided by iOS and Android are used for playback. Here, users can enjoy educational and entertainment content visually and aurally.

[0728] Step 6:

[0729] The user communicates questions and requests regarding the content to the conversational agent. This input is provided as a prompt to the generating AI model, which uses natural language processing techniques to generate an appropriate response. The output is an answer to the user's question.

[0730] Step 7:

[0731] The server analyzes user feedback and uses it to improve the system. This feedback is then reflected in the next curriculum generation process, providing a better user experience. This process involves collecting user response data and identifying areas for improvement through computational processing.

[0732] 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.

[0733] This invention further improves the effectiveness and interactivity of a textbook learning system for visually impaired individuals by incorporating an emotion engine that recognizes user emotions. This system consists of a server, a terminal, and a user, and its specific embodiments are described below.

[0734] The system first receives textbook data in digital format on a server, analyzes the data through natural language processing, and extracts important topics and key phrases. Using this information, a generative model generates emotionally charged speech from the text. Furthermore, the server selects sound effects related to this speech and synthesizes them into the audio data.

[0735] Furthermore, the server uses an emotion engine to recognize the user's emotions through user input and voice analysis. The emotion engine determines emotions from the user's facial expressions, voice tone, and entered text information, and has the function to edit responses in real time based on that data.

[0736] Based on this sentiment data, the server dynamically adjusts how content is presented to the user. For example, if the user is confused, the server can slow down the pace of the audio and repeat important information.

[0737] The conversational agent uses data from the emotion engine to appropriately modify its responses and tone. This allows for flexible responses, such as providing detailed explanations for items the user is interested in, or presenting shortened content if the user is feeling fatigued.

[0738] For example, if a user is struggling with a difficult math problem, the emotion engine can recognize that stress and the agent can appropriately encourage them by saying, "Don't rush. Let's take it one step at a time," thereby providing reassurance and supporting their continued learning.

[0739] Ultimately, the device presents the user with integrated data received from the server, providing a multi-sensory learning experience through audio, sound effects, video, and interactive dialogue. By reflecting data from the emotion engine, the user can receive more optimized learning support.

[0740] The following describes the processing flow.

[0741] Step 1:

[0742] The server receives textbook data provided in digital format. This can include text data, graphics, and multimedia files.

[0743] Step 2:

[0744] The server uses a natural language processing engine to analyze textbook data and extract important topics and key phrases. This helps to understand the main points and learning focus of the materials.

[0745] Step 3:

[0746] The server uses a generative model based on the extracted key phrases to generate emotionally charged speech. This speech reflects the importance and emotion of the content, making it easy for the listener to understand.

[0747] Step 4:

[0748] The server selects appropriate sound effects from a sound effects library for the generated audio and synthesizes them into the speech. This adds depth and realism to the learning content.

[0749] Step 5:

[0750] The server uses an emotion engine to analyze user input and audio feedback from the device to measure and recognize the user's emotional state. This data is collected in real time.

[0751] Step 6:

[0752] The server adjusts how it presents educational content based on the emotional data it receives. For example, if the user is tired, it might slow down the audio speed or simplify the content.

[0753] Step 7:

[0754] Conversational agents utilize emotional data to appropriately adjust their interactions with users (the content and tone of their dialogue). This allows them to provide responses that are attentive to the user's current emotional state.

[0755] Step 8:

[0756] The device plays audio, sound effects, and video data received from the server, providing the user with an integrated learning experience. It continuously monitors the user's reactions and emotions during the learning process.

[0757] Step 9:

[0758] Users can respond via their device as needed or ask questions through an interactive agent. User input is analyzed by an emotion engine and reflected in the generation of subsequent content.

[0759] (Example 2)

[0760] 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".

[0761] In textbook learning for visually impaired individuals, there is a challenge in the lack of sufficient interactive and flexible learning support that responds to users' emotions and levels of comprehension. There is a need for a system that can appropriately address situations where users experience difficulty understanding learning materials or feel stressed.

[0762] 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.

[0763] In this invention, the server includes language processing means for receiving textbook data and extracting important topics and key phrases from the textbook data; sentiment analysis means for analyzing user input and recognizing emotions; and content adjustment means for dynamically adjusting the method of presenting textbook content based on the sentiment analysis results. This enables flexible presentation of learning content according to the user's emotions and level of understanding, and provides an interactive learning experience.

[0764] "Textbook data" refers to a collection of digital information provided for learning purposes, and its content includes text, images, graphs, and other elements.

[0765] "Language processing tools" refers to a set of functions that use natural language processing techniques to extract important topics and key phrases from textbook data.

[0766] "Generative model means" refers to an algorithm and its execution environment for generating emotionally rich speech based on extracted key phrases.

[0767] "Sound generation means" refers to a device or program for selecting appropriate sound effects for generated speech and synthesizing them with the speech.

[0768] "Image generation means" refers to a device or program that has the function of generating visual images in synchronization with audio and sound effects.

[0769] "Emotion analysis methods" refer to technologies that recognize and analyze emotions in real time based on user input and actions.

[0770] "Content adjustment means" refers to a function for dynamically adjusting the presentation method of learning content based on the analysis results obtained by the emotion analysis means.

[0771] "Interactive agent means" refers to artificial intelligence systems designed to enable natural dialogue with users.

[0772] This invention is designed to make textbook learning systems for visually impaired individuals highly interactive and effective. The system primarily consists of a server, terminals, and users.

[0773] The server receives textbook data in digital format. The received data is parsed using natural language processing libraries (e.g., NLTK, spaCy). This involves tokenization, part-of-speech tagging, and dependency structure analysis, extracting important topics and key phrases. This parsed data is then converted into emotionally charged speech via a generative AI model (e.g., GPT-3). The Google Text-to-Speech API is recommended for speech synthesis.

[0774] Next, the server selects and synthesizes relevant sound effects from a database with the generated audio. Furthermore, it generates video in sync with the audio and sound effects. This creates a multi-sensory learning material.

[0775] The server uses emotion analysis technologies (e.g., Microsoft Azure's Emotion API, OpenCV) to recognize the user's emotions in real time. Based on this information, the server can dynamically adjust how learning materials are presented, providing a customized learning experience that is easy for the user to understand. For example, if the user is confused, the server can slow down the speed of the voice guidance and repeat important information.

[0776] The device receives integrated audio, sound effects, and video data from the server and presents it to the user. This allows the user to enjoy a rich learning experience without relying on visual information.

[0777] As a concrete example, when a user is studying a history unit, the server plays relevant events and important dates with immersive audio, adding sound effects that convey the historical context. In addition, sentiment analysis adjusts the content to provide more detailed explanations when the user indicates a desire for deeper understanding.

[0778] An example of a prompt might be, "What part of the following math problem do you find difficult?" This example demonstrates how an interactive agent can provide responses based on the user's interests and level of understanding.

[0779] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0780] Step 1:

[0781] The server receives digital textbook data via the internet. The input is raw data files obtained from the network, which are then analyzed on the server. The output is text data prepared for analysis. The data format is then modified as needed, such as to JSON or XML.

[0782] Step 2:

[0783] The server analyzes incoming data using a natural language processing library. It tokenizes, tags, and analyzes dependency structures on the formalized text input, extracting important topics and key phrases. The output is a dataset containing the analysis results. Efficient algorithms are used in the analysis to ensure high speed and accuracy.

[0784] Step 3:

[0785] The server uses a generative AI model to synthesize emotionally charged speech based on extracted key phrases. The input is the key phrases obtained from the analysis. The generative AI model converts these key phrases into emotionally rich speech data. The output is data in the form of an audio file. Pitch and tempo are adjusted to appropriately express emotions.

[0786] Step 4:

[0787] The server selects sound effects related to the generated audio and synthesizes them. The input consists of the audio file and topic information that serves as the selection criterion for the sound effects. The output is an integrated audio file combining the audio and sound effects. The sound effects are selected from a database that are appropriate to the theme and scene, and are seamlessly integrated with the audio.

[0788] Step 5:

[0789] The server receives user input and performs sentiment analysis. This input consists of user voice and text data. Based on this data, the sentiment analysis engine analyzes the user's facial expressions and tone of voice in real time. The output is metadata indicating the user's emotional state. Machine learning models are used in the analysis to achieve highly accurate sentiment recognition.

[0790] Step 6:

[0791] The server dynamically adjusts how content is presented based on the results of sentiment analysis. Inputs are sentiment analysis metadata and existing content data. Output is a presentation of learning content tailored to the user's emotions. Adjustments include changing the playback speed and repeating content.

[0792] Step 7:

[0793] The device presents integrated data received from the server to the user in a multi-sensory format. Inputs include audio, sound effects, and video information. Output provides an interactive learning experience that combines these elements. The device enhances acoustic instruction to enable comprehension even without visual information, and plays audio content and video in sync.

[0794] (Application Example 2)

[0795] 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".

[0796] In education and care systems for visually impaired individuals, the elderly, and especially those with dementia, there is a need for methods that appropriately recognize the emotional state of users and support the maintenance of learning and cognitive function. Current education systems and care services do not adequately respond to the emotions and learning pace of each individual user, making it difficult to maximize learning efficiency and the effectiveness of care.

[0797] 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.

[0798] In this invention, the server includes data analysis means, information generation means, emotion analysis means, and response adjustment means. This enables the recognition of the user's emotions and the presentation of individually optimized content and adjustment of dialogue.

[0799] "Data analysis means" refers to technology that receives textbook data and has the function of extracting important topics and key phrases.

[0800] "Information generation means" refers to a technology that generates emotionally charged voices based on extracted key phrases.

[0801] A "sound effect generation method" is a technology that has the function of selecting a sound effect that is appropriate for the generated audio and synthesizing it into the audio.

[0802] "Display generation means" refers to a technology that generates video in synchronization with audio and sound effects.

[0803] "Emotional analysis techniques" are technologies that analyze users' emotions and dynamically adjust how content is presented based on those emotions.

[0804] "Response adjustment means" refers to technology that has the function of adjusting the interaction with the user and appropriately changing the content and tone of voice.

[0805] This system recognizes users' emotions in real time and provides individually optimized content presentation and dialogue adjustments to support the education and care of visually impaired individuals, the elderly, and especially those with dementia.

[0806] The server receives textbook data using data analysis tools and extracts important topics and key phrases using natural language processing techniques. Next, information generation tools are used to generate speech that imbues the extracted key phrases with emotion. Appropriate sound effects are then synthesized into this speech using sound effect generation tools, resulting in a richer audio experience.

[0807] Furthermore, the server uses emotion analysis to determine the user's emotional state from their voice tone and input, and adjusts the dialogue content and tone using response adjustment mechanisms. This allows for flexible responses tailored to the user's learning pace and level of understanding, such as slowing down the pace of speech or simplifying the content if the user is confused.

[0808] The device receives integrated data from the server and presents audio, sound effects, and visuals to the user. This allows the user to receive multi-sensory, emotionally optimized learning support.

[0809] As a concrete example, a scenario could be envisioned where, for a user confused by a difficult problem, an emotion analysis tool recognizes their stress, and a response adjustment tool provides a reassuring message such as, "Don't worry, let's adjust to your pace."

[0810] An example of a prompt from a generative AI model is: "Create a scenario for an emotion-recognition-based care app for elderly people with visual impairments. This app will adjust the difficulty of quizzes and provide voice feedback according to the user's emotional state."

[0811] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0812] Step 1:

[0813] The server receives textbook data and uses data analysis tools to extract important topics and key phrases. The input is book data, and the output is the extracted topics and key phrases. In this process, natural language processing techniques are used to analyze the data and identify information that is considered important in education and care.

[0814] Step 2:

[0815] The server uses information generation means to generate emotionally charged speech based on the extracted key phrases. The input is the key phrases obtained in step 1, and the output is the generated speech data. This process includes specific actions that utilize a generation AI model to generate emotionally rich speech.

[0816] Step 3:

[0817] The server uses a sound effect generation mechanism to select and synthesize sound effects that are appropriate for the generated audio. The input is the audio generated in step 2, and the output is the final audio data with the sound effects synthesized. In this step, sound effects are selected and synthesized to add realism and emphasis to the audio.

[0818] Step 4:

[0819] The server uses emotion analysis tools to determine the user's emotional state from their voice tone and input data. The input is voice and text information obtained from the user, and the output is the analyzed emotion data. This process includes specific actions that perform analysis using an emotion recognition algorithm.

[0820] Step 5:

[0821] The server uses a response adjustment mechanism to adjust the dialogue content and tone based on the analyzed emotion data. The input is the emotion data obtained in step 4, and the output is the adjusted dialogue content. In this step, adjustment processing is performed to enable flexible content delivery in response to the user's emotions.

[0822] Step 6:

[0823] The device receives pre-configured data from the server and presents audio, sound effects, and video to the user. The input is the integrated data sent from the server, and the output is the user's viewing experience. In this final step, the actual presentation action is performed using the integrated data, and the user enjoys the content.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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."

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] The following is further disclosed regarding the embodiments described above.

[0846] (Claim 1)

[0847] A natural language processing means that receives textbook data and extracts important topics and key phrases from said textbook data,

[0848] A generative model means for generating emotionally charged speech based on extracted key phrases,

[0849] A sound effect generation means that selects and synthesizes sound effects that are appropriate to the generated audio,

[0850] A video generation means that generates video in synchronization with audio and sound effects,

[0851] A conversational agent means that enables interaction with the user,

[0852] A system that includes this.

[0853] (Claim 2)

[0854] The system according to claim 1, wherein the interactive agent means has the function of generating a dialogue that includes questions and answers based on textbook data.

[0855] (Claim 3)

[0856] The system according to claim 1, wherein the natural language processing means has a function to analyze user feedback and reflect the analysis results in the next material generation process.

[0857] "Example 1"

[0858] (Claim 1)

[0859] A natural language processing means that receives textbook data and extracts important information and concepts from said textbook data,

[0860] A speech synthesis means that generates emotionally charged voice data based on extracted information,

[0861] An audio processing means for selecting and combining sound effects that are appropriate for the generated audio data,

[0862] A media generation means that generates video data in synchronization with audio data and sound effects,

[0863] An interactive interface means that enables interaction with the user,

[0864] A system that includes this.

[0865] (Claim 2)

[0866] The system according to claim 1, wherein the interactive interface means has a function to generate conversations including inquiries and responses based on textbook data.

[0867] (Claim 3)

[0868] The system according to claim 1, wherein the natural language processing means has a function to analyze user feedback and reflect the analysis results in the next material generation process.

[0869] "Application Example 1"

[0870] (Claim 1)

[0871] A natural language processing means that receives textbook data and extracts important information from said data,

[0872] A voice generation means that generates emotionally charged voices based on extracted information,

[0873] An audio processing means for selecting and synthesizing sound effects that are appropriate to the generated audio,

[0874] A visual generation means that generates images in synchronization with sound and audio,

[0875] An interactive agent means that enables interaction with users,

[0876] Information provision methods for providing educational or entertainment content for the elderly,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, wherein the interactive agent means has the function of generating interactions including questions and answers based on educational information.

[0880] (Claim 3)

[0881] The system according to claim 1, wherein the natural language processing means has a function to analyze user responses and reflect the analysis results in the next information generation process.

[0882] "Example 2 of combining an emotion engine"

[0883] (Claim 1)

[0884] A language processing means that receives textbook data and extracts important topics and key phrases from said textbook data,

[0885] A generative model means for generating emotionally charged speech based on extracted key phrases,

[0886] Sound generation means for selecting and synthesizing sound effects that are appropriate to the generated audio,

[0887] A video generation means that generates video in synchronization with audio and sound effects,

[0888] A means of analyzing user input and recognizing emotions,

[0889] A content adjustment means that dynamically adjusts the presentation method of textbook content based on the results of emotion analysis,

[0890] A conversational agent means that enables interaction with the user,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, wherein the interactive agent means has the function of generating a dialogue including questions and answers based on textbook data and providing an adaptive response in accordance with the user's emotions.

[0894] (Claim 3)

[0895] The system according to claim 1, wherein the language processing means has a function to analyze user feedback and reflect the analysis results in the next material generation process, and generates materials that take into account the emotional data obtained by the emotion analysis means.

[0896] "Application example 2 when combining with an emotional engine"

[0897] (Claim 1)

[0898] A data analysis means that receives textbook data and extracts important topics and key phrases from said textbook data,

[0899] Information generation means that generates emotionally charged voice based on extracted key phrases,

[0900] A sound effect generation means that selects and synthesizes sound effects that are appropriate to the generated audio,

[0901] A display generation means that generates video in synchronization with audio and sound effects,

[0902] A sentiment analysis tool that analyzes user emotions and dynamically adjusts the content presentation method based on those emotions,

[0903] A response adjustment mechanism that adjusts the interaction with the user and appropriately changes the content and tone of voice,

[0904] A system that includes this.

[0905] (Claim 2)

[0906] The system according to claim 1, wherein the corresponding adjustment means has the function of generating a dialogue including questions and answers based on textbook data, and adjusting the difficulty level and pace of the quiz according to the user's emotional state.

[0907] (Claim 3)

[0908] The system according to claim 1, wherein the data analysis means has a function to analyze user feedback and reflect the analysis results and the user's emotions in the next material generation process, thereby providing a system for supporting cognitive care for the elderly. [Explanation of symbols]

[0909] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A natural language processing means that receives textbook data and extracts important topics and key phrases from said textbook data, A generative model means for generating emotionally charged speech based on extracted key phrases, A sound effect generation means that selects and synthesizes sound effects that are appropriate to the generated audio, A video generation means that generates video in synchronization with audio and sound effects, A conversational agent means that enables interaction with the user, A system that includes this.

2. The system according to claim 1, wherein the interactive agent means has a function to generate a dialogue including questions and answers based on textbook data.

3. The system according to claim 1, wherein the natural language processing means has a function to analyze user feedback and reflect the analysis results in the next material generation process.

Images